From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from dpdk.org (dpdk.org [92.243.14.124]) by inbox.dpdk.org (Postfix) with ESMTP id B61F2A0526 for ; Tue, 21 Jul 2020 22:23:37 +0200 (CEST) Received: from [92.243.14.124] (localhost [127.0.0.1]) by dpdk.org (Postfix) with ESMTP id A0AA31C06B; Tue, 21 Jul 2020 22:23:37 +0200 (CEST) Received: from mail-io1-f47.google.com (mail-io1-f47.google.com [209.85.166.47]) by dpdk.org (Postfix) with ESMTP id 5A95C1C068 for ; Tue, 21 Jul 2020 22:23:36 +0200 (CEST) Received: by mail-io1-f47.google.com with SMTP id a12so22808625ion.13 for ; Tue, 21 Jul 2020 13:23:36 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=iol.unh.edu; s=unh-iol; h=mime-version:from:date:message-id:subject:to; bh=OE21eIV8iRJ0hfo6ANPSKjtVgRwPfgKP5e3YSoQXM34=; b=PUixypohMgE7CJrjAFqGiNeUr7Qzhay8w+ag0Q/N6/6vsuDQ2wqgI5K9xYzvBalDed dGO4xtDiUc2mRTKZY1c2gx1FR2DfujTeQOCF8wY1gqzwwh/U8ez2hwA3lK93HtEv2/IM Tl75GL++y08VokMqzR4KuKFIEdz9galNAm7Ts= X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20161025; h=x-gm-message-state:mime-version:from:date:message-id:subject:to; bh=OE21eIV8iRJ0hfo6ANPSKjtVgRwPfgKP5e3YSoQXM34=; b=RncGtmknrLsKLTTl3QYzFhkEzYTdc6zwJYRmAasuLNsZq+n2/8YzM3LnDfFU0DUYO0 izT9xWmITvMtS6qc1Wl2GO6CEZhJj/yF4CQ5NVW9R44pr9gdlMBFsepsOoXudCk+GDKe stPsBMEfqLZjTSYaLaHokCt+KrCjevCJN8Nj/EeNLXMLPleZhz8UzmVTpZoGlSrYeYHK ZxGOocp+MJXS7f6/bqEF21MVbUPq6MUvcRBAyLUO0bSetJDo0mq+g3webyu7MUTBfkAu W1dT36e7WyEbCIQNvIPmfVi4d6MUKzrz5gDjHtTBGqZ7CbKhWZf3MfPOlm2dLtOCpdtf TaZg== X-Gm-Message-State: AOAM530Ki2M6qVv2n6mV77ha82AFkQusKW56eMAJBLbFiWdkARzcV0bP 1Ol8fq642/KYq6q89hEld1k+RSDW+azTooul3RjRAQ== X-Google-Smtp-Source: ABdhPJz1wRbyVujkjQfbE4ScsoFT3RR0cFoevi33wRhwuZEa8KGBpsuDFJrL6+AG8umHwCp1Zt2uU43tnfRJHegAlkU= X-Received: by 2002:a05:6638:1a:: with SMTP id z26mr7653815jao.15.1595363015586; Tue, 21 Jul 2020 13:23:35 -0700 (PDT) MIME-Version: 1.0 From: Brandon Lo Date: Tue, 21 Jul 2020 16:22:59 -0400 Message-ID: To: Ajit Khaparde , dpdklab , ci@dpdk.org Content-Type: multipart/alternative; boundary="000000000000d50b6d05aaf96539" Subject: [dpdk-ci] New 100G Broadcom NIC Ubuntu X-BeenThere: ci@dpdk.org X-Mailman-Version: 2.1.15 Precedence: list List-Id: DPDK CI discussions List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Errors-To: ci-bounces@dpdk.org Sender: "ci" --000000000000d50b6d05aaf96539 Content-Type: text/plain; charset="UTF-8" Hi Ajit, We've received the Broadcom 100G NIC and installed it onto the machine. However, the drivers don't seem to support Ubuntu, information from https://www.broadcom.com/products/ethernet-connectivity/network-adapters/100gb-nic-ocp/p2100g . I've also updated the kernel to the latest version. The card appears with the correct name in lspci and lshw, but it has no available MAC address, so I can't use it in setting up the nic single core performance testing. Do you know what could be causing this issue? Thanks, Brandon -- Brandon Lo UNH InterOperability Laboratory 21 Madbury Rd, Suite 100, Durham, NH 03824 blo@iol.unh.edu www.iol.unh.edu --000000000000d50b6d05aaf96539 Content-Type: text/html; charset="UTF-8" Content-Transfer-Encoding: quoted-printable
Hi Ajit,

We've received the Broadco= m 100G NIC and installed it onto the machine. However, the drivers don'= t seem to support Ubuntu, information from=C2=A0https://www.broadcom.com/products/ethernet-connectivity/network-adapter= s/100gb-nic-ocp/p2100g.=C2=A0

I've also up= dated the kernel to the latest version. The card appears with the correct n= ame in lspci and lshw, but it has no available MAC address, so I can't = use it in setting up the nic single core performance testing.
Do you know what could be causing this issue?=C2=A0
<= div>
Thanks,
Brandon

--

Brandon Lo

UNH InterOperabil= ity Laboratory

21 Madbury Rd, Suite 100, Durham, NH 03824

blo@iol.unh.edu

www.iol.unh.edu

--000000000000d50b6d05aaf96539-- From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from dpdk.org (dpdk.org [92.243.14.124]) by inbox.dpdk.org (Postfix) with ESMTP id 656A2A0526 for ; Tue, 21 Jul 2020 23:28:09 +0200 (CEST) Received: from [92.243.14.124] (localhost [127.0.0.1]) by dpdk.org (Postfix) with ESMTP id 403481C0B6; Tue, 21 Jul 2020 23:28:09 +0200 (CEST) Received: from mail-ot1-f46.google.com (mail-ot1-f46.google.com [209.85.210.46]) by dpdk.org (Postfix) with ESMTP id E25751C044 for ; Tue, 21 Jul 2020 23:28:07 +0200 (CEST) Received: by mail-ot1-f46.google.com with SMTP id w17so267791otl.4 for ; Tue, 21 Jul 2020 14:28:07 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=broadcom.com; s=google; h=mime-version:references:in-reply-to:from:date:message-id:subject:to :cc; bh=9+pEfYyWy4v8/1npqGSxjVecaMfV7rgNrYHzz9UBfRw=; b=ETpD9JcuHeObCeYBaHeAJ4vprrY9U1PEp31KOw8w3WQlOdNcl38BVdEHiiUpra7jfm nJfifDwnYQvPusOix0Cn+heQASCGpOjxt4zHhRnhJB3rrN886OnsBvgyHHVRFavkQ9MB lJt0KjL/lUd3rlomOas5/Zu3vQutF1RG74Y/g= X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20161025; h=x-gm-message-state:mime-version:references:in-reply-to:from:date :message-id:subject:to:cc; bh=9+pEfYyWy4v8/1npqGSxjVecaMfV7rgNrYHzz9UBfRw=; b=FhPZWiWjZj0opeiScZGkhBiFpKjD6fZutfzJfED7nNtSPo1wY104U0AehYGCrMLsWQ neReT7MyPjsZq6xyTOCdj3jKIIP2+kkRFGEVM/JwCbpW6yDsbqwGrB/7nHi+LE+NJ61U O6myqt4sswJIG4DPY6aZo36XJX+kqc4Cf03oTY/gQZrzcZAe8p9MlTb7ae+KGtjl7Szm 8gjK/R5pz7vfdhKj0H/Ci2ejLfoDa0n0CJqrNCn9I5WczAKpRQ9kmHTR8s5PYuhlgX5b HfKjkxaEjWlk+neIg5vG0K8AoCOMHD7yATJKMkOr//k4by8sRA/X0LWSGtoAA8k/UdoU wucQ== X-Gm-Message-State: AOAM533pTg+T4NUbXgQgJjxfkmBf389LTvkDwX7Ln9lRmyjygcH2b3kR Iabwf1w9n5+VpZ5vIDtlB8YQWJPrQIo1GP4UuLb6KA== X-Google-Smtp-Source: ABdhPJyAIM6MrKl/Dv/schVgrlWj8RHoaIh7L2UvYu1HTyhEQKFlVCJvK6ObtbWM0X8nsWuU1R7WC3iKP/mq3vmquds= X-Received: by 2002:a9d:3b1:: with SMTP id f46mr28082543otf.154.1595366886805; Tue, 21 Jul 2020 14:28:06 -0700 (PDT) MIME-Version: 1.0 References: In-Reply-To: From: Ajit Khaparde Date: Tue, 21 Jul 2020 14:27:50 -0700 Message-ID: To: Brandon Lo Cc: ci@dpdk.org, dpdklab Content-Type: multipart/alternative; boundary="000000000000935f9c05aafa4c50" Subject: Re: [dpdk-ci] New 100G Broadcom NIC Ubuntu X-BeenThere: ci@dpdk.org X-Mailman-Version: 2.1.15 Precedence: list List-Id: DPDK CI discussions List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Errors-To: ci-bounces@dpdk.org Sender: "ci" --000000000000935f9c05aafa4c50 Content-Type: text/plain; charset="UTF-8" Hi Brandon, Maybe I might have to update it to a newer firmware. Let me check internally and get back. Thanks Ajit On Tue, Jul 21, 2020 at 1:23 PM Brandon Lo wrote: > Hi Ajit, > > We've received the Broadcom 100G NIC and installed it onto the machine. > However, the drivers don't seem to support Ubuntu, information from > https://www.broadcom.com/products/ethernet-connectivity/network-adapters/100gb-nic-ocp/p2100g > . > > I've also updated the kernel to the latest version. The card appears with > the correct name in lspci and lshw, but it has no available MAC address, so > I can't use it in setting up the nic single core performance testing. > > Do you know what could be causing this issue? > > Thanks, > Brandon > > > -- > > Brandon Lo > > UNH InterOperability Laboratory > > 21 Madbury Rd, Suite 100, Durham, NH 03824 > > > blo@iol.unh.edu > > www.iol.unh.edu > --000000000000935f9c05aafa4c50 Content-Type: text/html; charset="UTF-8" Content-Transfer-Encoding: quoted-printable
Hi Brandon,
Maybe I might have to update it to a newer firmware.<= br>
Let me check internally and get back.

Thanks
Ajit


On Tue, Jul 21, 2020 at 1:23 PM Brandon Lo &l= t;blo@iol.unh.edu&= gt; wrote:
Hi Ajit,

We've received the Broadcom 100= G NIC and installed it onto the machine. However, the drivers don't see= m to support Ubuntu, information from=C2=A0https://www.broadcom.com/products/ethernet-connectivity/ne= twork-adapters/100gb-nic-ocp/p2100g.=C2=A0

I&#= 39;ve also updated the kernel to the latest version. The card appears with = the correct name in lspci and lshw, but it has no available MAC address, so= I can't use it in setting up the nic single core performance testing.<= /div>

Do you know what could be causing this issue?=C2= =A0

Thanks,
Brandon
--000000000000935f9c05aafa4c50-- From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from dpdk.org (dpdk.org [92.243.14.124]) by inbox.dpdk.org (Postfix) with ESMTP id D02D4A052B for ; Tue, 28 Jul 2020 18:48:34 +0200 (CEST) Received: from [92.243.14.124] (localhost [127.0.0.1]) by dpdk.org (Postfix) with ESMTP id 98E451BE8A; Tue, 28 Jul 2020 18:48:34 +0200 (CEST) Received: from mail-il1-f169.google.com (mail-il1-f169.google.com [209.85.166.169]) by dpdk.org (Postfix) with ESMTP id 2917E2B9C for ; Tue, 28 Jul 2020 18:48:33 +0200 (CEST) Received: by mail-il1-f169.google.com with SMTP id b18so11574489ilo.12 for ; Tue, 28 Jul 2020 09:48:33 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=iol.unh.edu; s=unh-iol; h=mime-version:references:in-reply-to:from:date:message-id:subject:to :cc; bh=5Xuyg3VIvxkaG96s3TtLX0+EtwyTNcG1CXh1LTYHPeA=; b=iNPjKFYWMeJklwTnbh3u0scxG2CDbJUMhsIcjcU3vrMjOLKhTtU2BqJDVEPQs9/GhI ZSDkha/OuhxkactBg/NiRNo8pagDquGlcexaJYjA14MLNIjvkcjEQfdGx67YGzVDSpay jsj2FyzPAppc205c93WGDsPMgMMaG66Co/tjY= X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20161025; h=x-gm-message-state:mime-version:references:in-reply-to:from:date :message-id:subject:to:cc; bh=5Xuyg3VIvxkaG96s3TtLX0+EtwyTNcG1CXh1LTYHPeA=; b=uSXiD0jscrmsMONgVCIU3wN72xD+xVH6msW4Vvb7b0JT2hM8ocyXwBzh6he8E0NX0x vZdCPABkNySQxwNockErIx0T+3UsoATyYI1YkjY9TWdO0C/smTHxBHsdcvQAB4Uo7CaC CLAF0HrUhcEQQPkN1RwGyhNoVMnCfn7Oag340VJJGerS5DNQAN5i2skEBnhNpwpj5qRq gT0qi+5GeRzHwmr447Cj0UvQDW8cFkm7HKesrnLmOIz9r8I6Gyff/VIwQSS3DEyUt4k9 lG9dnBqbVOUuVEI6eD25hl7liQl709ukWdaLN5xEDWEY5AEVXsAo1AJlhBJ6HVPRVGlH EQhw== X-Gm-Message-State: AOAM530rYy5SvufKkY2encwWyWQ56TxltT216ePcq8dgiIgxaSc3ga8h OsCuTgpBRiAD9U8O9ZWTvvVxnW8EqJH2BCt8aA8B9g== X-Google-Smtp-Source: ABdhPJxp9VglCT26Sgdu3kFN8bkR8KuFpDcgQj4rzTZxSn1SpuNX62/gsKR9+6iFmnNfLmozZUoS+nEQIgi0hSXmfdc= X-Received: by 2002:a92:d910:: with SMTP id s16mr22866584iln.20.1595954912408; Tue, 28 Jul 2020 09:48:32 -0700 (PDT) MIME-Version: 1.0 References: In-Reply-To: From: Brandon Lo Date: Tue, 28 Jul 2020 12:47:56 -0400 Message-ID: To: Ajit Khaparde Cc: ci@dpdk.org, dpdklab Content-Type: multipart/alternative; boundary="000000000000a1d69e05ab833521" Subject: Re: [dpdk-ci] New 100G Broadcom NIC Ubuntu X-BeenThere: ci@dpdk.org X-Mailman-Version: 2.1.15 Precedence: list List-Id: DPDK CI discussions List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Errors-To: ci-bounces@dpdk.org Sender: "ci" --000000000000a1d69e05ab833521 Content-Type: text/plain; charset="UTF-8" Hi Ajit, Have you gotten a response yet? I've tried the firmware from the official website but it's supported on Fedora/Redhat instead of Ubuntu. Thanks, Brandon On Tue, Jul 21, 2020 at 5:28 PM Ajit Khaparde wrote: > Hi Brandon, > Maybe I might have to update it to a newer firmware. > Let me check internally and get back. > > Thanks > Ajit > > > On Tue, Jul 21, 2020 at 1:23 PM Brandon Lo wrote: > >> Hi Ajit, >> >> We've received the Broadcom 100G NIC and installed it onto the machine. >> However, the drivers don't seem to support Ubuntu, information from >> https://www.broadcom.com/products/ethernet-connectivity/network-adapters/100gb-nic-ocp/p2100g >> . >> >> I've also updated the kernel to the latest version. The card appears with >> the correct name in lspci and lshw, but it has no available MAC address, so >> I can't use it in setting up the nic single core performance testing. >> >> Do you know what could be causing this issue? >> >> Thanks, >> Brandon >> >> >> -- >> >> Brandon Lo >> >> UNH InterOperability Laboratory >> >> 21 Madbury Rd, Suite 100, Durham, NH 03824 >> >> >> blo@iol.unh.edu >> >> www.iol.unh.edu >> > -- Brandon Lo UNH InterOperability Laboratory 21 Madbury Rd, Suite 100, Durham, NH 03824 blo@iol.unh.edu www.iol.unh.edu --000000000000a1d69e05ab833521 Content-Type: text/html; charset="UTF-8" Content-Transfer-Encoding: quoted-printable
Hi Ajit,

Have you gotten a response yet= ?
I've tried the firmware from the official website but it= 9;s supported on Fedora/Redhat instead of Ubuntu.

= Thanks,
Brandon

On Tue, Jul 21, 2020 at 5:28 PM Ajit Khapard= e <ajit.khaparde@broadcom.= com> wrote:
Hi Brandon,
Maybe I might have to update it to a newer firmwar= e.
Let me check internally and get back.

Thanks
Ajit


On Tue, Jul 21, 2020 at 1:23 PM Brandon L= o <blo@iol.unh.edu<= /a>> wrote:
<= div dir=3D"ltr">Hi Ajit,


I've also updated the kernel to the latest version. The card appears w= ith the correct name in lspci and lshw, but it has no available MAC address= , so I can't use it in setting up the nic single core performance testi= ng.

Do you know what could be causing this issue?= =C2=A0

Thanks,
Brandon
<= /div>


--
<= /div>


--

Brandon Lo

UNH = InterOperability Laboratory

21 Madbury Rd, Suite 100, Durham, NH 03824

blo@iol.unh.edu

<= a href=3D"http://www.iol.unh.edu/" target=3D"_blank">www.iol.unh.edu

--000000000000a1d69e05ab833521-- From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from dpdk.org (dpdk.org [92.243.14.124]) by inbox.dpdk.org (Postfix) with ESMTP id 17A09A052B for ; Tue, 28 Jul 2020 19:22:54 +0200 (CEST) Received: from [92.243.14.124] (localhost [127.0.0.1]) by dpdk.org (Postfix) with ESMTP id 0F6411BE8A; Tue, 28 Jul 2020 19:22:54 +0200 (CEST) Received: from mail-ot1-f46.google.com (mail-ot1-f46.google.com [209.85.210.46]) by dpdk.org (Postfix) with ESMTP id C81AE2B8D for ; Tue, 28 Jul 2020 19:22:52 +0200 (CEST) Received: by mail-ot1-f46.google.com with SMTP id a26so6646434otf.1 for ; Tue, 28 Jul 2020 10:22:52 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=broadcom.com; s=google; h=mime-version:references:in-reply-to:from:date:message-id:subject:to :cc; bh=4jGORJImqhDL7De31AoFt/jHRGC5T2NvalinKsAX/UU=; b=NZA0DRxFOKk6X6fc7mVppI9pDjSdTOLAM4JfyMG7ZwnzcgcQHU6dueM3wF/9ihrAyu 852Y30CcD88wS9sVrzfYx02bZ+QxORKq46qkvsEAnJrvJndGjXj2pQcpKyYSGr146pPn LczAScSB92xLH1iVlRol5FxVI8B/TPGvTEf20= X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20161025; h=x-gm-message-state:mime-version:references:in-reply-to:from:date :message-id:subject:to:cc; bh=4jGORJImqhDL7De31AoFt/jHRGC5T2NvalinKsAX/UU=; b=lKtztWZQcVR8rLQ+ac0Wjj3nNDkLpecKTDAJ3z10TWmI9mEXyF4W5hFuU9BMs0SI2s vDGs57/4nEAtevg1QhKq/sT54mn6wA2U7GRyyv0g/bF1NNwfYdRFJQha7FqPC4DBj1B5 fc+DZ4IMtdko6UpKZkzA8MOD9R1fAH0aQ2XyYrbEOpzQOVqmxNKnH/G/2LS4gTnflugJ jCuCxq0uaVfTG8Kxee9aQtd3/8/XLtATtsAUYrv1xKBK28iMqI/KGYVUd7QkVyiMBw1B /gAeekTkRn7+vOvjoXbuz0Fiz0W6gt9EjLLIxWQC6YNdLGorGb6cqC7o12IUj53ReE3q uexQ== X-Gm-Message-State: AOAM531rgqb426DdgS9UlBK1jg2I7PmTeze6P1WKzwtG/l9bcckXiXfP 8gUMDTsgE5B/NmcfNLn6mmkBUIRLdEV5ip+wMitI0w== X-Google-Smtp-Source: ABdhPJyYQqox2ZjV1A+6Fixq4AYH6Z/wQBvFoWXsnbyVv1Plp8K8RbQvvdI8ki5MVs+7KJmTbuvmOuygT+e4f9qOy1o= X-Received: by 2002:a9d:5f92:: with SMTP id g18mr23544886oti.95.1595956971793; Tue, 28 Jul 2020 10:22:51 -0700 (PDT) MIME-Version: 1.0 References: In-Reply-To: From: Ajit Khaparde Date: Tue, 28 Jul 2020 10:22:35 -0700 Message-ID: To: Brandon Lo Cc: ci@dpdk.org, dpdklab Content-Type: multipart/alternative; boundary="00000000000061e8b305ab83b020" Subject: Re: [dpdk-ci] New 100G Broadcom NIC Ubuntu X-BeenThere: ci@dpdk.org X-Mailman-Version: 2.1.15 Precedence: list List-Id: DPDK CI discussions List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Errors-To: ci-bounces@dpdk.org Sender: "ci" --00000000000061e8b305ab83b020 Content-Type: text/plain; charset="UTF-8" Brandon, I have sent them a reminder. I will keep you posted. But I tried to login into the system to peek around and the VPN seems to continuously negotiate/authenticate. For some reason the connection is getting reset. Any idea on what might be causing this? Thanks Ajit On Tue, Jul 28, 2020 at 9:48 AM Brandon Lo wrote: > Hi Ajit, > > Have you gotten a response yet? > I've tried the firmware from the official website but it's supported on > Fedora/Redhat instead of Ubuntu. > > Thanks, > Brandon > > On Tue, Jul 21, 2020 at 5:28 PM Ajit Khaparde > wrote: > >> Hi Brandon, >> Maybe I might have to update it to a newer firmware. >> Let me check internally and get back. >> >> Thanks >> Ajit >> >> >> On Tue, Jul 21, 2020 at 1:23 PM Brandon Lo wrote: >> >>> Hi Ajit, >>> >>> We've received the Broadcom 100G NIC and installed it onto the machine. >>> However, the drivers don't seem to support Ubuntu, information from >>> https://www.broadcom.com/products/ethernet-connectivity/network-adapters/100gb-nic-ocp/p2100g >>> . >>> >>> I've also updated the kernel to the latest version. The card appears >>> with the correct name in lspci and lshw, but it has no available MAC >>> address, so I can't use it in setting up the nic single core performance >>> testing. >>> >>> Do you know what could be causing this issue? >>> >>> Thanks, >>> Brandon >>> >>> >>> -- >>> >>> Brandon Lo >>> >>> UNH InterOperability Laboratory >>> >>> 21 Madbury Rd, Suite 100, Durham, NH 03824 >>> >>> >>> blo@iol.unh.edu >>> >>> www.iol.unh.edu >>> >> > > -- > > Brandon Lo > > UNH InterOperability Laboratory > > 21 Madbury Rd, Suite 100, Durham, NH 03824 > > blo@iol.unh.edu > > www.iol.unh.edu > --00000000000061e8b305ab83b020 Content-Type: text/html; charset="UTF-8" Content-Transfer-Encoding: quoted-printable
Brandon,
I have sent them a reminder. I will keep you posted.
But = I tried to login into the system to peek around and the VPN seems to
<= div class=3D"gmail_default" style=3D"font-family:tahoma,sans-serif">continu= ously negotiate/authenticate. For some=C2=A0reason the connection
is getting= reset.
Any idea on what might be=C2=A0causing this?

Thanks
Ajit=
= On Tue, Jul 28, 2020 at 9:48 AM Brandon Lo <blo@iol.unh.edu> wrote:
Hi Ajit,

Have you= gotten a response yet?
I've tried the firmware from the offi= cial website but it's supported on Fedora/Redhat instead of Ubuntu.

Thanks,
Brandon

On Tue, Jul 21, 2020= at 5:28 PM Ajit Khaparde <ajit.khaparde@broadcom.com> wrote:
Hi Brandon,
Maybe I = might have to update it to a newer firmware.
Let me check internally and= get back.

Thanks
Ajit

=

O= n Tue, Jul 21, 2020 at 1:23 PM Brandon Lo <blo@iol.unh.edu> wrote:
Hi Ajit,

We've received the Broadcom 100G NIC and installed it onto the= machine. However, the drivers don't seem to support Ubuntu, informatio= n from=C2=A0https://www.br= oadcom.com/products/ethernet-connectivity/network-adapters/100gb-nic-ocp/p2= 100g.=C2=A0

I've also updated the kernel t= o the latest version. The card appears with the correct name in lspci and l= shw, but it has no available MAC address, so I can't use it in setting = up the nic single core performance testing.

Do you= know what could be causing this issue?=C2=A0

Thanks,
Brandon


--

Brandon Lo

UNH InterOperability Laborator= y

21 Madbury Rd, Suite 100, Durham, NH 03824

blo@iol.unh.edu

www.iol.unh.edu

--00000000000061e8b305ab83b020-- From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from dpdk.org (dpdk.org [92.243.14.124]) by inbox.dpdk.org (Postfix) with ESMTP id 0E1AEA052B for ; Tue, 28 Jul 2020 19:33:04 +0200 (CEST) Received: from [92.243.14.124] (localhost [127.0.0.1]) by dpdk.org (Postfix) with ESMTP id C30321BE8A; Tue, 28 Jul 2020 19:33:03 +0200 (CEST) Received: from mail-io1-f45.google.com (mail-io1-f45.google.com [209.85.166.45]) by dpdk.org (Postfix) with ESMTP id B14A010A3 for ; Tue, 28 Jul 2020 19:33:02 +0200 (CEST) Received: by mail-io1-f45.google.com with SMTP id a5so6370203ioa.13 for ; Tue, 28 Jul 2020 10:33:02 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=iol.unh.edu; s=unh-iol; h=mime-version:references:in-reply-to:from:date:message-id:subject:to :cc; bh=TFKj2tlaQlDxjjmeXkN7FCWrZX/muZ9hkmitm+Qtnv4=; b=PVsL4vOmXr/W5MqUDgrF46REm/Du1Ue0KL33HPY3TsdJxjr3GWWlOqfAT1PMPHYndC Wsb+dqK0PxsrFHk1eVDI6DvdP0RNNVrmrbA00OMRr1z7FBa3PJrMRhybvCnDC8oMhmvw z0IeBnX++UFkKdcuSW4sc0b5AMBhj6R5Kl+fw= X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20161025; h=x-gm-message-state:mime-version:references:in-reply-to:from:date :message-id:subject:to:cc; bh=TFKj2tlaQlDxjjmeXkN7FCWrZX/muZ9hkmitm+Qtnv4=; b=G+7i/jOavlVu6QmlfmkkrXOMHLR8VwX+74G77pTevFmzJtv3hUtQnjPgwMGF612CWB 7TlV5vUbD3/iogkfShssqyQjAGVNLfGYlTJLosfrWGMJT/l4rUmNJBS1ageGQLSf3LDu na+WKYy9wD5p3O3GD4Hr3GdPaq1NyEOTcMqqhkU0LagBHuvhNpK9R5xHykfnOHD4YqAX c6/K6V/T6NmZ8FS7jeVEK+J3G/cBs8UGE18JRw/qWBgqUlAx6nVaH2zAxdCn3mjUrwpS 42pbWQEwmQ398lEP7UCkkTYLQi/fxJmuupoFaDdIj52jOgbwdCQycl0+N7uphya+oDCh 7xDw== X-Gm-Message-State: AOAM531gjQ/xyUNQ5QS5SWZtaSYFxo5tDlJ01yIFSjjV0LVbssghPgWJ KZ8alfeNshIqGcRY8VenaczsMn8rimZLJl1ZmiuUbA== X-Google-Smtp-Source: ABdhPJyPFQShAb5fKvzl72tjPXyVI7szC4h9OkGUnvJf37XsstJ5rn1tacrb2+epOzFzIIuQlsyY+HPUEuAg9ijbsws= X-Received: by 2002:a02:93c5:: with SMTP id z63mr10910318jah.70.1595957581901; Tue, 28 Jul 2020 10:33:01 -0700 (PDT) MIME-Version: 1.0 References: In-Reply-To: From: Brandon Lo Date: Tue, 28 Jul 2020 13:32:25 -0400 Message-ID: To: Ajit Khaparde Cc: ci@dpdk.org, dpdklab Content-Type: multipart/alternative; boundary="000000000000bf1b9b05ab83d46d" Subject: Re: [dpdk-ci] New 100G Broadcom NIC Ubuntu X-BeenThere: ci@dpdk.org X-Mailman-Version: 2.1.15 Precedence: list List-Id: DPDK CI discussions List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Errors-To: ci-bounces@dpdk.org Sender: "ci" --000000000000bf1b9b05ab83d46d Content-Type: text/plain; charset="UTF-8" Hi Ajit, That issue occurs sometimes on my end as well. There's no clear solution other than to try again later. I will look into the issue and try to make a permanent fix. Thanks, Brandon On Tue, Jul 28, 2020 at 1:22 PM Ajit Khaparde wrote: > Brandon, > I have sent them a reminder. I will keep you posted. > But I tried to login into the system to peek around and the VPN seems to > continuously negotiate/authenticate. For some reason the connection > is getting reset. > Any idea on what might be causing this? > > Thanks > Ajit > > On Tue, Jul 28, 2020 at 9:48 AM Brandon Lo wrote: > >> Hi Ajit, >> >> Have you gotten a response yet? >> I've tried the firmware from the official website but it's supported on >> Fedora/Redhat instead of Ubuntu. >> >> Thanks, >> Brandon >> >> On Tue, Jul 21, 2020 at 5:28 PM Ajit Khaparde >> wrote: >> >>> Hi Brandon, >>> Maybe I might have to update it to a newer firmware. >>> Let me check internally and get back. >>> >>> Thanks >>> Ajit >>> >>> >>> On Tue, Jul 21, 2020 at 1:23 PM Brandon Lo wrote: >>> >>>> Hi Ajit, >>>> >>>> We've received the Broadcom 100G NIC and installed it onto the machine. >>>> However, the drivers don't seem to support Ubuntu, information from >>>> https://www.broadcom.com/products/ethernet-connectivity/network-adapters/100gb-nic-ocp/p2100g >>>> . >>>> >>>> I've also updated the kernel to the latest version. The card appears >>>> with the correct name in lspci and lshw, but it has no available MAC >>>> address, so I can't use it in setting up the nic single core performance >>>> testing. >>>> >>>> Do you know what could be causing this issue? >>>> >>>> Thanks, >>>> Brandon >>>> >>>> >>>> -- >>>> >>>> Brandon Lo >>>> >>>> UNH InterOperability Laboratory >>>> >>>> 21 Madbury Rd, Suite 100, Durham, NH 03824 >>>> >>>> >>>> blo@iol.unh.edu >>>> >>>> www.iol.unh.edu >>>> >>> >> >> -- >> >> Brandon Lo >> >> UNH InterOperability Laboratory >> >> 21 Madbury Rd, Suite 100, Durham, NH 03824 >> >> blo@iol.unh.edu >> >> www.iol.unh.edu >> > -- Brandon Lo UNH InterOperability Laboratory 21 Madbury Rd, Suite 100, Durham, NH 03824 blo@iol.unh.edu www.iol.unh.edu --000000000000bf1b9b05ab83d46d Content-Type: text/html; charset="UTF-8" Content-Transfer-Encoding: quoted-printable
Hi Ajit,

That issue occurs sometimes on= my end as well. There's no clear solution other than to try again late= r.
I will look into the issue and try to make a permanent fix.

Thanks,
Brandon

On Tue, Jul 28, 2020= at 1:22 PM Ajit Khaparde <ajit.khaparde@broadcom.com> wrote:
Brandon,
I have sent them a reminder. = I will keep you posted.
But I tried to login into the system to peek around = and the VPN seems to
continuously negotiate/authenticate. For some=C2=A0reas= on the connection
is getting reset.
Any idea on what might be=C2=A0causing t= his?

Thanks
Ajit

On Tue, Jul 28, 2020 at 9:48 AM Brandon Lo &l= t;blo@iol.unh.edu&= gt; wrote:
Hi Ajit,

Have you gotten a response yet?
I've tried the firmware from the official website but it's s= upported on Fedora/Redhat instead of Ubuntu.

Thank= s,
Brandon

On Tue, Jul 21, 2020 at 5:28 PM Ajit Khaparde <= ;ajit.khapa= rde@broadcom.com> wrote:
Hi Brandon,
Maybe I might have to update it to a = newer firmware.
Let me check internally and get back.

Thanks
Ajit


On Tue, Jul 21, 2020 at 1:23 P= M Brandon Lo <blo@i= ol.unh.edu> wrote:
Hi Ajit,

We've received = the Broadcom 100G NIC and installed it onto the machine. However, the drive= rs don't seem to support Ubuntu, information from=C2=A0https://www.broadcom.com/products/ethernet= -connectivity/network-adapters/100gb-nic-ocp/p2100g.=C2=A0
I've also updated the kernel to the latest version. The ca= rd appears with the correct name in lspci and lshw, but it has no available= MAC address, so I can't use it in setting up the nic single core perfo= rmance testing.

Do you know what could be causing = this issue?=C2=A0

Thanks,
Brandon


--

Brandon Lo

UNH InterOperability Laborator= y

21 Madbury Rd, Suite 100, Durham, NH 03824

blo@iol.unh.edu

www.iol.unh.edu



--

Brandon Lo

UNH = InterOperability Laboratory

21 Madbury Rd, Suite 100, Durham, NH 03824

blo@iol.unh.edu

<= a href=3D"http://www.iol.unh.edu/" target=3D"_blank">www.iol.unh.edu

--000000000000bf1b9b05ab83d46d-- From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from dpdk.org (dpdk.org [92.243.14.124]) by inbox.dpdk.org (Postfix) with ESMTP id 28A3EA052B for ; Tue, 28 Jul 2020 21:19:44 +0200 (CEST) Received: from [92.243.14.124] (localhost [127.0.0.1]) by dpdk.org (Postfix) with ESMTP id DDCEC2B9C; Tue, 28 Jul 2020 21:19:43 +0200 (CEST) Received: from mail-oi1-f172.google.com (mail-oi1-f172.google.com [209.85.167.172]) by dpdk.org (Postfix) with ESMTP id 727922AB for ; Tue, 28 Jul 2020 21:19:42 +0200 (CEST) Received: by mail-oi1-f172.google.com with SMTP id u63so6773742oie.5 for ; Tue, 28 Jul 2020 12:19:42 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=broadcom.com; s=google; h=mime-version:references:in-reply-to:from:date:message-id:subject:to :cc; bh=s2vxgIEHUldchjbB4wnhYl/Inn4bFfmIrMeUBC+1g4w=; b=I+PR8YYJWmUcaz7lCWGznuWDUHVSjXsahBNCuOvptyvoahkdmgDiRjzuBNYmRBJrHp bmA6nNJ8EQV/BYiw+lgRqm9RZXRegE0cVDmWux9R4WC+T8/uoV5rLv/5IkD1Lu4CA3Hy r7TII0lc4OdnXs3v9RXdavpetV7/EgX3jJy+s= X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20161025; h=x-gm-message-state:mime-version:references:in-reply-to:from:date :message-id:subject:to:cc; bh=s2vxgIEHUldchjbB4wnhYl/Inn4bFfmIrMeUBC+1g4w=; b=KMyqo8dhNPh/ccK4y2/XOzWaWO2aoI33TCVuOoVYKxBuiZuNH0MYzpDsYJMp99mwI2 9yXecI5tuj505Jx0c4BhElLJQdhUsjgTNTWHqmM0wwZXDotKIKxCC78I8CcYEMy4q2Vk U5Vpm/5IfcqXxhAWppISrRAFfX8kmaKZgIpWPK/Q78cQdHNiPE9LIXkEX2SHaEYS9LMw sWOGArIbP+ie2m/Zj3TvSB2MRc/EN107RQzKUJ3q3JCU0IJ5LQ30VuwJ3Dr//50RHOtd q5AtLEr/CZwzlkXSPzbwuxeuJreiEdQ19EIz7NQ8SM2Qv548bAEXqTUPnxj4t2H+qpw6 BU0A== X-Gm-Message-State: AOAM532Jh5oPVN17o/P+KLw+K3q5R8Nh8Wm9O8QrTvNE4FD3rdEmNN4k yyMdwyV3arhlJTZzxkLS4qVGDCzLWy5Pj9CzHvkyBg== X-Google-Smtp-Source: ABdhPJyT0+z0GH4BmfSaD8YtUOJ3Eg8R/O7q9XJnu2bYqwdfgCkNPPMBtROeBXnJsdZfD0+WNGZ6/kGpx7g/SjtemC4= X-Received: by 2002:aca:3883:: with SMTP id f125mr4947329oia.27.1595963981405; Tue, 28 Jul 2020 12:19:41 -0700 (PDT) MIME-Version: 1.0 References: In-Reply-To: From: Ajit Khaparde Date: Tue, 28 Jul 2020 12:19:25 -0700 Message-ID: To: Brandon Lo Cc: ci@dpdk.org, dpdklab Content-Type: multipart/alternative; boundary="0000000000002ff38205ab85522b" Subject: Re: [dpdk-ci] New 100G Broadcom NIC Ubuntu X-BeenThere: ci@dpdk.org X-Mailman-Version: 2.1.15 Precedence: list List-Id: DPDK CI discussions List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Errors-To: ci-bounces@dpdk.org Sender: "ci" --0000000000002ff38205ab85522b Content-Type: text/plain; charset="UTF-8" Hi Brandon, I copied over a more recent code for the NIC. And it loads fine on the two systems. The code is currently in /home/ajitkhaparde/bnxt_en-1.10.1-216.1.142.0 Till I find a release version of the driver for Ubuntu, we could use this? We can copy the bnxt_en.ko over to /lib/modules/4.15.0-112-generic/kernel/drivers/net/ethernet/broa dcom/bnxt/bnxt_en.ko Please let me know. Thanks Ajit On Tue, Jul 28, 2020 at 10:33 AM Brandon Lo wrote: > Hi Ajit, > > That issue occurs sometimes on my end as well. There's no clear solution > other than to try again later. > I will look into the issue and try to make a permanent fix. > > Thanks, > Brandon > > On Tue, Jul 28, 2020 at 1:22 PM Ajit Khaparde > wrote: > >> Brandon, >> I have sent them a reminder. I will keep you posted. >> But I tried to login into the system to peek around and the VPN seems to >> continuously negotiate/authenticate. For some reason the connection >> is getting reset. >> Any idea on what might be causing this? >> >> Thanks >> Ajit >> >> On Tue, Jul 28, 2020 at 9:48 AM Brandon Lo wrote: >> >>> Hi Ajit, >>> >>> Have you gotten a response yet? >>> I've tried the firmware from the official website but it's supported on >>> Fedora/Redhat instead of Ubuntu. >>> >>> Thanks, >>> Brandon >>> >>> On Tue, Jul 21, 2020 at 5:28 PM Ajit Khaparde < >>> ajit.khaparde@broadcom.com> wrote: >>> >>>> Hi Brandon, >>>> Maybe I might have to update it to a newer firmware. >>>> Let me check internally and get back. >>>> >>>> Thanks >>>> Ajit >>>> >>>> >>>> On Tue, Jul 21, 2020 at 1:23 PM Brandon Lo wrote: >>>> >>>>> Hi Ajit, >>>>> >>>>> We've received the Broadcom 100G NIC and installed it onto the >>>>> machine. However, the drivers don't seem to support Ubuntu, information >>>>> from >>>>> https://www.broadcom.com/products/ethernet-connectivity/network-adapters/100gb-nic-ocp/p2100g >>>>> . >>>>> >>>>> I've also updated the kernel to the latest version. The card appears >>>>> with the correct name in lspci and lshw, but it has no available MAC >>>>> address, so I can't use it in setting up the nic single core performance >>>>> testing. >>>>> >>>>> Do you know what could be causing this issue? >>>>> >>>>> Thanks, >>>>> Brandon >>>>> >>>>> >>>>> -- >>>>> >>>>> Brandon Lo >>>>> >>>>> UNH InterOperability Laboratory >>>>> >>>>> 21 Madbury Rd, Suite 100, Durham, NH 03824 >>>>> >>>>> >>>>> blo@iol.unh.edu >>>>> >>>>> www.iol.unh.edu >>>>> >>>> >>> >>> -- >>> >>> Brandon Lo >>> >>> UNH InterOperability Laboratory >>> >>> 21 Madbury Rd, Suite 100, Durham, NH 03824 >>> >>> blo@iol.unh.edu >>> >>> www.iol.unh.edu >>> >> > > -- > > Brandon Lo > > UNH InterOperability Laboratory > > 21 Madbury Rd, Suite 100, Durham, NH 03824 > > blo@iol.unh.edu > > www.iol.unh.edu > --0000000000002ff38205ab85522b Content-Type: text/html; charset="UTF-8" Content-Transfer-Encoding: quoted-printable
Hi Brandon,
I copied over a more recent code for the NIC.
And it l= oads fine on the two systems.
The code is currently in=C2=A0/home/ajitkhapar= de/bnxt_en-1.10.1-216.1.142.0
Till I find a release version of the driver fo= r Ubuntu, we could use this?
<= font face=3D"tahoma, sans-serif">We can copy the bnxt_en.ko over to
/lib/modules/4.15= .0-112-generic/kernel/drivers/net/ethernet/broadcom/bnxt/bnxt_en.ko<= /div>

Please let me know.

Thanks
Ajit

On Tue, Jul 28, 2020 at 10:3= 3 AM Brandon Lo <blo@iol.unh.edu&= gt; wrote:
Hi Ajit,

That issue occurs sometimes on my e= nd as well. There's no clear solution other than to try again later.
I will look into the issue and try to make a permanent fix.

Thanks,
Brandon

On Tue, Jul 28, 2020 at 1:= 22 PM Ajit Khaparde <ajit.khaparde@broadcom.com> wrote:
Brandon,
I have sent them= a reminder. I will keep you posted.
But I tried to login into the system to= peek around and the VPN seems to
continuously negotiate/authenticate. For= some=C2=A0reason the connection
is getting reset.
Any idea on what might be= =C2=A0causing this?

Thanks
Ajit

On Tue, Jul 28, 2020 at 9:48 A= M Brandon Lo <blo@i= ol.unh.edu> wrote:
Hi Ajit,

Have you gotten a r= esponse yet?
I've tried the firmware from the official websit= e but it's supported on Fedora/Redhat instead of Ubuntu.

=
Thanks,
Brandon

On Tue, Jul 21, 2020 at 5:28 PM A= jit Khaparde <ajit.khaparde@broadcom.com> wrote:
Hi Brandon,
Maybe I might have t= o update it to a newer firmware.
Let me check internally and get back.
Thanks
Ajit


On Tue, Jul 2= 1, 2020 at 1:23 PM Brandon Lo <blo@iol.unh.edu> wrote:
Hi Ajit,

We&= #39;ve received the Broadcom 100G NIC and installed it onto the machine. Ho= wever, the drivers don't seem to support Ubuntu, information from=C2=A0= https://www.broadcom.com/p= roducts/ethernet-connectivity/network-adapters/100gb-nic-ocp/p2100g.=C2= =A0

I've also updated the kernel to the latest= version. The card appears with the correct name in lspci and lshw, but it = has no available MAC address, so I can't use it in setting up the nic s= ingle core performance testing.

Do you know what c= ould be causing this issue?=C2=A0

Thanks,
Brandon


--

= Brandon Lo

UNH InterOperability Laboratory

21 Madbury Rd, Suite 100, Durham, NH 03824<= /span>

blo@iol.unh.edu=

www.iol.unh.edu



--


--

Brandon Lo

UNH InterOperability Laborator= y

21 Madbury Rd, Suite 100, Durham, NH 03824

blo@iol.unh.edu

www.iol.unh.edu

--0000000000002ff38205ab85522b-- From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from dpdk.org (dpdk.org [92.243.14.124]) by inbox.dpdk.org (Postfix) with ESMTP id 026B4A052B for ; Tue, 28 Jul 2020 21:41:49 +0200 (CEST) Received: from [92.243.14.124] (localhost [127.0.0.1]) by dpdk.org (Postfix) with ESMTP id BC4F02B86; Tue, 28 Jul 2020 21:41:49 +0200 (CEST) Received: from mail-io1-f48.google.com (mail-io1-f48.google.com [209.85.166.48]) by dpdk.org (Postfix) with ESMTP id E15F11023 for ; Tue, 28 Jul 2020 21:41:47 +0200 (CEST) Received: by mail-io1-f48.google.com with SMTP id e64so21999111iof.12 for ; Tue, 28 Jul 2020 12:41:47 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=iol.unh.edu; s=unh-iol; h=mime-version:references:in-reply-to:from:date:message-id:subject:to :cc; bh=mt+HbQFSOEjUJqv5rUmeW1jScY7nUlHaN/GqiqhfzG8=; b=DEKnAehVurlQxOxeDmSgkmWt1lDg9V8chaUc/NKRKGC2vTPF3lviMI7usIsgq3v83t 0RdRsiwESabr1Qw2q/j/q3kGNT3LwhB12UOWPID/cUqKWQVlxR23bmKeCkGwJQgX5aFV g/EWD+tgr2SFkwNs247t3rc0FU3sugLNaI8Ak= X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20161025; h=x-gm-message-state:mime-version:references:in-reply-to:from:date :message-id:subject:to:cc; bh=mt+HbQFSOEjUJqv5rUmeW1jScY7nUlHaN/GqiqhfzG8=; b=c0HU5eCJjJG9F25Xf5bBN8fhjJBtgFu0uBb5k+CoS5Zr/qVxf5BavIxqcVEATxiZYd eGYZx5yzc63q0MqTAZlSCB377BhUmQuXH3zoh2VuO2iOn4lv7E/O1nzGA8m15viomCwk 5FQyunLVLXb4Jpo7zwsWQrsmm49aYbnKl61ZaTZQ8FCV8iT1+TKhXMbAQ4QPHczMnBqV m5SSGAbZUwPS9yIKDMweobL8U9e+5+VEuaHrDbUVlqoegGR78eZeoH4a0sc6mRAZnyII Pt18g8MIlRHKq0+DDUN/+e3vrrhQihvzPPvivkBeWO+ZXrtYTMT6ZYiMjBKxRd2HqKVn bTug== X-Gm-Message-State: AOAM532Pn+FNY8D+WzelQ0sn1Sq7d8AwpNFpg2BV9L/dxLi/W4M4dLqD Gm0Rly3HWRFjxslLUY1t2Rae/Sw/kF3wGk0pP/qbQg== X-Google-Smtp-Source: ABdhPJx+cdmeYYMgnEXPZOaLWOSeBvathQSefmm3boZDYnh5jaZyI+me15Y6f3Y7oFcPEDX+FbdnJlhmFArLXoiT2u4= X-Received: by 2002:a02:1988:: with SMTP id b130mr19175767jab.15.1595965305755; Tue, 28 Jul 2020 12:41:45 -0700 (PDT) MIME-Version: 1.0 References: In-Reply-To: From: Brandon Lo Date: Tue, 28 Jul 2020 15:41:10 -0400 Message-ID: To: Ajit Khaparde Cc: ci@dpdk.org, dpdklab Content-Type: multipart/alternative; boundary="0000000000001fb67f05ab85a172" Subject: Re: [dpdk-ci] New 100G Broadcom NIC Ubuntu X-BeenThere: ci@dpdk.org X-Mailman-Version: 2.1.15 Precedence: list List-Id: DPDK CI discussions List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Errors-To: ci-bounces@dpdk.org Sender: "ci" --0000000000001fb67f05ab85a172 Content-Type: text/plain; charset="UTF-8" Hi Ajit, Yes, I believe we can use this current version as the driver. I'll let you know if I run into any issues with this. Thank you for your help, Brandon On Tue, Jul 28, 2020 at 3:19 PM Ajit Khaparde wrote: > Hi Brandon, > I copied over a more recent code for the NIC. > And it loads fine on the two systems. > The code is currently in /home/ajitkhaparde/bnxt_en-1.10.1-216.1.142.0 > Till I find a release version of the driver for Ubuntu, we could use this? > We can copy the bnxt_en.ko over to > /lib/modules/4.15.0-112-generic/kernel/drivers/net/ethernet/broa > dcom/bnxt/bnxt_en.ko > > Please let me know. > > Thanks > Ajit > > On Tue, Jul 28, 2020 at 10:33 AM Brandon Lo wrote: > >> Hi Ajit, >> >> That issue occurs sometimes on my end as well. There's no clear solution >> other than to try again later. >> I will look into the issue and try to make a permanent fix. >> >> Thanks, >> Brandon >> >> On Tue, Jul 28, 2020 at 1:22 PM Ajit Khaparde >> wrote: >> >>> Brandon, >>> I have sent them a reminder. I will keep you posted. >>> But I tried to login into the system to peek around and the VPN seems to >>> continuously negotiate/authenticate. For some reason the connection >>> is getting reset. >>> Any idea on what might be causing this? >>> >>> Thanks >>> Ajit >>> >>> On Tue, Jul 28, 2020 at 9:48 AM Brandon Lo wrote: >>> >>>> Hi Ajit, >>>> >>>> Have you gotten a response yet? >>>> I've tried the firmware from the official website but it's supported on >>>> Fedora/Redhat instead of Ubuntu. >>>> >>>> Thanks, >>>> Brandon >>>> >>>> On Tue, Jul 21, 2020 at 5:28 PM Ajit Khaparde < >>>> ajit.khaparde@broadcom.com> wrote: >>>> >>>>> Hi Brandon, >>>>> Maybe I might have to update it to a newer firmware. >>>>> Let me check internally and get back. >>>>> >>>>> Thanks >>>>> Ajit >>>>> >>>>> >>>>> On Tue, Jul 21, 2020 at 1:23 PM Brandon Lo wrote: >>>>> >>>>>> Hi Ajit, >>>>>> >>>>>> We've received the Broadcom 100G NIC and installed it onto the >>>>>> machine. However, the drivers don't seem to support Ubuntu, information >>>>>> from >>>>>> https://www.broadcom.com/products/ethernet-connectivity/network-adapters/100gb-nic-ocp/p2100g >>>>>> . >>>>>> >>>>>> I've also updated the kernel to the latest version. The card appears >>>>>> with the correct name in lspci and lshw, but it has no available MAC >>>>>> address, so I can't use it in setting up the nic single core performance >>>>>> testing. >>>>>> >>>>>> Do you know what could be causing this issue? >>>>>> >>>>>> Thanks, >>>>>> Brandon >>>>>> >>>>>> >>>>>> -- >>>>>> >>>>>> Brandon Lo >>>>>> >>>>>> UNH InterOperability Laboratory >>>>>> >>>>>> 21 Madbury Rd, Suite 100, Durham, NH 03824 >>>>>> >>>>>> >>>>>> blo@iol.unh.edu >>>>>> >>>>>> www.iol.unh.edu >>>>>> >>>>> >>>> >>>> -- >>>> >>>> Brandon Lo >>>> >>>> UNH InterOperability Laboratory >>>> >>>> 21 Madbury Rd, Suite 100, Durham, NH 03824 >>>> >>>> blo@iol.unh.edu >>>> >>>> www.iol.unh.edu >>>> >>> >> >> -- >> >> Brandon Lo >> >> UNH InterOperability Laboratory >> >> 21 Madbury Rd, Suite 100, Durham, NH 03824 >> >> blo@iol.unh.edu >> >> www.iol.unh.edu >> > -- Brandon Lo UNH InterOperability Laboratory 21 Madbury Rd, Suite 100, Durham, NH 03824 blo@iol.unh.edu www.iol.unh.edu --0000000000001fb67f05ab85a172 Content-Type: text/html; charset="UTF-8" Content-Transfer-Encoding: quoted-printable
Hi Ajit,

Yes, I believe we can use this= current version as the driver.
I'll let you know if I run in= to any issues with this.

Thank you for your help,<= /div>
Brandon

On Tue, Jul 28, 2020 at 3:19 PM Ajit Khaparde <ajit.khaparde@broadcom.com&= gt; wrote:
Hi Brandon,
I copied over a more recent code for the NIC.
And it loads = fine on the two systems.
The code is currently in=C2=A0/home/ajitkhaparde/bn= xt_en-1.10.1-216.1.142.0
Till I find a release version of the driver for Ubu= ntu, we could use this?
We can copy the bnxt_en.ko over to
/lib/modules/4.15.0-112-generic= /kernel/drivers/net/ethernet/broadcom/bnxt/bnxt_en.ko

Please let me kn= ow.

Thanks
Ajit

On Tue, Jul 28, 2020= at 10:33 AM Brandon Lo <blo@iol.unh.edu> wrote:
Hi Ajit,

That issu= e occurs sometimes on my end as well. There's no clear solution other t= han to try again later.
I will look into the issue and try to mak= e a permanent fix.

Thanks,
Brandon
=

= On Tue, Jul 28, 2020 at 1:22 PM Ajit Khaparde <ajit.khaparde@broadcom.com> w= rote:
Brandon,
I have sent them a reminder. I will keep you posted.
But I tried = to login into the system to peek around and the VPN seems to
continuously ne= gotiate/authenticate. For some=C2=A0reason the connection
is getting reset= .
Any idea on what might be=C2=A0causing this?

Thanks
Ajit
=
On Tue= , Jul 28, 2020 at 9:48 AM Brandon Lo <blo@iol.unh.edu> wrote:
Hi Ajit,

<= div>Have you gotten a response yet?
I've tried the firmware f= rom the official website but it's supported on Fedora/Redhat instead of= Ubuntu.

Thanks,
Brandon

=
On Tue, Ju= l 21, 2020 at 5:28 PM Ajit Khaparde <ajit.khaparde@broadcom.com> wrote:
<= /div>
Hi Brando= n,
Maybe I might have to update it to a newer firmware.
Let me check int= ernally and get back.

Thanks
Ajit

<= /div>

On Tue, Jul 21, 2020 at 1:23 PM Brandon Lo <blo@iol.unh.edu> wrote:
=
Hi Ajit,=

We've received the Broadcom 100G NIC and installed = it onto the machine. However, the drivers don't seem to support Ubuntu,= information from=C2=A0htt= ps://www.broadcom.com/products/ethernet-connectivity/network-adapters/100gb= -nic-ocp/p2100g.=C2=A0

I've also updated t= he kernel to the latest version. The card appears with the correct name in = lspci and lshw, but it has no available MAC address, so I can't use it = in setting up the nic single core performance testing.

=
Do you know what could be causing this issue?=C2=A0
Thanks,
Brandon


--

Brandon Lo

UNH InterOperability Laboratory

=

<= span style=3D"font-size:10pt;font-family:Arial;color:rgb(0,0,0);background-= color:transparent;vertical-align:baseline;white-space:pre-wrap">21 Madbury Rd, Suite 100= , Durham, NH 03824

blo@iol.unh.edu

www.iol.unh.edu



--

Brandon Lo

UNH InterOperability Laborator= y

21 Madbury Rd, Suite 100, Durham, NH 03824

blo@iol.unh.edu

www.iol.unh.edu



--

Brandon Lo

UNH InterOperability Laborator= y

21 Madbury Rd, Suite 100, Durham, NH 03824

blo@iol.unh.edu

www.iol.unh.edu



--

Brandon Lo

UNH = InterOperability Laboratory

21 Madbury Rd, Suite 100, Durham, NH 03824

blo@iol.unh.edu

<= a href=3D"http://www.iol.unh.edu/" target=3D"_blank">www.iol.unh.edu

--0000000000001fb67f05ab85a172-- From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from dpdk.org (dpdk.org [92.243.14.124]) by inbox.dpdk.org (Postfix) with ESMTP id 057C8A053A for ; Tue, 4 Aug 2020 18:16:45 +0200 (CEST) Received: from [92.243.14.124] (localhost [127.0.0.1]) by dpdk.org (Postfix) with ESMTP id BA0E329D2; Tue, 4 Aug 2020 18:16:45 +0200 (CEST) Received: from mail-il1-f193.google.com (mail-il1-f193.google.com [209.85.166.193]) by dpdk.org (Postfix) with ESMTP id 87294F04 for ; Tue, 4 Aug 2020 18:16:44 +0200 (CEST) Received: by mail-il1-f193.google.com with SMTP id z17so19592246ill.6 for ; Tue, 04 Aug 2020 09:16:44 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=iol.unh.edu; s=unh-iol; h=mime-version:references:in-reply-to:from:date:message-id:subject:to :cc; bh=8pCl3TG1sQoyOz/Jh2ovWtvMyLm2BXbgPI67XT5rSWk=; b=ggASdBDxeHZV9OgvOFAOr9WWEibL0djhr3wLVdT+tT/wuXnzi2xJjDlRndBIgwDfQv W4iRNxuw0D1kvM20jgUTAwfzPkVA3okxrfMksqb1lVGQIUECsqtLB/pXESROiLn7aV65 MpAn5QRKysnz7vWN0DpYf0xyp4WuY48103vFY= X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20161025; h=x-gm-message-state:mime-version:references:in-reply-to:from:date :message-id:subject:to:cc; bh=8pCl3TG1sQoyOz/Jh2ovWtvMyLm2BXbgPI67XT5rSWk=; b=U6TPYYi44thdGFRP0Rkq3gfi8PkyR4kV4mTL/ghUxjx04i1eO5hnbBWqR6w2FCXovm i3n3rM7s0SIWX2yCjMO6lF/pHfYfbHDl2dOIViUt9uY4S1rb+r0iScHWFw0ID1xNEAkS pSTGxdA0gjeOyUqlJgPk7sFXN1iMAr05EfpxaI2a2hZlNSlUAg8CKP7vmWfQPcz1rPfE M//KuaLRPwlJgg7dlskwtlFjhhEoCiEVpWKT/poMlWi9UNhvMQfhPzIHwIrp4jw2WcHD cJpSHhS1cKSqLAs0BlffBg2dKzldQ/vfFJW4tGJuAsenLK+ASoGaT/hg4qRF+0I1nE4y Q3fw== X-Gm-Message-State: AOAM531JEGshQ/RPxDZgNc5uOhXEm28II0pHDXTktwEWFp9YaYZQLIja d+bp9CZiz3HDXh7FMmSr50Aj+Mkk7MjvmGSuxr+hZQ== X-Google-Smtp-Source: ABdhPJzZuOwIU2o7SCs8R9Q011N8UF/cnlliHZhb32h84tY7r32YV/VUrnP3WanuWmzoSrh7BPs2R2NdIf+xr0FZ898= X-Received: by 2002:a92:340d:: with SMTP id b13mr5937831ila.78.1596557803792; Tue, 04 Aug 2020 09:16:43 -0700 (PDT) MIME-Version: 1.0 References: In-Reply-To: From: Brandon Lo Date: Tue, 4 Aug 2020 12:16:09 -0400 Message-ID: To: Ajit Khaparde Cc: ci@dpdk.org, dpdklab Content-Type: multipart/alternative; boundary="000000000000c247c305ac0f9498" Subject: Re: [dpdk-ci] New 100G Broadcom NIC Ubuntu X-BeenThere: ci@dpdk.org X-Mailman-Version: 2.1.15 Precedence: list List-Id: DPDK CI discussions List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Errors-To: ci-bounces@dpdk.org Sender: "ci" --000000000000c247c305ac0f9498 Content-Type: text/plain; charset="UTF-8" Hi Ajit, I'm running into a problem with trying to run nic_single_core_perf on the new NIC. The current configuration uses trex version v2.82. However, I'm running into an error when it tries to actually do a test case in the nic_single_core_perf. The output looks like this when it reaches a test case: TestNicSingleCorePerf: Test running at parameters: framesize: 64, rxd/txd: > 512 > dut.rhea: ./x86_64-native-linuxapp-gcc/app/testpmd > -l 16,17 -n 4 -w 0000:81:00.0 -w 0000:81:00.1 > --file-prefix=dpdk_11307_20200804160513 -- -i --portmask=0x3 --txd=512 > --rxd=512 > dut.rhea: start > TestNicSingleCorePerf: Test Case test_perf_nic_single_core Result > ERROR: Traceback (most recent call last): > File "/opt/dts/framework/test_case.py", line 316, in _execute_test_case > case_obj() > File "tests/TestSuite_nic_single_core_perf.py", line 198, in > test_perf_nic_single_core > self.perf_test(self.nb_ports) > File "tests/TestSuite_nic_single_core_perf.py", line 259, in perf_test > _, packets_received = > self.tester.pktgen.measure_throughput(stream_ids=streams, > options=traffic_opt) > File "/opt/dts/framework/pktgen_base.py", line 245, in measure_throughput > self._prepare_transmission(stream_ids=stream_ids) > File "/opt/dts/framework/pktgen_trex.py", line 779, in > _prepare_transmission > self._conn.reset(ports=self._ports) > File > "/opt/v2.82/automation/trex_control_plane/interactive/trex/common/trex_api_annotators.py", > line 51, in wrap2 > ret = f(*args, **kwargs) > File > "/opt/v2.82/automation/trex_control_plane/interactive/trex/stl/trex_stl_client.py", > line 339, in reset > self.clear_stats(ports) > File > "/opt/v2.82/automation/trex_control_plane/interactive/trex/common/trex_api_annotators.py", > line 51, in wrap2 > ret = f(*args, **kwargs) > File > "/opt/v2.82/automation/trex_control_plane/interactive/trex/stl/trex_stl_client.py", > line 1467, in clear_stats > self._clear_stats_common(ports, clear_global, clear_xstats) > File > "/opt/v2.82/automation/trex_control_plane/interactive/trex/common/trex_client.py", > line 2840, in _clear_stats_common > raise TRexError(rc) > trex.common.trex_exceptions.TRexError: *** [RPC] - Failed to get server > response from tcp://127.0.0.1:4501 I have found one similar case on the github repository for trex, but the solution was vendor-specific: https://github.com/cisco-system-traffic-generator/trex-core/issues/147. Have you ran into this issue before? Thanks, Brandon --000000000000c247c305ac0f9498 Content-Type: text/html; charset="UTF-8" Content-Transfer-Encoding: quoted-printable
Hi Ajit,

I'm running=C2= =A0into a problem with trying to run nic_single_core_perf on the new NIC.
The current configuration uses trex version v2.82.
Howev= er, I'm running into an error when it tries to actually=C2=A0do a test = case in the nic_single_core_perf.

The output looks= like this when it reaches a test case:

TestNicSingleCo= rePerf: Test running at parameters: framesize: 64, rxd/txd: 512
=C2=A0 = =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 dut.r= hea: ./x86_64-native-linuxapp-gcc/app/testpmd -l 16,17 -n 4 -w 0000:81:00.0= -w 0000:81:00.1 =C2=A0--file-prefix=3Ddpdk_11307_20200804160513 =C2=A0 =C2= =A0-- -i =C2=A0--portmask=3D0x3 --txd=3D512 --rxd=3D512
=C2=A0 =C2=A0 = =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 dut.rhea: st= art
=C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0TestNicSingleCorePerf: Test Case t= est_perf_nic_single_core Result ERROR: Traceback (most recent call last):=C2=A0 File "/opt/dts/framework/test_case.py", line 316, in _ex= ecute_test_case
=C2=A0 =C2=A0 case_obj() =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2= =A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 = =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2= =A0
=C2=A0 File "tests/TestSuite_nic_single_core_perf.py", li= ne 198, in test_perf_nic_single_core
=C2=A0 =C2=A0 self.perf_test(self.n= b_ports)
=C2=A0 File "tests/TestSuite_nic_single_core_perf.py"= , line 259, in perf_test
=C2=A0 =C2=A0 _, packets_received =3D self.test= er.pktgen.measure_throughput(stream_ids=3Dstreams, options=3Dtraffic_opt)=C2=A0 File "/opt/dts/framework/pktgen_base.py", line 245, in m= easure_throughput
=C2=A0 =C2=A0 self._prepare_transmission(stream_ids=3D= stream_ids)
=C2=A0 File "/opt/dts/framework/pktgen_trex.py", l= ine 779, in _prepare_transmission
=C2=A0 =C2=A0 self._conn.reset(ports= =3Dself._ports)
=C2=A0 File "/opt/v2.82/automation/trex_control_pla= ne/interactive/trex/common/trex_api_annotators.py", line 51, in wrap2<= br>=C2=A0 =C2=A0 ret =3D f(*args, **kwargs) =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2= =A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 = =C2=A0 =C2=A0 =C2=A0 =C2=A0
=C2=A0 File "/opt/v2.82/automation/tre= x_control_plane/interactive/trex/stl/trex_stl_client.py", line 339, in= reset
=C2=A0 =C2=A0 self.clear_stats(ports) =C2=A0 =C2=A0 =C2=A0 =C2=A0= =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2= =A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0
=C2=A0 File "/opt/v2.82/auto= mation/trex_control_plane/interactive/trex/common/trex_api_annotators.py&qu= ot;, line 51, in wrap2
=C2=A0 =C2=A0 ret =3D f(*args, **kwargs) =C2=A0 = =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2= =A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0
=C2=A0 File "= /opt/v2.82/automation/trex_control_plane/interactive/trex/stl/trex_stl_clie= nt.py", line 1467, in clear_stats
=C2=A0 =C2=A0 self._clear_stats_c= ommon(ports, clear_global, clear_xstats)
=C2=A0 File "/opt/v2.82/au= tomation/trex_control_plane/interactive/trex/common/trex_client.py", l= ine 2840, in _clear_stats_common
=C2=A0 =C2=A0 raise TRexError(rc) =C2= =A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 = =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2= =A0
trex.common.trex_exceptions.TRexError: *** [RPC] - Failed to get ser= ver response from tcp://127.0.0.1:4501

Have you ran into this issue before?

=
Thanks,
Brandon
=
--000000000000c247c305ac0f9498-- From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from dpdk.org (dpdk.org [92.243.14.124]) by inbox.dpdk.org (Postfix) with ESMTP id 13DF7A053A for ; Tue, 4 Aug 2020 18:38:17 +0200 (CEST) Received: from [92.243.14.124] (localhost [127.0.0.1]) by dpdk.org (Postfix) with ESMTP id E216929D2; Tue, 4 Aug 2020 18:38:16 +0200 (CEST) Received: from mail-ot1-f47.google.com (mail-ot1-f47.google.com [209.85.210.47]) by dpdk.org (Postfix) with ESMTP id 0718F2AB for ; Tue, 4 Aug 2020 18:38:14 +0200 (CEST) Received: by mail-ot1-f47.google.com with SMTP id a65so21875240otc.8 for ; Tue, 04 Aug 2020 09:38:14 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=broadcom.com; s=google; h=mime-version:references:in-reply-to:from:date:message-id:subject:to :cc; bh=OUsE24zLsBnnDqSNJEPh4BzrxEknJ+JTK8pPKefZRzc=; b=d7VaVigafm+OpeMlgiKG7SCvhaNKfiS/OtXsDCd1Joh8d+zBO/MSzbGlhfaeXdVAPh LHRwojkCbol3/AbUXlrHBB5ol6vkKDMfffipVd6MmABAlo6xhU+UkQdvLw9xy3TzK/Lw 74cdWZNexHn6kguqxkSo24u3gP3/lFfVZDeeg= X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20161025; h=x-gm-message-state:mime-version:references:in-reply-to:from:date :message-id:subject:to:cc; bh=OUsE24zLsBnnDqSNJEPh4BzrxEknJ+JTK8pPKefZRzc=; b=sr4iFUEwSMZrlpgP+WtfWd9W3xRtKoED+syBpjff1ceypEAECzxdYnsYicMrhuS+dA bJW34wydssz7/lmF/ocN+7d5M2xR25UfE1Zf507jxZFN4GMk7Q4eZ0Hkn9CbLORyFXKh VgG0Q0XT01N3MiRw1nMgPO5IeyZVG3MAfyX9prxKLvGdMiw0UGZvhC8pox6EzQHfoShh SBuS8zayBfX3iyd54NCA2hKJkRk4WqJ+cP+Up4KBBqZS/Fi32d9X3Ox6LKQ0SLg/i4B9 mqA94C4mo2badGp5B89QsTlJ+tiiMiVLEPTkYsREXc4C6CcKWtGvFQZBev4GsW1BHH2u 5/0g== X-Gm-Message-State: AOAM532Vw4PFIk7aagPfv9s0FT4L1kztUhhs2ZbHAal/nA+EICe6Jdw9 AbxV1YLamAffmUL2fOnHZJO5i3/F5JAlWR9CNLgYXQ== X-Google-Smtp-Source: ABdhPJzaLn4K8YcTyLGjFEHwRLMHPIYDS80a1Qh8eUWlfEqm5580oxVlr82Y4cfmtSFYtu3wvGuC6pqneA+pwFg8/ZA= X-Received: by 2002:a9d:8c9:: with SMTP id 67mr3618634otf.154.1596559093997; Tue, 04 Aug 2020 09:38:13 -0700 (PDT) MIME-Version: 1.0 References: In-Reply-To: From: Ajit Khaparde Date: Tue, 4 Aug 2020 09:37:58 -0700 Message-ID: To: Brandon Lo Cc: ci@dpdk.org, dpdklab Content-Type: multipart/alternative; boundary="000000000000a9792705ac0fe17b" Subject: Re: [dpdk-ci] New 100G Broadcom NIC Ubuntu X-BeenThere: ci@dpdk.org X-Mailman-Version: 2.1.15 Precedence: list List-Id: DPDK CI discussions List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Errors-To: ci-bounces@dpdk.org Sender: "ci" --000000000000a9792705ac0fe17b Content-Type: text/plain; charset="UTF-8" Hi Brandon, No, I haven't seen or heard this before. But I will try to have someone run it again. Just to make sure - You are running trex on the 100G NIC and the problem is encountered on that setup? Or is it the system that is running testpmd where you are running into the issue? Thanks Ajit On Tue, Aug 4, 2020 at 9:16 AM Brandon Lo wrote: > Hi Ajit, > > I'm running into a problem with trying to run nic_single_core_perf on the > new NIC. > The current configuration uses trex version v2.82. > However, I'm running into an error when it tries to actually do a test > case in the nic_single_core_perf. > > The output looks like this when it reaches a test case: > > TestNicSingleCorePerf: Test running at parameters: framesize: 64, rxd/txd: >> 512 >> dut.rhea: ./x86_64-native-linuxapp-gcc/app/testpmd >> -l 16,17 -n 4 -w 0000:81:00.0 -w 0000:81:00.1 >> --file-prefix=dpdk_11307_20200804160513 -- -i --portmask=0x3 --txd=512 >> --rxd=512 >> dut.rhea: start >> TestNicSingleCorePerf: Test Case test_perf_nic_single_core >> Result ERROR: Traceback (most recent call last): >> File "/opt/dts/framework/test_case.py", line 316, in _execute_test_case >> case_obj() >> File "tests/TestSuite_nic_single_core_perf.py", line 198, in >> test_perf_nic_single_core >> self.perf_test(self.nb_ports) >> File "tests/TestSuite_nic_single_core_perf.py", line 259, in perf_test >> _, packets_received = >> self.tester.pktgen.measure_throughput(stream_ids=streams, >> options=traffic_opt) >> File "/opt/dts/framework/pktgen_base.py", line 245, in >> measure_throughput >> self._prepare_transmission(stream_ids=stream_ids) >> File "/opt/dts/framework/pktgen_trex.py", line 779, in >> _prepare_transmission >> self._conn.reset(ports=self._ports) >> File >> "/opt/v2.82/automation/trex_control_plane/interactive/trex/common/trex_api_annotators.py", >> line 51, in wrap2 >> ret = f(*args, **kwargs) >> File >> "/opt/v2.82/automation/trex_control_plane/interactive/trex/stl/trex_stl_client.py", >> line 339, in reset >> self.clear_stats(ports) >> File >> "/opt/v2.82/automation/trex_control_plane/interactive/trex/common/trex_api_annotators.py", >> line 51, in wrap2 >> ret = f(*args, **kwargs) >> File >> "/opt/v2.82/automation/trex_control_plane/interactive/trex/stl/trex_stl_client.py", >> line 1467, in clear_stats >> self._clear_stats_common(ports, clear_global, clear_xstats) >> File >> "/opt/v2.82/automation/trex_control_plane/interactive/trex/common/trex_client.py", >> line 2840, in _clear_stats_common >> raise TRexError(rc) >> trex.common.trex_exceptions.TRexError: *** [RPC] - Failed to get server >> response from tcp://127.0.0.1:4501 > > > I have found one similar case on the github repository for trex, but the > solution was vendor-specific: > https://github.com/cisco-system-traffic-generator/trex-core/issues/147. > Have you ran into this issue before? > > Thanks, > Brandon > --000000000000a9792705ac0fe17b Content-Type: text/html; charset="UTF-8" Content-Transfer-Encoding: quoted-printable
Hi Brandon,
No, I haven't seen or heard this=C2=A0before.
=
= But I will try to have someone=C2=A0run it again.

Just to make sure -
You= are running trex on the 100G NIC and the problem is encountered on that se= tup?
Or is it the system that is running testpmd where you are running into = the issue?

Thanks
Ajit

On Tue, Aug 4, 2020 at 9:16 AM Brandon Lo <= ;blo@iol.unh.edu> wrote:
Hi= Ajit,

I'm running=C2=A0into a problem with tr= ying to run nic_single_core_perf on the new NIC.
The current conf= iguration uses trex version v2.82.
However, I'm running into = an error when it tries to actually=C2=A0do a test case in the nic_single_co= re_perf.

The output looks like this when it reache= s a test case:

TestNicSingleCorePerf: Test running at = parameters: framesize: 64, rxd/txd: 512
=C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2= =A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 dut.rhea: ./x86_64-native-lin= uxapp-gcc/app/testpmd -l 16,17 -n 4 -w 0000:81:00.0 -w 0000:81:00.1 =C2=A0-= -file-prefix=3Ddpdk_11307_20200804160513 =C2=A0 =C2=A0-- -i =C2=A0--portmas= k=3D0x3 --txd=3D512 --rxd=3D512
=C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2= =A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 dut.rhea: start
=C2=A0 =C2=A0 =C2= =A0 =C2=A0 =C2=A0TestNicSingleCorePerf: Test Case test_perf_nic_single_core= Result ERROR: Traceback (most recent call last):
=C2=A0 File "/opt= /dts/framework/test_case.py", line 316, in _execute_test_case
=C2= =A0 =C2=A0 case_obj() =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2= =A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 = =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0
=C2=A0 File &qu= ot;tests/TestSuite_nic_single_core_perf.py", line 198, in test_perf_ni= c_single_core
=C2=A0 =C2=A0 self.perf_test(self.nb_ports)
=C2=A0 File= "tests/TestSuite_nic_single_core_perf.py", line 259, in perf_tes= t
=C2=A0 =C2=A0 _, packets_received =3D self.tester.pktgen.measure_throu= ghput(stream_ids=3Dstreams, options=3Dtraffic_opt)
=C2=A0 File "/op= t/dts/framework/pktgen_base.py", line 245, in measure_throughput
= =C2=A0 =C2=A0 self._prepare_transmission(stream_ids=3Dstream_ids)
=C2=A0= File "/opt/dts/framework/pktgen_trex.py", line 779, in _prepare_= transmission
=C2=A0 =C2=A0 self._conn.reset(ports=3Dself._ports)
=C2= =A0 File "/opt/v2.82/automation/trex_control_plane/interactive/trex/co= mmon/trex_api_annotators.py", line 51, in wrap2
=C2=A0 =C2=A0 ret = =3D f(*args, **kwargs) =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2= =A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 = =C2=A0
=C2=A0 File "/opt/v2.82/automation/trex_control_plane/inter= active/trex/stl/trex_stl_client.py", line 339, in reset
=C2=A0 =C2= =A0 self.clear_stats(ports) =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2= =A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 = =C2=A0 =C2=A0 =C2=A0
=C2=A0 File "/opt/v2.82/automation/trex_contro= l_plane/interactive/trex/common/trex_api_annotators.py", line 51, in w= rap2
=C2=A0 =C2=A0 ret =3D f(*args, **kwargs) =C2=A0 =C2=A0 =C2=A0 =C2= =A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 = =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0
=C2=A0 File "/opt/v2.82/automat= ion/trex_control_plane/interactive/trex/stl/trex_stl_client.py", line = 1467, in clear_stats
=C2=A0 =C2=A0 self._clear_stats_common(ports, clear= _global, clear_xstats)
=C2=A0 File "/opt/v2.82/automation/trex_cont= rol_plane/interactive/trex/common/trex_client.py", line 2840, in _clea= r_stats_common
=C2=A0 =C2=A0 raise TRexError(rc) =C2=A0 =C2=A0 =C2=A0 = =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2= =A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0
trex.common.= trex_exceptions.TRexError: *** [RPC] - Failed to get server response from t= cp://127.0.0.1:4501=

I have found one similar case on th= e github repository for trex, but the solution was vendor-specific:=C2=A0https://github.com/cisco-system-traffic-generator/t= rex-core/issues/147.
Have you ran into this issue before?

Thanks,
Brandon
--000000000000a9792705ac0fe17b-- From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from dpdk.org (dpdk.org [92.243.14.124]) by inbox.dpdk.org (Postfix) with ESMTP id DF0B3A053A for ; Tue, 4 Aug 2020 19:42:47 +0200 (CEST) Received: from [92.243.14.124] (localhost [127.0.0.1]) by dpdk.org (Postfix) with ESMTP id B99A62BA8; Tue, 4 Aug 2020 19:42:47 +0200 (CEST) Received: from mail-il1-f194.google.com (mail-il1-f194.google.com [209.85.166.194]) by dpdk.org (Postfix) with ESMTP id C2055F04 for ; Tue, 4 Aug 2020 19:42:45 +0200 (CEST) Received: by mail-il1-f194.google.com with SMTP id l17so24729039ilq.13 for ; Tue, 04 Aug 2020 10:42:45 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=iol.unh.edu; s=unh-iol; h=mime-version:references:in-reply-to:from:date:message-id:subject:to :cc; bh=99+TRrzCn8V5yHMr50P0XZ4pJ8laTrOleahkTlmJBWY=; b=AEE6gSAgDmB/AD2Wu0U5OUeCuERwvgDWbm269KiouF0CnSQflTbjwOlMFdDJ5XtVj6 ZlUS3NvPGQXGqy6ZoHj29QhhFby+/z9XbtlHsidW6ioq3skdwNICsGg321uyEDQVD6S6 wQ5LZ39i258haA47sHWzy1GA2xLl2m9xmOkPM= X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20161025; h=x-gm-message-state:mime-version:references:in-reply-to:from:date :message-id:subject:to:cc; bh=99+TRrzCn8V5yHMr50P0XZ4pJ8laTrOleahkTlmJBWY=; b=JBUV8UuXfY63eUKgK44uvX1ZzmcT6DZQakgYxKHAOCbIKy73fPS9pDYG65eR6vBrxU 0gGmAPAmaqcE4rQmwHUUHRvzcURdWPgiDbNByhutmka4zTcoaKF6TiTWDUJCX+cdGAsU TKYwsyoAW6gHCt9XUQA6vMuOh+mjKN5qRhpJIP97EC3oTh8jyOFPhNV92SPfAJ7IkrPQ ErRYKIgBCyXt5DwXhX7YBJleoIfAsfvyYbmVSySDZ2DXt5jRVb/uj5wq1BlC+HR7dUfQ uaUXN13mTjNC4YzwloGAKzp2qAzo29KOJiNqOeywCadG2q7M+k0OoO6+fhIK8+pJ9Cwo rvjw== X-Gm-Message-State: AOAM53100od2JRed6yJhF1P8lcNluVU/UDQ8gBZxRHs3vJ5VxzsJGDjS 7TfieNoylaM/nIQxt1A5g9LYNikB8a22m8mVrZ3Ifg== X-Google-Smtp-Source: ABdhPJwrSyaQMGlbFH49OtjmElY3+K/Aixov4u3Bv1dGoVSRcK9nQYQekTxkcdOumCaP7dDMoDZmPod+K+uIXjZ19gA= X-Received: by 2002:a05:6e02:8:: with SMTP id h8mr5563382ilr.188.1596562965090; Tue, 04 Aug 2020 10:42:45 -0700 (PDT) MIME-Version: 1.0 References: In-Reply-To: From: Brandon Lo Date: Tue, 4 Aug 2020 13:42:09 -0400 Message-ID: To: Ajit Khaparde Cc: ci@dpdk.org, dpdklab Content-Type: multipart/alternative; boundary="000000000000656aae05ac10c8a6" Subject: Re: [dpdk-ci] New 100G Broadcom NIC Ubuntu X-BeenThere: ci@dpdk.org X-Mailman-Version: 2.1.15 Precedence: list List-Id: DPDK CI discussions List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Errors-To: ci-bounces@dpdk.org Sender: "ci" --000000000000656aae05ac10c8a6 Content-Type: text/plain; charset="UTF-8" Hi Ajit, Yes, I believe the issue is coming from the trex/tester system with the 100G NIC. I'm not sure what causes this issue; if I run trex using the command "cd /opt/v2.82;./t-rex-64 -i --cfg /etc/trex_cfg_100g.yaml -c 7", which is the same command used in DTS, it seems to launch without failing. If you want to replicate it, here are the steps that I ran: 1. (on io) cd /opt/dts 2. export DTS_CFG_FOLDER='conf_100g' - conf_100g has the new configuration files to use the new PCI id and pktgen config file 3. ./dts -s Thanks for your help, Brandon On Tue, Aug 4, 2020 at 12:38 PM Ajit Khaparde wrote: > Hi Brandon, > No, I haven't seen or heard this before. > But I will try to have someone run it again. > > Just to make sure - > You are running trex on the 100G NIC and the problem is encountered on > that setup? > Or is it the system that is running testpmd where you are running into the > issue? > > Thanks > Ajit > > On Tue, Aug 4, 2020 at 9:16 AM Brandon Lo wrote: > >> Hi Ajit, >> >> I'm running into a problem with trying to run nic_single_core_perf on the >> new NIC. >> The current configuration uses trex version v2.82. >> However, I'm running into an error when it tries to actually do a test >> case in the nic_single_core_perf. >> >> The output looks like this when it reaches a test case: >> >> TestNicSingleCorePerf: Test running at parameters: framesize: 64, >>> rxd/txd: 512 >>> dut.rhea: ./x86_64-native-linuxapp-gcc/app/testpmd >>> -l 16,17 -n 4 -w 0000:81:00.0 -w 0000:81:00.1 >>> --file-prefix=dpdk_11307_20200804160513 -- -i --portmask=0x3 --txd=512 >>> --rxd=512 >>> dut.rhea: start >>> TestNicSingleCorePerf: Test Case test_perf_nic_single_core >>> Result ERROR: Traceback (most recent call last): >>> File "/opt/dts/framework/test_case.py", line 316, in _execute_test_case >>> case_obj() >>> File "tests/TestSuite_nic_single_core_perf.py", line 198, in >>> test_perf_nic_single_core >>> self.perf_test(self.nb_ports) >>> File "tests/TestSuite_nic_single_core_perf.py", line 259, in perf_test >>> _, packets_received = >>> self.tester.pktgen.measure_throughput(stream_ids=streams, >>> options=traffic_opt) >>> File "/opt/dts/framework/pktgen_base.py", line 245, in >>> measure_throughput >>> self._prepare_transmission(stream_ids=stream_ids) >>> File "/opt/dts/framework/pktgen_trex.py", line 779, in >>> _prepare_transmission >>> self._conn.reset(ports=self._ports) >>> File >>> "/opt/v2.82/automation/trex_control_plane/interactive/trex/common/trex_api_annotators.py", >>> line 51, in wrap2 >>> ret = f(*args, **kwargs) >>> File >>> "/opt/v2.82/automation/trex_control_plane/interactive/trex/stl/trex_stl_client.py", >>> line 339, in reset >>> self.clear_stats(ports) >>> File >>> "/opt/v2.82/automation/trex_control_plane/interactive/trex/common/trex_api_annotators.py", >>> line 51, in wrap2 >>> ret = f(*args, **kwargs) >>> File >>> "/opt/v2.82/automation/trex_control_plane/interactive/trex/stl/trex_stl_client.py", >>> line 1467, in clear_stats >>> self._clear_stats_common(ports, clear_global, clear_xstats) >>> File >>> "/opt/v2.82/automation/trex_control_plane/interactive/trex/common/trex_client.py", >>> line 2840, in _clear_stats_common >>> raise TRexError(rc) >>> trex.common.trex_exceptions.TRexError: *** [RPC] - Failed to get server >>> response from tcp://127.0.0.1:4501 >> >> >> I have found one similar case on the github repository for trex, but the >> solution was vendor-specific: >> https://github.com/cisco-system-traffic-generator/trex-core/issues/147. >> Have you ran into this issue before? >> >> Thanks, >> Brandon >> > -- Brandon Lo UNH InterOperability Laboratory 21 Madbury Rd, Suite 100, Durham, NH 03824 blo@iol.unh.edu www.iol.unh.edu --000000000000656aae05ac10c8a6 Content-Type: text/html; charset="UTF-8" Content-Transfer-Encoding: quoted-printable
Hi Ajit,

Yes, I believe the issue is co= ming from the trex/tester system with the 100G NIC.
I'm not s= ure what causes this issue; if I run trex using the command "cd /opt/v= 2.82;./t-rex-64 -i --cfg /etc/trex_cfg_100g.yaml -c 7", which is the s= ame command used in DTS, it seems to launch without failing.

=
If you want to replicate it, here are the steps that I ran:
  1. (on io) cd /opt/dts
  2. export DTS_CFG_FOLDER=3D'conf= _100g'
    • conf_100g has the new configuration files to use the= new PCI id and pktgen config file
  3. ./dts -s

=
Thanks for your help,
Brandon

On Tue, Aug 4= , 2020 at 12:38 PM Ajit Khaparde <ajit.khaparde@broadcom.com> wrote:
Hi Brandon,<= /div>
N= o, I haven't seen or heard this=C2=A0before.
But I will try to have = someone=C2=A0run it again.

Just to make sure -
You are running trex on th= e 100G NIC and the problem is encountered on that setup?
Or is it the system= that is running testpmd where you are running into the issue?

Thanks
Aji= t

On Tue, Aug 4, 2020 at 9:16 AM Brandon Lo <blo@iol.unh.edu> wrote:
Hi Ajit= ,

I'm running=C2=A0into a problem with trying = to run nic_single_core_perf on the new NIC.
The current configura= tion uses trex version v2.82.
However, I'm running into an er= ror when it tries to actually=C2=A0do a test case in the nic_single_core_pe= rf.

The output looks like this when it reaches a t= est case:

TestNicSingleCorePerf: Test running at parame= ters: framesize: 64, rxd/txd: 512
=C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2= =A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 dut.rhea: ./x86_64-native-linuxapp-g= cc/app/testpmd -l 16,17 -n 4 -w 0000:81:00.0 -w 0000:81:00.1 =C2=A0--file-p= refix=3Ddpdk_11307_20200804160513 =C2=A0 =C2=A0-- -i =C2=A0--portmask=3D0x3= --txd=3D512 --rxd=3D512
=C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2= =A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 dut.rhea: start
=C2=A0 =C2=A0 =C2=A0 =C2= =A0 =C2=A0TestNicSingleCorePerf: Test Case test_perf_nic_single_core Result= ERROR: Traceback (most recent call last):
=C2=A0 File "/opt/dts/fr= amework/test_case.py", line 316, in _execute_test_case
=C2=A0 =C2= =A0 case_obj() =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2= =A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 = =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0
=C2=A0 File "test= s/TestSuite_nic_single_core_perf.py", line 198, in test_perf_nic_singl= e_core
=C2=A0 =C2=A0 self.perf_test(self.nb_ports)
=C2=A0 File "= tests/TestSuite_nic_single_core_perf.py", line 259, in perf_test
= =C2=A0 =C2=A0 _, packets_received =3D self.tester.pktgen.measure_throughput= (stream_ids=3Dstreams, options=3Dtraffic_opt)
=C2=A0 File "/opt/dts= /framework/pktgen_base.py", line 245, in measure_throughput
=C2=A0 = =C2=A0 self._prepare_transmission(stream_ids=3Dstream_ids)
=C2=A0 File &= quot;/opt/dts/framework/pktgen_trex.py", line 779, in _prepare_transmi= ssion
=C2=A0 =C2=A0 self._conn.reset(ports=3Dself._ports)
=C2=A0 File= "/opt/v2.82/automation/trex_control_plane/interactive/trex/common/tre= x_api_annotators.py", line 51, in wrap2
=C2=A0 =C2=A0 ret =3D f(*ar= gs, **kwargs) =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2= =A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 File "/opt/v2.82/automation/trex_control_plane/interactive/t= rex/stl/trex_stl_client.py", line 339, in reset
=C2=A0 =C2=A0 self.= clear_stats(ports) =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 = =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2= =A0 =C2=A0
=C2=A0 File "/opt/v2.82/automation/trex_control_plane/in= teractive/trex/common/trex_api_annotators.py", line 51, in wrap2
= =C2=A0 =C2=A0 ret =3D f(*args, **kwargs) =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0= =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2= =A0 =C2=A0 =C2=A0 =C2=A0
=C2=A0 File "/opt/v2.82/automation/trex_c= ontrol_plane/interactive/trex/stl/trex_stl_client.py", line 1467, in c= lear_stats
=C2=A0 =C2=A0 self._clear_stats_common(ports, clear_global, c= lear_xstats)
=C2=A0 File "/opt/v2.82/automation/trex_control_plane/= interactive/trex/common/trex_client.py", line 2840, in _clear_stats_co= mmon
=C2=A0 =C2=A0 raise TRexError(rc) =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2= =A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 = =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0
trex.common.trex_except= ions.TRexError: *** [RPC] - Failed to get server response from tcp://127.0.0.1:4501

I have found one similar case on the github re= pository for trex, but the solution was vendor-specific:=C2=A0https://github.com/cisco-system-traffic-generator/trex-core/is= sues/147.
Have you ran into this issue before?

=
Thanks,
Brandon


--

Brandon Lo

UNH InterOperability Laborator= y

21 Madbury Rd, Suite 100, Durham, NH 03824

blo@iol.unh.edu

www.iol.unh.edu

--000000000000656aae05ac10c8a6-- From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from dpdk.org (dpdk.org [92.243.14.124]) by inbox.dpdk.org (Postfix) with ESMTP id 53BC1A04DE for ; Tue, 11 Aug 2020 19:46:06 +0200 (CEST) Received: from [92.243.14.124] (localhost [127.0.0.1]) by dpdk.org (Postfix) with ESMTP id 4C5EF1C022; Tue, 11 Aug 2020 19:46:06 +0200 (CEST) Received: from mail-il1-f194.google.com (mail-il1-f194.google.com [209.85.166.194]) by dpdk.org (Postfix) with ESMTP id 317011C01F for ; Tue, 11 Aug 2020 19:46:05 +0200 (CEST) Received: by mail-il1-f194.google.com with SMTP id c6so11452754ilo.13 for ; Tue, 11 Aug 2020 10:46:05 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=iol.unh.edu; s=unh-iol; h=mime-version:references:in-reply-to:from:date:message-id:subject:to :cc; bh=qfsTJ/IooiamCtRW/xt31sRWItN1R4nbKUsAJCec97c=; b=aFzij2xoV0QpSElLv4gv4w46CiigYjWXFd27fRaRpQ6jW4gW2DCUw+x5wUO7aJOCXq N5YgkzGMQpvE/A99O1SPVbDnQIvo9Tf5kfouUQiUJvjN96ulAKgkmcb0Ui12geKUmb6B ha2lwrxbBgQQevyWPKFpI585iX4bnCnScSlHI= X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20161025; h=x-gm-message-state:mime-version:references:in-reply-to:from:date :message-id:subject:to:cc; bh=qfsTJ/IooiamCtRW/xt31sRWItN1R4nbKUsAJCec97c=; b=cAOzavLEyozDuamdLS07debfqWD9Tw2RjNaSMdTyP1DZmtAABAo462YzoaIHqKaL/S Mr8zGlX+d58hz816ThcJ0HlEycSDg+qf3bwV0346jsgAot0DSkfDTWBVqJ/0YoiwfLKQ LeqccepPF2gzsQtrUDgUAiKKqtMukgsNctAmNxExtnnegSB7I6XjBjb/WxRZ3Vc3eZ42 dKIs8xK0WVD2VnGOqSBRQgipOXWBSg1X/Dh9/4UytrM7ztd3jGXoMSEDs/9S0MLWlvE3 Ji1Yfk70wHdrXhmj7sWrMCPGKhcNnqpYR6bhSX7SrsHWYCeEW+TFozVtij4g7mMADKV/ AAAg== X-Gm-Message-State: AOAM533aRA8N9uUPyzIm9x9GzN8twiLldeBIS6wbzBvdDex1JsNZSbAC gYEH0axfEfccYTgM2xTR1bkcucQvB4YTxEnykAGaxg== X-Google-Smtp-Source: ABdhPJzppxtjUodo/9mGyGTIckGsmg/WLvpLwRCSDoA8lsNBDY8FUU+txycvLIQLIZgP2vp6KaK5sQZ1GWPKIcI8/ME= X-Received: by 2002:a05:6e02:8:: with SMTP id h8mr22062600ilr.188.1597167964455; Tue, 11 Aug 2020 10:46:04 -0700 (PDT) MIME-Version: 1.0 References: In-Reply-To: From: Brandon Lo Date: Tue, 11 Aug 2020 13:45:28 -0400 Message-ID: To: Ajit Khaparde Cc: ci@dpdk.org, dpdklab Content-Type: multipart/alternative; boundary="0000000000002b2e6f05ac9da560" Subject: Re: [dpdk-ci] New 100G Broadcom NIC Ubuntu X-BeenThere: ci@dpdk.org X-Mailman-Version: 2.1.15 Precedence: list List-Id: DPDK CI discussions List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Errors-To: ci-bounces@dpdk.org Sender: "ci" --0000000000002b2e6f05ac9da560 Content-Type: text/plain; charset="UTF-8" Hi Ajit, I'm just checking in; have you heard of any updates on this issue? Thanks, Brandon On Tue, Aug 4, 2020 at 1:42 PM Brandon Lo wrote: > Hi Ajit, > > Yes, I believe the issue is coming from the trex/tester system with the > 100G NIC. > I'm not sure what causes this issue; if I run trex using the command "cd > /opt/v2.82;./t-rex-64 -i --cfg /etc/trex_cfg_100g.yaml -c 7", which is the > same command used in DTS, it seems to launch without failing. > > If you want to replicate it, here are the steps that I ran: > > 1. (on io) cd /opt/dts > 2. export DTS_CFG_FOLDER='conf_100g' > - conf_100g has the new configuration files to use the new PCI id > and pktgen config file > 3. ./dts -s > > > Thanks for your help, > Brandon > > On Tue, Aug 4, 2020 at 12:38 PM Ajit Khaparde > wrote: > >> Hi Brandon, >> No, I haven't seen or heard this before. >> But I will try to have someone run it again. >> >> Just to make sure - >> You are running trex on the 100G NIC and the problem is encountered on >> that setup? >> Or is it the system that is running testpmd where you are running into >> the issue? >> >> Thanks >> Ajit >> >> On Tue, Aug 4, 2020 at 9:16 AM Brandon Lo wrote: >> >>> Hi Ajit, >>> >>> I'm running into a problem with trying to run nic_single_core_perf on >>> the new NIC. >>> The current configuration uses trex version v2.82. >>> However, I'm running into an error when it tries to actually do a test >>> case in the nic_single_core_perf. >>> >>> The output looks like this when it reaches a test case: >>> >>> TestNicSingleCorePerf: Test running at parameters: framesize: 64, >>>> rxd/txd: 512 >>>> dut.rhea: >>>> ./x86_64-native-linuxapp-gcc/app/testpmd -l 16,17 -n 4 -w 0000:81:00.0 -w >>>> 0000:81:00.1 --file-prefix=dpdk_11307_20200804160513 -- -i >>>> --portmask=0x3 --txd=512 --rxd=512 >>>> dut.rhea: start >>>> TestNicSingleCorePerf: Test Case test_perf_nic_single_core >>>> Result ERROR: Traceback (most recent call last): >>>> File "/opt/dts/framework/test_case.py", line 316, in >>>> _execute_test_case >>>> case_obj() >>>> File "tests/TestSuite_nic_single_core_perf.py", line 198, in >>>> test_perf_nic_single_core >>>> self.perf_test(self.nb_ports) >>>> File "tests/TestSuite_nic_single_core_perf.py", line 259, in perf_test >>>> _, packets_received = >>>> self.tester.pktgen.measure_throughput(stream_ids=streams, >>>> options=traffic_opt) >>>> File "/opt/dts/framework/pktgen_base.py", line 245, in >>>> measure_throughput >>>> self._prepare_transmission(stream_ids=stream_ids) >>>> File "/opt/dts/framework/pktgen_trex.py", line 779, in >>>> _prepare_transmission >>>> self._conn.reset(ports=self._ports) >>>> File >>>> "/opt/v2.82/automation/trex_control_plane/interactive/trex/common/trex_api_annotators.py", >>>> line 51, in wrap2 >>>> ret = f(*args, **kwargs) >>>> File >>>> "/opt/v2.82/automation/trex_control_plane/interactive/trex/stl/trex_stl_client.py", >>>> line 339, in reset >>>> self.clear_stats(ports) >>>> File >>>> "/opt/v2.82/automation/trex_control_plane/interactive/trex/common/trex_api_annotators.py", >>>> line 51, in wrap2 >>>> ret = f(*args, **kwargs) >>>> File >>>> "/opt/v2.82/automation/trex_control_plane/interactive/trex/stl/trex_stl_client.py", >>>> line 1467, in clear_stats >>>> self._clear_stats_common(ports, clear_global, clear_xstats) >>>> File >>>> "/opt/v2.82/automation/trex_control_plane/interactive/trex/common/trex_client.py", >>>> line 2840, in _clear_stats_common >>>> raise TRexError(rc) >>>> trex.common.trex_exceptions.TRexError: *** [RPC] - Failed to get server >>>> response from tcp://127.0.0.1:4501 >>> >>> >>> I have found one similar case on the github repository for trex, but the >>> solution was vendor-specific: >>> https://github.com/cisco-system-traffic-generator/trex-core/issues/147. >>> Have you ran into this issue before? >>> >>> Thanks, >>> Brandon >>> >> > > -- > > Brandon Lo > > UNH InterOperability Laboratory > > 21 Madbury Rd, Suite 100, Durham, NH 03824 > > blo@iol.unh.edu > > www.iol.unh.edu > -- Brandon Lo UNH InterOperability Laboratory 21 Madbury Rd, Suite 100, Durham, NH 03824 blo@iol.unh.edu www.iol.unh.edu --0000000000002b2e6f05ac9da560 Content-Type: text/html; charset="UTF-8" Content-Transfer-Encoding: quoted-printable
Hi Ajit,

I'm just checking in; have= you heard of any updates on this issue?

Thanks,
Brandon

On Tue, Aug 4, 2020 at 1:42 PM Brandon Lo <blo@iol.unh.edu> wrote:
Hi Ajit,
Yes, I believe the issue is coming from the trex/tester system= with the 100G NIC.
I'm not sure what causes this issue; if I= run trex using the command "cd /opt/v2.82;./t-rex-64 -i --cfg /etc/tr= ex_cfg_100g.yaml -c 7", which is the same command used in DTS, it seem= s to launch without failing.

If you want to replic= ate it, here are the steps that I ran:
  1. (on io) cd /opt/dt= s
  2. export DTS_CFG_FOLDER=3D'conf_100g'
    • conf_100g= has the new configuration files to use the new PCI id and pktgen config fi= le
  3. ./dts -s

Thanks for your= help,
Brandon

On Tue, Aug 4, 2020 at 12:38 PM Ajit Khaparde= <ajit.k= haparde@broadcom.com> wrote:
Hi Brandon,
No, I haven't seen or heard t= his=C2=A0before.
But I will try to have someone=C2=A0run it again.
=

Ju= st to make sure -
You are running trex on the 100G NIC and the problem is en= countered on that setup?
Or is it the system that is running testpmd where y= ou are running into the issue?

Thanks
Ajit

On Tue, Aug 4, 2020 at 9= :16 AM Brandon Lo <= blo@iol.unh.edu> wrote:
Hi Ajit,

I= 9;m running=C2=A0into a problem with trying to run nic_single_core_perf on = the new NIC.
The current configuration uses trex version v2.82.
However, I'm running into an error when it tries to actually= =C2=A0do a test case in the nic_single_core_perf.

= The output looks like this when it reaches a test case:

TestNicSingleCorePerf: Test running at parameters: framesize: 64, rxd/txd:= 512
=C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2= =A0 =C2=A0 dut.rhea: ./x86_64-native-linuxapp-gcc/app/testpmd -l 16,17 -n 4= -w 0000:81:00.0 -w 0000:81:00.1 =C2=A0--file-prefix=3Ddpdk_11307_202008041= 60513 =C2=A0 =C2=A0-- -i =C2=A0--portmask=3D0x3 --txd=3D512 --rxd=3D512
= =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2= =A0 dut.rhea: start
=C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0TestNicSingleCoreP= erf: Test Case test_perf_nic_single_core Result ERROR: Traceback (most rece= nt call last):
=C2=A0 File "/opt/dts/framework/test_case.py", = line 316, in _execute_test_case
=C2=A0 =C2=A0 case_obj() =C2=A0 =C2=A0 = =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2= =A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 = =C2=A0 =C2=A0 =C2=A0
=C2=A0 File "tests/TestSuite_nic_single_core_= perf.py", line 198, in test_perf_nic_single_core
=C2=A0 =C2=A0 self= .perf_test(self.nb_ports)
=C2=A0 File "tests/TestSuite_nic_single_c= ore_perf.py", line 259, in perf_test
=C2=A0 =C2=A0 _, packets_recei= ved =3D self.tester.pktgen.measure_throughput(stream_ids=3Dstreams, options= =3Dtraffic_opt)
=C2=A0 File "/opt/dts/framework/pktgen_base.py"= ;, line 245, in measure_throughput
=C2=A0 =C2=A0 self._prepare_transmiss= ion(stream_ids=3Dstream_ids)
=C2=A0 File "/opt/dts/framework/pktgen= _trex.py", line 779, in _prepare_transmission
=C2=A0 =C2=A0 self._c= onn.reset(ports=3Dself._ports)
=C2=A0 File "/opt/v2.82/automation/t= rex_control_plane/interactive/trex/common/trex_api_annotators.py", lin= e 51, in wrap2
=C2=A0 =C2=A0 ret =3D f(*args, **kwargs) =C2=A0 =C2=A0 = =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2= =A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0
=C2=A0 File "/opt/v2= .82/automation/trex_control_plane/interactive/trex/stl/trex_stl_client.py&q= uot;, line 339, in reset
=C2=A0 =C2=A0 self.clear_stats(ports) =C2=A0 = =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2= =A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0
=C2=A0 File = "/opt/v2.82/automation/trex_control_plane/interactive/trex/common/trex= _api_annotators.py", line 51, in wrap2
=C2=A0 =C2=A0 ret =3D f(*arg= s, **kwargs) =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0= =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0
= =C2=A0 File "/opt/v2.82/automation/trex_control_plane/interactive/trex= /stl/trex_stl_client.py", line 1467, in clear_stats
=C2=A0 =C2=A0 s= elf._clear_stats_common(ports, clear_global, clear_xstats)
=C2=A0 File &= quot;/opt/v2.82/automation/trex_control_plane/interactive/trex/common/trex_= client.py", line 2840, in _clear_stats_common
=C2=A0 =C2=A0 raise T= RexError(rc) =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0= =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2= =A0 =C2=A0 =C2=A0
trex.common.trex_exceptions.TRexError: *** [RPC] - Fai= led to get server response from tcp://127.0.0.1:4501

I = have found one similar case on the github repository for trex, but the solu= tion was vendor-specific:=C2=A0https://github.com= /cisco-system-traffic-generator/trex-core/issues/147.
Have yo= u ran into this issue before?

Thanks,
Br= andon


--

Brandon Lo

UNH InterOperability Laborator= y

21 Madbury Rd, Suite 100, Durham, NH 03824

blo@iol.unh.edu

www.iol.unh.edu



--

Brandon Lo

UNH = InterOperability Laboratory

21 Madbury Rd, Suite 100, Durham, NH 03824

blo@iol.unh.edu

<= a href=3D"http://www.iol.unh.edu/" target=3D"_blank">www.iol.unh.edu

--0000000000002b2e6f05ac9da560-- From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from dpdk.org (dpdk.org [92.243.14.124]) by inbox.dpdk.org (Postfix) with ESMTP id B4A7FA04DE for ; Tue, 11 Aug 2020 19:48:05 +0200 (CEST) Received: from [92.243.14.124] (localhost [127.0.0.1]) by dpdk.org (Postfix) with ESMTP id 8E70C1C022; Tue, 11 Aug 2020 19:48:05 +0200 (CEST) Received: from mail-oi1-f173.google.com (mail-oi1-f173.google.com [209.85.167.173]) by dpdk.org (Postfix) with ESMTP id 516661C01F for ; Tue, 11 Aug 2020 19:48:04 +0200 (CEST) Received: by mail-oi1-f173.google.com with SMTP id v13so12981966oiv.13 for ; Tue, 11 Aug 2020 10:48:04 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=broadcom.com; s=google; h=mime-version:references:in-reply-to:from:date:message-id:subject:to :cc; bh=SnwwQ6x1GkJY0ulDeyurTJ5wPyvbPk2N8TaNwXPb5Zs=; b=FvfmjvB/bVFWkXJpnLgBOXlN2HkW2bsW7w/sISKgSB8wNf8UckfHSwDs+SwYCvarZy I9Guz3zbWio8G//hjVn2UMRZHEXG2knVRfzHItCjPHt2wYqH6Tl6of4PDa8ZtHMGLyaS N7AzW4UQ6SFA+Ge84a5BPUJ2umd1NcKidlf+I= X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20161025; h=x-gm-message-state:mime-version:references:in-reply-to:from:date :message-id:subject:to:cc; bh=SnwwQ6x1GkJY0ulDeyurTJ5wPyvbPk2N8TaNwXPb5Zs=; b=reLvVoAraRfUWwzNlOlgwVHPrDcWLW+eonQxHo5pO2iNsVKhG4mtmh1qfGNuHh4L37 8tTpv1SwHMnFhQlo/j8tQMQqaGFMj/5VtZpNHxaVm/Th2XT8f0zhvSVjzWnJ3mBx92ow 5SKwwWbrNIdB0izoZmztUavsBs9VEZvri3i4eV0lzGD87CzQiMyeZAyMn2mw7CCU8PUl azQh+n1HqrIpMiTY1S5Usj5H66o6KZyOXLZJRAptXs6EZdbkmuFJCHyPj07qqhnO4uVe WIsthQid+f7N+Bbyg9+dIqv/4ibhdsEETFhTo2smzzu3Uo3fEBvJ4Ybz5T6fNi7KXkUv tNSA== X-Gm-Message-State: AOAM530oeuzLOd8KwPZdHuR61lTaIMZSkQzcqjNjEwERSYXNRHlrNkDI 5QZ8GwcPLW9k8JEwYM1FRPBDqcwBk3G++rZuVMFVWg== X-Google-Smtp-Source: ABdhPJwjI1ocrhgajCjievDLpRma28JNpzMgO84csGuSMvxPueoIUyYxzvbieD6v4ouCGlCvb2e3Uu7K/VwLFYnsUGk= X-Received: by 2002:aca:f550:: with SMTP id t77mr4514997oih.168.1597168083116; Tue, 11 Aug 2020 10:48:03 -0700 (PDT) MIME-Version: 1.0 References: In-Reply-To: From: Ajit Khaparde Date: Tue, 11 Aug 2020 10:47:46 -0700 Message-ID: To: Brandon Lo Cc: ci@dpdk.org, dpdklab Content-Type: multipart/alternative; boundary="0000000000003dfed705ac9dac08" Subject: Re: [dpdk-ci] New 100G Broadcom NIC Ubuntu X-BeenThere: ci@dpdk.org X-Mailman-Version: 2.1.15 Precedence: list List-Id: DPDK CI discussions List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Errors-To: ci-bounces@dpdk.org Sender: "ci" --0000000000003dfed705ac9dac08 Content-Type: text/plain; charset="UTF-8" Hi Brandon, I haven't. I tried to login as well. But I had some issues doing it from the office. I just have to remind myself to try it again once I get home before I connect to the company VPN. Thanks for checking in. I will try to update you as soon as I can. Thanks Ajit On Tue, Aug 11, 2020 at 10:46 AM Brandon Lo wrote: > Hi Ajit, > > I'm just checking in; have you heard of any updates on this issue? > > Thanks, > Brandon > > On Tue, Aug 4, 2020 at 1:42 PM Brandon Lo wrote: > >> Hi Ajit, >> >> Yes, I believe the issue is coming from the trex/tester system with the >> 100G NIC. >> I'm not sure what causes this issue; if I run trex using the command "cd >> /opt/v2.82;./t-rex-64 -i --cfg /etc/trex_cfg_100g.yaml -c 7", which is the >> same command used in DTS, it seems to launch without failing. >> >> If you want to replicate it, here are the steps that I ran: >> >> 1. (on io) cd /opt/dts >> 2. export DTS_CFG_FOLDER='conf_100g' >> - conf_100g has the new configuration files to use the new PCI id >> and pktgen config file >> 3. ./dts -s >> >> >> Thanks for your help, >> Brandon >> >> On Tue, Aug 4, 2020 at 12:38 PM Ajit Khaparde >> wrote: >> >>> Hi Brandon, >>> No, I haven't seen or heard this before. >>> But I will try to have someone run it again. >>> >>> Just to make sure - >>> You are running trex on the 100G NIC and the problem is encountered on >>> that setup? >>> Or is it the system that is running testpmd where you are running into >>> the issue? >>> >>> Thanks >>> Ajit >>> >>> On Tue, Aug 4, 2020 at 9:16 AM Brandon Lo wrote: >>> >>>> Hi Ajit, >>>> >>>> I'm running into a problem with trying to run nic_single_core_perf on >>>> the new NIC. >>>> The current configuration uses trex version v2.82. >>>> However, I'm running into an error when it tries to actually do a test >>>> case in the nic_single_core_perf. >>>> >>>> The output looks like this when it reaches a test case: >>>> >>>> TestNicSingleCorePerf: Test running at parameters: framesize: 64, >>>>> rxd/txd: 512 >>>>> dut.rhea: >>>>> ./x86_64-native-linuxapp-gcc/app/testpmd -l 16,17 -n 4 -w 0000:81:00.0 -w >>>>> 0000:81:00.1 --file-prefix=dpdk_11307_20200804160513 -- -i >>>>> --portmask=0x3 --txd=512 --rxd=512 >>>>> dut.rhea: start >>>>> TestNicSingleCorePerf: Test Case test_perf_nic_single_core >>>>> Result ERROR: Traceback (most recent call last): >>>>> File "/opt/dts/framework/test_case.py", line 316, in >>>>> _execute_test_case >>>>> case_obj() >>>>> File "tests/TestSuite_nic_single_core_perf.py", line 198, in >>>>> test_perf_nic_single_core >>>>> self.perf_test(self.nb_ports) >>>>> File "tests/TestSuite_nic_single_core_perf.py", line 259, in >>>>> perf_test >>>>> _, packets_received = >>>>> self.tester.pktgen.measure_throughput(stream_ids=streams, >>>>> options=traffic_opt) >>>>> File "/opt/dts/framework/pktgen_base.py", line 245, in >>>>> measure_throughput >>>>> self._prepare_transmission(stream_ids=stream_ids) >>>>> File "/opt/dts/framework/pktgen_trex.py", line 779, in >>>>> _prepare_transmission >>>>> self._conn.reset(ports=self._ports) >>>>> File >>>>> "/opt/v2.82/automation/trex_control_plane/interactive/trex/common/trex_api_annotators.py", >>>>> line 51, in wrap2 >>>>> ret = f(*args, **kwargs) >>>>> File >>>>> "/opt/v2.82/automation/trex_control_plane/interactive/trex/stl/trex_stl_client.py", >>>>> line 339, in reset >>>>> self.clear_stats(ports) >>>>> File >>>>> "/opt/v2.82/automation/trex_control_plane/interactive/trex/common/trex_api_annotators.py", >>>>> line 51, in wrap2 >>>>> ret = f(*args, **kwargs) >>>>> File >>>>> "/opt/v2.82/automation/trex_control_plane/interactive/trex/stl/trex_stl_client.py", >>>>> line 1467, in clear_stats >>>>> self._clear_stats_common(ports, clear_global, clear_xstats) >>>>> File >>>>> "/opt/v2.82/automation/trex_control_plane/interactive/trex/common/trex_client.py", >>>>> line 2840, in _clear_stats_common >>>>> raise TRexError(rc) >>>>> trex.common.trex_exceptions.TRexError: *** [RPC] - Failed to get >>>>> server response from tcp://127.0.0.1:4501 >>>> >>>> >>>> I have found one similar case on the github repository for trex, but >>>> the solution was vendor-specific: >>>> https://github.com/cisco-system-traffic-generator/trex-core/issues/147. >>>> Have you ran into this issue before? >>>> >>>> Thanks, >>>> Brandon >>>> >>> >> >> -- >> >> Brandon Lo >> >> UNH InterOperability Laboratory >> >> 21 Madbury Rd, Suite 100, Durham, NH 03824 >> >> blo@iol.unh.edu >> >> www.iol.unh.edu >> > > > -- > > Brandon Lo > > UNH InterOperability Laboratory > > 21 Madbury Rd, Suite 100, Durham, NH 03824 > > blo@iol.unh.edu > > www.iol.unh.edu > --0000000000003dfed705ac9dac08 Content-Type: text/html; charset="UTF-8" Content-Transfer-Encoding: quoted-printable
Hi Brandon,
I haven't. I tried to login as well. But I had so= me issues doing it from the office.
I just have to remind myself to try it= =C2=A0again once I get home before I connect to the company VPN.
Thanks for = checking in. I will try to update you as soon as I can.

Thanks
Ajit
=

= On Tue, Aug 11, 2020 at 10:46 AM Brandon Lo <blo@iol.unh.edu> wrote:
Hi Ajit,

I'm= just checking in; have you heard of any updates on this issue?
<= br>
Thanks,
Brandon

On Tue, Aug 4, 2020 at 1:42 PM= Brandon Lo <blo@io= l.unh.edu> wrote:
Hi Ajit,

Yes, I believe the = issue is coming from the trex/tester system with the 100G NIC.
I&= #39;m not sure what causes this issue; if I run trex using the command &quo= t;cd /opt/v2.82;./t-rex-64 -i --cfg /etc/trex_cfg_100g.yaml -c 7", whi= ch is the same command used in DTS, it seems to launch without failing.

If you want to replicate it, here are the steps that = I ran:
  1. (on io) cd /opt/dts
  2. export DTS_CFG_FOLDER= =3D'conf_100g'
    • conf_100g has the new configuration file= s to use the new PCI id and pktgen config file
  3. ./dts -s

Thanks for your help,
Brandon
<= /div>
O= n Tue, Aug 4, 2020 at 12:38 PM Ajit Khaparde <ajit.khaparde@broadcom.com> wr= ote:
= Hi Brandon,
No, I haven't seen or heard this=C2=A0before.
But I will = try to have someone=C2=A0run it again.

Just to make sure -
You are runnin= g trex on the 100G NIC and the problem is encountered on that setup?
<= div class=3D"gmail_default" style=3D"font-family:tahoma,sans-serif">Or is i= t the system that is running testpmd where you are running into the issue?<= /div>
<= br>
Thanks
Ajit

On Tue, Aug 4, 2020 at 9:16 AM Brandon Lo <blo@iol.unh.edu> wrote:
=
Hi Ajit,

I'm running=C2=A0into a problem = with trying to run nic_single_core_perf on the new NIC.
The curre= nt configuration uses trex version v2.82.
However, I'm runnin= g into an error when it tries to actually=C2=A0do a test case in the nic_si= ngle_core_perf.

The output looks like this when it= reaches a test case:

TestNicSingleCorePerf: Test runni= ng at parameters: framesize: 64, rxd/txd: 512
=C2=A0 =C2=A0 =C2=A0 =C2= =A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 dut.rhea: ./x86_64-nat= ive-linuxapp-gcc/app/testpmd -l 16,17 -n 4 -w 0000:81:00.0 -w 0000:81:00.1 = =C2=A0--file-prefix=3Ddpdk_11307_20200804160513 =C2=A0 =C2=A0-- -i =C2=A0--= portmask=3D0x3 --txd=3D512 --rxd=3D512
=C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2= =A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 dut.rhea: start
=C2=A0 =C2= =A0 =C2=A0 =C2=A0 =C2=A0TestNicSingleCorePerf: Test Case test_perf_nic_sing= le_core Result ERROR: Traceback (most recent call last):
=C2=A0 File &qu= ot;/opt/dts/framework/test_case.py", line 316, in _execute_test_case=C2=A0 =C2=A0 case_obj() =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0= =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2= =A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0
=C2=A0 File= "tests/TestSuite_nic_single_core_perf.py", line 198, in test_per= f_nic_single_core
=C2=A0 =C2=A0 self.perf_test(self.nb_ports)
=C2=A0 = File "tests/TestSuite_nic_single_core_perf.py", line 259, in perf= _test
=C2=A0 =C2=A0 _, packets_received =3D self.tester.pktgen.measure_t= hroughput(stream_ids=3Dstreams, options=3Dtraffic_opt)
=C2=A0 File "= ;/opt/dts/framework/pktgen_base.py", line 245, in measure_throughput=C2=A0 =C2=A0 self._prepare_transmission(stream_ids=3Dstream_ids)
=C2= =A0 File "/opt/dts/framework/pktgen_trex.py", line 779, in _prepa= re_transmission
=C2=A0 =C2=A0 self._conn.reset(ports=3Dself._ports)
= =C2=A0 File "/opt/v2.82/automation/trex_control_plane/interactive/trex= /common/trex_api_annotators.py", line 51, in wrap2
=C2=A0 =C2=A0 re= t =3D f(*args, **kwargs) =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 = =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2= =A0 =C2=A0
=C2=A0 File "/opt/v2.82/automation/trex_control_plane/i= nteractive/trex/stl/trex_stl_client.py", line 339, in reset
=C2=A0 = =C2=A0 self.clear_stats(ports) =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 = =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2= =A0 =C2=A0 =C2=A0 =C2=A0
=C2=A0 File "/opt/v2.82/automation/trex_co= ntrol_plane/interactive/trex/common/trex_api_annotators.py", line 51, = in wrap2
=C2=A0 =C2=A0 ret =3D f(*args, **kwargs) =C2=A0 =C2=A0 =C2=A0 = =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2= =A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0
=C2=A0 File "/opt/v2.82/aut= omation/trex_control_plane/interactive/trex/stl/trex_stl_client.py", l= ine 1467, in clear_stats
=C2=A0 =C2=A0 self._clear_stats_common(ports, c= lear_global, clear_xstats)
=C2=A0 File "/opt/v2.82/automation/trex_= control_plane/interactive/trex/common/trex_client.py", line 2840, in _= clear_stats_common
=C2=A0 =C2=A0 raise TRexError(rc) =C2=A0 =C2=A0 =C2= =A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 = =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0
trex.comm= on.trex_exceptions.TRexError: *** [RPC] - Failed to get server response fro= m tcp://127.0.0.1:4501<= /a>

Have you ran into this issue before= ?

Thanks,
Brandon
=


--

Brandon Lo

UNH InterOperability Laborator= y

21 Madbury Rd, Suite 100, Durham, NH 03824

blo@iol.unh.edu

www.iol.unh.edu



--

Brandon Lo

UNH InterOperability Laborator= y

21 Madbury Rd, Suite 100, Durham, NH 03824

blo@iol.unh.edu

www.iol.unh.edu

--0000000000003dfed705ac9dac08-- From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from dpdk.org (dpdk.org [92.243.14.124]) by inbox.dpdk.org (Postfix) with ESMTP id 021CEA04AF for ; Thu, 20 Aug 2020 06:29:31 +0200 (CEST) Received: from [92.243.14.124] (localhost [127.0.0.1]) by dpdk.org (Postfix) with ESMTP id C36F7AAD5; Thu, 20 Aug 2020 06:29:31 +0200 (CEST) Received: from mail-ot1-f50.google.com (mail-ot1-f50.google.com [209.85.210.50]) by dpdk.org (Postfix) with ESMTP id CCED75F69 for ; Thu, 20 Aug 2020 06:29:29 +0200 (CEST) Received: by mail-ot1-f50.google.com with SMTP id x24so469392otp.3 for ; Wed, 19 Aug 2020 21:29:29 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=broadcom.com; s=google; h=mime-version:references:in-reply-to:from:date:message-id:subject:to :cc; bh=hefzneZMD+APyrRYyllOS+zliJVTAhoRwnLWqBTcoeg=; b=WW4xup3MJi3bzfL1GKng6Se6S9c7vTjJ+GSMt84wjaeshxKz78Im1FmeCbPZ9izpw3 x0AfGVkd217Xjz7zT+DWiO4xjtpBDTYIwWlNBdAchGCZ9hlLig+YgsIHbgU1s0XWwwWq 8vaQhyIWlqAtcbfdgxLwd2EdBgCJDYadXo5go= X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20161025; h=x-gm-message-state:mime-version:references:in-reply-to:from:date :message-id:subject:to:cc; bh=hefzneZMD+APyrRYyllOS+zliJVTAhoRwnLWqBTcoeg=; b=ZRfnbFsFNsMU2yNrbc+7/+9ranW0Rv5UE7nDDMom3Lb1SEj99nvbiWtu4AYECXjrv0 w/6j3mSbx0CnGT46Ggixe4CsJD7zLzKwvYc2A/e13HI1r6sbR113REWQcjjrx6zW/Mps QoWdnc1kOS92rqtJ1/reEMFwum9D4m84Ig17spf1mZElwaI2JzMkPlEKlE4KPmiRmpmw lkUKOHYAUCMsS3uxAknokJhol/I79r3poUNZaeWiKs6bL8dU24t+IZzFGHoxd2FLbXzf A3i3CIE/rCXmF3ckzx7n2DYuQBZqSaui68/HZZmb/oluzMQtFiPbdisSNlhPSXi2SsH1 fmFA== X-Gm-Message-State: AOAM533BMaxWFBAjCtvWL114GCPAPjcHu934CiN25VBQkERcMppuV9Ao 81h61gtqc8PjkNCAZKIy6fQTpwWD1PV+f1q2Fwm1sQ== X-Google-Smtp-Source: ABdhPJxJCL6Vw1ixMC/9xwUX3Io3peEtAITH0OdClW5aKFyrni5VXdk4cFw8bNNdatSM79wdcBwi30I7+SmZ/1NrP5Q= X-Received: by 2002:a05:6830:614:: with SMTP id w20mr902161oti.283.1597897768923; Wed, 19 Aug 2020 21:29:28 -0700 (PDT) MIME-Version: 1.0 References: In-Reply-To: From: Ajit Khaparde Date: Wed, 19 Aug 2020 21:29:12 -0700 Message-ID: To: Brandon Lo Cc: ci@dpdk.org, dpdklab Content-Type: multipart/alternative; boundary="000000000000e7cea205ad4790c1" Subject: Re: [dpdk-ci] New 100G Broadcom NIC Ubuntu X-BeenThere: ci@dpdk.org X-Mailman-Version: 2.1.15 Precedence: list List-Id: DPDK CI discussions List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Errors-To: ci-bounces@dpdk.org Sender: "ci" --000000000000e7cea205ad4790c1 Content-Type: text/plain; charset="UTF-8" Hi Brandon, I was trying to see what exactly is happening on the setup and what is causing the problem. But I will need your help to use the proper code and commands. I believe you run the testpmd command on io. And the trex is executed on rhea? Can you point me to the location of the code and the steps you are following while running the test? Thanks Ajit On Tue, Aug 11, 2020 at 10:47 AM Ajit Khaparde wrote: > Hi Brandon, > I haven't. I tried to login as well. But I had some issues doing it from > the office. > I just have to remind myself to try it again once I get home before I > connect to the company VPN. > Thanks for checking in. I will try to update you as soon as I can. > > Thanks > Ajit > > On Tue, Aug 11, 2020 at 10:46 AM Brandon Lo wrote: > >> Hi Ajit, >> >> I'm just checking in; have you heard of any updates on this issue? >> >> Thanks, >> Brandon >> >> On Tue, Aug 4, 2020 at 1:42 PM Brandon Lo wrote: >> >>> Hi Ajit, >>> >>> Yes, I believe the issue is coming from the trex/tester system with the >>> 100G NIC. >>> I'm not sure what causes this issue; if I run trex using the command "cd >>> /opt/v2.82;./t-rex-64 -i --cfg /etc/trex_cfg_100g.yaml -c 7", which is the >>> same command used in DTS, it seems to launch without failing. >>> >>> If you want to replicate it, here are the steps that I ran: >>> >>> 1. (on io) cd /opt/dts >>> 2. export DTS_CFG_FOLDER='conf_100g' >>> - conf_100g has the new configuration files to use the new PCI id >>> and pktgen config file >>> 3. ./dts -s >>> >>> >>> Thanks for your help, >>> Brandon >>> >>> On Tue, Aug 4, 2020 at 12:38 PM Ajit Khaparde < >>> ajit.khaparde@broadcom.com> wrote: >>> >>>> Hi Brandon, >>>> No, I haven't seen or heard this before. >>>> But I will try to have someone run it again. >>>> >>>> Just to make sure - >>>> You are running trex on the 100G NIC and the problem is encountered on >>>> that setup? >>>> Or is it the system that is running testpmd where you are running into >>>> the issue? >>>> >>>> Thanks >>>> Ajit >>>> >>>> On Tue, Aug 4, 2020 at 9:16 AM Brandon Lo wrote: >>>> >>>>> Hi Ajit, >>>>> >>>>> I'm running into a problem with trying to run nic_single_core_perf on >>>>> the new NIC. >>>>> The current configuration uses trex version v2.82. >>>>> However, I'm running into an error when it tries to actually do a test >>>>> case in the nic_single_core_perf. >>>>> >>>>> The output looks like this when it reaches a test case: >>>>> >>>>> TestNicSingleCorePerf: Test running at parameters: framesize: 64, >>>>>> rxd/txd: 512 >>>>>> dut.rhea: >>>>>> ./x86_64-native-linuxapp-gcc/app/testpmd -l 16,17 -n 4 -w 0000:81:00.0 -w >>>>>> 0000:81:00.1 --file-prefix=dpdk_11307_20200804160513 -- -i >>>>>> --portmask=0x3 --txd=512 --rxd=512 >>>>>> dut.rhea: start >>>>>> TestNicSingleCorePerf: Test Case test_perf_nic_single_core >>>>>> Result ERROR: Traceback (most recent call last): >>>>>> File "/opt/dts/framework/test_case.py", line 316, in >>>>>> _execute_test_case >>>>>> case_obj() >>>>>> File "tests/TestSuite_nic_single_core_perf.py", line 198, in >>>>>> test_perf_nic_single_core >>>>>> self.perf_test(self.nb_ports) >>>>>> File "tests/TestSuite_nic_single_core_perf.py", line 259, in >>>>>> perf_test >>>>>> _, packets_received = >>>>>> self.tester.pktgen.measure_throughput(stream_ids=streams, >>>>>> options=traffic_opt) >>>>>> File "/opt/dts/framework/pktgen_base.py", line 245, in >>>>>> measure_throughput >>>>>> self._prepare_transmission(stream_ids=stream_ids) >>>>>> File "/opt/dts/framework/pktgen_trex.py", line 779, in >>>>>> _prepare_transmission >>>>>> self._conn.reset(ports=self._ports) >>>>>> File >>>>>> "/opt/v2.82/automation/trex_control_plane/interactive/trex/common/trex_api_annotators.py", >>>>>> line 51, in wrap2 >>>>>> ret = f(*args, **kwargs) >>>>>> File >>>>>> "/opt/v2.82/automation/trex_control_plane/interactive/trex/stl/trex_stl_client.py", >>>>>> line 339, in reset >>>>>> self.clear_stats(ports) >>>>>> File >>>>>> "/opt/v2.82/automation/trex_control_plane/interactive/trex/common/trex_api_annotators.py", >>>>>> line 51, in wrap2 >>>>>> ret = f(*args, **kwargs) >>>>>> File >>>>>> "/opt/v2.82/automation/trex_control_plane/interactive/trex/stl/trex_stl_client.py", >>>>>> line 1467, in clear_stats >>>>>> self._clear_stats_common(ports, clear_global, clear_xstats) >>>>>> File >>>>>> "/opt/v2.82/automation/trex_control_plane/interactive/trex/common/trex_client.py", >>>>>> line 2840, in _clear_stats_common >>>>>> raise TRexError(rc) >>>>>> trex.common.trex_exceptions.TRexError: *** [RPC] - Failed to get >>>>>> server response from tcp://127.0.0.1:4501 >>>>> >>>>> >>>>> I have found one similar case on the github repository for trex, but >>>>> the solution was vendor-specific: >>>>> https://github.com/cisco-system-traffic-generator/trex-core/issues/147 >>>>> . >>>>> Have you ran into this issue before? >>>>> >>>>> Thanks, >>>>> Brandon >>>>> >>>> >>> >>> -- >>> >>> Brandon Lo >>> >>> UNH InterOperability Laboratory >>> >>> 21 Madbury Rd, Suite 100, Durham, NH 03824 >>> >>> blo@iol.unh.edu >>> >>> www.iol.unh.edu >>> >> >> >> -- >> >> Brandon Lo >> >> UNH InterOperability Laboratory >> >> 21 Madbury Rd, Suite 100, Durham, NH 03824 >> >> blo@iol.unh.edu >> >> www.iol.unh.edu >> > --000000000000e7cea205ad4790c1 Content-Type: text/html; charset="UTF-8" Content-Transfer-Encoding: quoted-printable
Hi Brandon,
I was trying to see what exactly is happening on the = setup and what is causing the=C2=A0problem.
But I will need your help to use= the proper code and commands.

I believe you run the testpmd command on= io. And the trex is executed on rhea?
Can you point me to the location of t= he code and the steps you are following while running the test?

Thanks
Aj= it

On Tue, Aug 11, 2020 at 10:47 AM Ajit Khaparde <ajit.khaparde@broadcom.com> wrote:
=
Hi Brand= on,
I haven't. I tried to login as well. But I had some issues doing it = from the office.
I just have to remind myself to try it=C2=A0again once I ge= t home before I connect to the company VPN.
Thanks for checking in. I will t= ry to update you as soon as I can.

Thanks
Ajit

On Tue, Aug 11, 2020= at 10:46 AM Brandon Lo <blo@iol.unh.edu> wrote:
Hi Ajit,

I'm j= ust checking in; have you heard of any updates on this issue?
Thanks,
Brandon

On Tue, Aug 4, 2020 at 1:42 PM B= randon Lo <blo@iol.= unh.edu> wrote:
Hi Ajit,

Yes, I believe the issu= e is coming from the trex/tester system with the 100G NIC.
I'= m not sure what causes this issue; if I run trex using the command "cd= /opt/v2.82;./t-rex-64 -i --cfg /etc/trex_cfg_100g.yaml -c 7", which i= s the same command used in DTS, it seems to launch without failing.

If you want to replicate it, here are the steps that I ra= n:
  1. (on io) cd /opt/dts
  2. export DTS_CFG_FOLDER=3D&#= 39;conf_100g'
    • conf_100g has the new configuration files to = use the new PCI id and pktgen config file
  3. ./dts -s

Thanks for your help,
Brandon
=
On Tue= , Aug 4, 2020 at 12:38 PM Ajit Khaparde <ajit.khaparde@broadcom.com> wrote:<= br>
Hi Br= andon,
No, I haven't seen or heard this=C2=A0before.
But I will try t= o have someone=C2=A0run it again.

Just to make sure -
You are running = trex on the 100G NIC and the problem is encountered on that setup?
Or is it = the system that is running testpmd where you are running into the issue?
Thanks
Ajit

On Tue, Aug 4, 2020 at 9:16 AM Brandon Lo <blo@iol.unh.edu> wrote:
=
Hi Ajit,

I'm running=C2=A0into a problem wi= th trying to run nic_single_core_perf on the new NIC.
The current= configuration uses trex version v2.82.
However, I'm running = into an error when it tries to actually=C2=A0do a test case in the nic_sing= le_core_perf.

The output looks like this when it r= eaches a test case:

TestNicSingleCorePerf: Test running= at parameters: framesize: 64, rxd/txd: 512
=C2=A0 =C2=A0 =C2=A0 =C2=A0 = =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 dut.rhea: ./x86_64-native-= linuxapp-gcc/app/testpmd -l 16,17 -n 4 -w 0000:81:00.0 -w 0000:81:00.1 =C2= =A0--file-prefix=3Ddpdk_11307_20200804160513 =C2=A0 =C2=A0-- -i =C2=A0--por= tmask=3D0x3 --txd=3D512 --rxd=3D512
=C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 = =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 dut.rhea: start
=C2=A0 =C2=A0 = =C2=A0 =C2=A0 =C2=A0TestNicSingleCorePerf: Test Case test_perf_nic_single_c= ore Result ERROR: Traceback (most recent call last):
=C2=A0 File "/= opt/dts/framework/test_case.py", line 316, in _execute_test_case
= =C2=A0 =C2=A0 case_obj() =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 = =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2= =A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0
=C2=A0 File= "tests/TestSuite_nic_single_core_perf.py", line 198, in test_per= f_nic_single_core
=C2=A0 =C2=A0 self.perf_test(self.nb_ports)
=C2=A0 = File "tests/TestSuite_nic_single_core_perf.py", line 259, in perf= _test
=C2=A0 =C2=A0 _, packets_received =3D self.tester.pktgen.measure_t= hroughput(stream_ids=3Dstreams, options=3Dtraffic_opt)
=C2=A0 File "= ;/opt/dts/framework/pktgen_base.py", line 245, in measure_throughput=C2=A0 =C2=A0 self._prepare_transmission(stream_ids=3Dstream_ids)
=C2= =A0 File "/opt/dts/framework/pktgen_trex.py", line 779, in _prepa= re_transmission
=C2=A0 =C2=A0 self._conn.reset(ports=3Dself._ports)
= =C2=A0 File "/opt/v2.82/automation/trex_control_plane/interactive/trex= /common/trex_api_annotators.py", line 51, in wrap2
=C2=A0 =C2=A0 re= t =3D f(*args, **kwargs) =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 = =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2= =A0 =C2=A0
=C2=A0 File "/opt/v2.82/automation/trex_control_plane/i= nteractive/trex/stl/trex_stl_client.py", line 339, in reset
=C2=A0 = =C2=A0 self.clear_stats(ports) =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 = =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2= =A0 =C2=A0 =C2=A0 =C2=A0
=C2=A0 File "/opt/v2.82/automation/trex_co= ntrol_plane/interactive/trex/common/trex_api_annotators.py", line 51, = in wrap2
=C2=A0 =C2=A0 ret =3D f(*args, **kwargs) =C2=A0 =C2=A0 =C2=A0 = =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2= =A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0
=C2=A0 File "/opt/v2.82/aut= omation/trex_control_plane/interactive/trex/stl/trex_stl_client.py", l= ine 1467, in clear_stats
=C2=A0 =C2=A0 self._clear_stats_common(ports, c= lear_global, clear_xstats)
=C2=A0 File "/opt/v2.82/automation/trex_= control_plane/interactive/trex/common/trex_client.py", line 2840, in _= clear_stats_common
=C2=A0 =C2=A0 raise TRexError(rc) =C2=A0 =C2=A0 =C2= =A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 = =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0
trex.comm= on.trex_exceptions.TRexError: *** [RPC] - Failed to get server response fro= m tcp://127.0.0.1:4501<= /a>

Have you ran into this issue before= ?

Thanks,
Brandon
=


--

Brandon Lo

UNH InterOperability Laborator= y

21 Madbury Rd, Suite 100, Durham, NH 03824

blo@iol.unh.edu

www.iol.unh.edu



--

Brandon Lo

UNH InterOperability Laborator= y

21 Madbury Rd, Suite 100, Durham, NH 03824

blo@iol.unh.edu

www.iol.unh.edu

--000000000000e7cea205ad4790c1-- From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from dpdk.org (dpdk.org [92.243.14.124]) by inbox.dpdk.org (Postfix) with ESMTP id DEABDA04AF for ; Thu, 20 Aug 2020 17:39:56 +0200 (CEST) Received: from [92.243.14.124] (localhost [127.0.0.1]) by dpdk.org (Postfix) with ESMTP id AB9071C027; Thu, 20 Aug 2020 17:39:56 +0200 (CEST) Received: from mail-il1-f169.google.com (mail-il1-f169.google.com [209.85.166.169]) by dpdk.org (Postfix) with ESMTP id 040981BEC4 for ; Thu, 20 Aug 2020 17:39:54 +0200 (CEST) Received: by mail-il1-f169.google.com with SMTP id t4so2032310iln.1 for ; Thu, 20 Aug 2020 08:39:54 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=iol.unh.edu; s=unh-iol; h=mime-version:references:in-reply-to:from:date:message-id:subject:to :cc; bh=reHrojqQYQYTavuI3l5H2L1gSBrr0Cy2mdBtVjy2Zg8=; b=BKY4X9k/ZVKi/gxEmLRBnYM2CcLZhU/2DGPbaz3bFI7Prtg0a+lZDDCiaK/jxyAf8e DO7oy6QYpWdUQiyKZ18Dge6pFVS3C0/HEU3joASuJepYmCZKwlYKN3f5DzxEKlv/IpeT KPj0UuTkhxZjZEDPq2mvMRto2FevypZW0saV4= X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20161025; h=x-gm-message-state:mime-version:references:in-reply-to:from:date :message-id:subject:to:cc; bh=reHrojqQYQYTavuI3l5H2L1gSBrr0Cy2mdBtVjy2Zg8=; b=iL8ZDy1iMhfDYje1U/WmRjUXyWAxnKAzFaKwyI1lVGRqtNa3e1vAUCQ9ii+6wr3IY2 GQNYODMXBZaiTiltlSt33j3KnFhTiGo2Z48Lq5Yv6EQWkYk2Q8eDGG3YbViQJIE31jpg UHvcUE7T/GaGcF+I3CaKI0WXaFgpcyN8jGlKRLaXnPySrQiKyRjv4kmyAhKINN0KXfK3 CLKS66/1W6mJeydul3V1oO2gfLobBUvKbxyjxYqsxGpyHVlFMvq1CYvMxp/vkLlCgc0p ATipyJVpNFrwTaW5QHZQd1B81PShTLvGkEg5e7g8Ej2jIP2BbJQ6xEKYi69wZb+CWHSF t1ww== X-Gm-Message-State: AOAM530T9be1A4JLVNb92QOdIB0aKibQhhu/TVUrEYz6MBNjTNOfF3dX EQyKoQMM/ITMaLDJDdXzMryrIelFGPpK9bs6l8qllw== X-Google-Smtp-Source: ABdhPJy6xd9zBol1YViNgE7Ef31cAW60mfZgbdQszjOOB+cZt32Q+uAhXmEnhpmwXA9MpIwbzjxnwf7OcP6sDvsivr4= X-Received: by 2002:a05:6e02:cb0:: with SMTP id 16mr2993030ilg.147.1597937994137; Thu, 20 Aug 2020 08:39:54 -0700 (PDT) MIME-Version: 1.0 References: In-Reply-To: From: Brandon Lo Date: Thu, 20 Aug 2020 11:39:18 -0400 Message-ID: To: Ajit Khaparde Cc: ci@dpdk.org, dpdklab Content-Type: text/plain; charset="UTF-8" Subject: Re: [dpdk-ci] New 100G Broadcom NIC Ubuntu X-BeenThere: ci@dpdk.org X-Mailman-Version: 2.1.15 Precedence: list List-Id: DPDK CI discussions List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Errors-To: ci-bounces@dpdk.org Sender: "ci" Hi Ajit, I believe DTS/TREX is run on the io machine as a tester. Rhea runs testpmd (through an ssh session from io --> rhea) to catch information as a DUT. The only commands that I run (on io) are: cd /opt/dts export DTS_CFG_FOLDER='conf_100g' ./dts -s The rest is managed by DTS itself. The issue occurs when DTS is trying to send packets to rhea from io on the new 100G NIC. It seems to happen after it tries to measure throughput using TREX's API. Thanks, Brandon On Thu, Aug 20, 2020 at 12:29 AM Ajit Khaparde wrote: > > Hi Brandon, > I was trying to see what exactly is happening on the setup and what is causing the problem. > But I will need your help to use the proper code and commands. > > I believe you run the testpmd command on io. And the trex is executed on rhea? > Can you point me to the location of the code and the steps you are following while running the test? > > Thanks > Ajit > > On Tue, Aug 11, 2020 at 10:47 AM Ajit Khaparde wrote: >> >> Hi Brandon, >> I haven't. I tried to login as well. But I had some issues doing it from the office. >> I just have to remind myself to try it again once I get home before I connect to the company VPN. >> Thanks for checking in. I will try to update you as soon as I can. >> >> Thanks >> Ajit >> >> On Tue, Aug 11, 2020 at 10:46 AM Brandon Lo wrote: >>> >>> Hi Ajit, >>> >>> I'm just checking in; have you heard of any updates on this issue? >>> >>> Thanks, >>> Brandon >>> >>> On Tue, Aug 4, 2020 at 1:42 PM Brandon Lo wrote: >>>> >>>> Hi Ajit, >>>> >>>> Yes, I believe the issue is coming from the trex/tester system with the 100G NIC. >>>> I'm not sure what causes this issue; if I run trex using the command "cd /opt/v2.82;./t-rex-64 -i --cfg /etc/trex_cfg_100g.yaml -c 7", which is the same command used in DTS, it seems to launch without failing. >>>> >>>> If you want to replicate it, here are the steps that I ran: >>>> >>>> (on io) cd /opt/dts >>>> export DTS_CFG_FOLDER='conf_100g' >>>> >>>> conf_100g has the new configuration files to use the new PCI id and pktgen config file >>>> >>>> ./dts -s >>>> >>>> >>>> Thanks for your help, >>>> Brandon >>>> >>>> On Tue, Aug 4, 2020 at 12:38 PM Ajit Khaparde wrote: >>>>> >>>>> Hi Brandon, >>>>> No, I haven't seen or heard this before. >>>>> But I will try to have someone run it again. >>>>> >>>>> Just to make sure - >>>>> You are running trex on the 100G NIC and the problem is encountered on that setup? >>>>> Or is it the system that is running testpmd where you are running into the issue? >>>>> >>>>> Thanks >>>>> Ajit >>>>> >>>>> On Tue, Aug 4, 2020 at 9:16 AM Brandon Lo wrote: >>>>>> >>>>>> Hi Ajit, >>>>>> >>>>>> I'm running into a problem with trying to run nic_single_core_perf on the new NIC. >>>>>> The current configuration uses trex version v2.82. >>>>>> However, I'm running into an error when it tries to actually do a test case in the nic_single_core_perf. >>>>>> >>>>>> The output looks like this when it reaches a test case: >>>>>> >>>>>>> TestNicSingleCorePerf: Test running at parameters: framesize: 64, rxd/txd: 512 >>>>>>> dut.rhea: ./x86_64-native-linuxapp-gcc/app/testpmd -l 16,17 -n 4 -w 0000:81:00.0 -w 0000:81:00.1 --file-prefix=dpdk_11307_20200804160513 -- -i --portmask=0x3 --txd=512 --rxd=512 >>>>>>> dut.rhea: start >>>>>>> TestNicSingleCorePerf: Test Case test_perf_nic_single_core Result ERROR: Traceback (most recent call last): >>>>>>> File "/opt/dts/framework/test_case.py", line 316, in _execute_test_case >>>>>>> case_obj() >>>>>>> File "tests/TestSuite_nic_single_core_perf.py", line 198, in test_perf_nic_single_core >>>>>>> self.perf_test(self.nb_ports) >>>>>>> File "tests/TestSuite_nic_single_core_perf.py", line 259, in perf_test >>>>>>> _, packets_received = self.tester.pktgen.measure_throughput(stream_ids=streams, options=traffic_opt) >>>>>>> File "/opt/dts/framework/pktgen_base.py", line 245, in measure_throughput >>>>>>> self._prepare_transmission(stream_ids=stream_ids) >>>>>>> File "/opt/dts/framework/pktgen_trex.py", line 779, in _prepare_transmission >>>>>>> self._conn.reset(ports=self._ports) >>>>>>> File "/opt/v2.82/automation/trex_control_plane/interactive/trex/common/trex_api_annotators.py", line 51, in wrap2 >>>>>>> ret = f(*args, **kwargs) >>>>>>> File "/opt/v2.82/automation/trex_control_plane/interactive/trex/stl/trex_stl_client.py", line 339, in reset >>>>>>> self.clear_stats(ports) >>>>>>> File "/opt/v2.82/automation/trex_control_plane/interactive/trex/common/trex_api_annotators.py", line 51, in wrap2 >>>>>>> ret = f(*args, **kwargs) >>>>>>> File "/opt/v2.82/automation/trex_control_plane/interactive/trex/stl/trex_stl_client.py", line 1467, in clear_stats >>>>>>> self._clear_stats_common(ports, clear_global, clear_xstats) >>>>>>> File "/opt/v2.82/automation/trex_control_plane/interactive/trex/common/trex_client.py", line 2840, in _clear_stats_common >>>>>>> raise TRexError(rc) >>>>>>> trex.common.trex_exceptions.TRexError: *** [RPC] - Failed to get server response from tcp://127.0.0.1:4501 >>>>>> >>>>>> >>>>>> I have found one similar case on the github repository for trex, but the solution was vendor-specific: https://github.com/cisco-system-traffic-generator/trex-core/issues/147. >>>>>> Have you ran into this issue before? >>>>>> >>>>>> Thanks, >>>>>> Brandon >>>> >>>> >>>> >>>> -- >>>> >>>> Brandon Lo >>>> >>>> UNH InterOperability Laboratory >>>> >>>> 21 Madbury Rd, Suite 100, Durham, NH 03824 >>>> >>>> blo@iol.unh.edu >>>> >>>> www.iol.unh.edu >>> >>> >>> >>> -- >>> >>> Brandon Lo >>> >>> UNH InterOperability Laboratory >>> >>> 21 Madbury Rd, Suite 100, Durham, NH 03824 >>> >>> blo@iol.unh.edu >>> >>> www.iol.unh.edu -- Brandon Lo UNH InterOperability Laboratory 21 Madbury Rd, Suite 100, Durham, NH 03824 blo@iol.unh.edu www.iol.unh.edu From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from dpdk.org (dpdk.org [92.243.14.124]) by inbox.dpdk.org (Postfix) with ESMTP id 808B7A04AF for ; Thu, 20 Aug 2020 23:07:40 +0200 (CEST) Received: from [92.243.14.124] (localhost [127.0.0.1]) by dpdk.org (Postfix) with ESMTP id 787E11C021; Thu, 20 Aug 2020 23:07:40 +0200 (CEST) Received: from mail-oi1-f182.google.com (mail-oi1-f182.google.com [209.85.167.182]) by dpdk.org (Postfix) with ESMTP id 816C91BEC4 for ; Thu, 20 Aug 2020 23:07:39 +0200 (CEST) Received: by mail-oi1-f182.google.com with SMTP id k4so3148115oik.2 for ; Thu, 20 Aug 2020 14:07:39 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=broadcom.com; s=google; h=mime-version:references:in-reply-to:from:date:message-id:subject:to :cc; bh=5cg8HQ9glMrFYfnCOt2/g633nONMTbcGGEpYcLGfPcc=; b=EQ3ZLyGnBKvP6ufeGob5+B4WbRI0WUoiAPuNQFvDrvziwiS99NhiSxrdIZ46nCR6So GR2rY4Lqjkpwdq3UCIKhNEQD96zxCRvpfxlADN6vGd9AnFjjTzA6wJCLVoKC7+SOsLLe 1gjxG0yHHOQBChvxxUnyD+SOwHrYv0+yt5ByA= X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20161025; h=x-gm-message-state:mime-version:references:in-reply-to:from:date :message-id:subject:to:cc; bh=5cg8HQ9glMrFYfnCOt2/g633nONMTbcGGEpYcLGfPcc=; b=eTzlJnxw/yFGT2sIa8XEYM89iUbe0vcfQEiKMgSjYy//sYGsZNkWpkwprrzLaQKj5F 6bHnPG9gEGoWeW2irf9kc90S/MGYnESXDz1ohBEvWbP1Q5mXy19LHLfDOI+VpIuf6RCo MJZtj5E/7ZhfhT3yoKkCNGKYoFYYOc88ngAjMW2shAAdPSKFYIR2r737bCYViUSqxRSg zZ6amB7r7XfVxVl+EFtFBn/nnsqykULzoBGU4m6aXfOgnOoX1Oy1ImKx5rxTdBtf/+Ay cFBDMn4UpBpj1xiZvK6Qa3r3ejttbxKFaQTyOy69QdxQoSY3Cv2+0uvS2bOQcZwA8MQS u60g== X-Gm-Message-State: AOAM53352Npvh39Kv6L9uq/4nz5KMOjB0r53YgtEnL1g33p221rgHTCS mUiBJ1WnfmFlLoez8onB5RYN5l9sMbQpxh7CGLWBhQ== X-Google-Smtp-Source: ABdhPJyRxOUC0Uqsb+LJouMY2ciCsBnVyzdo6a8eZndAownfIbo+poitqpObdkiOrtkfg3s6XwuCEE6jHVsQKXIE+ho= X-Received: by 2002:a54:4f85:: with SMTP id g5mr177244oiy.27.1597957658525; Thu, 20 Aug 2020 14:07:38 -0700 (PDT) MIME-Version: 1.0 References: In-Reply-To: From: Ajit Khaparde Date: Thu, 20 Aug 2020 14:07:22 -0700 Message-ID: To: Brandon Lo Cc: ci@dpdk.org, dpdklab Content-Type: multipart/alternative; boundary="0000000000009aa94f05ad558233" Subject: Re: [dpdk-ci] New 100G Broadcom NIC Ubuntu X-BeenThere: ci@dpdk.org X-Mailman-Version: 2.1.15 Precedence: list List-Id: DPDK CI discussions List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Errors-To: ci-bounces@dpdk.org Sender: "ci" --0000000000009aa94f05ad558233 Content-Type: text/plain; charset="UTF-8" Hi Brandon, I do see some issues while running trex on this setup. I will have to dig further. I will let you know once I find something or may be a fix. Thanks Ajit On Thu, Aug 20, 2020 at 8:39 AM Brandon Lo wrote: > Hi Ajit, > > I believe DTS/TREX is run on the io machine as a tester. Rhea runs > testpmd (through an ssh session from io --> rhea) to catch information > as a DUT. > > The only commands that I run (on io) are: > cd /opt/dts > export DTS_CFG_FOLDER='conf_100g' > ./dts -s > > The rest is managed by DTS itself. > The issue occurs when DTS is trying to send packets to rhea from io on > the new 100G NIC. > It seems to happen after it tries to measure throughput using TREX's API. > > Thanks, > Brandon > > On Thu, Aug 20, 2020 at 12:29 AM Ajit Khaparde > wrote: > > > > Hi Brandon, > > I was trying to see what exactly is happening on the setup and what is > causing the problem. > > But I will need your help to use the proper code and commands. > > > > I believe you run the testpmd command on io. And the trex is executed on > rhea? > > Can you point me to the location of the code and the steps you are > following while running the test? > > > > Thanks > > Ajit > > > > On Tue, Aug 11, 2020 at 10:47 AM Ajit Khaparde < > ajit.khaparde@broadcom.com> wrote: > >> > >> Hi Brandon, > >> I haven't. I tried to login as well. But I had some issues doing it > from the office. > >> I just have to remind myself to try it again once I get home before I > connect to the company VPN. > >> Thanks for checking in. I will try to update you as soon as I can. > >> > >> Thanks > >> Ajit > >> > >> On Tue, Aug 11, 2020 at 10:46 AM Brandon Lo wrote: > >>> > >>> Hi Ajit, > >>> > >>> I'm just checking in; have you heard of any updates on this issue? > >>> > >>> Thanks, > >>> Brandon > >>> > >>> On Tue, Aug 4, 2020 at 1:42 PM Brandon Lo wrote: > >>>> > >>>> Hi Ajit, > >>>> > >>>> Yes, I believe the issue is coming from the trex/tester system with > the 100G NIC. > >>>> I'm not sure what causes this issue; if I run trex using the command > "cd /opt/v2.82;./t-rex-64 -i --cfg /etc/trex_cfg_100g.yaml -c 7", which is > the same command used in DTS, it seems to launch without failing. > >>>> > >>>> If you want to replicate it, here are the steps that I ran: > >>>> > >>>> (on io) cd /opt/dts > >>>> export DTS_CFG_FOLDER='conf_100g' > >>>> > >>>> conf_100g has the new configuration files to use the new PCI id and > pktgen config file > >>>> > >>>> ./dts -s > >>>> > >>>> > >>>> Thanks for your help, > >>>> Brandon > >>>> > >>>> On Tue, Aug 4, 2020 at 12:38 PM Ajit Khaparde < > ajit.khaparde@broadcom.com> wrote: > >>>>> > >>>>> Hi Brandon, > >>>>> No, I haven't seen or heard this before. > >>>>> But I will try to have someone run it again. > >>>>> > >>>>> Just to make sure - > >>>>> You are running trex on the 100G NIC and the problem is encountered > on that setup? > >>>>> Or is it the system that is running testpmd where you are running > into the issue? > >>>>> > >>>>> Thanks > >>>>> Ajit > >>>>> > >>>>> On Tue, Aug 4, 2020 at 9:16 AM Brandon Lo wrote: > >>>>>> > >>>>>> Hi Ajit, > >>>>>> > >>>>>> I'm running into a problem with trying to run nic_single_core_perf > on the new NIC. > >>>>>> The current configuration uses trex version v2.82. > >>>>>> However, I'm running into an error when it tries to actually do a > test case in the nic_single_core_perf. > >>>>>> > >>>>>> The output looks like this when it reaches a test case: > >>>>>> > >>>>>>> TestNicSingleCorePerf: Test running at parameters: framesize: 64, > rxd/txd: 512 > >>>>>>> dut.rhea: > ./x86_64-native-linuxapp-gcc/app/testpmd -l 16,17 -n 4 -w 0000:81:00.0 -w > 0000:81:00.1 --file-prefix=dpdk_11307_20200804160513 -- -i > --portmask=0x3 --txd=512 --rxd=512 > >>>>>>> dut.rhea: start > >>>>>>> TestNicSingleCorePerf: Test Case > test_perf_nic_single_core Result ERROR: Traceback (most recent call last): > >>>>>>> File "/opt/dts/framework/test_case.py", line 316, in > _execute_test_case > >>>>>>> case_obj() > >>>>>>> File "tests/TestSuite_nic_single_core_perf.py", line 198, in > test_perf_nic_single_core > >>>>>>> self.perf_test(self.nb_ports) > >>>>>>> File "tests/TestSuite_nic_single_core_perf.py", line 259, in > perf_test > >>>>>>> _, packets_received = > self.tester.pktgen.measure_throughput(stream_ids=streams, > options=traffic_opt) > >>>>>>> File "/opt/dts/framework/pktgen_base.py", line 245, in > measure_throughput > >>>>>>> self._prepare_transmission(stream_ids=stream_ids) > >>>>>>> File "/opt/dts/framework/pktgen_trex.py", line 779, in > _prepare_transmission > >>>>>>> self._conn.reset(ports=self._ports) > >>>>>>> File > "/opt/v2.82/automation/trex_control_plane/interactive/trex/common/trex_api_annotators.py", > line 51, in wrap2 > >>>>>>> ret = f(*args, **kwargs) > >>>>>>> File > "/opt/v2.82/automation/trex_control_plane/interactive/trex/stl/trex_stl_client.py", > line 339, in reset > >>>>>>> self.clear_stats(ports) > >>>>>>> File > "/opt/v2.82/automation/trex_control_plane/interactive/trex/common/trex_api_annotators.py", > line 51, in wrap2 > >>>>>>> ret = f(*args, **kwargs) > >>>>>>> File > "/opt/v2.82/automation/trex_control_plane/interactive/trex/stl/trex_stl_client.py", > line 1467, in clear_stats > >>>>>>> self._clear_stats_common(ports, clear_global, clear_xstats) > >>>>>>> File > "/opt/v2.82/automation/trex_control_plane/interactive/trex/common/trex_client.py", > line 2840, in _clear_stats_common > >>>>>>> raise TRexError(rc) > >>>>>>> trex.common.trex_exceptions.TRexError: *** [RPC] - Failed to get > server response from tcp://127.0.0.1:4501 > >>>>>> > >>>>>> > >>>>>> I have found one similar case on the github repository for trex, > but the solution was vendor-specific: > https://github.com/cisco-system-traffic-generator/trex-core/issues/147. > >>>>>> Have you ran into this issue before? > >>>>>> > >>>>>> Thanks, > >>>>>> Brandon > >>>> > >>>> > >>>> > >>>> -- > >>>> > >>>> Brandon Lo > >>>> > >>>> UNH InterOperability Laboratory > >>>> > >>>> 21 Madbury Rd, Suite 100, Durham, NH 03824 > >>>> > >>>> blo@iol.unh.edu > >>>> > >>>> www.iol.unh.edu > >>> > >>> > >>> > >>> -- > >>> > >>> Brandon Lo > >>> > >>> UNH InterOperability Laboratory > >>> > >>> 21 Madbury Rd, Suite 100, Durham, NH 03824 > >>> > >>> blo@iol.unh.edu > >>> > >>> www.iol.unh.edu > > > > -- > > Brandon Lo > > UNH InterOperability Laboratory > > 21 Madbury Rd, Suite 100, Durham, NH 03824 > > blo@iol.unh.edu > > www.iol.unh.edu > --0000000000009aa94f05ad558233 Content-Type: text/html; charset="UTF-8" Content-Transfer-Encoding: quoted-printable
Hi Brandon,
I do see some issues while running trex on this setup= .
I will have to dig further. I will let you know once I find something or m= ay be a fix.

Thanks
Ajit

On Thu, Aug 20, 2020 at 8:39 AM Brandon Lo = <blo@iol.unh.edu> wrote:
Hi Ajit,

I believe DTS/TREX is run on the io machine as a tester. Rhea runs
testpmd (through an ssh session from io --> rhea) to catch information as a DUT.

The only commands that I run (on io) are:
cd /opt/dts
export DTS_CFG_FOLDER=3D'conf_100g'
./dts -s

The rest is managed by DTS itself.
The issue occurs when DTS is trying to send packets to rhea from io on
the new 100G NIC.
It seems to happen after it tries to measure throughput using TREX's AP= I.

Thanks,
Brandon

On Thu, Aug 20, 2020 at 12:29 AM Ajit Khaparde
<ajit.kh= aparde@broadcom.com> wrote:
>
> Hi Brandon,
> I was trying to see what exactly is happening on the setup and what is= causing the problem.
> But I will need your help to use the proper code and commands.
>
> I believe you run the testpmd command on io. And the trex is executed = on rhea?
> Can you point me to the location of the code and the steps you are fol= lowing while running the test?
>
> Thanks
> Ajit
>
> On Tue, Aug 11, 2020 at 10:47 AM Ajit Khaparde <ajit.khaparde@broadcom.com= > wrote:
>>
>> Hi Brandon,
>> I haven't. I tried to login as well. But I had some issues doi= ng it from the office.
>> I just have to remind myself to try it again once I get home befor= e I connect to the company VPN.
>> Thanks for checking in. I will try to update you as soon as I can.=
>>
>> Thanks
>> Ajit
>>
>> On Tue, Aug 11, 2020 at 10:46 AM Brandon Lo <blo@iol.unh.edu> wrote:
>>>
>>> Hi Ajit,
>>>
>>> I'm just checking in; have you heard of any updates on thi= s issue?
>>>
>>> Thanks,
>>> Brandon
>>>
>>> On Tue, Aug 4, 2020 at 1:42 PM Brandon Lo <blo@iol.unh.edu> wrote:
>>>>
>>>> Hi Ajit,
>>>>
>>>> Yes, I believe the issue is coming from the trex/tester sy= stem with the 100G NIC.
>>>> I'm not sure what causes this issue; if I run trex usi= ng the command "cd /opt/v2.82;./t-rex-64 -i --cfg /etc/trex_cfg_100g.y= aml -c 7", which is the same command used in DTS, it seems to launch w= ithout failing.
>>>>
>>>> If you want to replicate it, here are the steps that I ran= :
>>>>
>>>> (on io) cd /opt/dts
>>>> export DTS_CFG_FOLDER=3D'conf_100g'
>>>>
>>>> conf_100g has the new configuration files to use the new P= CI id and pktgen config file
>>>>
>>>> ./dts -s
>>>>
>>>>
>>>> Thanks for your help,
>>>> Brandon
>>>>
>>>> On Tue, Aug 4, 2020 at 12:38 PM Ajit Khaparde <ajit.khaparde@broa= dcom.com> wrote:
>>>>>
>>>>> Hi Brandon,
>>>>> No, I haven't seen or heard this before.
>>>>> But I will try to have someone run it again.
>>>>>
>>>>> Just to make sure -
>>>>> You are running trex on the 100G NIC and the problem i= s encountered on that setup?
>>>>> Or is it the system that is running testpmd where you = are running into the issue?
>>>>>
>>>>> Thanks
>>>>> Ajit
>>>>>
>>>>> On Tue, Aug 4, 2020 at 9:16 AM Brandon Lo <blo@iol.unh.edu> wrote= :
>>>>>>
>>>>>> Hi Ajit,
>>>>>>
>>>>>> I'm running into a problem with trying to run = nic_single_core_perf on the new NIC.
>>>>>> The current configuration uses trex version v2.82.=
>>>>>> However, I'm running into an error when it tri= es to actually do a test case in the nic_single_core_perf.
>>>>>>
>>>>>> The output looks like this when it reaches a test = case:
>>>>>>
>>>>>>> TestNicSingleCorePerf: Test running at paramet= ers: framesize: 64, rxd/txd: 512
>>>>>>>=C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2= =A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0dut.rhea: ./x86_64-native-linuxapp-gc= c/app/testpmd -l 16,17 -n 4 -w 0000:81:00.0 -w 0000:81:00.1=C2=A0 --file-pr= efix=3Ddpdk_11307_20200804160513=C2=A0 =C2=A0 -- -i=C2=A0 --portmask=3D0x3 = --txd=3D512 --rxd=3D512
>>>>>>>=C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2= =A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0dut.rhea: start
>>>>>>>=C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 TestNicSingl= eCorePerf: Test Case test_perf_nic_single_core Result ERROR: Traceback (mos= t recent call last):
>>>>>>>=C2=A0 =C2=A0File "/opt/dts/framework/test= _case.py", line 316, in _execute_test_case
>>>>>>>=C2=A0 =C2=A0 =C2=A0case_obj()
>>>>>>>=C2=A0 =C2=A0File "tests/TestSuite_nic_sin= gle_core_perf.py", line 198, in test_perf_nic_single_core
>>>>>>>=C2=A0 =C2=A0 =C2=A0self.perf_test(self.nb_port= s)
>>>>>>>=C2=A0 =C2=A0File "tests/TestSuite_nic_sin= gle_core_perf.py", line 259, in perf_test
>>>>>>>=C2=A0 =C2=A0 =C2=A0_, packets_received =3D sel= f.tester.pktgen.measure_throughput(stream_ids=3Dstreams, options=3Dtraffic_= opt)
>>>>>>>=C2=A0 =C2=A0File "/opt/dts/framework/pktg= en_base.py", line 245, in measure_throughput
>>>>>>>=C2=A0 =C2=A0 =C2=A0self._prepare_transmission(= stream_ids=3Dstream_ids)
>>>>>>>=C2=A0 =C2=A0File "/opt/dts/framework/pktg= en_trex.py", line 779, in _prepare_transmission
>>>>>>>=C2=A0 =C2=A0 =C2=A0self._conn.reset(ports=3Dse= lf._ports)
>>>>>>>=C2=A0 =C2=A0File "/opt/v2.82/automation/t= rex_control_plane/interactive/trex/common/trex_api_annotators.py", lin= e 51, in wrap2
>>>>>>>=C2=A0 =C2=A0 =C2=A0ret =3D f(*args, **kwargs)<= br> >>>>>>>=C2=A0 =C2=A0File "/opt/v2.82/automation/t= rex_control_plane/interactive/trex/stl/trex_stl_client.py", line 339, = in reset
>>>>>>>=C2=A0 =C2=A0 =C2=A0self.clear_stats(ports)
>>>>>>>=C2=A0 =C2=A0File "/opt/v2.82/automation/t= rex_control_plane/interactive/trex/common/trex_api_annotators.py", lin= e 51, in wrap2
>>>>>>>=C2=A0 =C2=A0 =C2=A0ret =3D f(*args, **kwargs)<= br> >>>>>>>=C2=A0 =C2=A0File "/opt/v2.82/automation/t= rex_control_plane/interactive/trex/stl/trex_stl_client.py", line 1467,= in clear_stats
>>>>>>>=C2=A0 =C2=A0 =C2=A0self._clear_stats_common(po= rts, clear_global, clear_xstats)
>>>>>>>=C2=A0 =C2=A0File "/opt/v2.82/automation/t= rex_control_plane/interactive/trex/common/trex_client.py", line 2840, = in _clear_stats_common
>>>>>>>=C2=A0 =C2=A0 =C2=A0raise TRexError(rc)
>>>>>>> trex.common.trex_exceptions.TRexError: *** [RP= C] - Failed to get server response from tcp://127.0.0.1:4501
>>>>>>
>>>>>>
>>>>>> I have found one similar case on the github reposi= tory for trex, but the solution was vendor-specific: https://github.com/cisco-system-traffic-generator/tr= ex-core/issues/147.
>>>>>> Have you ran into this issue before?
>>>>>>
>>>>>> Thanks,
>>>>>> Brandon
>>>>
>>>>
>>>>
>>>> --
>>>>
>>>> Brandon Lo
>>>>
>>>> UNH InterOperability Laboratory
>>>>
>>>> 21 Madbury Rd, Suite 100, Durham, NH 03824
>>>>
>>>> blo@i= ol.unh.edu
>>>>
>>>> www.iol.unh.edu
>>>
>>>
>>>
>>> --
>>>
>>> Brandon Lo
>>>
>>> UNH InterOperability Laboratory
>>>
>>> 21 Madbury Rd, Suite 100, Durham, NH 03824
>>>
>>> blo@iol.u= nh.edu
>>>
>>> www.iol.unh.edu



--

Brandon Lo

UNH InterOperability Laboratory

21 Madbury Rd, Suite 100, Durham, NH 03824

blo@iol.unh.edu
www= .iol.unh.edu
--0000000000009aa94f05ad558233-- From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from dpdk.org (dpdk.org [92.243.14.124]) by inbox.dpdk.org (Postfix) with ESMTP id 015B7A04B1 for ; Tue, 25 Aug 2020 22:13:50 +0200 (CEST) Received: from [92.243.14.124] (localhost [127.0.0.1]) by dpdk.org (Postfix) with ESMTP id C67C7B62; Tue, 25 Aug 2020 22:13:50 +0200 (CEST) Received: from mail-il1-f169.google.com (mail-il1-f169.google.com [209.85.166.169]) by dpdk.org (Postfix) with ESMTP id B8012255 for ; Tue, 25 Aug 2020 22:13:49 +0200 (CEST) Received: by mail-il1-f169.google.com with SMTP id j9so34558ilc.11 for ; Tue, 25 Aug 2020 13:13:49 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=iol.unh.edu; s=unh-iol; h=mime-version:references:in-reply-to:from:date:message-id:subject:to :cc; bh=wffQ0LLFl/sA2VTLqiBj1vg8nYEYj5oN+v0bsolgHus=; b=EXNlBxIL/MWggFAQLksIwsa9KGp+ACtSSD8sWt5sW0klZkTPQWcq5ERkyPvWohTgsq qOSHYLW0vG7QyF+uyOxhjvdhkmex0t2tiakJVDM3Ni4vR8XO8Mq1JJ+tHWZoHGccJ6iF ivzDh/Rm6yKJcejXkBInFF4u6t+zAjAnSVu9s= X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20161025; h=x-gm-message-state:mime-version:references:in-reply-to:from:date :message-id:subject:to:cc; bh=wffQ0LLFl/sA2VTLqiBj1vg8nYEYj5oN+v0bsolgHus=; b=jhH5l3mzMueAli5+LaiPHD0Z5Yy/roI8yyUp8BeWQs4gghsHmnjpoMPqlftn+YWpEC O19P9bX46RQilLJmWq+CYdgFgg/mKo/C72tJNW0dbUqZUPeBTrtONVjGuIU3o8af+Yfd nnCAVNzAHuE/xUffcoegg1B5TCNCDpcf3aF9b0VIe9O3vuOVB5s99xHhNCbeo40FVUzE K9cj3a3biVebweXCuojoyp+fLBpR0mYmiZj+U7D5QU8OIdExuwV79A3iLLgQQCMt2qCL vfb2jIvc2xZVko1ogu+GbWbn5P72bUUkcr5EwXaFJc8DE1NQoK73Zoy1F+PYZ5WaMDuI PSOQ== X-Gm-Message-State: AOAM533UIHlXN06GlGQZXjW6ZWtLxuwbY5K+owANwgLou2An6L0A4gtA UN+kh/mapZ/3rqZKgwiS+Ll8VaiCK5HzO1nSrOxiUQ== X-Google-Smtp-Source: ABdhPJx8WXs3C+Q8DortnKYMWWEYe+bMcjmIyLg3dJTsOWNHssZytd9Js2zT1kvQbTbG7txsp2D7Eo3OuvhvFS5QS5g= X-Received: by 2002:a92:48da:: with SMTP id j87mr8598751ilg.78.1598386428788; Tue, 25 Aug 2020 13:13:48 -0700 (PDT) MIME-Version: 1.0 References: In-Reply-To: From: Brandon Lo Date: Tue, 25 Aug 2020 16:13:14 -0400 Message-ID: To: Ajit Khaparde Cc: ci@dpdk.org, dpdklab Content-Type: text/plain; charset="UTF-8" Subject: Re: [dpdk-ci] New 100G Broadcom NIC Ubuntu X-BeenThere: ci@dpdk.org X-Mailman-Version: 2.1.15 Precedence: list List-Id: DPDK CI discussions List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Errors-To: ci-bounces@dpdk.org Sender: "ci" Hi Ajit, Did you find anything of interest on the machine? I could help out if needed. Thanks, Brandon On Thu, Aug 20, 2020 at 5:07 PM Ajit Khaparde wrote: > > Hi Brandon, > I do see some issues while running trex on this setup. > I will have to dig further. I will let you know once I find something or may be a fix. > > Thanks > Ajit > > On Thu, Aug 20, 2020 at 8:39 AM Brandon Lo wrote: >> >> Hi Ajit, >> >> I believe DTS/TREX is run on the io machine as a tester. Rhea runs >> testpmd (through an ssh session from io --> rhea) to catch information >> as a DUT. >> >> The only commands that I run (on io) are: >> cd /opt/dts >> export DTS_CFG_FOLDER='conf_100g' >> ./dts -s >> >> The rest is managed by DTS itself. >> The issue occurs when DTS is trying to send packets to rhea from io on >> the new 100G NIC. >> It seems to happen after it tries to measure throughput using TREX's API. >> >> Thanks, >> Brandon >> >> On Thu, Aug 20, 2020 at 12:29 AM Ajit Khaparde >> wrote: >> > >> > Hi Brandon, >> > I was trying to see what exactly is happening on the setup and what is causing the problem. >> > But I will need your help to use the proper code and commands. >> > >> > I believe you run the testpmd command on io. And the trex is executed on rhea? >> > Can you point me to the location of the code and the steps you are following while running the test? >> > >> > Thanks >> > Ajit >> > >> > On Tue, Aug 11, 2020 at 10:47 AM Ajit Khaparde wrote: >> >> >> >> Hi Brandon, >> >> I haven't. I tried to login as well. But I had some issues doing it from the office. >> >> I just have to remind myself to try it again once I get home before I connect to the company VPN. >> >> Thanks for checking in. I will try to update you as soon as I can. >> >> >> >> Thanks >> >> Ajit >> >> >> >> On Tue, Aug 11, 2020 at 10:46 AM Brandon Lo wrote: >> >>> >> >>> Hi Ajit, >> >>> >> >>> I'm just checking in; have you heard of any updates on this issue? >> >>> >> >>> Thanks, >> >>> Brandon >> >>> >> >>> On Tue, Aug 4, 2020 at 1:42 PM Brandon Lo wrote: >> >>>> >> >>>> Hi Ajit, >> >>>> >> >>>> Yes, I believe the issue is coming from the trex/tester system with the 100G NIC. >> >>>> I'm not sure what causes this issue; if I run trex using the command "cd /opt/v2.82;./t-rex-64 -i --cfg /etc/trex_cfg_100g.yaml -c 7", which is the same command used in DTS, it seems to launch without failing. >> >>>> >> >>>> If you want to replicate it, here are the steps that I ran: >> >>>> >> >>>> (on io) cd /opt/dts >> >>>> export DTS_CFG_FOLDER='conf_100g' >> >>>> >> >>>> conf_100g has the new configuration files to use the new PCI id and pktgen config file >> >>>> >> >>>> ./dts -s >> >>>> >> >>>> >> >>>> Thanks for your help, >> >>>> Brandon >> >>>> >> >>>> On Tue, Aug 4, 2020 at 12:38 PM Ajit Khaparde wrote: >> >>>>> >> >>>>> Hi Brandon, >> >>>>> No, I haven't seen or heard this before. >> >>>>> But I will try to have someone run it again. >> >>>>> >> >>>>> Just to make sure - >> >>>>> You are running trex on the 100G NIC and the problem is encountered on that setup? >> >>>>> Or is it the system that is running testpmd where you are running into the issue? >> >>>>> >> >>>>> Thanks >> >>>>> Ajit >> >>>>> >> >>>>> On Tue, Aug 4, 2020 at 9:16 AM Brandon Lo wrote: >> >>>>>> >> >>>>>> Hi Ajit, >> >>>>>> >> >>>>>> I'm running into a problem with trying to run nic_single_core_perf on the new NIC. >> >>>>>> The current configuration uses trex version v2.82. >> >>>>>> However, I'm running into an error when it tries to actually do a test case in the nic_single_core_perf. >> >>>>>> >> >>>>>> The output looks like this when it reaches a test case: >> >>>>>> >> >>>>>>> TestNicSingleCorePerf: Test running at parameters: framesize: 64, rxd/txd: 512 >> >>>>>>> dut.rhea: ./x86_64-native-linuxapp-gcc/app/testpmd -l 16,17 -n 4 -w 0000:81:00.0 -w 0000:81:00.1 --file-prefix=dpdk_11307_20200804160513 -- -i --portmask=0x3 --txd=512 --rxd=512 >> >>>>>>> dut.rhea: start >> >>>>>>> TestNicSingleCorePerf: Test Case test_perf_nic_single_core Result ERROR: Traceback (most recent call last): >> >>>>>>> File "/opt/dts/framework/test_case.py", line 316, in _execute_test_case >> >>>>>>> case_obj() >> >>>>>>> File "tests/TestSuite_nic_single_core_perf.py", line 198, in test_perf_nic_single_core >> >>>>>>> self.perf_test(self.nb_ports) >> >>>>>>> File "tests/TestSuite_nic_single_core_perf.py", line 259, in perf_test >> >>>>>>> _, packets_received = self.tester.pktgen.measure_throughput(stream_ids=streams, options=traffic_opt) >> >>>>>>> File "/opt/dts/framework/pktgen_base.py", line 245, in measure_throughput >> >>>>>>> self._prepare_transmission(stream_ids=stream_ids) >> >>>>>>> File "/opt/dts/framework/pktgen_trex.py", line 779, in _prepare_transmission >> >>>>>>> self._conn.reset(ports=self._ports) >> >>>>>>> File "/opt/v2.82/automation/trex_control_plane/interactive/trex/common/trex_api_annotators.py", line 51, in wrap2 >> >>>>>>> ret = f(*args, **kwargs) >> >>>>>>> File "/opt/v2.82/automation/trex_control_plane/interactive/trex/stl/trex_stl_client.py", line 339, in reset >> >>>>>>> self.clear_stats(ports) >> >>>>>>> File "/opt/v2.82/automation/trex_control_plane/interactive/trex/common/trex_api_annotators.py", line 51, in wrap2 >> >>>>>>> ret = f(*args, **kwargs) >> >>>>>>> File "/opt/v2.82/automation/trex_control_plane/interactive/trex/stl/trex_stl_client.py", line 1467, in clear_stats >> >>>>>>> self._clear_stats_common(ports, clear_global, clear_xstats) >> >>>>>>> File "/opt/v2.82/automation/trex_control_plane/interactive/trex/common/trex_client.py", line 2840, in _clear_stats_common >> >>>>>>> raise TRexError(rc) >> >>>>>>> trex.common.trex_exceptions.TRexError: *** [RPC] - Failed to get server response from tcp://127.0.0.1:4501 >> >>>>>> >> >>>>>> >> >>>>>> I have found one similar case on the github repository for trex, but the solution was vendor-specific: https://github.com/cisco-system-traffic-generator/trex-core/issues/147. >> >>>>>> Have you ran into this issue before? >> >>>>>> >> >>>>>> Thanks, >> >>>>>> Brandon >> >>>> >> >>>> >> >>>> >> >>>> -- >> >>>> >> >>>> Brandon Lo >> >>>> >> >>>> UNH InterOperability Laboratory >> >>>> >> >>>> 21 Madbury Rd, Suite 100, Durham, NH 03824 >> >>>> >> >>>> blo@iol.unh.edu >> >>>> >> >>>> www.iol.unh.edu >> >>> >> >>> >> >>> >> >>> -- >> >>> >> >>> Brandon Lo >> >>> >> >>> UNH InterOperability Laboratory >> >>> >> >>> 21 Madbury Rd, Suite 100, Durham, NH 03824 >> >>> >> >>> blo@iol.unh.edu >> >>> >> >>> www.iol.unh.edu >> >> >> >> -- >> >> Brandon Lo >> >> UNH InterOperability Laboratory >> >> 21 Madbury Rd, Suite 100, Durham, NH 03824 >> >> blo@iol.unh.edu >> >> www.iol.unh.edu -- Brandon Lo UNH InterOperability Laboratory 21 Madbury Rd, Suite 100, Durham, NH 03824 blo@iol.unh.edu www.iol.unh.edu From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from dpdk.org (dpdk.org [92.243.14.124]) by inbox.dpdk.org (Postfix) with ESMTP id EC408A04B1 for ; Wed, 26 Aug 2020 21:58:14 +0200 (CEST) Received: from [92.243.14.124] (localhost [127.0.0.1]) by dpdk.org (Postfix) with ESMTP id C16FB1F1C; Wed, 26 Aug 2020 21:58:14 +0200 (CEST) Received: from mail-ot1-f42.google.com (mail-ot1-f42.google.com [209.85.210.42]) by dpdk.org (Postfix) with ESMTP id 46677255 for ; Wed, 26 Aug 2020 21:58:14 +0200 (CEST) Received: by mail-ot1-f42.google.com with SMTP id f42so2517136otf.13 for ; Wed, 26 Aug 2020 12:58:14 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=broadcom.com; s=google; h=mime-version:references:in-reply-to:from:date:message-id:subject:to :cc; bh=W8ajtGlZS4BoRqyAox2nmFu2+fCvEpZRhhIYsvwCnxg=; b=SO9PUmZ6OFjMNnfV2nFlrdkl4ChXuKAFMjjrBh2H3jqT+hEkX6yTAwCMS3LQ58sHz2 TgKtRI6EJFpUlo+LWBicqpewV01Zi2O+lz2Jk4qQpatzZg0wzkkpwxUY2db8k8PUgJVC 7Kr8ZHmUSnV1tQJ+1S5F+3u2Fi+3hsEpVyD1Y= X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20161025; h=x-gm-message-state:mime-version:references:in-reply-to:from:date :message-id:subject:to:cc; bh=W8ajtGlZS4BoRqyAox2nmFu2+fCvEpZRhhIYsvwCnxg=; b=sofrLPD4w+lCtsp3NFbRbZ+1L/c0KwY0IdzfqRI5qXFY1N50yNA0S1XkLAc/7udimM D8Feq+rUKHSEZC77C5btV74W3BTyrrIzrywsDxrsJJiRR/kuCIxP8esse6WhKqrIJG5z lD6EcVy4Xpzu9QggznQvbYcd4U3tlAT4vb7lmevtEpKpbK6GnScEprJKar6b+3oiQ+Fd EKK+hs49P9TvdikNoB4yHMMvjHKTZel2Mxw+KemYTfWd8QNGBLgDVMOsjOJaiim+a6DP m3HV4WwXsVEv9rGiAgijNVwyhdJfklomvQVWValiykHt5AmLQ3Ac1uEXWnf9nsgRlo16 rsKA== X-Gm-Message-State: AOAM531xHq++0HxUqX1KU5LvxPaiCbN0T5Fj80cXylDeSXg5biFXREsD Lu/rj1/5Lyi+3bXLtoCYsejUu69yrYhg8VR3KaKvFw== X-Google-Smtp-Source: ABdhPJys9uqemAnrvt+gSLM87DnS/fKwMct7Cr5i+2yi1SgYZvu2iGC1lNGaG+2/qL/w9G0p5OYIkUsP3xd4HYs1IXU= X-Received: by 2002:a9d:1905:: with SMTP id j5mr8496963ota.283.1598471892388; Wed, 26 Aug 2020 12:58:12 -0700 (PDT) MIME-Version: 1.0 References: In-Reply-To: From: Ajit Khaparde Date: Wed, 26 Aug 2020 12:57:56 -0700 Message-ID: To: Brandon Lo Cc: ci@dpdk.org, dpdklab Content-Type: multipart/alternative; boundary="00000000000054bae805adcd3d31" Subject: Re: [dpdk-ci] New 100G Broadcom NIC Ubuntu X-BeenThere: ci@dpdk.org X-Mailman-Version: 2.1.15 Precedence: list List-Id: DPDK CI discussions List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Errors-To: ci-bounces@dpdk.org Sender: "ci" --00000000000054bae805adcd3d31 Content-Type: text/plain; charset="UTF-8" Not yet Brandon. But I believe I might have to look at what trex is doing to make progress. I will let you know if I need any help. Thanks Ajit On Tue, Aug 25, 2020 at 1:13 PM Brandon Lo wrote: > Hi Ajit, > > Did you find anything of interest on the machine? > I could help out if needed. > > Thanks, > Brandon > > On Thu, Aug 20, 2020 at 5:07 PM Ajit Khaparde > wrote: > > > > Hi Brandon, > > I do see some issues while running trex on this setup. > > I will have to dig further. I will let you know once I find something or > may be a fix. > > > > Thanks > > Ajit > > > > On Thu, Aug 20, 2020 at 8:39 AM Brandon Lo wrote: > >> > >> Hi Ajit, > >> > >> I believe DTS/TREX is run on the io machine as a tester. Rhea runs > >> testpmd (through an ssh session from io --> rhea) to catch information > >> as a DUT. > >> > >> The only commands that I run (on io) are: > >> cd /opt/dts > >> export DTS_CFG_FOLDER='conf_100g' > >> ./dts -s > >> > >> The rest is managed by DTS itself. > >> The issue occurs when DTS is trying to send packets to rhea from io on > >> the new 100G NIC. > >> It seems to happen after it tries to measure throughput using TREX's > API. > >> > >> Thanks, > >> Brandon > >> > >> On Thu, Aug 20, 2020 at 12:29 AM Ajit Khaparde > >> wrote: > >> > > >> > Hi Brandon, > >> > I was trying to see what exactly is happening on the setup and what > is causing the problem. > >> > But I will need your help to use the proper code and commands. > >> > > >> > I believe you run the testpmd command on io. And the trex is executed > on rhea? > >> > Can you point me to the location of the code and the steps you are > following while running the test? > >> > > >> > Thanks > >> > Ajit > >> > > >> > On Tue, Aug 11, 2020 at 10:47 AM Ajit Khaparde < > ajit.khaparde@broadcom.com> wrote: > >> >> > >> >> Hi Brandon, > >> >> I haven't. I tried to login as well. But I had some issues doing it > from the office. > >> >> I just have to remind myself to try it again once I get home before > I connect to the company VPN. > >> >> Thanks for checking in. I will try to update you as soon as I can. > >> >> > >> >> Thanks > >> >> Ajit > >> >> > >> >> On Tue, Aug 11, 2020 at 10:46 AM Brandon Lo wrote: > >> >>> > >> >>> Hi Ajit, > >> >>> > >> >>> I'm just checking in; have you heard of any updates on this issue? > >> >>> > >> >>> Thanks, > >> >>> Brandon > >> >>> > >> >>> On Tue, Aug 4, 2020 at 1:42 PM Brandon Lo wrote: > >> >>>> > >> >>>> Hi Ajit, > >> >>>> > >> >>>> Yes, I believe the issue is coming from the trex/tester system > with the 100G NIC. > >> >>>> I'm not sure what causes this issue; if I run trex using the > command "cd /opt/v2.82;./t-rex-64 -i --cfg /etc/trex_cfg_100g.yaml -c 7", > which is the same command used in DTS, it seems to launch without failing. > >> >>>> > >> >>>> If you want to replicate it, here are the steps that I ran: > >> >>>> > >> >>>> (on io) cd /opt/dts > >> >>>> export DTS_CFG_FOLDER='conf_100g' > >> >>>> > >> >>>> conf_100g has the new configuration files to use the new PCI id > and pktgen config file > >> >>>> > >> >>>> ./dts -s > >> >>>> > >> >>>> > >> >>>> Thanks for your help, > >> >>>> Brandon > >> >>>> > >> >>>> On Tue, Aug 4, 2020 at 12:38 PM Ajit Khaparde < > ajit.khaparde@broadcom.com> wrote: > >> >>>>> > >> >>>>> Hi Brandon, > >> >>>>> No, I haven't seen or heard this before. > >> >>>>> But I will try to have someone run it again. > >> >>>>> > >> >>>>> Just to make sure - > >> >>>>> You are running trex on the 100G NIC and the problem is > encountered on that setup? > >> >>>>> Or is it the system that is running testpmd where you are running > into the issue? > >> >>>>> > >> >>>>> Thanks > >> >>>>> Ajit > >> >>>>> > >> >>>>> On Tue, Aug 4, 2020 at 9:16 AM Brandon Lo > wrote: > >> >>>>>> > >> >>>>>> Hi Ajit, > >> >>>>>> > >> >>>>>> I'm running into a problem with trying to run > nic_single_core_perf on the new NIC. > >> >>>>>> The current configuration uses trex version v2.82. > >> >>>>>> However, I'm running into an error when it tries to actually do > a test case in the nic_single_core_perf. > >> >>>>>> > >> >>>>>> The output looks like this when it reaches a test case: > >> >>>>>> > >> >>>>>>> TestNicSingleCorePerf: Test running at parameters: framesize: > 64, rxd/txd: 512 > >> >>>>>>> dut.rhea: > ./x86_64-native-linuxapp-gcc/app/testpmd -l 16,17 -n 4 -w 0000:81:00.0 -w > 0000:81:00.1 --file-prefix=dpdk_11307_20200804160513 -- -i > --portmask=0x3 --txd=512 --rxd=512 > >> >>>>>>> dut.rhea: start > >> >>>>>>> TestNicSingleCorePerf: Test Case > test_perf_nic_single_core Result ERROR: Traceback (most recent call last): > >> >>>>>>> File "/opt/dts/framework/test_case.py", line 316, in > _execute_test_case > >> >>>>>>> case_obj() > >> >>>>>>> File "tests/TestSuite_nic_single_core_perf.py", line 198, in > test_perf_nic_single_core > >> >>>>>>> self.perf_test(self.nb_ports) > >> >>>>>>> File "tests/TestSuite_nic_single_core_perf.py", line 259, in > perf_test > >> >>>>>>> _, packets_received = > self.tester.pktgen.measure_throughput(stream_ids=streams, > options=traffic_opt) > >> >>>>>>> File "/opt/dts/framework/pktgen_base.py", line 245, in > measure_throughput > >> >>>>>>> self._prepare_transmission(stream_ids=stream_ids) > >> >>>>>>> File "/opt/dts/framework/pktgen_trex.py", line 779, in > _prepare_transmission > >> >>>>>>> self._conn.reset(ports=self._ports) > >> >>>>>>> File > "/opt/v2.82/automation/trex_control_plane/interactive/trex/common/trex_api_annotators.py", > line 51, in wrap2 > >> >>>>>>> ret = f(*args, **kwargs) > >> >>>>>>> File > "/opt/v2.82/automation/trex_control_plane/interactive/trex/stl/trex_stl_client.py", > line 339, in reset > >> >>>>>>> self.clear_stats(ports) > >> >>>>>>> File > "/opt/v2.82/automation/trex_control_plane/interactive/trex/common/trex_api_annotators.py", > line 51, in wrap2 > >> >>>>>>> ret = f(*args, **kwargs) > >> >>>>>>> File > "/opt/v2.82/automation/trex_control_plane/interactive/trex/stl/trex_stl_client.py", > line 1467, in clear_stats > >> >>>>>>> self._clear_stats_common(ports, clear_global, clear_xstats) > >> >>>>>>> File > "/opt/v2.82/automation/trex_control_plane/interactive/trex/common/trex_client.py", > line 2840, in _clear_stats_common > >> >>>>>>> raise TRexError(rc) > >> >>>>>>> trex.common.trex_exceptions.TRexError: *** [RPC] - Failed to > get server response from tcp://127.0.0.1:4501 > >> >>>>>> > >> >>>>>> > >> >>>>>> I have found one similar case on the github repository for trex, > but the solution was vendor-specific: > https://github.com/cisco-system-traffic-generator/trex-core/issues/147. > >> >>>>>> Have you ran into this issue before? > >> >>>>>> > >> >>>>>> Thanks, > >> >>>>>> Brandon > >> >>>> > >> >>>> > >> >>>> > >> >>>> -- > >> >>>> > >> >>>> Brandon Lo > >> >>>> > >> >>>> UNH InterOperability Laboratory > >> >>>> > >> >>>> 21 Madbury Rd, Suite 100, Durham, NH 03824 > >> >>>> > >> >>>> blo@iol.unh.edu > >> >>>> > >> >>>> www.iol.unh.edu > >> >>> > >> >>> > >> >>> > >> >>> -- > >> >>> > >> >>> Brandon Lo > >> >>> > >> >>> UNH InterOperability Laboratory > >> >>> > >> >>> 21 Madbury Rd, Suite 100, Durham, NH 03824 > >> >>> > >> >>> blo@iol.unh.edu > >> >>> > >> >>> www.iol.unh.edu > >> > >> > >> > >> -- > >> > >> Brandon Lo > >> > >> UNH InterOperability Laboratory > >> > >> 21 Madbury Rd, Suite 100, Durham, NH 03824 > >> > >> blo@iol.unh.edu > >> > >> www.iol.unh.edu > > > > -- > > Brandon Lo > > UNH InterOperability Laboratory > > 21 Madbury Rd, Suite 100, Durham, NH 03824 > > blo@iol.unh.edu > > www.iol.unh.edu > --00000000000054bae805adcd3d31 Content-Type: text/html; charset="UTF-8" Content-Transfer-Encoding: quoted-printable
Not yet Brandon.
But I believe I might have to look at what trex = is doing to make progress.
I will let you know if I need any help.

=
Thanks=
= Ajit

On Tue, Aug 25, 2020 at 1:13 PM Brandon Lo <blo@iol.unh.edu> wrote:
Hi Ajit,

Did you find anything of interest on the machine?
I could help out if needed.

Thanks,
Brandon

On Thu, Aug 20, 2020 at 5:07 PM Ajit Khaparde
<ajit.kh= aparde@broadcom.com> wrote:
>
> Hi Brandon,
> I do see some issues while running trex on this setup.
> I will have to dig further. I will let you know once I find something = or may be a fix.
>
> Thanks
> Ajit
>
> On Thu, Aug 20, 2020 at 8:39 AM Brandon Lo <blo@iol.unh.edu> wrote:
>>
>> Hi Ajit,
>>
>> I believe DTS/TREX is run on the io machine as a tester. Rhea runs=
>> testpmd (through an ssh session from io --> rhea) to catch info= rmation
>> as a DUT.
>>
>> The only commands that I run (on io) are:
>> cd /opt/dts
>> export DTS_CFG_FOLDER=3D'conf_100g'
>> ./dts -s
>>
>> The rest is managed by DTS itself.
>> The issue occurs when DTS is trying to send packets to rhea from i= o on
>> the new 100G NIC.
>> It seems to happen after it tries to measure throughput using TREX= 's API.
>>
>> Thanks,
>> Brandon
>>
>> On Thu, Aug 20, 2020 at 12:29 AM Ajit Khaparde
>> <ajit.khaparde@broadcom.com> wrote:
>> >
>> > Hi Brandon,
>> > I was trying to see what exactly is happening on the setup an= d what is causing the problem.
>> > But I will need your help to use the proper code and commands= .
>> >
>> > I believe you run the testpmd command on io. And the trex is = executed on rhea?
>> > Can you point me to the location of the code and the steps yo= u are following while running the test?
>> >
>> > Thanks
>> > Ajit
>> >
>> > On Tue, Aug 11, 2020 at 10:47 AM Ajit Khaparde <ajit.khaparde@broadco= m.com> wrote:
>> >>
>> >> Hi Brandon,
>> >> I haven't. I tried to login as well. But I had some i= ssues doing it from the office.
>> >> I just have to remind myself to try it again once I get h= ome before I connect to the company VPN.
>> >> Thanks for checking in. I will try to update you as soon = as I can.
>> >>
>> >> Thanks
>> >> Ajit
>> >>
>> >> On Tue, Aug 11, 2020 at 10:46 AM Brandon Lo <blo@iol.unh.edu> wrote= :
>> >>>
>> >>> Hi Ajit,
>> >>>
>> >>> I'm just checking in; have you heard of any updat= es on this issue?
>> >>>
>> >>> Thanks,
>> >>> Brandon
>> >>>
>> >>> On Tue, Aug 4, 2020 at 1:42 PM Brandon Lo <blo@iol.unh.edu> wrote= :
>> >>>>
>> >>>> Hi Ajit,
>> >>>>
>> >>>> Yes, I believe the issue is coming from the trex/= tester system with the 100G NIC.
>> >>>> I'm not sure what causes this issue; if I run= trex using the command "cd /opt/v2.82;./t-rex-64 -i --cfg /etc/trex_c= fg_100g.yaml -c 7", which is the same command used in DTS, it seems to= launch without failing.
>> >>>>
>> >>>> If you want to replicate it, here are the steps t= hat I ran:
>> >>>>
>> >>>> (on io) cd /opt/dts
>> >>>> export DTS_CFG_FOLDER=3D'conf_100g'
>> >>>>
>> >>>> conf_100g has the new configuration files to use = the new PCI id and pktgen config file
>> >>>>
>> >>>> ./dts -s
>> >>>>
>> >>>>
>> >>>> Thanks for your help,
>> >>>> Brandon
>> >>>>
>> >>>> On Tue, Aug 4, 2020 at 12:38 PM Ajit Khaparde <= ;ajit.khapa= rde@broadcom.com> wrote:
>> >>>>>
>> >>>>> Hi Brandon,
>> >>>>> No, I haven't seen or heard this before.<= br> >> >>>>> But I will try to have someone run it again.<= br> >> >>>>>
>> >>>>> Just to make sure -
>> >>>>> You are running trex on the 100G NIC and the = problem is encountered on that setup?
>> >>>>> Or is it the system that is running testpmd w= here you are running into the issue?
>> >>>>>
>> >>>>> Thanks
>> >>>>> Ajit
>> >>>>>
>> >>>>> On Tue, Aug 4, 2020 at 9:16 AM Brandon Lo <= ;blo@iol.unh.edu&g= t; wrote:
>> >>>>>>
>> >>>>>> Hi Ajit,
>> >>>>>>
>> >>>>>> I'm running into a problem with tryin= g to run nic_single_core_perf on the new NIC.
>> >>>>>> The current configuration uses trex versi= on v2.82.
>> >>>>>> However, I'm running into an error wh= en it tries to actually do a test case in the nic_single_core_perf.
>> >>>>>>
>> >>>>>> The output looks like this when it reache= s a test case:
>> >>>>>>
>> >>>>>>> TestNicSingleCorePerf: Test running a= t parameters: framesize: 64, rxd/txd: 512
>> >>>>>>>=C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2= =A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0dut.rhea: ./x86_64-native-linu= xapp-gcc/app/testpmd -l 16,17 -n 4 -w 0000:81:00.0 -w 0000:81:00.1=C2=A0 --= file-prefix=3Ddpdk_11307_20200804160513=C2=A0 =C2=A0 -- -i=C2=A0 --portmask= =3D0x3 --txd=3D512 --rxd=3D512
>> >>>>>>>=C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2= =A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0dut.rhea: start
>> >>>>>>>=C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 Tes= tNicSingleCorePerf: Test Case test_perf_nic_single_core Result ERROR: Trace= back (most recent call last):
>> >>>>>>>=C2=A0 =C2=A0File "/opt/dts/frame= work/test_case.py", line 316, in _execute_test_case
>> >>>>>>>=C2=A0 =C2=A0 =C2=A0case_obj()
>> >>>>>>>=C2=A0 =C2=A0File "tests/TestSuit= e_nic_single_core_perf.py", line 198, in test_perf_nic_single_core
>> >>>>>>>=C2=A0 =C2=A0 =C2=A0self.perf_test(sel= f.nb_ports)
>> >>>>>>>=C2=A0 =C2=A0File "tests/TestSuit= e_nic_single_core_perf.py", line 259, in perf_test
>> >>>>>>>=C2=A0 =C2=A0 =C2=A0_, packets_receive= d =3D self.tester.pktgen.measure_throughput(stream_ids=3Dstreams, options= =3Dtraffic_opt)
>> >>>>>>>=C2=A0 =C2=A0File "/opt/dts/frame= work/pktgen_base.py", line 245, in measure_throughput
>> >>>>>>>=C2=A0 =C2=A0 =C2=A0self._prepare_tran= smission(stream_ids=3Dstream_ids)
>> >>>>>>>=C2=A0 =C2=A0File "/opt/dts/frame= work/pktgen_trex.py", line 779, in _prepare_transmission
>> >>>>>>>=C2=A0 =C2=A0 =C2=A0self._conn.reset(p= orts=3Dself._ports)
>> >>>>>>>=C2=A0 =C2=A0File "/opt/v2.82/aut= omation/trex_control_plane/interactive/trex/common/trex_api_annotators.py&q= uot;, line 51, in wrap2
>> >>>>>>>=C2=A0 =C2=A0 =C2=A0ret =3D f(*args, *= *kwargs)
>> >>>>>>>=C2=A0 =C2=A0File "/opt/v2.82/aut= omation/trex_control_plane/interactive/trex/stl/trex_stl_client.py", l= ine 339, in reset
>> >>>>>>>=C2=A0 =C2=A0 =C2=A0self.clear_stats(p= orts)
>> >>>>>>>=C2=A0 =C2=A0File "/opt/v2.82/aut= omation/trex_control_plane/interactive/trex/common/trex_api_annotators.py&q= uot;, line 51, in wrap2
>> >>>>>>>=C2=A0 =C2=A0 =C2=A0ret =3D f(*args, *= *kwargs)
>> >>>>>>>=C2=A0 =C2=A0File "/opt/v2.82/aut= omation/trex_control_plane/interactive/trex/stl/trex_stl_client.py", l= ine 1467, in clear_stats
>> >>>>>>>=C2=A0 =C2=A0 =C2=A0self._clear_stats_= common(ports, clear_global, clear_xstats)
>> >>>>>>>=C2=A0 =C2=A0File "/opt/v2.82/aut= omation/trex_control_plane/interactive/trex/common/trex_client.py", li= ne 2840, in _clear_stats_common
>> >>>>>>>=C2=A0 =C2=A0 =C2=A0raise TRexError(rc= )
>> >>>>>>> trex.common.trex_exceptions.TRexError= : *** [RPC] - Failed to get server response from tcp://127.0.0.1:4501
>> >>>>>>
>> >>>>>>
>> >>>>>> I have found one similar case on the gith= ub repository for trex, but the solution was vendor-specific: https://github.com/cisco-system-traffic-g= enerator/trex-core/issues/147.
>> >>>>>> Have you ran into this issue before?
>> >>>>>>
>> >>>>>> Thanks,
>> >>>>>> Brandon
>> >>>>
>> >>>>
>> >>>>
>> >>>> --
>> >>>>
>> >>>> Brandon Lo
>> >>>>
>> >>>> UNH InterOperability Laboratory
>> >>>>
>> >>>> 21 Madbury Rd, Suite 100, Durham, NH 03824
>> >>>>
>> >>>> blo@iol.unh.edu
>> >>>>
>> >>>> www.iol.unh.edu
>> >>>
>> >>>
>> >>>
>> >>> --
>> >>>
>> >>> Brandon Lo
>> >>>
>> >>> UNH InterOperability Laboratory
>> >>>
>> >>> 21 Madbury Rd, Suite 100, Durham, NH 03824
>> >>>
>> >>> = blo@iol.unh.edu
>> >>>
>> >>> www.iol.unh.edu
>>
>>
>>
>> --
>>
>> Brandon Lo
>>
>> UNH InterOperability Laboratory
>>
>> 21 Madbury Rd, Suite 100, Durham, NH 03824
>>
>> blo@iol.unh.e= du
>>
>> www.iol.unh.edu



--

Brandon Lo

UNH InterOperability Laboratory

21 Madbury Rd, Suite 100, Durham, NH 03824

blo@iol.unh.edu
www= .iol.unh.edu
--00000000000054bae805adcd3d31-- From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from dpdk.org (dpdk.org [92.243.14.124]) by inbox.dpdk.org (Postfix) with ESMTP id BED68A04AC for ; Tue, 1 Sep 2020 20:09:58 +0200 (CEST) Received: from [92.243.14.124] (localhost [127.0.0.1]) by dpdk.org (Postfix) with ESMTP id 93ADA1C0B1; Tue, 1 Sep 2020 20:09:58 +0200 (CEST) Received: from mail-io1-f45.google.com (mail-io1-f45.google.com [209.85.166.45]) by dpdk.org (Postfix) with ESMTP id E17D21C0AF for ; Tue, 1 Sep 2020 20:09:57 +0200 (CEST) Received: by mail-io1-f45.google.com with SMTP id b6so1817350iof.6 for ; Tue, 01 Sep 2020 11:09:57 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=iol.unh.edu; s=unh-iol; h=mime-version:references:in-reply-to:from:date:message-id:subject:to :cc; bh=CHRNG8K9rQbast0/0qF/wS1eZokx/vWC8rOYvUroar0=; b=bHKIsUoMzyE339vSXlaEdYkT1fvb7q1xNyJAI+ZUq46gZRL0rr40S8pBncK2elKuiQ SffCfGT6etm8t6tG+ODlTVN0wkVpaOGmA2WKukXdSNxLPbgyMbzJmQzpXX3VtF5+F3w7 ae0TeeOApjmKFpQy/SzQ73aWMRmopUo/lAxXM= X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20161025; h=x-gm-message-state:mime-version:references:in-reply-to:from:date :message-id:subject:to:cc; bh=CHRNG8K9rQbast0/0qF/wS1eZokx/vWC8rOYvUroar0=; b=rlBiC7lfzUOhfg6+QWo9/TSpwNjqIaqjdzBsaY8P0XCR9mh7aHu00loNg2Uf2cZjmw wwZfGy5lF6f2QGeQo5lwmbwVi2zJ+gmA0PrRTvGjVX4EnahW1bRHoQtsqv7oLKAh/G9H 4MLV5rqKWxdlGjIrRFXPMHDZ9to0MC8D4H3eeL5NpvWTPYInuVaybWHlv2e2FSnhSX87 mXxu1xh698ODyNdfoYiuBpdK0oFd/aOwVf8YFREjGwVit6z6dvkVS7z3lMbYqTWH+BcI DY2RLd6u1+UMydidI/HIRIwlpnneFOTk1iQf5n6wqBRRVc15pVjRt2vN6lTGDd7Du/FO Yz8A== X-Gm-Message-State: AOAM530O0o+YwHJ+F4dYYU8QJdCLXA+HZEsygrzEvx1HoJnJQU1V/KuK kLOZxQUDNVDN2MM7RTbXbenGNrCG2hWmsQdllNUfDw== X-Google-Smtp-Source: ABdhPJxtow2x6x7LR6TIBQZ0jDfE8w26MoK+Hrs2+YO36cKN989/rdd8LSr3xV7ZaNt2GnNUoSVpsAq5Sam6zREE45A= X-Received: by 2002:a5d:888b:: with SMTP id d11mr253019ioo.188.1598983796946; Tue, 01 Sep 2020 11:09:56 -0700 (PDT) MIME-Version: 1.0 References: In-Reply-To: From: Brandon Lo Date: Tue, 1 Sep 2020 14:09:21 -0400 Message-ID: To: Ajit Khaparde Cc: ci@dpdk.org, dpdklab Content-Type: text/plain; charset="UTF-8" Subject: Re: [dpdk-ci] New 100G Broadcom NIC Ubuntu X-BeenThere: ci@dpdk.org X-Mailman-Version: 2.1.15 Precedence: list List-Id: DPDK CI discussions List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Errors-To: ci-bounces@dpdk.org Sender: "ci" Hi Ajit, I'm going to re-enable the Broadcom 25G NIC in production performance and functional testing. If you would like to do testing/debugging on the machine, such as on the 100G NIC, then please disable these two pipelines on our Jenkins: https://dpdklab.iol.unh.edu/jenkins/job/Broadcom-25G-Functional-Test-Pipeline/ https://dpdklab.iol.unh.edu/jenkins/job/Broadcom-25G-Performance-Test-Pipeline/ You will need to sign in using the same credentials as your VPN. This will prevent any overlapping of DTS/TREX runs which is known to cause errors. Please let me know if you run into any issues. Thanks, Brandon On Wed, Aug 26, 2020 at 3:58 PM Ajit Khaparde wrote: > > Not yet Brandon. > But I believe I might have to look at what trex is doing to make progress. > I will let you know if I need any help. > > Thanks > Ajit > > On Tue, Aug 25, 2020 at 1:13 PM Brandon Lo wrote: >> >> Hi Ajit, >> >> Did you find anything of interest on the machine? >> I could help out if needed. >> >> Thanks, >> Brandon >> >> On Thu, Aug 20, 2020 at 5:07 PM Ajit Khaparde >> wrote: >> > >> > Hi Brandon, >> > I do see some issues while running trex on this setup. >> > I will have to dig further. I will let you know once I find something or may be a fix. >> > >> > Thanks >> > Ajit >> > >> > On Thu, Aug 20, 2020 at 8:39 AM Brandon Lo wrote: >> >> >> >> Hi Ajit, >> >> >> >> I believe DTS/TREX is run on the io machine as a tester. Rhea runs >> >> testpmd (through an ssh session from io --> rhea) to catch information >> >> as a DUT. >> >> >> >> The only commands that I run (on io) are: >> >> cd /opt/dts >> >> export DTS_CFG_FOLDER='conf_100g' >> >> ./dts -s >> >> >> >> The rest is managed by DTS itself. >> >> The issue occurs when DTS is trying to send packets to rhea from io on >> >> the new 100G NIC. >> >> It seems to happen after it tries to measure throughput using TREX's API. >> >> >> >> Thanks, >> >> Brandon >> >> >> >> On Thu, Aug 20, 2020 at 12:29 AM Ajit Khaparde >> >> wrote: >> >> > >> >> > Hi Brandon, >> >> > I was trying to see what exactly is happening on the setup and what is causing the problem. >> >> > But I will need your help to use the proper code and commands. >> >> > >> >> > I believe you run the testpmd command on io. And the trex is executed on rhea? >> >> > Can you point me to the location of the code and the steps you are following while running the test? >> >> > >> >> > Thanks >> >> > Ajit >> >> > >> >> > On Tue, Aug 11, 2020 at 10:47 AM Ajit Khaparde wrote: >> >> >> >> >> >> Hi Brandon, >> >> >> I haven't. I tried to login as well. But I had some issues doing it from the office. >> >> >> I just have to remind myself to try it again once I get home before I connect to the company VPN. >> >> >> Thanks for checking in. I will try to update you as soon as I can. >> >> >> >> >> >> Thanks >> >> >> Ajit >> >> >> >> >> >> On Tue, Aug 11, 2020 at 10:46 AM Brandon Lo wrote: >> >> >>> >> >> >>> Hi Ajit, >> >> >>> >> >> >>> I'm just checking in; have you heard of any updates on this issue? >> >> >>> >> >> >>> Thanks, >> >> >>> Brandon >> >> >>> >> >> >>> On Tue, Aug 4, 2020 at 1:42 PM Brandon Lo wrote: >> >> >>>> >> >> >>>> Hi Ajit, >> >> >>>> >> >> >>>> Yes, I believe the issue is coming from the trex/tester system with the 100G NIC. >> >> >>>> I'm not sure what causes this issue; if I run trex using the command "cd /opt/v2.82;./t-rex-64 -i --cfg /etc/trex_cfg_100g.yaml -c 7", which is the same command used in DTS, it seems to launch without failing. >> >> >>>> >> >> >>>> If you want to replicate it, here are the steps that I ran: >> >> >>>> >> >> >>>> (on io) cd /opt/dts >> >> >>>> export DTS_CFG_FOLDER='conf_100g' >> >> >>>> >> >> >>>> conf_100g has the new configuration files to use the new PCI id and pktgen config file >> >> >>>> >> >> >>>> ./dts -s >> >> >>>> >> >> >>>> >> >> >>>> Thanks for your help, >> >> >>>> Brandon >> >> >>>> >> >> >>>> On Tue, Aug 4, 2020 at 12:38 PM Ajit Khaparde wrote: >> >> >>>>> >> >> >>>>> Hi Brandon, >> >> >>>>> No, I haven't seen or heard this before. >> >> >>>>> But I will try to have someone run it again. >> >> >>>>> >> >> >>>>> Just to make sure - >> >> >>>>> You are running trex on the 100G NIC and the problem is encountered on that setup? >> >> >>>>> Or is it the system that is running testpmd where you are running into the issue? >> >> >>>>> >> >> >>>>> Thanks >> >> >>>>> Ajit >> >> >>>>> >> >> >>>>> On Tue, Aug 4, 2020 at 9:16 AM Brandon Lo wrote: >> >> >>>>>> >> >> >>>>>> Hi Ajit, >> >> >>>>>> >> >> >>>>>> I'm running into a problem with trying to run nic_single_core_perf on the new NIC. >> >> >>>>>> The current configuration uses trex version v2.82. >> >> >>>>>> However, I'm running into an error when it tries to actually do a test case in the nic_single_core_perf. >> >> >>>>>> >> >> >>>>>> The output looks like this when it reaches a test case: >> >> >>>>>> >> >> >>>>>>> TestNicSingleCorePerf: Test running at parameters: framesize: 64, rxd/txd: 512 >> >> >>>>>>> dut.rhea: ./x86_64-native-linuxapp-gcc/app/testpmd -l 16,17 -n 4 -w 0000:81:00.0 -w 0000:81:00.1 --file-prefix=dpdk_11307_20200804160513 -- -i --portmask=0x3 --txd=512 --rxd=512 >> >> >>>>>>> dut.rhea: start >> >> >>>>>>> TestNicSingleCorePerf: Test Case test_perf_nic_single_core Result ERROR: Traceback (most recent call last): >> >> >>>>>>> File "/opt/dts/framework/test_case.py", line 316, in _execute_test_case >> >> >>>>>>> case_obj() >> >> >>>>>>> File "tests/TestSuite_nic_single_core_perf.py", line 198, in test_perf_nic_single_core >> >> >>>>>>> self.perf_test(self.nb_ports) >> >> >>>>>>> File "tests/TestSuite_nic_single_core_perf.py", line 259, in perf_test >> >> >>>>>>> _, packets_received = self.tester.pktgen.measure_throughput(stream_ids=streams, options=traffic_opt) >> >> >>>>>>> File "/opt/dts/framework/pktgen_base.py", line 245, in measure_throughput >> >> >>>>>>> self._prepare_transmission(stream_ids=stream_ids) >> >> >>>>>>> File "/opt/dts/framework/pktgen_trex.py", line 779, in _prepare_transmission >> >> >>>>>>> self._conn.reset(ports=self._ports) >> >> >>>>>>> File "/opt/v2.82/automation/trex_control_plane/interactive/trex/common/trex_api_annotators.py", line 51, in wrap2 >> >> >>>>>>> ret = f(*args, **kwargs) >> >> >>>>>>> File "/opt/v2.82/automation/trex_control_plane/interactive/trex/stl/trex_stl_client.py", line 339, in reset >> >> >>>>>>> self.clear_stats(ports) >> >> >>>>>>> File "/opt/v2.82/automation/trex_control_plane/interactive/trex/common/trex_api_annotators.py", line 51, in wrap2 >> >> >>>>>>> ret = f(*args, **kwargs) >> >> >>>>>>> File "/opt/v2.82/automation/trex_control_plane/interactive/trex/stl/trex_stl_client.py", line 1467, in clear_stats >> >> >>>>>>> self._clear_stats_common(ports, clear_global, clear_xstats) >> >> >>>>>>> File "/opt/v2.82/automation/trex_control_plane/interactive/trex/common/trex_client.py", line 2840, in _clear_stats_common >> >> >>>>>>> raise TRexError(rc) >> >> >>>>>>> trex.common.trex_exceptions.TRexError: *** [RPC] - Failed to get server response from tcp://127.0.0.1:4501 >> >> >>>>>> >> >> >>>>>> >> >> >>>>>> I have found one similar case on the github repository for trex, but the solution was vendor-specific: https://github.com/cisco-system-traffic-generator/trex-core/issues/147. >> >> >>>>>> Have you ran into this issue before? >> >> >>>>>> >> >> >>>>>> Thanks, >> >> >>>>>> Brandon >> >> >>>> >> >> >>>> >> >> >>>> >> >> >>>> -- >> >> >>>> >> >> >>>> Brandon Lo >> >> >>>> >> >> >>>> UNH InterOperability Laboratory >> >> >>>> >> >> >>>> 21 Madbury Rd, Suite 100, Durham, NH 03824 >> >> >>>> >> >> >>>> blo@iol.unh.edu >> >> >>>> >> >> >>>> www.iol.unh.edu >> >> >>> >> >> >>> >> >> >>> >> >> >>> -- >> >> >>> >> >> >>> Brandon Lo >> >> >>> >> >> >>> UNH InterOperability Laboratory >> >> >>> >> >> >>> 21 Madbury Rd, Suite 100, Durham, NH 03824 >> >> >>> >> >> >>> blo@iol.unh.edu >> >> >>> >> >> >>> www.iol.unh.edu >> >> >> >> >> >> >> >> -- >> >> >> >> Brandon Lo >> >> >> >> UNH InterOperability Laboratory >> >> >> >> 21 Madbury Rd, Suite 100, Durham, NH 03824 >> >> >> >> blo@iol.unh.edu >> >> >> >> www.iol.unh.edu >> >> >> >> -- >> >> Brandon Lo >> >> UNH InterOperability Laboratory >> >> 21 Madbury Rd, Suite 100, Durham, NH 03824 >> >> blo@iol.unh.edu >> >> www.iol.unh.edu -- Brandon Lo UNH InterOperability Laboratory 21 Madbury Rd, Suite 100, Durham, NH 03824 blo@iol.unh.edu www.iol.unh.edu From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from dpdk.org (dpdk.org [92.243.14.124]) by inbox.dpdk.org (Postfix) with ESMTP id 36607A04AC for ; Tue, 1 Sep 2020 20:12:14 +0200 (CEST) Received: from [92.243.14.124] (localhost [127.0.0.1]) by dpdk.org (Postfix) with ESMTP id 07AC61C0B1; Tue, 1 Sep 2020 20:12:14 +0200 (CEST) Received: from mail-ot1-f45.google.com (mail-ot1-f45.google.com [209.85.210.45]) by dpdk.org (Postfix) with ESMTP id 9B1BA1C0B0 for ; Tue, 1 Sep 2020 20:12:12 +0200 (CEST) Received: by mail-ot1-f45.google.com with SMTP id 37so1988857oto.4 for ; Tue, 01 Sep 2020 11:12:12 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=broadcom.com; s=google; h=mime-version:references:in-reply-to:from:date:message-id:subject:to :cc; bh=8WlDhOxtu0hyezP2YOdAgh0ZIbIaw+kg9MCw2Rr20Ww=; b=VObKs+b3AXQoHxSC5dzFVuTSGB7SpCrcqXmxGAdK1auPOlvPE6QMSzJgxQ3qz33WO6 ME6/uvZcSXHzGdI1R6CPH0FxX7Is58Pl+AENN5pRtVsRNvH5RvVXacZw7Eet8HVlOm+S MpYrfC33/HwusmbeJhkAh1MEkfaqbOH5Wo/Ws= X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20161025; h=x-gm-message-state:mime-version:references:in-reply-to:from:date :message-id:subject:to:cc; bh=8WlDhOxtu0hyezP2YOdAgh0ZIbIaw+kg9MCw2Rr20Ww=; b=YwathX1rBfKgsb/pxINmsn1FNxhx8BGAsyKP6NekXEmRQTzfxyS16uQrlrmdm6f5Tz Y+VuTTxzm7pDdXdCFOCmJ2SQ1rqOkzAAOjyUkjLPPWkrYqv1OBYR6/HBEwcPxjgClZkr 0+/ZY4Z5SRCm13AqpkwzzmUnnMPg+Yzrmu/oQq5UhYVIMBcFupipwS+ylyZ2jXWyxXoW Cp1ePVIvsXVI2M9iRl/1UXdbS56fWaTbGRnQx2Kpxiqv3KsxwO9nKtrDhsuP5QdDnZZp vqvcSmruPhQGb7gxvpHpCOBHbto7Czfb/Aco4LptUKGycyQ5IRy9na9w+DYlwbm6P/Eq HYuw== X-Gm-Message-State: AOAM531HnXRCCL0EDagKH5Sv6BYBU+8faNqaXUXR25Hk4FTkqPkad7ZC tzL7a0bsiZZVf5BYLeKiw4FurtidgeIrsOztSrVDXg== X-Google-Smtp-Source: ABdhPJxjH6uOmB72/cdxUis+rFnvRDQbMY8wvQF7JuiwHeeXptzijs3HE1Si0i25XKFNbGY3vrRr9jmxMdc5q5jAhGE= X-Received: by 2002:a9d:ae7:: with SMTP id 94mr2433904otq.283.1598983931748; Tue, 01 Sep 2020 11:12:11 -0700 (PDT) MIME-Version: 1.0 References: In-Reply-To: From: Ajit Khaparde Date: Tue, 1 Sep 2020 11:11:55 -0700 Message-ID: To: Brandon Lo Cc: ci@dpdk.org, dpdklab Content-Type: multipart/alternative; boundary="00000000000041292905ae447516" Subject: Re: [dpdk-ci] New 100G Broadcom NIC Ubuntu X-BeenThere: ci@dpdk.org X-Mailman-Version: 2.1.15 Precedence: list List-Id: DPDK CI discussions List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Errors-To: ci-bounces@dpdk.org Sender: "ci" --00000000000041292905ae447516 Content-Type: text/plain; charset="UTF-8" Hi Brandon, Thanks for this. I have been stretched thin lately, and this will surely help. Thanks Ajit On Tue, Sep 1, 2020 at 11:09 AM Brandon Lo wrote: > Hi Ajit, > > I'm going to re-enable the Broadcom 25G NIC in production performance > and functional testing. > > If you would like to do testing/debugging on the machine, such as on > the 100G NIC, then please disable these two pipelines on our Jenkins: > > https://dpdklab.iol.unh.edu/jenkins/job/Broadcom-25G-Functional-Test-Pipeline/ > > https://dpdklab.iol.unh.edu/jenkins/job/Broadcom-25G-Performance-Test-Pipeline/ > > You will need to sign in using the same credentials as your VPN. > > This will prevent any overlapping of DTS/TREX runs which is known to > cause errors. > Please let me know if you run into any issues. > > Thanks, > Brandon > > On Wed, Aug 26, 2020 at 3:58 PM Ajit Khaparde > wrote: > > > > Not yet Brandon. > > But I believe I might have to look at what trex is doing to make > progress. > > I will let you know if I need any help. > > > > Thanks > > Ajit > > > > On Tue, Aug 25, 2020 at 1:13 PM Brandon Lo wrote: > >> > >> Hi Ajit, > >> > >> Did you find anything of interest on the machine? > >> I could help out if needed. > >> > >> Thanks, > >> Brandon > >> > >> On Thu, Aug 20, 2020 at 5:07 PM Ajit Khaparde > >> wrote: > >> > > >> > Hi Brandon, > >> > I do see some issues while running trex on this setup. > >> > I will have to dig further. I will let you know once I find something > or may be a fix. > >> > > >> > Thanks > >> > Ajit > >> > > >> > On Thu, Aug 20, 2020 at 8:39 AM Brandon Lo wrote: > >> >> > >> >> Hi Ajit, > >> >> > >> >> I believe DTS/TREX is run on the io machine as a tester. Rhea runs > >> >> testpmd (through an ssh session from io --> rhea) to catch > information > >> >> as a DUT. > >> >> > >> >> The only commands that I run (on io) are: > >> >> cd /opt/dts > >> >> export DTS_CFG_FOLDER='conf_100g' > >> >> ./dts -s > >> >> > >> >> The rest is managed by DTS itself. > >> >> The issue occurs when DTS is trying to send packets to rhea from io > on > >> >> the new 100G NIC. > >> >> It seems to happen after it tries to measure throughput using TREX's > API. > >> >> > >> >> Thanks, > >> >> Brandon > >> >> > >> >> On Thu, Aug 20, 2020 at 12:29 AM Ajit Khaparde > >> >> wrote: > >> >> > > >> >> > Hi Brandon, > >> >> > I was trying to see what exactly is happening on the setup and > what is causing the problem. > >> >> > But I will need your help to use the proper code and commands. > >> >> > > >> >> > I believe you run the testpmd command on io. And the trex is > executed on rhea? > >> >> > Can you point me to the location of the code and the steps you are > following while running the test? > >> >> > > >> >> > Thanks > >> >> > Ajit > >> >> > > >> >> > On Tue, Aug 11, 2020 at 10:47 AM Ajit Khaparde < > ajit.khaparde@broadcom.com> wrote: > >> >> >> > >> >> >> Hi Brandon, > >> >> >> I haven't. I tried to login as well. But I had some issues doing > it from the office. > >> >> >> I just have to remind myself to try it again once I get home > before I connect to the company VPN. > >> >> >> Thanks for checking in. I will try to update you as soon as I can. > >> >> >> > >> >> >> Thanks > >> >> >> Ajit > >> >> >> > >> >> >> On Tue, Aug 11, 2020 at 10:46 AM Brandon Lo > wrote: > >> >> >>> > >> >> >>> Hi Ajit, > >> >> >>> > >> >> >>> I'm just checking in; have you heard of any updates on this > issue? > >> >> >>> > >> >> >>> Thanks, > >> >> >>> Brandon > >> >> >>> > >> >> >>> On Tue, Aug 4, 2020 at 1:42 PM Brandon Lo > wrote: > >> >> >>>> > >> >> >>>> Hi Ajit, > >> >> >>>> > >> >> >>>> Yes, I believe the issue is coming from the trex/tester system > with the 100G NIC. > >> >> >>>> I'm not sure what causes this issue; if I run trex using the > command "cd /opt/v2.82;./t-rex-64 -i --cfg /etc/trex_cfg_100g.yaml -c 7", > which is the same command used in DTS, it seems to launch without failing. > >> >> >>>> > >> >> >>>> If you want to replicate it, here are the steps that I ran: > >> >> >>>> > >> >> >>>> (on io) cd /opt/dts > >> >> >>>> export DTS_CFG_FOLDER='conf_100g' > >> >> >>>> > >> >> >>>> conf_100g has the new configuration files to use the new PCI id > and pktgen config file > >> >> >>>> > >> >> >>>> ./dts -s > >> >> >>>> > >> >> >>>> > >> >> >>>> Thanks for your help, > >> >> >>>> Brandon > >> >> >>>> > >> >> >>>> On Tue, Aug 4, 2020 at 12:38 PM Ajit Khaparde < > ajit.khaparde@broadcom.com> wrote: > >> >> >>>>> > >> >> >>>>> Hi Brandon, > >> >> >>>>> No, I haven't seen or heard this before. > >> >> >>>>> But I will try to have someone run it again. > >> >> >>>>> > >> >> >>>>> Just to make sure - > >> >> >>>>> You are running trex on the 100G NIC and the problem is > encountered on that setup? > >> >> >>>>> Or is it the system that is running testpmd where you are > running into the issue? > >> >> >>>>> > >> >> >>>>> Thanks > >> >> >>>>> Ajit > >> >> >>>>> > >> >> >>>>> On Tue, Aug 4, 2020 at 9:16 AM Brandon Lo > wrote: > >> >> >>>>>> > >> >> >>>>>> Hi Ajit, > >> >> >>>>>> > >> >> >>>>>> I'm running into a problem with trying to run > nic_single_core_perf on the new NIC. > >> >> >>>>>> The current configuration uses trex version v2.82. > >> >> >>>>>> However, I'm running into an error when it tries to actually > do a test case in the nic_single_core_perf. > >> >> >>>>>> > >> >> >>>>>> The output looks like this when it reaches a test case: > >> >> >>>>>> > >> >> >>>>>>> TestNicSingleCorePerf: Test running at parameters: > framesize: 64, rxd/txd: 512 > >> >> >>>>>>> dut.rhea: > ./x86_64-native-linuxapp-gcc/app/testpmd -l 16,17 -n 4 -w 0000:81:00.0 -w > 0000:81:00.1 --file-prefix=dpdk_11307_20200804160513 -- -i > --portmask=0x3 --txd=512 --rxd=512 > >> >> >>>>>>> dut.rhea: start > >> >> >>>>>>> TestNicSingleCorePerf: Test Case > test_perf_nic_single_core Result ERROR: Traceback (most recent call last): > >> >> >>>>>>> File "/opt/dts/framework/test_case.py", line 316, in > _execute_test_case > >> >> >>>>>>> case_obj() > >> >> >>>>>>> File "tests/TestSuite_nic_single_core_perf.py", line 198, > in test_perf_nic_single_core > >> >> >>>>>>> self.perf_test(self.nb_ports) > >> >> >>>>>>> File "tests/TestSuite_nic_single_core_perf.py", line 259, > in perf_test > >> >> >>>>>>> _, packets_received = > self.tester.pktgen.measure_throughput(stream_ids=streams, > options=traffic_opt) > >> >> >>>>>>> File "/opt/dts/framework/pktgen_base.py", line 245, in > measure_throughput > >> >> >>>>>>> self._prepare_transmission(stream_ids=stream_ids) > >> >> >>>>>>> File "/opt/dts/framework/pktgen_trex.py", line 779, in > _prepare_transmission > >> >> >>>>>>> self._conn.reset(ports=self._ports) > >> >> >>>>>>> File > "/opt/v2.82/automation/trex_control_plane/interactive/trex/common/trex_api_annotators.py", > line 51, in wrap2 > >> >> >>>>>>> ret = f(*args, **kwargs) > >> >> >>>>>>> File > "/opt/v2.82/automation/trex_control_plane/interactive/trex/stl/trex_stl_client.py", > line 339, in reset > >> >> >>>>>>> self.clear_stats(ports) > >> >> >>>>>>> File > "/opt/v2.82/automation/trex_control_plane/interactive/trex/common/trex_api_annotators.py", > line 51, in wrap2 > >> >> >>>>>>> ret = f(*args, **kwargs) > >> >> >>>>>>> File > "/opt/v2.82/automation/trex_control_plane/interactive/trex/stl/trex_stl_client.py", > line 1467, in clear_stats > >> >> >>>>>>> self._clear_stats_common(ports, clear_global, > clear_xstats) > >> >> >>>>>>> File > "/opt/v2.82/automation/trex_control_plane/interactive/trex/common/trex_client.py", > line 2840, in _clear_stats_common > >> >> >>>>>>> raise TRexError(rc) > >> >> >>>>>>> trex.common.trex_exceptions.TRexError: *** [RPC] - Failed to > get server response from tcp://127.0.0.1:4501 > >> >> >>>>>> > >> >> >>>>>> > >> >> >>>>>> I have found one similar case on the github repository for > trex, but the solution was vendor-specific: > https://github.com/cisco-system-traffic-generator/trex-core/issues/147. > >> >> >>>>>> Have you ran into this issue before? > >> >> >>>>>> > >> >> >>>>>> Thanks, > >> >> >>>>>> Brandon > >> >> >>>> > >> >> >>>> > >> >> >>>> > >> >> >>>> -- > >> >> >>>> > >> >> >>>> Brandon Lo > >> >> >>>> > >> >> >>>> UNH InterOperability Laboratory > >> >> >>>> > >> >> >>>> 21 Madbury Rd, Suite 100, Durham, NH 03824 > >> >> >>>> > >> >> >>>> blo@iol.unh.edu > >> >> >>>> > >> >> >>>> www.iol.unh.edu > >> >> >>> > >> >> >>> > >> >> >>> > >> >> >>> -- > >> >> >>> > >> >> >>> Brandon Lo > >> >> >>> > >> >> >>> UNH InterOperability Laboratory > >> >> >>> > >> >> >>> 21 Madbury Rd, Suite 100, Durham, NH 03824 > >> >> >>> > >> >> >>> blo@iol.unh.edu > >> >> >>> > >> >> >>> www.iol.unh.edu > >> >> > >> >> > >> >> > >> >> -- > >> >> > >> >> Brandon Lo > >> >> > >> >> UNH InterOperability Laboratory > >> >> > >> >> 21 Madbury Rd, Suite 100, Durham, NH 03824 > >> >> > >> >> blo@iol.unh.edu > >> >> > >> >> www.iol.unh.edu > >> > >> > >> > >> -- > >> > >> Brandon Lo > >> > >> UNH InterOperability Laboratory > >> > >> 21 Madbury Rd, Suite 100, Durham, NH 03824 > >> > >> blo@iol.unh.edu > >> > >> www.iol.unh.edu > > > > -- > > Brandon Lo > > UNH InterOperability Laboratory > > 21 Madbury Rd, Suite 100, Durham, NH 03824 > > blo@iol.unh.edu > > www.iol.unh.edu > --00000000000041292905ae447516 Content-Type: text/html; charset="UTF-8" Content-Transfer-Encoding: quoted-printable
Hi Brandon,
Thanks for this.
I have been stretched thin lately, an= d this will surely help.

Thanks
Ajit

On Tue, Sep 1, 2020 at 11:09 A= M Brandon Lo <blo@iol.unh.edu>= wrote:
Hi Ajit,=

I'm going to re-enable the Broadcom 25G NIC in production performance and functional testing.

If you would like to do testing/debugging on the machine, such as on
the 100G NIC, then please disable these two pipelines on our Jenkins:
=C2=A0 =C2=A0 https://= dpdklab.iol.unh.edu/jenkins/job/Broadcom-25G-Functional-Test-Pipeline/<= br> =C2=A0 =C2=A0 https:/= /dpdklab.iol.unh.edu/jenkins/job/Broadcom-25G-Performance-Test-Pipeline/

You will need to sign in using the same credentials as your VPN.

This will prevent any overlapping of DTS/TREX runs which is known to
cause errors.
Please let me know if you run into any issues.

Thanks,
Brandon

On Wed, Aug 26, 2020 at 3:58 PM Ajit Khaparde
<ajit.kh= aparde@broadcom.com> wrote:
>
> Not yet Brandon.
> But I believe I might have to look at what trex is doing to make progr= ess.
> I will let you know if I need any help.
>
> Thanks
> Ajit
>
> On Tue, Aug 25, 2020 at 1:13 PM Brandon Lo <blo@iol.unh.edu> wrote:
>>
>> Hi Ajit,
>>
>> Did you find anything of interest on the machine?
>> I could help out if needed.
>>
>> Thanks,
>> Brandon
>>
>> On Thu, Aug 20, 2020 at 5:07 PM Ajit Khaparde
>> <ajit.khaparde@broadcom.com> wrote:
>> >
>> > Hi Brandon,
>> > I do see some issues while running trex on this setup.
>> > I will have to dig further. I will let you know once I find s= omething or may be a fix.
>> >
>> > Thanks
>> > Ajit
>> >
>> > On Thu, Aug 20, 2020 at 8:39 AM Brandon Lo <blo@iol.unh.edu> wrote:
>> >>
>> >> Hi Ajit,
>> >>
>> >> I believe DTS/TREX is run on the io machine as a tester. = Rhea runs
>> >> testpmd (through an ssh session from io --> rhea) to c= atch information
>> >> as a DUT.
>> >>
>> >> The only commands that I run (on io) are:
>> >> cd /opt/dts
>> >> export DTS_CFG_FOLDER=3D'conf_100g'
>> >> ./dts -s
>> >>
>> >> The rest is managed by DTS itself.
>> >> The issue occurs when DTS is trying to send packets to rh= ea from io on
>> >> the new 100G NIC.
>> >> It seems to happen after it tries to measure throughput u= sing TREX's API.
>> >>
>> >> Thanks,
>> >> Brandon
>> >>
>> >> On Thu, Aug 20, 2020 at 12:29 AM Ajit Khaparde
>> >> <ajit.khaparde@broadcom.com> wrote:
>> >> >
>> >> > Hi Brandon,
>> >> > I was trying to see what exactly is happening on the= setup and what is causing the problem.
>> >> > But I will need your help to use the proper code and= commands.
>> >> >
>> >> > I believe you run the testpmd command on io. And the= trex is executed on rhea?
>> >> > Can you point me to the location of the code and the= steps you are following while running the test?
>> >> >
>> >> > Thanks
>> >> > Ajit
>> >> >
>> >> > On Tue, Aug 11, 2020 at 10:47 AM Ajit Khaparde <<= a href=3D"mailto:ajit.khaparde@broadcom.com" target=3D"_blank">ajit.khapard= e@broadcom.com> wrote:
>> >> >>
>> >> >> Hi Brandon,
>> >> >> I haven't. I tried to login as well. But I h= ad some issues doing it from the office.
>> >> >> I just have to remind myself to try it again onc= e I get home before I connect to the company VPN.
>> >> >> Thanks for checking in. I will try to update you= as soon as I can.
>> >> >>
>> >> >> Thanks
>> >> >> Ajit
>> >> >>
>> >> >> On Tue, Aug 11, 2020 at 10:46 AM Brandon Lo <= blo@iol.unh.edu>= ; wrote:
>> >> >>>
>> >> >>> Hi Ajit,
>> >> >>>
>> >> >>> I'm just checking in; have you heard of = any updates on this issue?
>> >> >>>
>> >> >>> Thanks,
>> >> >>> Brandon
>> >> >>>
>> >> >>> On Tue, Aug 4, 2020 at 1:42 PM Brandon Lo &l= t;blo@iol.unh.edu&= gt; wrote:
>> >> >>>>
>> >> >>>> Hi Ajit,
>> >> >>>>
>> >> >>>> Yes, I believe the issue is coming from = the trex/tester system with the 100G NIC.
>> >> >>>> I'm not sure what causes this issue;= if I run trex using the command "cd /opt/v2.82;./t-rex-64 -i --cfg /e= tc/trex_cfg_100g.yaml -c 7", which is the same command used in DTS, it= seems to launch without failing.
>> >> >>>>
>> >> >>>> If you want to replicate it, here are th= e steps that I ran:
>> >> >>>>
>> >> >>>> (on io) cd /opt/dts
>> >> >>>> export DTS_CFG_FOLDER=3D'conf_100g&#= 39;
>> >> >>>>
>> >> >>>> conf_100g has the new configuration file= s to use the new PCI id and pktgen config file
>> >> >>>>
>> >> >>>> ./dts -s
>> >> >>>>
>> >> >>>>
>> >> >>>> Thanks for your help,
>> >> >>>> Brandon
>> >> >>>>
>> >> >>>> On Tue, Aug 4, 2020 at 12:38 PM Ajit Kha= parde <a= jit.khaparde@broadcom.com> wrote:
>> >> >>>>>
>> >> >>>>> Hi Brandon,
>> >> >>>>> No, I haven't seen or heard this= before.
>> >> >>>>> But I will try to have someone run i= t again.
>> >> >>>>>
>> >> >>>>> Just to make sure -
>> >> >>>>> You are running trex on the 100G NIC= and the problem is encountered on that setup?
>> >> >>>>> Or is it the system that is running = testpmd where you are running into the issue?
>> >> >>>>>
>> >> >>>>> Thanks
>> >> >>>>> Ajit
>> >> >>>>>
>> >> >>>>> On Tue, Aug 4, 2020 at 9:16 AM Brand= on Lo <blo@iol.unh.= edu> wrote:
>> >> >>>>>>
>> >> >>>>>> Hi Ajit,
>> >> >>>>>>
>> >> >>>>>> I'm running into a problem w= ith trying to run nic_single_core_perf on the new NIC.
>> >> >>>>>> The current configuration uses t= rex version v2.82.
>> >> >>>>>> However, I'm running into an= error when it tries to actually do a test case in the nic_single_core_perf= .
>> >> >>>>>>
>> >> >>>>>> The output looks like this when = it reaches a test case:
>> >> >>>>>>
>> >> >>>>>>> TestNicSingleCorePerf: Test = running at parameters: framesize: 64, rxd/txd: 512
>> >> >>>>>>>=C2=A0 =C2=A0 =C2=A0 =C2=A0 = =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0dut.rhea: ./x86_64-n= ative-linuxapp-gcc/app/testpmd -l 16,17 -n 4 -w 0000:81:00.0 -w 0000:81:00.= 1=C2=A0 --file-prefix=3Ddpdk_11307_20200804160513=C2=A0 =C2=A0 -- -i=C2=A0 = --portmask=3D0x3 --txd=3D512 --rxd=3D512
>> >> >>>>>>>=C2=A0 =C2=A0 =C2=A0 =C2=A0 = =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0dut.rhea: start
>> >> >>>>>>>=C2=A0 =C2=A0 =C2=A0 =C2=A0 = =C2=A0 TestNicSingleCorePerf: Test Case test_perf_nic_single_core Result ER= ROR: Traceback (most recent call last):
>> >> >>>>>>>=C2=A0 =C2=A0File "/opt/= dts/framework/test_case.py", line 316, in _execute_test_case
>> >> >>>>>>>=C2=A0 =C2=A0 =C2=A0case_obj(= )
>> >> >>>>>>>=C2=A0 =C2=A0File "tests= /TestSuite_nic_single_core_perf.py", line 198, in test_perf_nic_single= _core
>> >> >>>>>>>=C2=A0 =C2=A0 =C2=A0self.perf= _test(self.nb_ports)
>> >> >>>>>>>=C2=A0 =C2=A0File "tests= /TestSuite_nic_single_core_perf.py", line 259, in perf_test
>> >> >>>>>>>=C2=A0 =C2=A0 =C2=A0_, packet= s_received =3D self.tester.pktgen.measure_throughput(stream_ids=3Dstreams, = options=3Dtraffic_opt)
>> >> >>>>>>>=C2=A0 =C2=A0File "/opt/= dts/framework/pktgen_base.py", line 245, in measure_throughput
>> >> >>>>>>>=C2=A0 =C2=A0 =C2=A0self._pre= pare_transmission(stream_ids=3Dstream_ids)
>> >> >>>>>>>=C2=A0 =C2=A0File "/opt/= dts/framework/pktgen_trex.py", line 779, in _prepare_transmission
>> >> >>>>>>>=C2=A0 =C2=A0 =C2=A0self._con= n.reset(ports=3Dself._ports)
>> >> >>>>>>>=C2=A0 =C2=A0File "/opt/= v2.82/automation/trex_control_plane/interactive/trex/common/trex_api_annota= tors.py", line 51, in wrap2
>> >> >>>>>>>=C2=A0 =C2=A0 =C2=A0ret =3D f= (*args, **kwargs)
>> >> >>>>>>>=C2=A0 =C2=A0File "/opt/= v2.82/automation/trex_control_plane/interactive/trex/stl/trex_stl_client.py= ", line 339, in reset
>> >> >>>>>>>=C2=A0 =C2=A0 =C2=A0self.clea= r_stats(ports)
>> >> >>>>>>>=C2=A0 =C2=A0File "/opt/= v2.82/automation/trex_control_plane/interactive/trex/common/trex_api_annota= tors.py", line 51, in wrap2
>> >> >>>>>>>=C2=A0 =C2=A0 =C2=A0ret =3D f= (*args, **kwargs)
>> >> >>>>>>>=C2=A0 =C2=A0File "/opt/= v2.82/automation/trex_control_plane/interactive/trex/stl/trex_stl_client.py= ", line 1467, in clear_stats
>> >> >>>>>>>=C2=A0 =C2=A0 =C2=A0self._cle= ar_stats_common(ports, clear_global, clear_xstats)
>> >> >>>>>>>=C2=A0 =C2=A0File "/opt/= v2.82/automation/trex_control_plane/interactive/trex/common/trex_client.py&= quot;, line 2840, in _clear_stats_common
>> >> >>>>>>>=C2=A0 =C2=A0 =C2=A0raise TRe= xError(rc)
>> >> >>>>>>> trex.common.trex_exceptions.= TRexError: *** [RPC] - Failed to get server response from tcp://127.0.0.1:4501<= /a>
>> >> >>>>>>
>> >> >>>>>>
>> >> >>>>>> I have found one similar case on= the github repository for trex, but the solution was vendor-specific: https://github.com/cisco-system-tr= affic-generator/trex-core/issues/147.
>> >> >>>>>> Have you ran into this issue bef= ore?
>> >> >>>>>>
>> >> >>>>>> Thanks,
>> >> >>>>>> Brandon
>> >> >>>>
>> >> >>>>
>> >> >>>>
>> >> >>>> --
>> >> >>>>
>> >> >>>> Brandon Lo
>> >> >>>>
>> >> >>>> UNH InterOperability Laboratory
>> >> >>>>
>> >> >>>> 21 Madbury Rd, Suite 100, Durham, NH 038= 24
>> >> >>>>
>> >> >>>> blo@iol.unh.edu
>> >> >>>>
>> >> >>>> www.iol.unh.edu
>> >> >>>
>> >> >>>
>> >> >>>
>> >> >>> --
>> >> >>>
>> >> >>> Brandon Lo
>> >> >>>
>> >> >>> UNH InterOperability Laboratory
>> >> >>>
>> >> >>> 21 Madbury Rd, Suite 100, Durham, NH 03824 >> >> >>>
>> >> >>> blo@iol.unh.edu
>> >> >>>
>> >> >>> www.iol.unh.edu
>> >>
>> >>
>> >>
>> >> --
>> >>
>> >> Brandon Lo
>> >>
>> >> UNH InterOperability Laboratory
>> >>
>> >> 21 Madbury Rd, Suite 100, Durham, NH 03824
>> >>
>> >> blo@= iol.unh.edu
>> >>
>> >> www.iol.unh.edu
>>
>>
>>
>> --
>>
>> Brandon Lo
>>
>> UNH InterOperability Laboratory
>>
>> 21 Madbury Rd, Suite 100, Durham, NH 03824
>>
>> blo@iol.unh.e= du
>>
>> www.iol.unh.edu



--

Brandon Lo

UNH InterOperability Laboratory

21 Madbury Rd, Suite 100, Durham, NH 03824

blo@iol.unh.edu
www= .iol.unh.edu
--00000000000041292905ae447516-- From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from dpdk.org (dpdk.org [92.243.14.124]) by inbox.dpdk.org (Postfix) with ESMTP id 96207A04DD for ; Thu, 22 Oct 2020 21:04:39 +0200 (CEST) Received: from [92.243.14.124] (localhost [127.0.0.1]) by dpdk.org (Postfix) with ESMTP id 5A8995ABB; Thu, 22 Oct 2020 21:04:38 +0200 (CEST) Received: from mail-il1-f182.google.com (mail-il1-f182.google.com [209.85.166.182]) by dpdk.org (Postfix) with ESMTP id C0E3B5AB7 for ; Thu, 22 Oct 2020 21:04:35 +0200 (CEST) Received: by mail-il1-f182.google.com with SMTP id p16so2722678ilq.5 for ; Thu, 22 Oct 2020 12:04:35 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=iol.unh.edu; s=unh-iol; h=mime-version:references:in-reply-to:from:date:message-id:subject:to :cc; bh=jl6yWKRK8vub2FDo6Ueja7CwPga8+e46mlB1ru39Aig=; b=Nt+GtBu75GmG3Vjyx3eQoqHq7/J6STAjTvlmWjmKpBWATF2Uwsm0q30KK9orMiTUqx sKmGHex/e5hH0rbSm4gbItIhwJ8dFUxwBOwxYrTpexezCt5sQXM0nILRLOGomPLXQsMH uUg6qJpW2/1u4n6AwcckaoWTD/oeodKILWtGI= X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20161025; h=x-gm-message-state:mime-version:references:in-reply-to:from:date :message-id:subject:to:cc; bh=jl6yWKRK8vub2FDo6Ueja7CwPga8+e46mlB1ru39Aig=; b=o/x8RRtm+2gk4ixPEYV4vAc4tfHy7fV8n58lZQ2MxN258dT5bi4Dxg2nDEQMI+qPp0 5onwgc2Hikepou33g6hGSxW9JW9Hi8yblMWIK+I2JKYJwCqWr4bfoCwIecDVlkuJ+CNt +21BXX91B7R1DFiYShNGewtb3ArnZS7DAJrXIe4DJxa2HWs4DgxYWBB2iaJ/pmblERLa t2uwi+nIEKXMgN1u4w3RAOmxP2h9N9cFUjLWUeUE9xcCrYqkIg2MtaY6Xel3Tn3lK2mK IDCnnpqb3w5IH1lBjS5qmY1I8JOu2d0iYPNFiY00JXhRNgIBI2ZByI4p/b9fddmWQD3Y Xvdg== X-Gm-Message-State: AOAM5331M7cpvEUY0fIEbPbUwL1olHnaSJDJ0d9CORICVspKc8+ngvYi vBCWOrga/aDxOI+U/w+DApeRc6mN09EJS9mP9U5k8A== X-Google-Smtp-Source: ABdhPJx7geOILQQ1C5cgHAA2xZINsZAMlu8AQ6mRFBhA5X0rDXSkUtrvKCxVFM7bBn4WncOvSfxQrRocIHw2YWVrCDQ= X-Received: by 2002:a92:c646:: with SMTP id 6mr2931763ill.234.1603393474892; Thu, 22 Oct 2020 12:04:34 -0700 (PDT) MIME-Version: 1.0 References: In-Reply-To: From: Brandon Lo Date: Thu, 22 Oct 2020 15:03:59 -0400 Message-ID: To: Ajit Khaparde Cc: ci@dpdk.org, dpdklab Content-Type: text/plain; charset="UTF-8" Subject: Re: [dpdk-ci] New 100G Broadcom NIC Ubuntu X-BeenThere: ci@dpdk.org X-Mailman-Version: 2.1.15 Precedence: list List-Id: DPDK CI discussions List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Errors-To: ci-bounces@dpdk.org Sender: "ci" Hi Ajit, Just checking in to make sure this issue is not dropped. I have tested the 100G NIC running TREX/DTS again, it still seems that the 100G NIC is not able to use TREX as the console is outputting "Connection lost - Subscriber timeout: no data from TRex server." However, I know that some developers are busy for DPDK so I understand if you are a bit pressed on time currently. Thanks, Brandon On Tue, Sep 1, 2020 at 2:12 PM Ajit Khaparde wrote: > > Hi Brandon, > Thanks for this. > I have been stretched thin lately, and this will surely help. > > Thanks > Ajit > > On Tue, Sep 1, 2020 at 11:09 AM Brandon Lo wrote: >> >> Hi Ajit, >> >> I'm going to re-enable the Broadcom 25G NIC in production performance >> and functional testing. >> >> If you would like to do testing/debugging on the machine, such as on >> the 100G NIC, then please disable these two pipelines on our Jenkins: >> https://dpdklab.iol.unh.edu/jenkins/job/Broadcom-25G-Functional-Test-Pipeline/ >> https://dpdklab.iol.unh.edu/jenkins/job/Broadcom-25G-Performance-Test-Pipeline/ >> >> You will need to sign in using the same credentials as your VPN. >> >> This will prevent any overlapping of DTS/TREX runs which is known to >> cause errors. >> Please let me know if you run into any issues. >> >> Thanks, >> Brandon >> >> On Wed, Aug 26, 2020 at 3:58 PM Ajit Khaparde >> wrote: >> > >> > Not yet Brandon. >> > But I believe I might have to look at what trex is doing to make progress. >> > I will let you know if I need any help. >> > >> > Thanks >> > Ajit >> > >> > On Tue, Aug 25, 2020 at 1:13 PM Brandon Lo wrote: >> >> >> >> Hi Ajit, >> >> >> >> Did you find anything of interest on the machine? >> >> I could help out if needed. >> >> >> >> Thanks, >> >> Brandon >> >> >> >> On Thu, Aug 20, 2020 at 5:07 PM Ajit Khaparde >> >> wrote: >> >> > >> >> > Hi Brandon, >> >> > I do see some issues while running trex on this setup. >> >> > I will have to dig further. I will let you know once I find something or may be a fix. >> >> > >> >> > Thanks >> >> > Ajit >> >> > >> >> > On Thu, Aug 20, 2020 at 8:39 AM Brandon Lo wrote: >> >> >> >> >> >> Hi Ajit, >> >> >> >> >> >> I believe DTS/TREX is run on the io machine as a tester. Rhea runs >> >> >> testpmd (through an ssh session from io --> rhea) to catch information >> >> >> as a DUT. >> >> >> >> >> >> The only commands that I run (on io) are: >> >> >> cd /opt/dts >> >> >> export DTS_CFG_FOLDER='conf_100g' >> >> >> ./dts -s >> >> >> >> >> >> The rest is managed by DTS itself. >> >> >> The issue occurs when DTS is trying to send packets to rhea from io on >> >> >> the new 100G NIC. >> >> >> It seems to happen after it tries to measure throughput using TREX's API. >> >> >> >> >> >> Thanks, >> >> >> Brandon >> >> >> >> >> >> On Thu, Aug 20, 2020 at 12:29 AM Ajit Khaparde >> >> >> wrote: >> >> >> > >> >> >> > Hi Brandon, >> >> >> > I was trying to see what exactly is happening on the setup and what is causing the problem. >> >> >> > But I will need your help to use the proper code and commands. >> >> >> > >> >> >> > I believe you run the testpmd command on io. And the trex is executed on rhea? >> >> >> > Can you point me to the location of the code and the steps you are following while running the test? >> >> >> > >> >> >> > Thanks >> >> >> > Ajit >> >> >> > >> >> >> > On Tue, Aug 11, 2020 at 10:47 AM Ajit Khaparde wrote: >> >> >> >> >> >> >> >> Hi Brandon, >> >> >> >> I haven't. I tried to login as well. But I had some issues doing it from the office. >> >> >> >> I just have to remind myself to try it again once I get home before I connect to the company VPN. >> >> >> >> Thanks for checking in. I will try to update you as soon as I can. >> >> >> >> >> >> >> >> Thanks >> >> >> >> Ajit >> >> >> >> >> >> >> >> On Tue, Aug 11, 2020 at 10:46 AM Brandon Lo wrote: >> >> >> >>> >> >> >> >>> Hi Ajit, >> >> >> >>> >> >> >> >>> I'm just checking in; have you heard of any updates on this issue? >> >> >> >>> >> >> >> >>> Thanks, >> >> >> >>> Brandon >> >> >> >>> >> >> >> >>> On Tue, Aug 4, 2020 at 1:42 PM Brandon Lo wrote: >> >> >> >>>> >> >> >> >>>> Hi Ajit, >> >> >> >>>> >> >> >> >>>> Yes, I believe the issue is coming from the trex/tester system with the 100G NIC. >> >> >> >>>> I'm not sure what causes this issue; if I run trex using the command "cd /opt/v2.82;./t-rex-64 -i --cfg /etc/trex_cfg_100g.yaml -c 7", which is the same command used in DTS, it seems to launch without failing. >> >> >> >>>> >> >> >> >>>> If you want to replicate it, here are the steps that I ran: >> >> >> >>>> >> >> >> >>>> (on io) cd /opt/dts >> >> >> >>>> export DTS_CFG_FOLDER='conf_100g' >> >> >> >>>> >> >> >> >>>> conf_100g has the new configuration files to use the new PCI id and pktgen config file >> >> >> >>>> >> >> >> >>>> ./dts -s >> >> >> >>>> >> >> >> >>>> >> >> >> >>>> Thanks for your help, >> >> >> >>>> Brandon >> >> >> >>>> >> >> >> >>>> On Tue, Aug 4, 2020 at 12:38 PM Ajit Khaparde wrote: >> >> >> >>>>> >> >> >> >>>>> Hi Brandon, >> >> >> >>>>> No, I haven't seen or heard this before. >> >> >> >>>>> But I will try to have someone run it again. >> >> >> >>>>> >> >> >> >>>>> Just to make sure - >> >> >> >>>>> You are running trex on the 100G NIC and the problem is encountered on that setup? >> >> >> >>>>> Or is it the system that is running testpmd where you are running into the issue? >> >> >> >>>>> >> >> >> >>>>> Thanks >> >> >> >>>>> Ajit >> >> >> >>>>> >> >> >> >>>>> On Tue, Aug 4, 2020 at 9:16 AM Brandon Lo wrote: >> >> >> >>>>>> >> >> >> >>>>>> Hi Ajit, >> >> >> >>>>>> >> >> >> >>>>>> I'm running into a problem with trying to run nic_single_core_perf on the new NIC. >> >> >> >>>>>> The current configuration uses trex version v2.82. >> >> >> >>>>>> However, I'm running into an error when it tries to actually do a test case in the nic_single_core_perf. >> >> >> >>>>>> >> >> >> >>>>>> The output looks like this when it reaches a test case: >> >> >> >>>>>> >> >> >> >>>>>>> TestNicSingleCorePerf: Test running at parameters: framesize: 64, rxd/txd: 512 >> >> >> >>>>>>> dut.rhea: ./x86_64-native-linuxapp-gcc/app/testpmd -l 16,17 -n 4 -w 0000:81:00.0 -w 0000:81:00.1 --file-prefix=dpdk_11307_20200804160513 -- -i --portmask=0x3 --txd=512 --rxd=512 >> >> >> >>>>>>> dut.rhea: start >> >> >> >>>>>>> TestNicSingleCorePerf: Test Case test_perf_nic_single_core Result ERROR: Traceback (most recent call last): >> >> >> >>>>>>> File "/opt/dts/framework/test_case.py", line 316, in _execute_test_case >> >> >> >>>>>>> case_obj() >> >> >> >>>>>>> File "tests/TestSuite_nic_single_core_perf.py", line 198, in test_perf_nic_single_core >> >> >> >>>>>>> self.perf_test(self.nb_ports) >> >> >> >>>>>>> File "tests/TestSuite_nic_single_core_perf.py", line 259, in perf_test >> >> >> >>>>>>> _, packets_received = self.tester.pktgen.measure_throughput(stream_ids=streams, options=traffic_opt) >> >> >> >>>>>>> File "/opt/dts/framework/pktgen_base.py", line 245, in measure_throughput >> >> >> >>>>>>> self._prepare_transmission(stream_ids=stream_ids) >> >> >> >>>>>>> File "/opt/dts/framework/pktgen_trex.py", line 779, in _prepare_transmission >> >> >> >>>>>>> self._conn.reset(ports=self._ports) >> >> >> >>>>>>> File "/opt/v2.82/automation/trex_control_plane/interactive/trex/common/trex_api_annotators.py", line 51, in wrap2 >> >> >> >>>>>>> ret = f(*args, **kwargs) >> >> >> >>>>>>> File "/opt/v2.82/automation/trex_control_plane/interactive/trex/stl/trex_stl_client.py", line 339, in reset >> >> >> >>>>>>> self.clear_stats(ports) >> >> >> >>>>>>> File "/opt/v2.82/automation/trex_control_plane/interactive/trex/common/trex_api_annotators.py", line 51, in wrap2 >> >> >> >>>>>>> ret = f(*args, **kwargs) >> >> >> >>>>>>> File "/opt/v2.82/automation/trex_control_plane/interactive/trex/stl/trex_stl_client.py", line 1467, in clear_stats >> >> >> >>>>>>> self._clear_stats_common(ports, clear_global, clear_xstats) >> >> >> >>>>>>> File "/opt/v2.82/automation/trex_control_plane/interactive/trex/common/trex_client.py", line 2840, in _clear_stats_common >> >> >> >>>>>>> raise TRexError(rc) >> >> >> >>>>>>> trex.common.trex_exceptions.TRexError: *** [RPC] - Failed to get server response from tcp://127.0.0.1:4501 >> >> >> >>>>>> >> >> >> >>>>>> >> >> >> >>>>>> I have found one similar case on the github repository for trex, but the solution was vendor-specific: https://github.com/cisco-system-traffic-generator/trex-core/issues/147. >> >> >> >>>>>> Have you ran into this issue before? >> >> >> >>>>>> >> >> >> >>>>>> Thanks, >> >> >> >>>>>> Brandon >> >> >> >>>> >> >> >> >>>> >> >> >> >>>> >> >> >> >>>> -- >> >> >> >>>> >> >> >> >>>> Brandon Lo >> >> >> >>>> >> >> >> >>>> UNH InterOperability Laboratory >> >> >> >>>> >> >> >> >>>> 21 Madbury Rd, Suite 100, Durham, NH 03824 >> >> >> >>>> >> >> >> >>>> blo@iol.unh.edu >> >> >> >>>> >> >> >> >>>> www.iol.unh.edu >> >> >> >>> >> >> >> >>> >> >> >> >>> >> >> >> >>> -- >> >> >> >>> >> >> >> >>> Brandon Lo >> >> >> >>> >> >> >> >>> UNH InterOperability Laboratory >> >> >> >>> >> >> >> >>> 21 Madbury Rd, Suite 100, Durham, NH 03824 >> >> >> >>> >> >> >> >>> blo@iol.unh.edu >> >> >> >>> >> >> >> >>> www.iol.unh.edu >> >> >> >> >> >> >> >> >> >> >> >> -- >> >> >> >> >> >> Brandon Lo >> >> >> >> >> >> UNH InterOperability Laboratory >> >> >> >> >> >> 21 Madbury Rd, Suite 100, Durham, NH 03824 >> >> >> >> >> >> blo@iol.unh.edu >> >> >> >> >> >> www.iol.unh.edu >> >> >> >> >> >> >> >> -- >> >> >> >> Brandon Lo >> >> >> >> UNH InterOperability Laboratory >> >> >> >> 21 Madbury Rd, Suite 100, Durham, NH 03824 >> >> >> >> blo@iol.unh.edu >> >> >> >> www.iol.unh.edu >> >> >> >> -- >> >> Brandon Lo >> >> UNH InterOperability Laboratory >> >> 21 Madbury Rd, Suite 100, Durham, NH 03824 >> >> blo@iol.unh.edu >> >> www.iol.unh.edu -- Brandon Lo UNH InterOperability Laboratory 21 Madbury Rd, Suite 100, Durham, NH 03824 blo@iol.unh.edu www.iol.unh.edu From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from dpdk.org (dpdk.org [92.243.14.124]) by inbox.dpdk.org (Postfix) with ESMTP id BBD9AA04DD for ; Thu, 22 Oct 2020 21:28:00 +0200 (CEST) Received: from [92.243.14.124] (localhost [127.0.0.1]) by dpdk.org (Postfix) with ESMTP id 9990F5A30; Thu, 22 Oct 2020 21:27:59 +0200 (CEST) Received: from mail-ot1-f49.google.com (mail-ot1-f49.google.com [209.85.210.49]) by dpdk.org (Postfix) with ESMTP id E83C25A0F for ; Thu, 22 Oct 2020 21:27:56 +0200 (CEST) Received: by mail-ot1-f49.google.com with SMTP id h62so2545349oth.9 for ; Thu, 22 Oct 2020 12:27:56 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=broadcom.com; s=google; h=mime-version:references:in-reply-to:from:date:message-id:subject:to :cc; bh=gs6F0ShfTOpVFGF9CdTNhhONF7jeoPU5PeL4WFQ7X7Q=; b=AnjJ1s/NBnG2JBwmSguvePHqfLVAmR6wKbE5PDU5SEgOCmt8Y4apjeie16GJTn4o5s cJ1P8637cuZCDFjMLN5ywCQDmdvXXCNaMso4pDCFWDJPHIjyi4dPtAf4BKE0XRRNv6we +1On6pOZTfeNtc2V6k30gjDF/jH2BOsfCpncE= X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20161025; h=x-gm-message-state:mime-version:references:in-reply-to:from:date :message-id:subject:to:cc; bh=gs6F0ShfTOpVFGF9CdTNhhONF7jeoPU5PeL4WFQ7X7Q=; b=bAff9KAbNEULUfRwfIZM8/Cl9xouYdM41ieNcM8Cet4wo1ZsuadvqFViwirnQ1gc3/ JRo9gJVBcS43fA18SHaq4Yf8aK2N964k2pqma8x4jO2G+K8mrkI0xxlanJwn8ZTeofO7 R4ynmMjI+WGccePHM84k/JQrMOJBv3C4eEld5L+h+NEtTn0o6RvX3gJJ782zdJCOLJVe rSzJnW1jzxuzsqCwoNb57/ihz++ngmkQ1zjJ1MTFVnDgRhdpUhdYHCpFWIXwM+Djtu5W bxGNz9fBkFrTRt9eK2qeOVR7WNpY+c1gxT7Bn6sKeVysel3HOQdTnhsYsXl5/5PHel5P eGEw== X-Gm-Message-State: AOAM5312dFuPkq1UTCtdoFcvYMqU51J62lcFbsseH61tmBxDcnk+/JXo MY9FkPeHM1m4LaaSiZX5vcf6m/qq04oE+a4uHA0t2w== X-Google-Smtp-Source: ABdhPJycZVNHPyWTHZZaFEPFBbkU8szlj1tk+aydVCKnVajJHyOFhY3TNNWXpzYHrS1UFwv6uO+gm0ZEOYfanDCrH1o= X-Received: by 2002:a9d:f67:: with SMTP id 94mr3224782ott.154.1603394874866; Thu, 22 Oct 2020 12:27:54 -0700 (PDT) MIME-Version: 1.0 References: In-Reply-To: From: Ajit Khaparde Date: Thu, 22 Oct 2020 12:27:38 -0700 Message-ID: To: Brandon Lo Cc: ci@dpdk.org, dpdklab Content-Type: multipart/signed; protocol="application/pkcs7-signature"; micalg=sha-256; boundary="000000000000fbf6e005b247752f" Subject: Re: [dpdk-ci] New 100G Broadcom NIC Ubuntu X-BeenThere: ci@dpdk.org X-Mailman-Version: 2.1.15 Precedence: list List-Id: DPDK CI discussions List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Errors-To: ci-bounces@dpdk.org Sender: "ci" --000000000000fbf6e005b247752f Content-Type: text/plain; charset="UTF-8" Hi Brandon, Yes. I haven't been able to spend time on this because of the release. But I will try to get to it soon. Thanks for checking. Thanks Ajit On Thu, Oct 22, 2020 at 12:04 PM Brandon Lo wrote: > > Hi Ajit, > > Just checking in to make sure this issue is not dropped. > I have tested the 100G NIC running TREX/DTS again, it still seems that > the 100G NIC is not able to use TREX as the console is outputting > "Connection lost - Subscriber timeout: no data from TRex server." > However, I know that some developers are busy for DPDK so I understand > if you are a bit pressed on time currently. > > Thanks, > Brandon > > On Tue, Sep 1, 2020 at 2:12 PM Ajit Khaparde wrote: > > > > Hi Brandon, > > Thanks for this. > > I have been stretched thin lately, and this will surely help. > > > > Thanks > > Ajit > > > > On Tue, Sep 1, 2020 at 11:09 AM Brandon Lo wrote: > >> > >> Hi Ajit, > >> > >> I'm going to re-enable the Broadcom 25G NIC in production performance > >> and functional testing. > >> > >> If you would like to do testing/debugging on the machine, such as on > >> the 100G NIC, then please disable these two pipelines on our Jenkins: > >> https://dpdklab.iol.unh.edu/jenkins/job/Broadcom-25G-Functional-Test-Pipeline/ > >> https://dpdklab.iol.unh.edu/jenkins/job/Broadcom-25G-Performance-Test-Pipeline/ > >> > >> You will need to sign in using the same credentials as your VPN. > >> > >> This will prevent any overlapping of DTS/TREX runs which is known to > >> cause errors. > >> Please let me know if you run into any issues. > >> > >> Thanks, > >> Brandon > >> > >> On Wed, Aug 26, 2020 at 3:58 PM Ajit Khaparde > >> wrote: > >> > > >> > Not yet Brandon. > >> > But I believe I might have to look at what trex is doing to make progress. > >> > I will let you know if I need any help. > >> > > >> > Thanks > >> > Ajit > >> > > >> > On Tue, Aug 25, 2020 at 1:13 PM Brandon Lo wrote: > >> >> > >> >> Hi Ajit, > >> >> > >> >> Did you find anything of interest on the machine? > >> >> I could help out if needed. > >> >> > >> >> Thanks, > >> >> Brandon > >> >> > >> >> On Thu, Aug 20, 2020 at 5:07 PM Ajit Khaparde > >> >> wrote: > >> >> > > >> >> > Hi Brandon, > >> >> > I do see some issues while running trex on this setup. > >> >> > I will have to dig further. I will let you know once I find something or may be a fix. > >> >> > > >> >> > Thanks > >> >> > Ajit > >> >> > > >> >> > On Thu, Aug 20, 2020 at 8:39 AM Brandon Lo wrote: > >> >> >> > >> >> >> Hi Ajit, > >> >> >> > >> >> >> I believe DTS/TREX is run on the io machine as a tester. Rhea runs > >> >> >> testpmd (through an ssh session from io --> rhea) to catch information > >> >> >> as a DUT. > >> >> >> > >> >> >> The only commands that I run (on io) are: > >> >> >> cd /opt/dts > >> >> >> export DTS_CFG_FOLDER='conf_100g' > >> >> >> ./dts -s > >> >> >> > >> >> >> The rest is managed by DTS itself. > >> >> >> The issue occurs when DTS is trying to send packets to rhea from io on > >> >> >> the new 100G NIC. > >> >> >> It seems to happen after it tries to measure throughput using TREX's API. > >> >> >> > >> >> >> Thanks, > >> >> >> Brandon > >> >> >> > >> >> >> On Thu, Aug 20, 2020 at 12:29 AM Ajit Khaparde > >> >> >> wrote: > >> >> >> > > >> >> >> > Hi Brandon, > >> >> >> > I was trying to see what exactly is happening on the setup and what is causing the problem. > >> >> >> > But I will need your help to use the proper code and commands. > >> >> >> > > >> >> >> > I believe you run the testpmd command on io. And the trex is executed on rhea? > >> >> >> > Can you point me to the location of the code and the steps you are following while running the test? > >> >> >> > > >> >> >> > Thanks > >> >> >> > Ajit > >> >> >> > > >> >> >> > On Tue, Aug 11, 2020 at 10:47 AM Ajit Khaparde wrote: > >> >> >> >> > >> >> >> >> Hi Brandon, > >> >> >> >> I haven't. I tried to login as well. But I had some issues doing it from the office. > >> >> >> >> I just have to remind myself to try it again once I get home before I connect to the company VPN. > >> >> >> >> Thanks for checking in. I will try to update you as soon as I can. > >> >> >> >> > >> >> >> >> Thanks > >> >> >> >> Ajit > >> >> >> >> > >> >> >> >> On Tue, Aug 11, 2020 at 10:46 AM Brandon Lo wrote: > >> >> >> >>> > >> >> >> >>> Hi Ajit, > >> >> >> >>> > >> >> >> >>> I'm just checking in; have you heard of any updates on this issue? > >> >> >> >>> > >> >> >> >>> Thanks, > >> >> >> >>> Brandon > >> >> >> >>> > >> >> >> >>> On Tue, Aug 4, 2020 at 1:42 PM Brandon Lo wrote: > >> >> >> >>>> > >> >> >> >>>> Hi Ajit, > >> >> >> >>>> > >> >> >> >>>> Yes, I believe the issue is coming from the trex/tester system with the 100G NIC. > >> >> >> >>>> I'm not sure what causes this issue; if I run trex using the command "cd /opt/v2.82;./t-rex-64 -i --cfg /etc/trex_cfg_100g.yaml -c 7", which is the same command used in DTS, it seems to launch without failing. > >> >> >> >>>> > >> >> >> >>>> If you want to replicate it, here are the steps that I ran: > >> >> >> >>>> > >> >> >> >>>> (on io) cd /opt/dts > >> >> >> >>>> export DTS_CFG_FOLDER='conf_100g' > >> >> >> >>>> > >> >> >> >>>> conf_100g has the new configuration files to use the new PCI id and pktgen config file > >> >> >> >>>> > >> >> >> >>>> ./dts -s > >> >> >> >>>> > >> >> >> >>>> > >> >> >> >>>> Thanks for your help, > >> >> >> >>>> Brandon > >> >> >> >>>> > >> >> >> >>>> On Tue, Aug 4, 2020 at 12:38 PM Ajit Khaparde wrote: > >> >> >> >>>>> > >> >> >> >>>>> Hi Brandon, > >> >> >> >>>>> No, I haven't seen or heard this before. > >> >> >> >>>>> But I will try to have someone run it again. > >> >> >> >>>>> > >> >> >> >>>>> Just to make sure - > >> >> >> >>>>> You are running trex on the 100G NIC and the problem is encountered on that setup? > >> >> >> >>>>> Or is it the system that is running testpmd where you are running into the issue? > >> >> >> >>>>> > >> >> >> >>>>> Thanks > >> >> >> >>>>> Ajit > >> >> >> >>>>> > >> >> >> >>>>> On Tue, Aug 4, 2020 at 9:16 AM Brandon Lo wrote: > >> >> >> >>>>>> > >> >> >> >>>>>> Hi Ajit, > >> >> >> >>>>>> > >> >> >> >>>>>> I'm running into a problem with trying to run nic_single_core_perf on the new NIC. > >> >> >> >>>>>> The current configuration uses trex version v2.82. > >> >> >> >>>>>> However, I'm running into an error when it tries to actually do a test case in the nic_single_core_perf. > >> >> >> >>>>>> > >> >> >> >>>>>> The output looks like this when it reaches a test case: > >> >> >> >>>>>> > >> >> >> >>>>>>> TestNicSingleCorePerf: Test running at parameters: framesize: 64, rxd/txd: 512 > >> >> >> >>>>>>> dut.rhea: ./x86_64-native-linuxapp-gcc/app/testpmd -l 16,17 -n 4 -w 0000:81:00.0 -w 0000:81:00.1 --file-prefix=dpdk_11307_20200804160513 -- -i --portmask=0x3 --txd=512 --rxd=512 > >> >> >> >>>>>>> dut.rhea: start > >> >> >> >>>>>>> TestNicSingleCorePerf: Test Case test_perf_nic_single_core Result ERROR: Traceback (most recent call last): > >> >> >> >>>>>>> File "/opt/dts/framework/test_case.py", line 316, in _execute_test_case > >> >> >> >>>>>>> case_obj() > >> >> >> >>>>>>> File "tests/TestSuite_nic_single_core_perf.py", line 198, in test_perf_nic_single_core > >> >> >> >>>>>>> self.perf_test(self.nb_ports) > >> >> >> >>>>>>> File "tests/TestSuite_nic_single_core_perf.py", line 259, in perf_test > >> >> >> >>>>>>> _, packets_received = self.tester.pktgen.measure_throughput(stream_ids=streams, options=traffic_opt) > >> >> >> >>>>>>> File "/opt/dts/framework/pktgen_base.py", line 245, in measure_throughput > >> >> >> >>>>>>> self._prepare_transmission(stream_ids=stream_ids) > >> >> >> >>>>>>> File "/opt/dts/framework/pktgen_trex.py", line 779, in _prepare_transmission > >> >> >> >>>>>>> self._conn.reset(ports=self._ports) > >> >> >> >>>>>>> File "/opt/v2.82/automation/trex_control_plane/interactive/trex/common/trex_api_annotators.py", line 51, in wrap2 > >> >> >> >>>>>>> ret = f(*args, **kwargs) > >> >> >> >>>>>>> File "/opt/v2.82/automation/trex_control_plane/interactive/trex/stl/trex_stl_client.py", line 339, in reset > >> >> >> >>>>>>> self.clear_stats(ports) > >> >> >> >>>>>>> File "/opt/v2.82/automation/trex_control_plane/interactive/trex/common/trex_api_annotators.py", line 51, in wrap2 > >> >> >> >>>>>>> ret = f(*args, **kwargs) > >> >> >> >>>>>>> File "/opt/v2.82/automation/trex_control_plane/interactive/trex/stl/trex_stl_client.py", line 1467, in clear_stats > >> >> >> >>>>>>> self._clear_stats_common(ports, clear_global, clear_xstats) > >> >> >> >>>>>>> File "/opt/v2.82/automation/trex_control_plane/interactive/trex/common/trex_client.py", line 2840, in _clear_stats_common > >> >> >> >>>>>>> raise TRexError(rc) > >> >> >> >>>>>>> trex.common.trex_exceptions.TRexError: *** [RPC] - Failed to get server response from tcp://127.0.0.1:4501 > >> >> >> >>>>>> > >> >> >> >>>>>> > >> >> >> >>>>>> I have found one similar case on the github repository for trex, but the solution was vendor-specific: https://github.com/cisco-system-traffic-generator/trex-core/issues/147. > >> >> >> >>>>>> Have you ran into this issue before? > >> >> >> >>>>>> > >> >> >> >>>>>> Thanks, > >> >> >> >>>>>> Brandon > >> >> >> >>>> > >> >> >> >>>> > >> >> >> >>>> > >> >> >> >>>> -- > >> >> >> >>>> > >> >> >> >>>> Brandon Lo > >> >> >> >>>> > >> >> >> >>>> UNH InterOperability Laboratory > >> >> >> >>>> > >> >> >> >>>> 21 Madbury Rd, Suite 100, Durham, NH 03824 > >> >> >> >>>> > >> >> >> >>>> blo@iol.unh.edu > >> >> >> >>>> > >> >> >> >>>> www.iol.unh.edu > >> >> >> >>> > >> >> >> >>> > >> >> >> >>> > >> >> >> >>> -- > >> >> >> >>> > >> >> >> >>> Brandon Lo > >> >> >> >>> > >> >> >> >>> UNH InterOperability Laboratory > >> >> >> >>> > >> >> >> >>> 21 Madbury Rd, Suite 100, Durham, NH 03824 > >> >> >> >>> > >> >> >> >>> blo@iol.unh.edu > >> >> >> >>> > >> >> >> >>> www.iol.unh.edu > >> >> >> > >> >> >> > >> >> >> > >> >> >> -- > >> >> >> > >> >> >> Brandon Lo > >> >> >> > >> >> >> UNH InterOperability Laboratory > >> >> >> > >> >> >> 21 Madbury Rd, Suite 100, Durham, NH 03824 > >> >> >> > >> >> >> blo@iol.unh.edu > >> >> >> > >> >> >> www.iol.unh.edu > >> >> > >> >> > >> >> > >> >> -- > >> >> > >> >> Brandon Lo > >> >> > >> >> UNH InterOperability Laboratory > >> >> > >> >> 21 Madbury Rd, Suite 100, Durham, NH 03824 > >> >> > >> >> blo@iol.unh.edu > >> >> > >> >> www.iol.unh.edu > >> > >> > >> > >> -- > >> > >> Brandon Lo > >> > >> UNH InterOperability Laboratory > >> > >> 21 Madbury Rd, Suite 100, Durham, NH 03824 > >> > >> blo@iol.unh.edu > >> > >> www.iol.unh.edu > > > > -- > > Brandon Lo > > UNH InterOperability Laboratory > > 21 Madbury Rd, Suite 100, Durham, NH 03824 > > blo@iol.unh.edu > > www.iol.unh.edu --000000000000fbf6e005b247752f Content-Type: application/pkcs7-signature; name="smime.p7s" Content-Transfer-Encoding: base64 Content-Disposition: attachment; filename="smime.p7s" Content-Description: S/MIME Cryptographic Signature MIIQSwYJKoZIhvcNAQcCoIIQPDCCEDgCAQExDzANBglghkgBZQMEAgEFADALBgkqhkiG9w0BBwGg gg2gMIIE6DCCA9CgAwIBAgIOSBtqCRO9gCTKXSLwFPMwDQYJKoZIhvcNAQELBQAwTDEgMB4GA1UE CxMXR2xvYmFsU2lnbiBSb290IENBIC0gUjMxEzARBgNVBAoTCkdsb2JhbFNpZ24xEzARBgNVBAMT Ckdsb2JhbFNpZ24wHhcNMTYwNjE1MDAwMDAwWhcNMjQwNjE1MDAwMDAwWjBdMQswCQYDVQQGEwJC RTEZMBcGA1UEChMQR2xvYmFsU2lnbiBudi1zYTEzMDEGA1UEAxMqR2xvYmFsU2lnbiBQZXJzb25h bFNpZ24gMiBDQSAtIFNIQTI1NiAtIEczMIIBIjANBgkqhkiG9w0BAQEFAAOCAQ8AMIIBCgKCAQEA tpZok2X9LAHsYqMNVL+Ly6RDkaKar7GD8rVtb9nw6tzPFnvXGeOEA4X5xh9wjx9sScVpGR5wkTg1 fgJIXTlrGESmaqXIdPRd9YQ+Yx9xRIIIPu3Jp/bpbiZBKYDJSbr/2Xago7sb9nnfSyjTSnucUcIP ZVChn6hKneVGBI2DT9yyyD3PmCEJmEzA8Y96qT83JmVH2GaPSSbCw0C+Zj1s/zqtKUbwE5zh8uuZ p4vC019QbaIOb8cGlzgvTqGORwK0gwDYpOO6QQdg5d03WvIHwTunnJdoLrfvqUg2vOlpqJmqR+nH 9lHS+bEstsVJtZieU1Pa+3LzfA/4cT7XA/pnwwIDAQABo4IBtTCCAbEwDgYDVR0PAQH/BAQDAgEG MGoGA1UdJQRjMGEGCCsGAQUFBwMCBggrBgEFBQcDBAYIKwYBBQUHAwkGCisGAQQBgjcUAgIGCisG AQQBgjcKAwQGCSsGAQQBgjcVBgYKKwYBBAGCNwoDDAYIKwYBBQUHAwcGCCsGAQUFBwMRMBIGA1Ud EwEB/wQIMAYBAf8CAQAwHQYDVR0OBBYEFGlygmIxZ5VEhXeRgMQENkmdewthMB8GA1UdIwQYMBaA FI/wS3+oLkUkrk1Q+mOai97i3Ru8MD4GCCsGAQUFBwEBBDIwMDAuBggrBgEFBQcwAYYiaHR0cDov L29jc3AyLmdsb2JhbHNpZ24uY29tL3Jvb3RyMzA2BgNVHR8ELzAtMCugKaAnhiVodHRwOi8vY3Js Lmdsb2JhbHNpZ24uY29tL3Jvb3QtcjMuY3JsMGcGA1UdIARgMF4wCwYJKwYBBAGgMgEoMAwGCisG AQQBoDIBKAowQQYJKwYBBAGgMgFfMDQwMgYIKwYBBQUHAgEWJmh0dHBzOi8vd3d3Lmdsb2JhbHNp Z24uY29tL3JlcG9zaXRvcnkvMA0GCSqGSIb3DQEBCwUAA4IBAQConc0yzHxn4gtQ16VccKNm4iXv 6rS2UzBuhxI3XDPiwihW45O9RZXzWNgVcUzz5IKJFL7+pcxHvesGVII+5r++9eqI9XnEKCILjHr2 DgvjKq5Jmg6bwifybLYbVUoBthnhaFB0WLwSRRhPrt5eGxMw51UmNICi/hSKBKsHhGFSEaJQALZy 4HL0EWduE6ILYAjX6BSXRDtHFeUPddb46f5Hf5rzITGLsn9BIpoOVrgS878O4JnfUWQi29yBfn75 HajifFvPC+uqn+rcVnvrpLgsLOYG/64kWX/FRH8+mhVe+mcSX3xsUpcxK9q9vLTVtroU/yJUmEC4 OcH5dQsbHBqjMIIDXzCCAkegAwIBAgILBAAAAAABIVhTCKIwDQYJKoZIhvcNAQELBQAwTDEgMB4G A1UECxMXR2xvYmFsU2lnbiBSb290IENBIC0gUjMxEzARBgNVBAoTCkdsb2JhbFNpZ24xEzARBgNV BAMTCkdsb2JhbFNpZ24wHhcNMDkwMzE4MTAwMDAwWhcNMjkwMzE4MTAwMDAwWjBMMSAwHgYDVQQL ExdHbG9iYWxTaWduIFJvb3QgQ0EgLSBSMzETMBEGA1UEChMKR2xvYmFsU2lnbjETMBEGA1UEAxMK R2xvYmFsU2lnbjCCASIwDQYJKoZIhvcNAQEBBQADggEPADCCAQoCggEBAMwldpB5BngiFvXAg7aE yiie/QV2EcWtiHL8RgJDx7KKnQRfJMsuS+FggkbhUqsMgUdwbN1k0ev1LKMPgj0MK66X17YUhhB5 uzsTgHeMCOFJ0mpiLx9e+pZo34knlTifBtc+ycsmWQ1z3rDI6SYOgxXG71uL0gRgykmmKPZpO/bL yCiR5Z2KYVc3rHQU3HTgOu5yLy6c+9C7v/U9AOEGM+iCK65TpjoWc4zdQQ4gOsC0p6Hpsk+QLjJg 6VfLuQSSaGjlOCZgdbKfd/+RFO+uIEn8rUAVSNECMWEZXriX7613t2Saer9fwRPvm2L7DWzgVGkW qQPabumDk3F2xmmFghcCAwEAAaNCMEAwDgYDVR0PAQH/BAQDAgEGMA8GA1UdEwEB/wQFMAMBAf8w HQYDVR0OBBYEFI/wS3+oLkUkrk1Q+mOai97i3Ru8MA0GCSqGSIb3DQEBCwUAA4IBAQBLQNvAUKr+ yAzv95ZURUm7lgAJQayzE4aGKAczymvmdLm6AC2upArT9fHxD4q/c2dKg8dEe3jgr25sbwMpjjM5 RcOO5LlXbKr8EpbsU8Yt5CRsuZRj+9xTaGdWPoO4zzUhw8lo/s7awlOqzJCK6fBdRoyV3XpYKBov Hd7NADdBj+1EbddTKJd+82cEHhXXipa0095MJ6RMG3NzdvQXmcIfeg7jLQitChws/zyrVQ4PkX42 68NXSb7hLi18YIvDQVETI53O9zJrlAGomecsMx86OyXShkDOOyyGeMlhLxS67ttVb9+E7gUJTb0o 2HLO02JQZR7rkpeDMdmztcpHWD9fMIIFTTCCBDWgAwIBAgIMWs606KnVdB7v7hD5MA0GCSqGSIb3 DQEBCwUAMF0xCzAJBgNVBAYTAkJFMRkwFwYDVQQKExBHbG9iYWxTaWduIG52LXNhMTMwMQYDVQQD EypHbG9iYWxTaWduIFBlcnNvbmFsU2lnbiAyIENBIC0gU0hBMjU2IC0gRzMwHhcNMjAwOTIxMTQ1 MTQ5WhcNMjIwOTIyMTQ1MTQ5WjCBljELMAkGA1UEBhMCSU4xEjAQBgNVBAgTCUthcm5hdGFrYTES MBAGA1UEBxMJQmFuZ2Fsb3JlMRYwFAYDVQQKEw1Ccm9hZGNvbSBJbmMuMRwwGgYDVQQDExNBaml0 IEt1bWFyIEtoYXBhcmRlMSkwJwYJKoZIhvcNAQkBFhphaml0LmtoYXBhcmRlQGJyb2FkY29tLmNv bTCCASIwDQYJKoZIhvcNAQEBBQADggEPADCCAQoCggEBAOhBaP/RIbOGTKhCsLzb9X0I5a4kY6la gzIaM13KRKL3a5xDUUFEjC+wbXJ8DyLYr1dsPBBEKONfPUuASy6EhKwdeSVsxcI+so2l92AvVZhE l92YBd3q46HQC3/IaJEOo2GwPsdss8UAQ7J+REQ8XlGps2HosYRMB7gg+mjvL4KirIO8n4VzI0yw wddaxyocNjhGPqDZY+vSF6PoSZftcxZ4+ii8ZvnmgiFCaBOIIs+Xn2EfMjXltvKse1vDRaiZBk68 OP0l4s7M3bo4QgJ6iIVLVGzk11634A8gkDIuyN70OjNrk+mJzr2soL96gWCtihGzZx3DNVXvAE4v BOM6XisCAwEAAaOCAdEwggHNMA4GA1UdDwEB/wQEAwIFoDCBngYIKwYBBQUHAQEEgZEwgY4wTQYI KwYBBQUHMAKGQWh0dHA6Ly9zZWN1cmUuZ2xvYmFsc2lnbi5jb20vY2FjZXJ0L2dzcGVyc29uYWxz aWduMnNoYTJnM29jc3AuY3J0MD0GCCsGAQUFBzABhjFodHRwOi8vb2NzcDIuZ2xvYmFsc2lnbi5j b20vZ3NwZXJzb25hbHNpZ24yc2hhMmczME0GA1UdIARGMEQwQgYKKwYBBAGgMgEoCjA0MDIGCCsG AQUFBwIBFiZodHRwczovL3d3dy5nbG9iYWxzaWduLmNvbS9yZXBvc2l0b3J5LzAJBgNVHRMEAjAA MEQGA1UdHwQ9MDswOaA3oDWGM2h0dHA6Ly9jcmwuZ2xvYmFsc2lnbi5jb20vZ3NwZXJzb25hbHNp Z24yc2hhMmczLmNybDAlBgNVHREEHjAcgRphaml0LmtoYXBhcmRlQGJyb2FkY29tLmNvbTATBgNV HSUEDDAKBggrBgEFBQcDBDAfBgNVHSMEGDAWgBRpcoJiMWeVRIV3kYDEBDZJnXsLYTAdBgNVHQ4E FgQUQxsth1DA/HVRbtquFGuNJtQHpTQwDQYJKoZIhvcNAQELBQADggEBAKOwmI3EGjvaxM3BrAb7 jvhi4b/nfJdooJFtUO8HfCml5RzENqM9Z/SnuY0F4wtgVMHXCXacbAKx+WoBSsVFa535gn/ijhIZ 1PKqiiG70K4oCXEmnNSqUxtT9tuOy2mYu4g2CR1h1hGsLDvGbMwsfpf/KozGjRwSnMf/sDk1wfsO OWBXqzzK/3MryAsF6V6eb7o066XXNzD817tZKZsyOTjEzmse/4658A5r3uMITkV+fmODaTs9STSf 8o0jTovkYAbGjfoFVQjsC5Vtax7Pb1NWVE9Nz8NyOBzDall5Qau0m1fVM4WOtpoAJNymEzh5X+yW Camkvj28WxOFADJ45gsxggJvMIICawIBATBtMF0xCzAJBgNVBAYTAkJFMRkwFwYDVQQKExBHbG9i YWxTaWduIG52LXNhMTMwMQYDVQQDEypHbG9iYWxTaWduIFBlcnNvbmFsU2lnbiAyIENBIC0gU0hB MjU2IC0gRzMCDFrOtOip1XQe7+4Q+TANBglghkgBZQMEAgEFAKCB1DAvBgkqhkiG9w0BCQQxIgQg aSaQ/KnYz7dzcN3fOCskJybBPu9en5LcD0is8p4bcAIwGAYJKoZIhvcNAQkDMQsGCSqGSIb3DQEH ATAcBgkqhkiG9w0BCQUxDxcNMjAxMDIyMTkyNzU1WjBpBgkqhkiG9w0BCQ8xXDBaMAsGCWCGSAFl AwQBKjALBglghkgBZQMEARYwCwYJYIZIAWUDBAECMAoGCCqGSIb3DQMHMAsGCSqGSIb3DQEBCjAL BgkqhkiG9w0BAQcwCwYJYIZIAWUDBAIBMA0GCSqGSIb3DQEBAQUABIIBABh4jzbstQkrgG4Jqd9R vLOciDZ1VuVqIlfI1DVeTkaRXKl9nHTl66esFtjDHAfSJYb4oUwEKgRCLvgzoz1xisx9ymazUcZ1 OmBMCaaAONrcyIB8qheuq3csIYmjMsng3PDmp/n6fmjoCcpzylfrC9Xre7hd9zvcfNkErr8Op9eZ iadwhqbTbQbxChUqMrs7U4sTxdQz6H9QEw0vKHpUOKC3Fa/3WCESFhFwAvuwXxfkw0KDQn4O7JX6 8+lKGHzzTXjEmY16bwY8LdsXn6CekqJ8Qi4xlakj2T8G5peF9gWsLX97FyQI3maeh9toF+SgAC+o c6+A/+ZKcD7Yn4oRx6s= --000000000000fbf6e005b247752f-- From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from dpdk.org (dpdk.org [92.243.14.124]) by inbox.dpdk.org (Postfix) with ESMTP id 87110A0524 for ; Thu, 3 Dec 2020 17:49:07 +0100 (CET) Received: from [92.243.14.124] (localhost [127.0.0.1]) by dpdk.org (Postfix) with ESMTP id 60D13C970; Thu, 3 Dec 2020 17:49:06 +0100 (CET) Received: from mail-lf1-f52.google.com (mail-lf1-f52.google.com [209.85.167.52]) by dpdk.org (Postfix) with ESMTP id 83768C954 for ; Thu, 3 Dec 2020 17:49:03 +0100 (CET) Received: by mail-lf1-f52.google.com with SMTP id d20so3661410lfe.11 for ; Thu, 03 Dec 2020 08:49:03 -0800 (PST) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=iol.unh.edu; s=unh-iol; h=mime-version:references:in-reply-to:from:date:message-id:subject:to :cc; bh=qu88GxGf5AY6oB2M5Yt2lC7n/ZO6G+dosFP021Ievmk=; b=iaze1t7/BDTThYDzWGTOwlgakE8o1a0Qm5tYfye338FqL2OQy1uHWqy7fDs2pZy1kv HWYXo55fuTDzqT9MECMxAwC2Ix7yG5tBJ7ZHpDsFQWVltnmIxVx3/z658V/Z2fGtonMG ZehLunMqJcnYzwqtpb1l/sZsnDxKPk2FQPf+8= X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20161025; h=x-gm-message-state:mime-version:references:in-reply-to:from:date :message-id:subject:to:cc; bh=qu88GxGf5AY6oB2M5Yt2lC7n/ZO6G+dosFP021Ievmk=; b=MohNvHvtez1waZUVRUsUxOoxpIjjKSSVH4bmnBi2YyRi/u/24hLh/ePq1F7ScthhES g6FR+2/E/KSizIPaEOoBAzzfFLSELKbl3XbBS8POPN8gNZD8DKq/Fkc+RrZe3FADxYTh hyHEIy7fvLdq1CMR0WHKFKxWfYFC6LyQrbAFQyxeg5h//6o+sT4Qn4znNLC0cI8go+oj PLepxeadbQ6BGAx11/7DSFas/MZCnO+GRPgVybDY5/YzIEhs3sZGnhRULNKb/BENJ4pB orPNfkbtLmO806vTZIIECV+Z8vn4cl+nwE5KVC1P14f1gPcfujGVjJLrp0Y0BHajpEZl Nv3A== X-Gm-Message-State: AOAM533TTFKSmXQ8bvMgZ6Wa5q6rjwlfcuStDQ1lQTifl+j+iXEj/hlW fmtuE7UFBfIN90FiRbjqZBu/DD0Y+z0NRIhVQGWg/Q== X-Google-Smtp-Source: ABdhPJxeTdc21txOhmp4taC+E94sZuR0dKwQY/ueCbTGiFONwfJ0GBKo1HhdNonEDtAdgVnMQm1dkQNMqg96FpSysEw= X-Received: by 2002:a19:794:: with SMTP id 142mr1664192lfh.232.1607014142753; Thu, 03 Dec 2020 08:49:02 -0800 (PST) MIME-Version: 1.0 References: In-Reply-To: From: Brandon Lo Date: Thu, 3 Dec 2020 11:48:26 -0500 Message-ID: To: Ajit Khaparde Cc: ci@dpdk.org, dpdklab Content-Type: text/plain; charset="UTF-8" Subject: Re: [dpdk-ci] [dpdklab] Re: New 100G Broadcom NIC Ubuntu X-BeenThere: ci@dpdk.org X-Mailman-Version: 2.1.15 Precedence: list List-Id: DPDK CI discussions List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Errors-To: ci-bounces@dpdk.org Sender: "ci" Hi Ajit, Hope you are doing well. Have you had a chance to investigate what could cause this issue? At UNH, we are facing a similar issue with some of the new Arm systems. Maybe they could be related and help us figure out how to fix the Broadcom machine as well. I will let you know if anything pops up that could be interesting. Thanks, Brandon On Thu, Oct 22, 2020 at 3:27 PM 'Ajit Khaparde' via dpdklab wrote: > > Hi Brandon, > Yes. I haven't been able to spend time on this because of the release. > But I will try to get to it soon. > Thanks for checking. > > Thanks > Ajit > > On Thu, Oct 22, 2020 at 12:04 PM Brandon Lo wrote: > > > > Hi Ajit, > > > > Just checking in to make sure this issue is not dropped. > > I have tested the 100G NIC running TREX/DTS again, it still seems that > > the 100G NIC is not able to use TREX as the console is outputting > > "Connection lost - Subscriber timeout: no data from TRex server." > > However, I know that some developers are busy for DPDK so I understand > > if you are a bit pressed on time currently. > > > > Thanks, > > Brandon > > > > On Tue, Sep 1, 2020 at 2:12 PM Ajit Khaparde wrote: > > > > > > Hi Brandon, > > > Thanks for this. > > > I have been stretched thin lately, and this will surely help. > > > > > > Thanks > > > Ajit > > > > > > On Tue, Sep 1, 2020 at 11:09 AM Brandon Lo wrote: > > >> > > >> Hi Ajit, > > >> > > >> I'm going to re-enable the Broadcom 25G NIC in production performance > > >> and functional testing. > > >> > > >> If you would like to do testing/debugging on the machine, such as on > > >> the 100G NIC, then please disable these two pipelines on our Jenkins: > > >> https://dpdklab.iol.unh.edu/jenkins/job/Broadcom-25G-Functional-Test-Pipeline/ > > >> https://dpdklab.iol.unh.edu/jenkins/job/Broadcom-25G-Performance-Test-Pipeline/ > > >> > > >> You will need to sign in using the same credentials as your VPN. > > >> > > >> This will prevent any overlapping of DTS/TREX runs which is known to > > >> cause errors. > > >> Please let me know if you run into any issues. > > >> > > >> Thanks, > > >> Brandon > > >> > > >> On Wed, Aug 26, 2020 at 3:58 PM Ajit Khaparde > > >> wrote: > > >> > > > >> > Not yet Brandon. > > >> > But I believe I might have to look at what trex is doing to make progress. > > >> > I will let you know if I need any help. > > >> > > > >> > Thanks > > >> > Ajit > > >> > > > >> > On Tue, Aug 25, 2020 at 1:13 PM Brandon Lo wrote: > > >> >> > > >> >> Hi Ajit, > > >> >> > > >> >> Did you find anything of interest on the machine? > > >> >> I could help out if needed. > > >> >> > > >> >> Thanks, > > >> >> Brandon > > >> >> > > >> >> On Thu, Aug 20, 2020 at 5:07 PM Ajit Khaparde > > >> >> wrote: > > >> >> > > > >> >> > Hi Brandon, > > >> >> > I do see some issues while running trex on this setup. > > >> >> > I will have to dig further. I will let you know once I find something or may be a fix. > > >> >> > > > >> >> > Thanks > > >> >> > Ajit > > >> >> > > > >> >> > On Thu, Aug 20, 2020 at 8:39 AM Brandon Lo wrote: > > >> >> >> > > >> >> >> Hi Ajit, > > >> >> >> > > >> >> >> I believe DTS/TREX is run on the io machine as a tester. Rhea runs > > >> >> >> testpmd (through an ssh session from io --> rhea) to catch information > > >> >> >> as a DUT. > > >> >> >> > > >> >> >> The only commands that I run (on io) are: > > >> >> >> cd /opt/dts > > >> >> >> export DTS_CFG_FOLDER='conf_100g' > > >> >> >> ./dts -s > > >> >> >> > > >> >> >> The rest is managed by DTS itself. > > >> >> >> The issue occurs when DTS is trying to send packets to rhea from io on > > >> >> >> the new 100G NIC. > > >> >> >> It seems to happen after it tries to measure throughput using TREX's API. > > >> >> >> > > >> >> >> Thanks, > > >> >> >> Brandon > > >> >> >> > > >> >> >> On Thu, Aug 20, 2020 at 12:29 AM Ajit Khaparde > > >> >> >> wrote: > > >> >> >> > > > >> >> >> > Hi Brandon, > > >> >> >> > I was trying to see what exactly is happening on the setup and what is causing the problem. > > >> >> >> > But I will need your help to use the proper code and commands. > > >> >> >> > > > >> >> >> > I believe you run the testpmd command on io. And the trex is executed on rhea? > > >> >> >> > Can you point me to the location of the code and the steps you are following while running the test? > > >> >> >> > > > >> >> >> > Thanks > > >> >> >> > Ajit > > >> >> >> > > > >> >> >> > On Tue, Aug 11, 2020 at 10:47 AM Ajit Khaparde wrote: > > >> >> >> >> > > >> >> >> >> Hi Brandon, > > >> >> >> >> I haven't. I tried to login as well. But I had some issues doing it from the office. > > >> >> >> >> I just have to remind myself to try it again once I get home before I connect to the company VPN. > > >> >> >> >> Thanks for checking in. I will try to update you as soon as I can. > > >> >> >> >> > > >> >> >> >> Thanks > > >> >> >> >> Ajit > > >> >> >> >> > > >> >> >> >> On Tue, Aug 11, 2020 at 10:46 AM Brandon Lo wrote: > > >> >> >> >>> > > >> >> >> >>> Hi Ajit, > > >> >> >> >>> > > >> >> >> >>> I'm just checking in; have you heard of any updates on this issue? > > >> >> >> >>> > > >> >> >> >>> Thanks, > > >> >> >> >>> Brandon > > >> >> >> >>> > > >> >> >> >>> On Tue, Aug 4, 2020 at 1:42 PM Brandon Lo wrote: > > >> >> >> >>>> > > >> >> >> >>>> Hi Ajit, > > >> >> >> >>>> > > >> >> >> >>>> Yes, I believe the issue is coming from the trex/tester system with the 100G NIC. > > >> >> >> >>>> I'm not sure what causes this issue; if I run trex using the command "cd /opt/v2.82;./t-rex-64 -i --cfg /etc/trex_cfg_100g.yaml -c 7", which is the same command used in DTS, it seems to launch without failing. > > >> >> >> >>>> > > >> >> >> >>>> If you want to replicate it, here are the steps that I ran: > > >> >> >> >>>> > > >> >> >> >>>> (on io) cd /opt/dts > > >> >> >> >>>> export DTS_CFG_FOLDER='conf_100g' > > >> >> >> >>>> > > >> >> >> >>>> conf_100g has the new configuration files to use the new PCI id and pktgen config file > > >> >> >> >>>> > > >> >> >> >>>> ./dts -s > > >> >> >> >>>> > > >> >> >> >>>> > > >> >> >> >>>> Thanks for your help, > > >> >> >> >>>> Brandon > > >> >> >> >>>> > > >> >> >> >>>> On Tue, Aug 4, 2020 at 12:38 PM Ajit Khaparde wrote: > > >> >> >> >>>>> > > >> >> >> >>>>> Hi Brandon, > > >> >> >> >>>>> No, I haven't seen or heard this before. > > >> >> >> >>>>> But I will try to have someone run it again. > > >> >> >> >>>>> > > >> >> >> >>>>> Just to make sure - > > >> >> >> >>>>> You are running trex on the 100G NIC and the problem is encountered on that setup? > > >> >> >> >>>>> Or is it the system that is running testpmd where you are running into the issue? > > >> >> >> >>>>> > > >> >> >> >>>>> Thanks > > >> >> >> >>>>> Ajit > > >> >> >> >>>>> > > >> >> >> >>>>> On Tue, Aug 4, 2020 at 9:16 AM Brandon Lo wrote: > > >> >> >> >>>>>> > > >> >> >> >>>>>> Hi Ajit, > > >> >> >> >>>>>> > > >> >> >> >>>>>> I'm running into a problem with trying to run nic_single_core_perf on the new NIC. > > >> >> >> >>>>>> The current configuration uses trex version v2.82. > > >> >> >> >>>>>> However, I'm running into an error when it tries to actually do a test case in the nic_single_core_perf. > > >> >> >> >>>>>> > > >> >> >> >>>>>> The output looks like this when it reaches a test case: > > >> >> >> >>>>>> > > >> >> >> >>>>>>> TestNicSingleCorePerf: Test running at parameters: framesize: 64, rxd/txd: 512 > > >> >> >> >>>>>>> dut.rhea: ./x86_64-native-linuxapp-gcc/app/testpmd -l 16,17 -n 4 -w 0000:81:00.0 -w 0000:81:00.1 --file-prefix=dpdk_11307_20200804160513 -- -i --portmask=0x3 --txd=512 --rxd=512 > > >> >> >> >>>>>>> dut.rhea: start > > >> >> >> >>>>>>> TestNicSingleCorePerf: Test Case test_perf_nic_single_core Result ERROR: Traceback (most recent call last): > > >> >> >> >>>>>>> File "/opt/dts/framework/test_case.py", line 316, in _execute_test_case > > >> >> >> >>>>>>> case_obj() > > >> >> >> >>>>>>> File "tests/TestSuite_nic_single_core_perf.py", line 198, in test_perf_nic_single_core > > >> >> >> >>>>>>> self.perf_test(self.nb_ports) > > >> >> >> >>>>>>> File "tests/TestSuite_nic_single_core_perf.py", line 259, in perf_test > > >> >> >> >>>>>>> _, packets_received = self.tester.pktgen.measure_throughput(stream_ids=streams, options=traffic_opt) > > >> >> >> >>>>>>> File "/opt/dts/framework/pktgen_base.py", line 245, in measure_throughput > > >> >> >> >>>>>>> self._prepare_transmission(stream_ids=stream_ids) > > >> >> >> >>>>>>> File "/opt/dts/framework/pktgen_trex.py", line 779, in _prepare_transmission > > >> >> >> >>>>>>> self._conn.reset(ports=self._ports) > > >> >> >> >>>>>>> File "/opt/v2.82/automation/trex_control_plane/interactive/trex/common/trex_api_annotators.py", line 51, in wrap2 > > >> >> >> >>>>>>> ret = f(*args, **kwargs) > > >> >> >> >>>>>>> File "/opt/v2.82/automation/trex_control_plane/interactive/trex/stl/trex_stl_client.py", line 339, in reset > > >> >> >> >>>>>>> self.clear_stats(ports) > > >> >> >> >>>>>>> File "/opt/v2.82/automation/trex_control_plane/interactive/trex/common/trex_api_annotators.py", line 51, in wrap2 > > >> >> >> >>>>>>> ret = f(*args, **kwargs) > > >> >> >> >>>>>>> File "/opt/v2.82/automation/trex_control_plane/interactive/trex/stl/trex_stl_client.py", line 1467, in clear_stats > > >> >> >> >>>>>>> self._clear_stats_common(ports, clear_global, clear_xstats) > > >> >> >> >>>>>>> File "/opt/v2.82/automation/trex_control_plane/interactive/trex/common/trex_client.py", line 2840, in _clear_stats_common > > >> >> >> >>>>>>> raise TRexError(rc) > > >> >> >> >>>>>>> trex.common.trex_exceptions.TRexError: *** [RPC] - Failed to get server response from tcp://127.0.0.1:4501 > > >> >> >> >>>>>> > > >> >> >> >>>>>> > > >> >> >> >>>>>> I have found one similar case on the github repository for trex, but the solution was vendor-specific: https://github.com/cisco-system-traffic-generator/trex-core/issues/147. > > >> >> >> >>>>>> Have you ran into this issue before? > > >> >> >> >>>>>> > > >> >> >> >>>>>> Thanks, > > >> >> >> >>>>>> Brandon > > >> >> >> >>>> > > >> >> >> >>>> > > >> >> >> >>>> > > >> >> >> >>>> -- > > >> >> >> >>>> > > >> >> >> >>>> Brandon Lo > > >> >> >> >>>> > > >> >> >> >>>> UNH InterOperability Laboratory > > >> >> >> >>>> > > >> >> >> >>>> 21 Madbury Rd, Suite 100, Durham, NH 03824 > > >> >> >> >>>> > > >> >> >> >>>> blo@iol.unh.edu > > >> >> >> >>>> > > >> >> >> >>>> www.iol.unh.edu > > >> >> >> >>> > > >> >> >> >>> > > >> >> >> >>> > > >> >> >> >>> -- > > >> >> >> >>> > > >> >> >> >>> Brandon Lo > > >> >> >> >>> > > >> >> >> >>> UNH InterOperability Laboratory > > >> >> >> >>> > > >> >> >> >>> 21 Madbury Rd, Suite 100, Durham, NH 03824 > > >> >> >> >>> > > >> >> >> >>> blo@iol.unh.edu > > >> >> >> >>> > > >> >> >> >>> www.iol.unh.edu > > >> >> >> > > >> >> >> > > >> >> >> > > >> >> >> -- > > >> >> >> > > >> >> >> Brandon Lo > > >> >> >> > > >> >> >> UNH InterOperability Laboratory > > >> >> >> > > >> >> >> 21 Madbury Rd, Suite 100, Durham, NH 03824 > > >> >> >> > > >> >> >> blo@iol.unh.edu > > >> >> >> > > >> >> >> www.iol.unh.edu > > >> >> > > >> >> > > >> >> > > >> >> -- > > >> >> > > >> >> Brandon Lo > > >> >> > > >> >> UNH InterOperability Laboratory > > >> >> > > >> >> 21 Madbury Rd, Suite 100, Durham, NH 03824 > > >> >> > > >> >> blo@iol.unh.edu > > >> >> > > >> >> www.iol.unh.edu > > >> > > >> > > >> > > >> -- > > >> > > >> Brandon Lo > > >> > > >> UNH InterOperability Laboratory > > >> > > >> 21 Madbury Rd, Suite 100, Durham, NH 03824 > > >> > > >> blo@iol.unh.edu > > >> > > >> www.iol.unh.edu > > > > > > > > -- > > > > Brandon Lo > > > > UNH InterOperability Laboratory > > > > 21 Madbury Rd, Suite 100, Durham, NH 03824 > > > > blo@iol.unh.edu > > > > www.iol.unh.edu -- Brandon Lo UNH InterOperability Laboratory 21 Madbury Rd, Suite 100, Durham, NH 03824 blo@iol.unh.edu www.iol.unh.edu