From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from mails.dpdk.org (mails.dpdk.org [217.70.189.124]) by inbox.dpdk.org (Postfix) with ESMTP id 33471466CC; Mon, 5 May 2025 14:55:32 +0200 (CEST) Received: from mails.dpdk.org (localhost [127.0.0.1]) by mails.dpdk.org (Postfix) with ESMTP id DAC3341101; Mon, 5 May 2025 14:51:50 +0200 (CEST) Received: from mail-vk1-f174.google.com (mail-vk1-f174.google.com [209.85.221.174]) by mails.dpdk.org (Postfix) with ESMTP id 07C484021F for ; Mon, 28 Apr 2025 13:25:20 +0200 (CEST) Received: by mail-vk1-f174.google.com with SMTP id 71dfb90a1353d-5240a432462so4809850e0c.1 for ; Mon, 28 Apr 2025 04:25:19 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gmail.com; s=20230601; t=1745839519; x=1746444319; darn=dpdk.org; h=to:subject:message-id:date:from:mime-version:from:to:cc:subject :date:message-id:reply-to; bh=21wTbIADrIVQ+iMCczsUx+mf7967eWxkp8lrTFEeKiM=; b=Ma9XaJ7mroU7Y39pzLFoF2oh37iTgC6xXpMdID+4A5rVDxuiBTJGfK8SvrWqaIxlkb NSiUiySy0rQeW4nTWeJx/dxOfe0h9bLH/eC0ofkqxx8yUBPA49pugSoHTEIP+1vhBf8N gN9uuB8jbkdylsbUdkcMflFc8afC264fCsoaF3J54lg/ebYojAvzesvsI14xXaci8CdZ hFjQRBERS3gM/AQuhq4kDuqwrREK31ob6CUqVodOqQNhhSKUHLSzoTU0SKXbNleV4Ilj XCJGSFiChG54Ti7CaplEWMwjkNwON8/pKZfciAkoyZs0k61hGo2EmQ89b9cUz5zZFRU3 PfYA== X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20230601; t=1745839519; x=1746444319; h=to:subject:message-id:date:from:mime-version:x-gm-message-state :from:to:cc:subject:date:message-id:reply-to; bh=21wTbIADrIVQ+iMCczsUx+mf7967eWxkp8lrTFEeKiM=; b=Hm2F4NdrJqPuC5dgc9D8NPl9BLi0hnO+T3fSNPEUvh2o5K2Rm4JsuIoGKVebP5ID1l ogmc50bJ2/GtzKD1Ioi+KGbPW/IJL3tTo4tat1BBoDTAHGu5/DCcIYHfka4+YPfH+oCs KK41uKIeMUsRj0rrdt0q/VIux4ohiUu9jFv//h8C/eugyr5IscrdwdJeFzglJx4HwNti OQdG8shimra7IQdAPCKWSXGVT2EfK9SQ2yWkBxpTKXaH7jqtHxPoPDI0CnBNFP3vqz/Q RanBlcfNAl33drPFIvchhaTXJ5xVSTHtnCaF7G59XX7BS/ZxiXe9nfKZO0iwbR8GAMAa 2//Q== X-Gm-Message-State: AOJu0YyuWODNTaT0NjKTJ7rpvBBerjxrIo1Xfu6gCm3eCrpD9KXYJcXU Nl5e9N0+NA100A/UdgnDjA7wbWfWdzjcJYcrvxuEI2bPKos+FJUlrZk2o6T+0doHhGDQmDA2mZK YnWNPY/lxMY1r1JOP7/u6AfRhLdJcKT3w X-Gm-Gg: ASbGncuMnMbX8jVbRl+Bcv/HuylWlatgkwkD0wKsg0njoFkCaRqEz+FsOZ+WpDzIFUZ JnI8KolxP8HOHGVQqmQm2yJCzZ5YOqE+HaponmN68HTCnCjx4IbG3bH12h4Lq0ZPRHsVoSbGULf 6mjIPImfthVvrHjVlnYkIQK0Y= X-Google-Smtp-Source: AGHT+IEOVIHg0W4O2cGtkL3uAKgP/3D+W0PbavauUxL6bsIk94Hi/FU1xdjlqtpUQToW4bps72Ur1nq5dJo3khzhiNk= X-Received: by 2002:ac5:cc67:0:b0:524:2fe0:3898 with SMTP id 71dfb90a1353d-52a79eba883mr9719471e0c.5.1745839518923; Mon, 28 Apr 2025 04:25:18 -0700 (PDT) MIME-Version: 1.0 From: farooq basha Date: Mon, 28 Apr 2025 16:55:07 +0530 X-Gm-Features: ATxdqUGVMKWCqmgfUmnWR3JA1MCeK7OpySnI2jmR9TQapbkewnbA9SuRcWXjCKA Message-ID: Subject: [dpdk-dev] Regarding HQOS with run-to-completion Model To: dev@dpdk.org Content-Type: multipart/alternative; boundary="0000000000005c46680633d4f076" X-Mailman-Approved-At: Mon, 05 May 2025 14:51:04 +0200 X-BeenThere: dev@dpdk.org X-Mailman-Version: 2.1.29 Precedence: list List-Id: DPDK patches and discussions List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Errors-To: dev-bounces@dpdk.org --0000000000005c46680633d4f076 Content-Type: text/plain; charset="UTF-8" Content-Transfer-Encoding: quoted-printable Hello DevTeam, I am planning to use DPDK HQOS for Traffic shaping with a run-to-completion Model. While I was reading the dpdk-qos document, I came across the following statement. "*Running enqueue and dequeue operations for the same output port from different cores is likely to cause significant impact on scheduler=E2=80=99= s performance and it is therefore not recommended"* Let's take an example, Port1 & Port2 have 4 Rx queues and each Queue mapped to a different CPU. Traffic coming on port1 gets forwarded to port2 . With the above limitation application needs to take a lock before doing rte_sched_port_enqueue & dequeue operation. Performance is limited to only 1 CPU even though Traffic is coming on 4 Different CPUs. Correct me if my understanding is Wrong? Thanks Basha --0000000000005c46680633d4f076 Content-Type: text/html; charset="UTF-8" Content-Transfer-Encoding: quoted-printable
Hello DevTeam,=C2=A0

= =C2=A0 =C2=A0 I am planning to use DPDK HQOS for Traffic shaping with a run= -to-completion Model. While I was reading the dpdk-qos document, I came acr= oss the following statement.=C2=A0

"Runni= ng enqueue and dequeue operations for the same output port from different c= ores is likely to cause significant impact on scheduler=E2=80=99s performan= ce and it is therefore not recommended"

=
=C2=A0Let's take an=C2=A0 example, Port1=C2=A0 & Port2 hav= e 4 Rx queues and each Queue mapped to a different CPU. Traffic coming on p= ort1=C2=A0 gets forwarded to port2 . With the above limitation application = needs to take a lock before doing rte_sched_port_enqueue & dequeue oper= ation. Performance is limited to only 1 CPU even though Traffic is coming o= n 4 Different CPUs.=C2=A0

Correct me if m= y understanding is Wrong?=C2=A0

Thanks
--0000000000005c46680633d4f076--