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 44715457DB; Thu, 15 Aug 2024 21:34:00 +0200 (CEST) Received: from mails.dpdk.org (localhost [127.0.0.1]) by mails.dpdk.org (Postfix) with ESMTP id 0B27A427C7; Thu, 15 Aug 2024 21:34:00 +0200 (CEST) Received: from mail-ed1-f43.google.com (mail-ed1-f43.google.com [209.85.208.43]) by mails.dpdk.org (Postfix) with ESMTP id 0E3CB42794 for ; Thu, 15 Aug 2024 21:33:59 +0200 (CEST) Received: by mail-ed1-f43.google.com with SMTP id 4fb4d7f45d1cf-5b8c2a6135dso1632119a12.1 for ; Thu, 15 Aug 2024 12:33:59 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gmail.com; s=20230601; t=1723750438; x=1724355238; darn=dpdk.org; h=to:subject:message-id:date:from:mime-version:from:to:cc:subject :date:message-id:reply-to; bh=t2NgMKanRBOMhshIlaVyEDr/XOVlKM3zWV+lzedbBn0=; b=dC585SIFg6Mgye4DjqiUsxIpZgW1oamcfEfS5J9kCSp10H/tcmsbZX31PBxPh0vdli 6YeglvVuAdrZs6ZfRs9Z6PoFiEQVX4ifjXT4IB+0lKUudmTLU/QR5J59feof9pvhCRoo P+li/GbwtV6Mm6E5/j+betHCgtDWPqelouULHuMde3uyRslmUBEpszPGjuowNi0KJIYy cBxCcer1BquRHa50lvvMUtwNTKJ2QC3QKSSFCZw1FXR/mG1mzG8h6/wY65r6MoSB7wTN X4fIsHIjpLe9KWG8xC0s9ivL2I5tr0cRSfZqLKrYCztiQvQwFSJus3ZiDXr93rzh3/ty 8uXA== X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20230601; t=1723750438; x=1724355238; h=to:subject:message-id:date:from:mime-version:x-gm-message-state :from:to:cc:subject:date:message-id:reply-to; bh=t2NgMKanRBOMhshIlaVyEDr/XOVlKM3zWV+lzedbBn0=; b=UZymUppNY2Epze69V29LnbtGDR/BotVODTzvMY9d87MsZaBjnikFKeS0QgSqxzIaQr n+0fYFLs+Vs+EkNuxnHK3yy9AWBiIfEKgh2jJEhbRERRI5XV/KxUkSAlTSeHpleT58gn UPkwDzKlso0xKDjh+yHhaFFZqOFfkRKJIMb1Ct2LuTlht20mHPE95SZZt+2/upyN32GY ZCMyRwPylMDFek9smrfOiAi/D6BVajjDoLy5/1DGTo9mS7rRGXQlyMeC3RzlOzSmge0Z IVQB8GiBVG+fB+soUnqdrAK7cIahOvz9X2wDVuvIK5DH5FcWSbtY+B1QC8JNax/GU8Re b8Xw== X-Gm-Message-State: AOJu0Yy8F0w1Juq8dfuZ34sWC7ainsic7vSYYzIkm8UTTvgTI6zZ/Wzz v6vJPk0ftfe4wG26e4t+YqapguLxAfMeSzGQm6RWL5NmxksR+t1PmxgopDQ8ZmiGS0gwMm5l2kz h+Fj0acqLEapJuVh/CdIwTJPWhw/wfFyoV3M= X-Google-Smtp-Source: AGHT+IF56PuxnE7rMOeyeUA97r8qCIRuaCJF3nSTapUWz9HmVPCEz73BSVDemPo5zBZnvot9zn2dCgbD4eSw97XWzjw= X-Received: by 2002:a17:907:e24d:b0:a7a:acae:340e with SMTP id a640c23a62f3a-a8392932543mr47602666b.26.1723750437966; Thu, 15 Aug 2024 12:33:57 -0700 (PDT) MIME-Version: 1.0 From: Adel Belkhiri Date: Thu, 15 Aug 2024 15:32:50 -0400 Message-ID: Subject: Ethdev tracepoints optimization To: dev@dpdk.org Content-Type: multipart/alternative; boundary="000000000000895bdc061fbdec37" 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 --000000000000895bdc061fbdec37 Content-Type: text/plain; charset="UTF-8" Content-Transfer-Encoding: quoted-printable Hi DPDK Community, I am currently working on developing performance analyses for applications using the ethdev library. These analyses are being implemented in Trace Compass, an open-source performance analyzer. One of the views I=E2=80=99ve implemented shows the rate of traffic received or sent by an ethernet port, measured in packets per second. However, I've encountered an issue with the lib.ethdev.rx.burst event, which triggers even when no packets are polled, leading to a significant number of irrelevant events in the trace. This becomes problematic as these "empty" events can overwhelm the tracer buffer, potentially causing the loss of more critical events due to their high frequency. To address this, I've modified the DPDK code in lib/ethdev/rte_ethdev.h to add a conditional statement that only triggers the event when nb_rx > 0. My question to the community is whether there are use cases where an "empty" lib.ethdev.rx.burst event could be useful. If not, would there be interest in submitting a patch with this modification? Moreover, I am looking to develop an analysis that calculates the throughput (in kb/s, mb/s, etc.) per NIC, utilizing the same events (i.e., lib.ethdev.rx.burst and lib.ethdev.tx.burst). These tracepoints do not provide packet size directly, only a pointer to the packet array. My attempt to use an eBPF program to iterate through that array to access the packet sizes was unsuccessful, as I found no method to export the computed data (e.g., via a custom tracepoint). Does anyone have suggestions or alternative approaches for achieving a throughput measurement? I would be grateful for any insights or suggestions you might have. Thank you! Adel --000000000000895bdc061fbdec37 Content-Type: text/html; charset="UTF-8" Content-Transfer-Encoding: quoted-printable
Hi DPDK Community,

I am currently working on develo= ping performance analyses for applications using the ethdev library. These = analyses are being implemented in Trace Compass, an open-source performance= analyzer. One of the views I=E2=80=99ve implemented shows the rate of traf= fic received or sent by an ethernet port, measured in packets per second. H= owever, I've encountered an issue with the lib.ethdev.rx.burst event, w= hich triggers even when no packets are polled, leading to a significant num= ber of irrelevant events in the trace. This becomes problematic as these &q= uot;empty" events can overwhelm the tracer buffer, potentially causing= the loss of more critical events due to their high frequency.

To ad= dress this, I've modified the DPDK code in lib/ethdev/rte_ethdev.h to a= dd a conditional statement that only triggers the event when nb_rx > 0. = My question to the community is whether there are use cases where an "= empty" lib.ethdev.rx.burst event could be useful. If not, would there = be interest in submitting a patch with this modification?

Moreover, = I am looking to develop an analysis that calculates the throughput (in kb/s= , mb/s, etc.) per NIC, utilizing the same events (i.e., lib.ethdev.rx.burst= and lib.ethdev.tx.burst). These tracepoints do not provide packet size dir= ectly, only a pointer to the packet array. My attempt to use an eBPF progra= m to iterate through that array to access the packet sizes was unsuccessful= , as I found no method to export the computed data (e.g., via a custom trac= epoint). Does anyone have suggestions or alternative approaches for achievi= ng a throughput measurement?

I would be grateful for any insights or= suggestions you might have.

Thank you!
Adel
--000000000000895bdc061fbdec37--