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 357BBA0527; Wed, 25 Nov 2020 06:40:05 +0100 (CET) Received: from [92.243.14.124] (localhost [127.0.0.1]) by dpdk.org (Postfix) with ESMTP id A5139C940; Wed, 25 Nov 2020 06:40:02 +0100 (CET) Received: from dish-sg.nttdocomo.co.jp (dish-sg.nttdocomo.co.jp [202.19.227.74]) by dpdk.org (Postfix) with ESMTP id 7B13FC93E for ; Wed, 25 Nov 2020 06:40:00 +0100 (CET) X-dD-Source: Outbound Received: from zssg-mailmd102.ddreams.local (zssg-mailmd900.ddreams.local [10.160.172.63]) by zssg-mailou101.ddreams.local (Postfix) with ESMTP id 2435A120176 for ; Wed, 25 Nov 2020 14:39:58 +0900 (JST) Received: from t131sg-mailcc12.ddreams.local (t131sg-mailcc12.ddreams.local [100.66.31.87]) by zssg-mailmd102.ddreams.local (dDREAMS) with ESMTP id <0QKC000B27QMGV30@dDREAMS> for dev@dpdk.org; Wed, 25 Nov 2020 14:39:58 +0900 (JST) Received: from t131sg-mailcc11 (localhost [127.0.0.1]) by t131sg-mailcc12.ddreams.local (unknown) with SMTP id 0AP5dv5I022306 for ; Wed, 25 Nov 2020 14:39:58 +0900 Received: from zssg-mailmf101.ddreams.local (unknown [127.0.0.1]) by zssg-mailmf101.ddreams.local (Postfix) with ESMTP id 40DC97E603A for ; Wed, 25 Nov 2020 14:39:37 +0900 (JST) Received: from zssg-mailmf101.ddreams.local (unknown [127.0.0.1]) by IMSVA (Postfix) with ESMTP id 403598E605A for ; Wed, 25 Nov 2020 14:39:37 +0900 (JST) Received: from localhost (unknown [127.0.0.1]) by IMSVA (Postfix) with SMTP id 3EFC68E6051 for ; Wed, 25 Nov 2020 14:39:37 +0900 (JST) X-IMSS-HAND-OFF-DIRECTIVE: localhost:10026 Received: from zssg-mailmf101.ddreams.local (unknown [127.0.0.1]) by IMSVA (Postfix) with ESMTP id C4E898E6054 for ; Wed, 25 Nov 2020 14:39:36 +0900 (JST) Received: from zssg-mailua101.ddreams.local (unknown [10.160.172.62]) by zssg-mailmf101.ddreams.local (Postfix) with ESMTP for ; Wed, 25 Nov 2020 14:39:36 +0900 (JST) Received: from [10.87.198.18] (unknown [10.160.183.129]) by zssg-mailua101.ddreams.local (dDREAMS) with ESMTPA id <0QKC00SHM7PVZ430@dDREAMS> for dev@dpdk.org; Wed, 25 Nov 2020 14:39:31 +0900 (JST) Date: Wed, 25 Nov 2020 14:39:31 +0900 From: Hideyuki Yamashita In-reply-to: References: Message-id: <20201125143930.C6ED.17218CA3@ntt-tx.co.jp_1> MIME-version: 1.0 Content-type: text/plain; charset=US-ASCII Content-transfer-encoding: 7bit X-Mailer: Becky! ver. 2.75.01 [ja] X-TM-AS-GCONF: 00 To: "dev@dpdk.org" Subject: [dpdk-dev] NTT TechnoCross roadmap for 21.02 X-BeenThere: dev@dpdk.org X-Mailman-Version: 2.1.15 Precedence: list List-Id: DPDK patches and discussions List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Errors-To: dev-bounces@dpdk.org Sender: "dev" Hello, Following are the work items planned for 21.02 from NTT TechnoCross: I will try to post patch set after 20.11 is released. --- 1) Introduce API stats function In general, DPDK application consumes CPU usage because it polls incoming packets using rx_burst API in infinite loop. This makes difficult to estimate how much CPU usage is really used to send/receive packets by the DPDK application. For example, even if no incoming packets arriving, CPU usage looks nearly 100% when observed by top command. It is beneficial if developers can observe real CPU usage of the DPDK application. Such information can be exported to monitoring application like prometheus/graphana and shows CPU usage graphically. To achieve above, this patch set provides apistats functionality. apistats provides the followiing two counters for each lcore. - rx_burst_counts[RTE_MAX_LCORE] - tx_burst_counts[RTE_MAX_LCORE] Those accumulates rx_burst/tx_burst counts since the application starts. By using those values, developers can roughly estimate CPU usage. Let us assume a DPDK application is simply forwarding packets. It calls tx_burst only if it receive packets. If rx_burst_counts=1000 and tx_burst_count=1000 during certain period of time, one can assume CPU usage is 100%. If rx_burst_counts=1000 and tx_burst_count=100 during certain period of time, one can assume CPU usage is 10%. Here we assumes that tx_burst_count equals counts which rx_burst function really receives incoming packets. -- Thank you, Hideyuki Yamashita NTT TechnoCross