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 28D0D42555 for ; Sat, 9 Sep 2023 16:46:25 +0200 (CEST) Received: from mails.dpdk.org (localhost [127.0.0.1]) by mails.dpdk.org (Postfix) with ESMTP id 912FF4029E; Sat, 9 Sep 2023 16:46:24 +0200 (CEST) Received: from mail-pf1-f172.google.com (mail-pf1-f172.google.com [209.85.210.172]) by mails.dpdk.org (Postfix) with ESMTP id 4332840295 for ; Sat, 9 Sep 2023 16:46:23 +0200 (CEST) Received: by mail-pf1-f172.google.com with SMTP id d2e1a72fcca58-68a3082c771so2105095b3a.0 for ; Sat, 09 Sep 2023 07:46:23 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=networkplumber-org.20230601.gappssmtp.com; s=20230601; t=1694270782; x=1694875582; darn=dpdk.org; h=content-transfer-encoding:mime-version:references:in-reply-to :message-id:subject:cc:to:from:date:from:to:cc:subject:date :message-id:reply-to; bh=21MZmgmVaF++oCbMnnA2cImadY38CVm9JVNxk2i4SbY=; b=wjikBEleQv94d/meo8VGZjT8Gx/JnxZ3pTupqw/UgAeL9whUUQcwv7TxvQRmpzsJZa jd6ydsXQjUOkl/z7GJGpXKPw07sUv4BqU173pFnWXScaLPyipbgiwE+ZtuIesaU7IWWh HX3r9m7HNhrEccARBv05r52wVggpFUnwXKgYfHXOEl03CS6pVOckVpebHjJwcrmxZ++d cO4ms1sS3TyrKhxvtRlMyqqys9DVTQpMCSgzVU5Wv0WtRQPimbiZCu8IWjsz9Uv2WuaE HQIY2TYbzibuF54hfs4fycFpP5AeAeI77nF6j7K5KbAdQOaXDMPe+YJTY7P7O5/gS5zr A8KA== X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20230601; t=1694270782; x=1694875582; h=content-transfer-encoding:mime-version:references:in-reply-to :message-id:subject:cc:to:from:date:x-gm-message-state:from:to:cc :subject:date:message-id:reply-to; bh=21MZmgmVaF++oCbMnnA2cImadY38CVm9JVNxk2i4SbY=; b=pbnWLD/T9AtzMUj2P/GXqQ1Lpkcpj0zCwFuGti5Ey8qbwJlH9USHrtflhTrZuYbOaT ENMPuXV0GMzlJ7MBMy/vZqI2zUsDbCf4CwTVEd4INNG8kw8PjJSnlMWffagCXhm0WbC4 gynFFlJXeT7SYOTObBdljuDosWKS9ik7Une7q8M/XtirVhe5lh2Wn5oxRVVlN47Bi6ZE ecQ/3lKuT3hGK3CBCEJPVAqrKxfk6jKyouHV5on1owfD19PFLMgm+UsvY8Ag/nuP6nnx qi/Sp2SDQVEJsiNMXZdHFY2yZo72HNMZFcybEdnFDiCJS6e7OXaGTj7+X2MGUc/kY+Nu T9AA== X-Gm-Message-State: AOJu0Yyu0rZfUPEMMUzFpD6Al5oA7Ikr0qEnflkcbdlS01tgZDobXqi3 oUcM+ULGuyJSuM+Dt6nRCo6Qpg== X-Google-Smtp-Source: AGHT+IG9xkQ6pSZea6bswCDhOmQgMN0QauxM0gjok8sB1/BlYQfWZ8X9kJnVNL/LlOItPWQLc3yoIg== X-Received: by 2002:a05:6a00:2da2:b0:68a:582b:6b62 with SMTP id fb34-20020a056a002da200b0068a582b6b62mr6963878pfb.7.1694270782152; Sat, 09 Sep 2023 07:46:22 -0700 (PDT) Received: from hermes.local (204-195-112-131.wavecable.com. [204.195.112.131]) by smtp.gmail.com with ESMTPSA id q12-20020a638c4c000000b005637030d00csm2695909pgn.30.2023.09.09.07.46.21 (version=TLS1_3 cipher=TLS_AES_256_GCM_SHA384 bits=256/256); Sat, 09 Sep 2023 07:46:22 -0700 (PDT) Date: Sat, 9 Sep 2023 07:46:20 -0700 From: Stephen Hemminger To: Amy Smith Cc: "users@dpdk.org" Subject: Re: Can independent dpdk applications in 2 separate pod use same cpu. Message-ID: <20230909074620.2803d7ce@hermes.local> In-Reply-To: <1346556956.3870791.1694264663662@mail.yahoo.com> References: <1346556956.3870791.1694264663662.ref@mail.yahoo.com> <1346556956.3870791.1694264663662@mail.yahoo.com> MIME-Version: 1.0 Content-Type: text/plain; charset=US-ASCII Content-Transfer-Encoding: 7bit X-BeenThere: users@dpdk.org X-Mailman-Version: 2.1.29 Precedence: list List-Id: DPDK usage discussions List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Errors-To: users-bounces@dpdk.org On Sat, 9 Sep 2023 13:04:23 +0000 (UTC) Amy Smith wrote: > Hi,I have 2 independent dpdk application pods working now using different set of cpu cores. For low cost use case I would like them to use same cpu. I have 1 cpu core which I want both pods to share. Is it possible? Do I need to make any changes to applications to use non eal thread, changes to scheduling thread etc.Thanks! Possible yes, but will kill performance since most DPDK applications do pure polling. What will happen is one application will run until preempted by the kernel scheduler, then the other one. The preemption happens on clock tick so each one will run until the clock interrupt (usually 4 ms). And the overhead of context switching and cache misses.