From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from mail-vs1-f65.google.com (mail-vs1-f65.google.com [209.85.217.65]) by dpdk.org (Postfix) with ESMTP id 93B6C5F24 for ; Thu, 14 Feb 2019 11:16:39 +0100 (CET) Received: by mail-vs1-f65.google.com with SMTP id b20so3284321vsl.9 for ; Thu, 14 Feb 2019 02:16:39 -0800 (PST) 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=Cum6GIYgC082osRwzOQ/4xZ7Znt1/eoekrQLS9RAA9o=; b=oakrVn08bf0X0b9SMRWk+jGub1b5+zVvxEhoZmq/cwuaIPoZOcbUI0CxfeWLLuSQ/H Dx4qe1Vo41wb5Sll4i6HkXpDLdAUO9Kd40GpWlgWk7bXccuxWnvTFIn9eS67pcYWZXmJ +zOpdSRwxJuHmieTKbY6YWMXEySvlP/CldxuzjMVYb1I+JzYJIDWDQSvpe5nM2Z03EKU /eDZJwwe6y8i6q2xCkFubstIxPYO0E8ZOpu+VLgFbSlgkQ+wclihHECydeAswMC8iG5t 06BfPF80N2LpLl9FeCoVaQCXD55Gn+Dhm9eHIFedZNKB0o+e8vDWJGqhBpwpa4gGcRq/ LDgA== X-Gm-Message-State: AHQUAuY6okIspfcmtb5Dou3w8LX6Eze7594kuImj3R31OyHUh6oL9saC mWeMATPXZuZiU8YcqjZFIJ15V1Q2LxEhGWgRimNRwA== X-Google-Smtp-Source: AHgI3IZm7uMX4BF9fZpUNkeNHZgDKLXdg2cr0tinoTSoFx9mnN4PrF/DOONTEHCvD+OpTILZRnrfg94wmqkA+81+Hco= X-Received: by 2002:a67:2045:: with SMTP id g66mr1512875vsg.180.1550139398931; Thu, 14 Feb 2019 02:16:38 -0800 (PST) MIME-Version: 1.0 References: <1550074412-31285-1-git-send-email-david.marchand@redhat.com> <4304821e-dd76-da80-2dec-e1c540e95ea5@intel.com> In-Reply-To: <4304821e-dd76-da80-2dec-e1c540e95ea5@intel.com> From: David Marchand Date: Thu, 14 Feb 2019 11:16:27 +0100 Message-ID: To: "Burakov, Anatoly" Cc: dev@dpdk.org, Olivier Matz , Kevin Traynor , dpdk stable Content-Type: text/plain; charset="UTF-8" X-Content-Filtered-By: Mailman/MimeDel 2.1.15 Subject: Re: [dpdk-stable] [PATCH] eal: restrict ctrl threads to startup cpu affinity X-BeenThere: stable@dpdk.org X-Mailman-Version: 2.1.15 Precedence: list List-Id: patches for DPDK stable branches List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Thu, 14 Feb 2019 10:16:39 -0000 On Thu, Feb 14, 2019 at 11:05 AM Burakov, Anatoly wrote: > On 14-Feb-19 9:53 AM, David Marchand wrote: > > > A bit more context then, if you want to clearly pin cpu resources for > > the processes on your system (let's say having virtual machines and a > > popular vswitch), I can only think of two solutions. > > Either you have something to configure your processes to have them call > > sched_setaffinity/pthread_set_affinity_np, or you use taskset to get > > them "jailed" without them caring. > > > > Before the incriminated commit, we were keeping all threads on the > > coremask that had been passed, but as Olivier said, we would end up with > > ctrl threads spanwed on core running dataplane threads as well. > > > > Now, the ctrl threads can be spawned anywhere on all & ~coremask, with > > no way to configure this. > > I considered adding a new eal option, but I think relying on the current > > cpu affinity is a better default behavior and I can't see drawbacks at > > the moment. > > OK, that makes sense. However, i feel this behavior (both old and new, > for that matter) should be better documented somewhere in the EAL docs. > > I'll see what I can add in the doc for v2. -- David Marchand