From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from mga09.intel.com (mga09.intel.com [134.134.136.24]) by dpdk.org (Postfix) with ESMTP id 7F2215909 for ; Fri, 12 Sep 2014 10:02:01 +0200 (CEST) Received: from orsmga001.jf.intel.com ([10.7.209.18]) by orsmga102.jf.intel.com with ESMTP; 12 Sep 2014 01:01:09 -0700 X-ExtLoop1: 1 X-IronPort-AV: E=Sophos;i="5.04,511,1406617200"; d="scan'208";a="572185705" Received: from irsmsx101.ger.corp.intel.com ([163.33.3.153]) by orsmga001.jf.intel.com with ESMTP; 12 Sep 2014 01:07:13 -0700 Received: from irsmsx103.ger.corp.intel.com ([169.254.3.112]) by IRSMSX101.ger.corp.intel.com ([169.254.1.194]) with mapi id 14.03.0195.001; Fri, 12 Sep 2014 09:07:13 +0100 From: "Richardson, Bruce" To: Hiroshi Shimamoto , "dev@dpdk.org" Thread-Topic: [dpdk-dev] [PATCH 0/3] eal affinitize low priority threads to lcore 0 Thread-Index: AQHPzhtF/S0lu4jOq0eszQHkj6HD05v9JEqQ Date: Fri, 12 Sep 2014 08:07:12 +0000 Message-ID: <59AF69C657FD0841A61C55336867B5B0343F0F16@IRSMSX103.ger.corp.intel.com> References: <1410445387-4849-1-git-send-email-bruce.richardson@intel.com> <7F861DC0615E0C47A872E6F3C5FCDDBD011AC7A6@BPXM14GP.gisp.nec.co.jp> In-Reply-To: <7F861DC0615E0C47A872E6F3C5FCDDBD011AC7A6@BPXM14GP.gisp.nec.co.jp> Accept-Language: en-GB, en-US Content-Language: en-US X-MS-Has-Attach: X-MS-TNEF-Correlator: x-originating-ip: [163.33.239.182] Content-Type: text/plain; charset="us-ascii" Content-Transfer-Encoding: quoted-printable MIME-Version: 1.0 Subject: Re: [dpdk-dev] [PATCH 0/3] eal affinitize low priority threads to lcore 0 X-BeenThere: dev@dpdk.org X-Mailman-Version: 2.1.15 Precedence: list List-Id: patches and discussions about DPDK List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Fri, 12 Sep 2014 08:02:02 -0000 > -----Original Message----- > From: Hiroshi Shimamoto [mailto:h-shimamoto@ct.jp.nec.com] > Sent: Friday, September 12, 2014 12:48 AM > To: Richardson, Bruce; dev@dpdk.org > Subject: RE: [dpdk-dev] [PATCH 0/3] eal affinitize low priority threads t= o lcore 0 >=20 > Hi Bruce, >=20 > > Subject: [dpdk-dev] [PATCH 0/3] eal affinitize low priority threads to = lcore 0 > > > > This patchset sets things up so that we can affinitize the interrupt, > > vfio management, and hpet timer management threads to lcore 0, so that > > they never interfere with data plane threads. >=20 > I don't think it works well always. > The management threads can be floating all cpus on demand, because those > threads are created before the master thread affinity is set. The kernel > scheduler will take care of it. And we should isolate cpus which data pla= ne > threads are pinned to, so the management threads cannot run on those isol= ated > cpus data plane thread run. Yes, this was my understanding as well of how things would work - we just h= ad a report back of where the management threads were using the same core a= s the data-plane despite the core being isolated. I'll double-check to see = if this really is happening and resubmit a new patch with a configurable co= re assignment if it is definitely needed. /Bruce > In some cases, the user may run data plane thread on lcore 0, but with > this patchset the data plane pinned to lcore 0 always run with the > management threads. That doesn't seem good. >=20 > I think this functionality should be conditional. > How about to add a parameter to specify the mask for the management threa= ds > instead of statically assignment to lcore 0? >=20 > thanks, > Hiroshi >=20 > > > > Bruce Richardson (3): > > eal: add core id param to eal_thread_set_affinity > > eal: increase scope of eal_thread_set_affinity > > eal: affinitize low-priority threads to lcore 0 > > > > lib/librte_eal/bsdapp/eal/eal_thread.c | 12 ++++++------ > > lib/librte_eal/common/include/eal_private.h | 10 ++++++++++ > > lib/librte_eal/linuxapp/eal/eal_interrupts.c | 5 +++++ > > lib/librte_eal/linuxapp/eal/eal_pci_vfio_mp_sync.c | 6 ++++++ > > lib/librte_eal/linuxapp/eal/eal_thread.c | 12 ++++++------ > > lib/librte_eal/linuxapp/eal/eal_timer.c | 5 +++++ > > 6 files changed, 38 insertions(+), 12 deletions(-) > > > > -- > > 1.9.3