Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1752838AbdLDVfd (ORCPT ); Mon, 4 Dec 2017 16:35:33 -0500 Received: from mx1.redhat.com ([209.132.183.28]:55354 "EHLO mx1.redhat.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1752604AbdLDVf2 (ORCPT ); Mon, 4 Dec 2017 16:35:28 -0500 From: Jeff Moyer To: Kirill Tkhai Cc: Benjamin LaHaise , axboe@kernel.dk, viro@zeniv.linux.org.uk, tj@kernel.org, linux-block@vger.kernel.org, linux-kernel@vger.kernel.org, linux-aio@kvack.org, oleg@redhat.com Subject: Re: [PATCH 0/5] blkcg: Limit maximum number of aio requests available for cgroup References: <151240305010.10164.15584502480037205018.stgit@localhost.localdomain> <20171204165213.GF11494@kvack.org> <08b9cab6-5237-c027-3bf3-08a69de7fe41@virtuozzo.com> X-PGP-KeyID: 1F78E1B4 X-PGP-CertKey: F6FE 280D 8293 F72C 65FD 5A58 1FF8 A7CA 1F78 E1B4 X-PCLoadLetter: What the f**k does that mean? Date: Mon, 04 Dec 2017 16:35:23 -0500 In-Reply-To: <08b9cab6-5237-c027-3bf3-08a69de7fe41@virtuozzo.com> (Kirill Tkhai's message of "Tue, 5 Dec 2017 00:27:37 +0300") Message-ID: User-Agent: Gnus/5.13 (Gnus v5.13) Emacs/24.3 (gnu/linux) MIME-Version: 1.0 Content-Type: text/plain X-Greylist: Sender IP whitelisted, not delayed by milter-greylist-4.5.16 (mx1.redhat.com [10.5.110.30]); Mon, 04 Dec 2017 21:35:28 +0000 (UTC) Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Length: 2279 Lines: 67 Kirill Tkhai writes: > Hi, Benjamin, > > On 04.12.2017 19:52, Benjamin LaHaise wrote: >> Hi Kirill, >> >> On Mon, Dec 04, 2017 at 07:12:51PM +0300, Kirill Tkhai wrote: >>> Hi, >>> >>> this patch set introduces accounting aio_nr and aio_max_nr per blkio cgroup. >>> It may be used to limit number of aio requests, which are available for >>> a cgroup, and could be useful for containers. >>> >>> The accounting is hierarchical, and aio contexts, allocated in child cgroup, >>> are accounted in parent cgroups too. >>> >>> Also, new cgroup file "io.aio_nr" is introduced. It's used to set cgroup >>> aio requests limit, to show current limit and number of currenly occupied >>> requests. >> >> Where are your test cases to check this functionality in the libaio test >> suite? > > I tried to find actual libaio test suite repository url in google, > but there is no certain answer. Also, there is no information in kernel > anywhere (I hope I grepped right). > > Could you please provide url where actual upstream libaio could be obtained? https://pagure.io/libaio Patches can be sent to this list (linux-aio). Cheers, Jeff >>> Patches 1-3 are refactoring. >>> Patch 4 is the place where the accounting actually introduced. >>> Patch 5 adds "io.aio_nr" file. >>> >>> --- >>> >>> Kirill Tkhai (5): >>> aio: Move aio_nr increment to separate function >>> aio: Export aio_nr_lock and aio_max_nr initial value to include/linux/aio.h >>> blkcg: Add blkcg::blkg_aio_nr and blkcg::blkg_aio_max_nr >>> blkcg: Charge aio requests in blkio cgroup hierarchy >>> blkcg: Add cgroup file to configure blkcg::blkg_aio_max_nr >>> >>> >>> block/blk-cgroup.c | 88 +++++++++++++++++++++++++- >>> fs/aio.c | 151 ++++++++++++++++++++++++++++++++++++++++---- >>> include/linux/aio.h | 21 ++++++ >>> include/linux/blk-cgroup.h | 4 + >>> 4 files changed, 247 insertions(+), 17 deletions(-) >>> >>> -- >>> Signed-off-by: Kirill Tkhai >>> >> > > -- > To unsubscribe, send a message with 'unsubscribe linux-aio' in > the body to majordomo@kvack.org. For more info on Linux AIO, > see: http://www.kvack.org/aio/ > Don't email: aart@kvack.org