From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1752114AbeFESvh (ORCPT ); Tue, 5 Jun 2018 14:51:37 -0400 Received: from userp2130.oracle.com ([156.151.31.86]:50452 "EHLO userp2130.oracle.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1751812AbeFESvf (ORCPT ); Tue, 5 Jun 2018 14:51:35 -0400 Subject: Re: [PATCH V4] mlx4_core: allocate ICM memory in page size chunks To: Vlastimil Babka , Michal Hocko Cc: Eric Dumazet , David Miller , tariqt@mellanox.com, haakon.bugge@oracle.com, yanjun.zhu@oracle.com, netdev@vger.kernel.org, linux-rdma@vger.kernel.org, linux-kernel@vger.kernel.org, gi-oh.kim@profitbricks.com, "santosh.shilimkar@oracle.com" , rama nichanamatlu References: <7a353b65-6b7f-1aee-1c48-e83c8e02f693@gmail.com> <0e11e0fc-6ccf-aa93-9c4f-b9eae1b90643@gmail.com> <20180531065405.GH15278@dhcp22.suse.cz> <20180531085532.GK15278@dhcp22.suse.cz> <20180531091022.GL15278@dhcp22.suse.cz> <7d8f52e1-aa16-d20c-a9a8-35ad88c0b1ab@oracle.com> <20180601073137.GV15278@dhcp22.suse.cz> <20180604062737.GA19202@dhcp22.suse.cz> From: Qing Huang Message-ID: Date: Tue, 5 Jun 2018 11:51:18 -0700 User-Agent: Mozilla/5.0 (Windows NT 6.1; WOW64; rv:52.0) Gecko/20100101 Thunderbird/52.8.0 MIME-Version: 1.0 In-Reply-To: Content-Type: text/plain; charset=utf-8; format=flowed Content-Transfer-Encoding: 7bit Content-Language: en-US X-Proofpoint-Virus-Version: vendor=nai engine=5900 definitions=8915 signatures=668702 X-Proofpoint-Spam-Details: rule=notspam policy=default score=0 suspectscore=2 malwarescore=0 phishscore=0 bulkscore=0 spamscore=0 mlxscore=0 mlxlogscore=999 adultscore=0 classifier=spam adjust=0 reason=mlx scancount=1 engine=8.0.1-1805220000 definitions=main-1806050213 Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org On 6/4/2018 5:40 AM, Vlastimil Babka wrote: > On 06/04/2018 08:27 AM, Michal Hocko wrote: >> On Fri 01-06-18 15:05:26, Qing Huang wrote: >>> >>> On 6/1/2018 12:31 AM, Michal Hocko wrote: >>>> On Thu 31-05-18 19:04:46, Qing Huang wrote: >>>>> On 5/31/2018 2:10 AM, Michal Hocko wrote: >>>>>> On Thu 31-05-18 10:55:32, Michal Hocko wrote: >>>>>>> On Thu 31-05-18 04:35:31, Eric Dumazet wrote: >>>>>> [...] >>>>>>>> I merely copied/pasted from alloc_skb_with_frags() :/ >>>>>>> I will have a look at it. Thanks! >>>>>> OK, so this is an example of an incremental development ;). >>>>>> >>>>>> __GFP_NORETRY was added by ed98df3361f0 ("net: use __GFP_NORETRY for >>>>>> high order allocations") to prevent from OOM killer. Yet this was >>>>>> not enough because fb05e7a89f50 ("net: don't wait for order-3 page >>>>>> allocation") didn't want an excessive reclaim for non-costly orders >>>>>> so it made it completely NOWAIT while it preserved __GFP_NORETRY in >>>>>> place which is now redundant. Should I send a patch? >>>>>> >>>>> Just curious, how about GFP_ATOMIC flag? Would it work in a similar fashion? >>>>> We experimented >>>>> with it a bit in the past but it seemed to cause other issue in our tests. >>>>> :-) >>>> GFP_ATOMIC is a non-sleeping (aka no reclaim) context with an access to >>>> memory reserves. So the risk is that you deplete those reserves and >>>> cause issues to other subsystems which need them as well. >>>> >>>>> By the way, we didn't encounter any OOM killer events. It seemed that the >>>>> mlx4_alloc_icm() triggered slowpath. >>>>> We still had about 2GB free memory while it was highly fragmented. >>>> The compaction was able to make a reasonable forward progress for you. >>>> But considering mlx4_alloc_icm is called with GFP_KERNEL resp. GFP_HIGHUSER >>>> then the OOM killer is clearly possible as long as the order is lower >>>> than 4. >>> The allocation was 256KB so the order was much higher than 4. The compaction >>> seemed to be the root >>> cause for our problem. It took too long to finish its work while putting >>> mlx4_alloc_icm to sleep in a heavily >>> fragmented memory situation . Will NORETRY flag avoid the compaction ops and >>> fail the 256KB allocation >>> immediately so mlx4_alloc_icm can enter adjustable lower order allocation >>> code path quickly? >> Costly orders should only perform a light compaction attempt unless >> __GFP_RETRY_MAY_FAIL is used IIRC. CCing Vlastimil. So __GFP_NORETRY >> shouldn't make any difference. > It's a bit more complicated. Costly allocations will try the light > compaction attempt first, even before reclaim. This is followed by > reclaim and a more costly compaction attempt. With __GFP_NORETRY, the > second compaction attempt is also only the light one, so the flag does > make a difference here. Thanks for the clarification! Looks like our production kernel is kinda old, neither __GFP_DIRECT_RECLAIM nor __GFP_NORETRY has been used in __alloc_pages_slowpath() in our kernel.