From patchwork Tue Mar 22 21:43:54 2022 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Andrew Morton X-Patchwork-Id: 12789146 Return-Path: X-Spam-Checker-Version: SpamAssassin 3.4.0 (2014-02-07) on aws-us-west-2-korg-lkml-1.web.codeaurora.org Received: from kanga.kvack.org (kanga.kvack.org [205.233.56.17]) by smtp.lore.kernel.org (Postfix) with ESMTP id F3BF8C433EF for ; Tue, 22 Mar 2022 21:43:58 +0000 (UTC) Received: by kanga.kvack.org (Postfix) id 8BD016B00F6; Tue, 22 Mar 2022 17:43:58 -0400 (EDT) Received: by kanga.kvack.org (Postfix, from userid 40) id 892B66B00F7; Tue, 22 Mar 2022 17:43:58 -0400 (EDT) X-Delivered-To: int-list-linux-mm@kvack.org Received: by kanga.kvack.org (Postfix, from userid 63042) id 733A66B00F8; Tue, 22 Mar 2022 17:43:58 -0400 (EDT) X-Delivered-To: linux-mm@kvack.org Received: from relay.hostedemail.com (relay.hostedemail.com [64.99.140.28]) by kanga.kvack.org (Postfix) with ESMTP id 605256B00F6 for ; Tue, 22 Mar 2022 17:43:58 -0400 (EDT) Received: from smtpin03.hostedemail.com (a10.router.float.18 [10.200.18.1]) by unirelay08.hostedemail.com (Postfix) with ESMTP id 2AA7421B15 for ; Tue, 22 Mar 2022 21:43:58 +0000 (UTC) X-FDA: 79273350156.03.00D4878 Received: from ams.source.kernel.org (ams.source.kernel.org [145.40.68.75]) by imf30.hostedemail.com (Postfix) with ESMTP id 7831E8001F for ; Tue, 22 Mar 2022 21:43:57 +0000 (UTC) Received: from smtp.kernel.org (relay.kernel.org [52.25.139.140]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (No client certificate requested) by ams.source.kernel.org (Postfix) with ESMTPS id 6E997B81DB7; Tue, 22 Mar 2022 21:43:56 +0000 (UTC) Received: by smtp.kernel.org (Postfix) with ESMTPSA id 28386C340EC; Tue, 22 Mar 2022 21:43:55 +0000 (UTC) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/simple; d=linux-foundation.org; s=korg; t=1647985435; bh=S/eyA2HwSh27Qj38qgVfJnrFJHeLMF87XhC8sk0Sb1k=; h=Date:To:From:In-Reply-To:Subject:From; b=LW+CRqO5Vx4Wz5V6elTfWc71oJwF60oYGmUUo65ziUyeTvjf4YGAf0NikBQ4l60VX rajogBY7Zt6X0cMkYo2hMgbEeY34F1ufiXaKb2mZyrgF8c5oOAjDuzEpepNWHLxK/i SD6nNl8Xn94gkGaeQCPMQrSSlsh8mLUelNzwp1JA= Date: Tue, 22 Mar 2022 14:43:54 -0700 To: timmurray@google.com,shakeelb@google.com,roman.gushchin@linux.dev,pmladek@suse.com,peterz@infradead.org,minchan@kernel.org,mhocko@suse.com,hannes@cmpxchg.org,surenb@google.com,akpm@linux-foundation.org,patches@lists.linux.dev,linux-mm@kvack.org,mm-commits@vger.kernel.org,torvalds@linux-foundation.org,akpm@linux-foundation.org From: Andrew Morton In-Reply-To: <20220322143803.04a5e59a07e48284f196a2f9@linux-foundation.org> Subject: [patch 106/227] mm: count time in drain_all_pages during direct reclaim as memory pressure Message-Id: <20220322214355.28386C340EC@smtp.kernel.org> X-Stat-Signature: 5xk95nc54ftakpewfhwbhjwbbsxjo53o Authentication-Results: imf30.hostedemail.com; dkim=pass header.d=linux-foundation.org header.s=korg header.b=LW+CRqO5; spf=pass (imf30.hostedemail.com: domain of akpm@linux-foundation.org designates 145.40.68.75 as permitted sender) smtp.mailfrom=akpm@linux-foundation.org; dmarc=none X-Rspam-User: X-Rspamd-Server: rspam08 X-Rspamd-Queue-Id: 7831E8001F X-HE-Tag: 1647985437-762448 X-Bogosity: Ham, tests=bogofilter, spamicity=0.000000, version=1.2.4 Sender: owner-linux-mm@kvack.org Precedence: bulk X-Loop: owner-majordomo@kvack.org List-ID: From: Suren Baghdasaryan Subject: mm: count time in drain_all_pages during direct reclaim as memory pressure When page allocation in direct reclaim path fails, the system will make one attempt to shrink per-cpu page lists and free pages from high alloc reserves. Draining per-cpu pages into buddy allocator can be a very slow operation because it's done using workqueues and the task in direct reclaim waits for all of them to finish before proceeding. Currently this time is not accounted as psi memory stall. While testing mobile devices under extreme memory pressure, when allocations are failing during direct reclaim, we notices that psi events which would be expected in such conditions were not triggered. After profiling these cases it was determined that the reason for missing psi events was that a big chunk of time spent in direct reclaim is not accounted as memory stall, therefore psi would not reach the levels at which an event is generated. Further investigation revealed that the bulk of that unaccounted time was spent inside drain_all_pages call. A typical captured case when drain_all_pages path gets activated: __alloc_pages_slowpath took 44.644.613ns __perform_reclaim took 751.668ns (1.7%) drain_all_pages took 43.887.167ns (98.3%) PSI in this case records the time spent in __perform_reclaim but ignores drain_all_pages, IOW it misses 98.3% of the time spent in __alloc_pages_slowpath. Annotate __alloc_pages_direct_reclaim in its entirety so that delays from handling page allocation failure in the direct reclaim path are accounted as memory stall. Link: https://lkml.kernel.org/r/20220223194812.1299646-1-surenb@google.com Signed-off-by: Suren Baghdasaryan Reported-by: Tim Murray Acked-by: Johannes Weiner Acked-by: Michal Hocko Reviewed-by: Shakeel Butt Cc: Petr Mladek Cc: Peter Zijlstra Cc: Roman Gushchin Cc: Minchan Kim Signed-off-by: Andrew Morton --- mm/page_alloc.c | 10 ++++++---- 1 file changed, 6 insertions(+), 4 deletions(-) --- a/mm/page_alloc.c~mm-count-time-in-drain_all_pages-during-direct-reclaim-as-memory-pressure +++ a/mm/page_alloc.c @@ -4554,13 +4554,12 @@ __perform_reclaim(gfp_t gfp_mask, unsign const struct alloc_context *ac) { unsigned int noreclaim_flag; - unsigned long pflags, progress; + unsigned long progress; cond_resched(); /* We now go into synchronous reclaim */ cpuset_memory_pressure_bump(); - psi_memstall_enter(&pflags); fs_reclaim_acquire(gfp_mask); noreclaim_flag = memalloc_noreclaim_save(); @@ -4569,7 +4568,6 @@ __perform_reclaim(gfp_t gfp_mask, unsign memalloc_noreclaim_restore(noreclaim_flag); fs_reclaim_release(gfp_mask); - psi_memstall_leave(&pflags); cond_resched(); @@ -4583,11 +4581,13 @@ __alloc_pages_direct_reclaim(gfp_t gfp_m unsigned long *did_some_progress) { struct page *page = NULL; + unsigned long pflags; bool drained = false; + psi_memstall_enter(&pflags); *did_some_progress = __perform_reclaim(gfp_mask, order, ac); if (unlikely(!(*did_some_progress))) - return NULL; + goto out; retry: page = get_page_from_freelist(gfp_mask, order, alloc_flags, ac); @@ -4603,6 +4603,8 @@ retry: drained = true; goto retry; } +out: + psi_memstall_leave(&pflags); return page; }