From mboxrd@z Thu Jan 1 00:00:00 1970 Received: from smtp.kernel.org (aws-us-west-2-korg-mail-alma10-1.taild15c8.ts.net [100.103.45.18]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (No client certificate requested) by smtp.subspace.kernel.org (Postfix) with ESMTPS id A9DCD26159E; Fri, 2 Oct 2026 01:30:47 +0000 (UTC) Authentication-Results: smtp.subspace.kernel.org; arc=none smtp.client-ip=100.103.45.18 ARC-Seal:i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1790904650; cv=none; b=MuYvr8ynlN/jtGnNX2Em0Nd/iuxh8Xl7evqioMZFQ9X5oQBUBbZfu2uOMhRE56jX0xwVETiL9tue4o03t3QAN97ba4Kn37Vrbrp14Dy/mE2PF0LdlBlMXwurbs1rvxFmrki/qyGf8wSyMN+cwLHwAap87ejDcOSEcfmkv8VVNQs= ARC-Message-Signature:i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1790904650; c=relaxed/simple; bh=qz5PN78HNL43ZK1gQ2c22DgN5XZ87brUq6yZ+CPdn5A=; h=Date:To:From:Subject:Message-Id; b=VMaVCZXZaaLAQzB2Clw2N7TkCcfRBLbh9XRYkvUJlVsLCCWk+wX9tGHuCTISyw5F0pXkc0H/ae6+ATS97oQLnerf1IKfpmgNV999R9/m1zlytBi6qu9WTRCgbjx0qDwIY0cr+4h847OXAxpO+DrmsNdd6bA2ct7k16ZVn+61aEU= ARC-Authentication-Results:i=1; smtp.subspace.kernel.org; dkim=pass (1024-bit key) header.d=linux-foundation.org header.i=@linux-foundation.org header.b=D9hErHOj; arc=none smtp.client-ip=100.103.45.18 Authentication-Results: smtp.subspace.kernel.org; dkim=pass (1024-bit key) header.d=linux-foundation.org header.i=@linux-foundation.org header.b="D9hErHOj" Received: by smtp.kernel.org (Postfix) with ESMTPSA id 7324F1F000FF; Fri, 2 Oct 2026 01:30:46 +0000 (UTC) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=linux-foundation.org; s=korg; t=1790904646; bh=7pyfTfsh0lsZPvF09yeKsG9F9R2NsSl7Lr2Qw2MjXTA=; h=Date:To:From:Subject; b=D9hErHOjrZw+TyQua66oKPR/LEC9NLewlvY5UrA2lz+TPGXDo93OWQYAGdSncQibC CEBUEZSEc/T3MI8BXBE2CAPWDcurEYyY6WjwiR5VB8bsLZ2MIAGq2GiICRxW9Rk9DB vJTMEqSMzBVqYq4/+nt2bUsleJseJmEnfr9zHYaA= Date: Thu, 01 Oct 2026 18:30:46 -0700 To: mm-commits@vger.kernel.org,ziy@nvidia.com,willy@infradead.org,vbabka@kernel.org,surenb@google.com,stable@vger.kernel.org,rvvandan@amazon.com,ritesh.list@gmail.com,mhocko@suse.com,hch@lst.de,hannes@cmpxchg.org,djwong@kernel.org,dipietro.salvatore@gmail.com,d@ilvokhin.com,dgc@kernel.org,david@kernel.org,brendan.jackman@linux.dev,brauner@kernel.org,blakgeof@amazon.com,alisaidi@amazon.com,abuehaze@amazon.com,dipiets@amazon.it,akpm@linux-foundation.org From: Andrew Morton Subject: + mm-page_alloc-avoid-direct-reclaim-and-compaction-for-costly-__gfp_noretry-allocations.patch added to mm-hotfixes-unstable branch Message-Id: <20261002013046.7324F1F000FF@smtp.kernel.org> Precedence: bulk X-Mailing-List: mm-commits@vger.kernel.org List-Id: List-Subscribe: List-Unsubscribe: The patch titled Subject: mm/page_alloc: avoid direct reclaim and compaction for costly __GFP_NORETRY allocations has been added to the -mm mm-hotfixes-unstable branch. Its filename is mm-page_alloc-avoid-direct-reclaim-and-compaction-for-costly-__gfp_noretry-allocations.patch This patch will shortly appear at https://git.kernel.org/pub/scm/linux/kernel/git/akpm/25-new.git/tree/patches/mm-page_alloc-avoid-direct-reclaim-and-compaction-for-costly-__gfp_noretry-allocations.patch This patch will later appear in the mm-hotfixes-unstable branch at git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm Before you just go and hit "reply", please: a) Consider who else should be cc'ed b) Prefer to cc a suitable mailing list as well c) Ideally: find the original patch on the mailing list and do a reply-to-all to that, adding suitable additional cc's *** Remember to use Documentation/process/submit-checklist.rst when testing your code *** The -mm tree is included into linux-next via various branches at git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm and is updated there most days ------------------------------------------------------ From: Salvatore Dipietro Subject: mm/page_alloc: avoid direct reclaim and compaction for costly __GFP_NORETRY allocations Date: Thu, 1 Oct 2026 08:21:51 +0000 Commit 5d8edfb900d5 ("iomap: Copy larger chunks from userspace") introduced high-order folio allocations in the iomap buffered write path. When memory is fragmented, each failed costly-order allocation enters __alloc_pages_slowpath() which runs direct reclaim, direct compaction and drain_all_pages(), causing a 0.38x throughput drop on PostgreSQL pgbench (simple-update) with 1024 clients on a 96-vCPU arm64 system. The root issue is that direct reclaim and direct compaction are too expensive for hot allocation paths that have fallbacks to smaller allocations. __filemap_get_folio_mpol() already marks higher-order allocations with __GFP_NORETRY | __GFP_NOWARN, signalling that the caller can handle failure. However, the page allocator still enters the full blocking slowpath for costly orders with __GFP_NORETRY, which is unnecessarily aggressive when the caller will simply retry at a lower order. For costly-order allocations with __GFP_NORETRY, clear __GFP_DIRECT_RECLAIM at the very start of the slowpath, before can_direct_reclaim, can_compact and the nofail checks are evaluated. This makes the entire slowpath treat the request as non-blocking: no direct reclaim, no direct compaction and no drain_all_pages() IPI across every CPU. Reclaim and compaction move to the background instead: kswapd is still woken for reclaim, and it wakes kcompactd for defragmentation. The system keeps its long-term health while the latency-critical direct allocation path no longer stalls. Allocations that also request __GFP_THISNODE are exempted. That flag pairing identifies the local-node-first THP attempt issued by alloc_pages_mpol() (mempolicy.c), which relies on direct compaction to form transparent huge pages. Clearing __GFP_DIRECT_RECLAIM makes these allocations reach the !can_direct_reclaim bailout, which since commit 4c0ed883e051 ("mm/page_alloc: fix defrag_mode for non-reclaimable allocations") drops ALLOC_NOFRAGMENT and retries instead of failing when defrag_mode is on. With vm.defrag_mode=1 a __GFP_NORETRY allocation could therefore succeed by fragmenting another migratetype's pageblock. That is the wrong trade for a caller that has already communicated it can handle failure and has a cheap lower-order fallback, so exclude __GFP_NORETRY from the relaxation. The exclusion is not restricted to costly orders: any __GFP_NORETRY caller has said it can cope with failure, so failing is preferable to fragmenting for all of them. Test environment: Hardware: AWS EC2 m8g.24xlarge (96 vCPU, arm64) 12x 1TB IO2 32000 IOPS RAID0 XFS OS: AL2023 Kernel: v7.3-rc1 Database: PostgreSQL 18.4 Workload: pgbench simple-update, 1024 clients, 96 threads, 1200s Results (average of 3 runs, TPS): Config Avg TPS % vs baseline v7.3-rc1 baseline (vm.defrag_mode=0) 58,602 - v7.3-rc1 + this patch (vm.defrag_mode=0) 157,246 +168.3% v7.3-rc1 baseline (vm.defrag_mode=1) 109,012 - v7.3-rc1 + this patch (vm.defrag_mode=1) 157,778 +44.7% Link: https://lore.kernel.org/20261001082152.2879289-1-dipiets@amazon.it Link: https://lore.kernel.org/all/20260403193535.9970-1-dipiets@amazon.it/T/#t [v1] Link: https://lore.kernel.org/linux-mm/20260420161404.642-1-dipiets@amazon.it/T/#u [v2] Link: https://lore.kernel.org/all/20260710143437.12379-1-dipiets@amazon.it/T/#u [v3] Link: https://lore.kernel.org/all/20260904115629.3993331-1-dipiets@amazon.it/T/#u [v4] Link: https://lore.kernel.org/all/20260911142102.2294202-1-dipiets@amazon.it/T/#u [v5] Fixes: 5d8edfb900d5 ("iomap: Copy larger chunks from userspace") Signed-off-by: Salvatore Dipietro Signed-off-by: Andrew Morton Acked-by: Vlastimil Babka (SUSE) Acked-by: Zi Yan Reviewed-by: Johannes Weiner Reviewed-by: Christoph Hellwig Cc: David Hildenbrand Cc: Michal Hocko Cc: Matthew Wilcox Cc: Dave Chinner Cc: Ritesh Harjani Cc: Dmitry Ilvokhin Cc: Hazem Mohamed Abuelfotoh Cc: Ali Saidi Cc: Geoff Blake Cc: Christian Brauner Cc: Cc: Darrick J. Wong Cc: Brendan Jackman Cc: Cc: Suren Baghdasaryan Cc: --- mm/page_alloc.c | 21 ++++++++++++++++++--- 1 file changed, 18 insertions(+), 3 deletions(-) --- a/mm/page_alloc.c~mm-page_alloc-avoid-direct-reclaim-and-compaction-for-costly-__gfp_noretry-allocations +++ a/mm/page_alloc.c @@ -4805,10 +4805,10 @@ static inline struct page * __alloc_pages_slowpath(gfp_t gfp_mask, unsigned int order, struct alloc_context *ac) { - bool can_direct_reclaim = gfp_mask & __GFP_DIRECT_RECLAIM; - bool can_compact = can_direct_reclaim && gfp_compaction_allowed(gfp_mask); - bool nofail = gfp_mask & __GFP_NOFAIL; const bool costly_order = order > PAGE_ALLOC_COSTLY_ORDER; + bool can_direct_reclaim; + bool can_compact; + bool nofail; struct page *page = NULL; unsigned int alloc_flags; unsigned long did_some_progress; @@ -4823,6 +4823,18 @@ __alloc_pages_slowpath(gfp_t gfp_mask, u bool can_retry_reserves = true; unsigned long alloc_start_time = jiffies; + /* + * Costly __GFP_NORETRY callers have a cheap fallback, so don't stall + * them in reclaim or compaction. __GFP_THISNODE callers are exempt. + */ + if (costly_order && (gfp_mask & __GFP_NORETRY) && + !(gfp_mask & __GFP_THISNODE)) + gfp_mask &= ~__GFP_DIRECT_RECLAIM; + + can_direct_reclaim = gfp_mask & __GFP_DIRECT_RECLAIM; + can_compact = can_direct_reclaim && gfp_compaction_allowed(gfp_mask); + nofail = gfp_mask & __GFP_NOFAIL; + if (unlikely(nofail)) { /* * Also we don't support __GFP_NOFAIL without __GFP_DIRECT_RECLAIM, @@ -4939,8 +4951,11 @@ retry: * Reclaim/compaction cannot run, so defrag_mode's strategy * of enforcing ALLOC_NOFRAGMENT cannot be fulfilled. Allow * fallbacks rather than failing the allocation outright. + * Not for __GFP_NORETRY: those have a cheap lower order + * fallback, so failing beats fragmenting. */ if (defrag_mode && (alloc_flags & ALLOC_NOFRAGMENT) && + !(gfp_mask & __GFP_NORETRY) && (gfp_mask & __GFP_KSWAPD_RECLAIM)) { alloc_flags &= ~ALLOC_NOFRAGMENT; goto retry; _ Patches currently in -mm which might be from dipiets@amazon.it are mm-page_alloc-avoid-direct-reclaim-and-compaction-for-costly-__gfp_noretry-allocations.patch