From mboxrd@z Thu Jan 1 00:00:00 1970 Authentication-Results: smtp.subspace.kernel.org; arc=none smtp.remote-ip=52.34.181.151 ARC-Seal: i=1; d=subspace.kernel.org; s=arc20261015; a=rsa-sha256; cv=none; t=1794567803; b=bCLlVIxQDf7Db6M8U9fYyhNXu9SzoJIdQWVOuME5FpGIDVLG3GDcMLA5Wxqfyj5Dx2C1 jFB+DtQhOkJkQRlYYdLXbfw/eeW2tTMGOwiaWcFknzSmx4TBj9cCPasBfbgOMyhGNolx2 TDOfKAoZ628Flh30IIG5xvIrwQo2KTK9YdgLoNG5c7c4xjcYGV4MJakjjFSN8CTTKZwpu ubODzDe2JNqjE05qTPbWzcmbv93C1ZOpaMh1fBUx6kLxNLY/WWDu18f32qBdEc42H5YXI XfoinaeXF1lUGoZlvNHHO6L7BoKH3lffs4q0XYPdAW+H/6NDZqGqc3fmAPIypO+84IQ== ARC-Message-Signature: i=1; d=subspace.kernel.org; s=arc20261015; a=rsa-sha256; c=relaxed/relaxed; t=1794567803; h=DMARC-Filter:DKIM-Signature:X-CSE-ConnectionGUID:X-CSE-MsgGUID: X-IronPort-AV:Received:Received:X-Farcaster-Flow-ID:Received:Received: From:To:CC:Subject:Date:Message-ID:X-Mailer:In-Reply-To:References: MIME-Version:X-Originating-IP:X-ClientProxiedBy:Content-Type: Content-Transfer-Encoding; bh=LBrctbWCr0zoW4q3CpOYQqWzbyJ/Y4Bqv54BvH7JL1M=; b=FKDlnJRsd1UV2Tzoz+4XePPnJlZcmBcXbbaLEeX75QaenLgsn/DIC9Ic400WUiNoHSPY 4RjHLH8235LjODE5jgNSHrIuGPkedooPrmxxg+Rusti9S2Y/JiQSg0EiFvTxM5Rp3g0ut 0Hb85liDzpY5aZ4gMBBlSnfnOKOw+OjVF0FSvMwWoIoAJlE/vftxjTbV4ks7uqJL0chI8 eWQrM/Ctc6cO0f5vjzwnuwUJC2NED7xU/1Fx5/agUyxAOKY/fju0/+OxxHAr53vY5Dm10 DNgX9kbJ5g4cgYQ8iGnOWZ94ntI0BMlvV0valY48xP7K+XukrLMck+7MnVue2mxgoTA== ARC-Authentication-Results: i=1; smtp.subspace.kernel.org; dmarc=pass header.from=amazon.it; spf=pass smtp.mailfrom=amazon.it; dkim=pass header.d=amazon.it header.i=@amazon.it header.a=rsa-sha256 header.s=amazoncorp2 header.b=n+AmwGCd; arc=none smtp.remote-ip=52.34.181.151 Received: from pdx-out-007.esa.us-west-2.outbound.mail-perimeter.amazon.com (pdx-out-007.esa.us-west-2.outbound.mail-perimeter.amazon.com [52.34.181.151]) (using TLSv1.2 with cipher ECDHE-ECDSA-AES256-GCM-SHA384 (256/256 bits)) (No client certificate requested) by smtp.subspace.kernel.org (Postfix) with ESMTPS id A7D7C606A331 for ; Fri, 13 Nov 2026 11:03:22 +0000 (UTC) DMARC-Filter: OpenDMARC Filter v1.4.2 smtp.subspace.kernel.org A7D7C606A331 Authentication-Results: smtp.subspace.kernel.org; dmarc=pass (p=quarantine dis=none) header.from=amazon.it Authentication-Results: smtp.subspace.kernel.org; spf=pass smtp.mailfrom=amazon.it Authentication-Results: smtp.subspace.kernel.org; dkim=pass (2048-bit key, unprotected) header.d=amazon.it header.i=@amazon.it header.a=rsa-sha256 header.s=amazoncorp2 header.b=n+AmwGCd DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=amazon.it; i=@amazon.it; q=dns/txt; s=amazoncorp2; t=1794567802; x=1826103802; h=from:to:cc:subject:date:message-id:in-reply-to: references:mime-version:content-transfer-encoding; bh=LBrctbWCr0zoW4q3CpOYQqWzbyJ/Y4Bqv54BvH7JL1M=; b=n+AmwGCdfrRdqCE6DtuczUps7PXOxLr5lKZOHL9SSj5yE+urGHhcYgxA 2Us+UI79uVge1mZBXA2MHp3+PB4+He9ShxfUFXoqhFHA1zjSGHBlSHpJf OwZDTAMGBRdTYosdhdVEIhg40KEE2EzMtnwt1bd7wHJlPQTSrBu2wZ5qo px3TXqiiUEsvK4e4bl5gzHkk3oKSwVDjVeiIpskf6x3Y+eXGgxQIKow5z k9hZ4Mrcj05r8XNCebv2u1Xc6akkp0dATGJEmX5bEgBw5o83tVl8kIGA7 Uk+s3CYr+MWLe+Vdj4YBSHHhLDafBXD6smKQHZ5+V1YImtm4+s1Ppx5fG g==; X-CSE-ConnectionGUID: dzx5j+V7SlyOc5phpvLg1w== X-CSE-MsgGUID: CJlgEYTrQ3GbNQnddhx25A== X-IronPort-AV: E=Sophos;i="6.27,211,1787011200"; d="scan'208";a="33872378" Received: from ip-10-5-0-115.us-west-2.compute.internal (HELO smtpout.naws.us-west-2.prod.farcaster.email.amazon.dev) ([10.5.0.115]) by internal-pdx-out-007.esa.us-west-2.outbound.mail-perimeter.amazon.com with ESMTP/TLS/ECDHE-RSA-AES256-GCM-SHA384; 13 Nov 2026 11:03:19 +0000 Received: from EX19MTAUWC002.ant.amazon.com [205.251.233.111:17871] by smtpin.naws.us-west-2.prod.farcaster.email.amazon.dev [10.0.55.227:2525] with esmtp (Farcaster) id fd0d30c5-6cbb-42e5-b507-e181ed6e2226; Fri, 13 Nov 2026 11:03:19 +0000 (UTC) X-Farcaster-Flow-ID: fd0d30c5-6cbb-42e5-b507-e181ed6e2226 Received: from EX19D001UWA001.ant.amazon.com (10.13.138.214) by EX19MTAUWC002.ant.amazon.com (10.250.64.143) with Microsoft SMTP Server (version=TLS1_2, cipher=TLS_ECDHE_RSA_WITH_AES_128_CBC_SHA) id 15.2.2562.56; Fri, 13 Nov 2026 11:03:18 +0000 Received: from dev-dsk-dipiets-1b-77b833da.eu-west-1.amazon.com (10.253.66.177) by EX19D001UWA001.ant.amazon.com (10.13.138.214) with Microsoft SMTP Server (version=TLS1_2, cipher=TLS_ECDHE_RSA_WITH_AES_128_CBC_SHA) id 15.2.2562.56; Fri, 13 Nov 2026 11:03:17 +0000 From: Salvatore Dipietro To: CC: , Andrew Morton , Vlastimil Babka , Johannes Weiner , Subject: [PATCH 6.18.y 3/3] mm/page_alloc: avoid direct reclaim and compaction for costly __GFP_NORETRY allocations Date: Fri, 13 Nov 2026 11:02:59 +0000 Message-ID: <20261113110259.2901456-4-dipiets@amazon.it> X-Mailer: git-send-email 2.50.1 In-Reply-To: <20261113110259.2901456-1-dipiets@amazon.it> References: <20261113110259.2901456-1-dipiets@amazon.it> X-Mailing-List: stable@vger.kernel.org List-Id: List-Post: List-Help: List-Subscribe: List-Unsubscribe: List-Owner: Precedence: list MIME-Version: 1.0 X-ClientProxiedBy: EX19D031UWC001.ant.amazon.com (10.13.139.241) To EX19D001UWA001.ant.amazon.com (10.13.138.214) Content-Type: text/plain; charset="us-ascii" Content-Transfer-Encoding: 7bit [ Upstream commit 0e05a469c29400eb6e35448ce7318581688a1806 ] 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: "Garg, Shivank" [ Salvatore: backport to 6.18.y: can_direct_reclaim is initialised at its declaration here, so assign it after clearing __GFP_DIRECT_RECLAIM. Dropped the defrag_mode hunk: it targets 4c0ed883e051 ("mm/page_alloc: fix defrag_mode for non-reclaimable allocations"), which is not in this tree, and without it the !can_direct_reclaim bailout already fails instead of fragmenting. ] --- mm/page_alloc.c | 12 +++++++++++- 1 file changed, 11 insertions(+), 1 deletion(-) diff --git a/mm/page_alloc.c b/mm/page_alloc.c index fced085ae4a4..3cc4ccb722fe 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -4733,7 +4733,7 @@ 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_direct_reclaim; bool can_compact = gfp_compaction_allowed(gfp_mask); bool nofail = gfp_mask & __GFP_NOFAIL; const bool costly_order = order > PAGE_ALLOC_COSTLY_ORDER; @@ -4748,6 +4748,16 @@ __alloc_pages_slowpath(gfp_t gfp_mask, unsigned int order, unsigned int zonelist_iter_cookie; int reserve_flags; + /* + * 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; + if (unlikely(nofail)) { /* * We most definitely don't want callers attempting to -- 2.50.1 AMAZON DEVELOPMENT CENTER ITALY SRL, viale Monte Grappa 3/5, 20124 Milano, Italia, Registro delle Imprese di Milano Monza Brianza Lodi REA n. 2504859, Capitale Sociale: 10.000 EUR i.v., Cod. Fisc. e P.IVA 10100050961, Societa con Socio Unico