From mboxrd@z Thu Jan 1 00:00:00 1970 Received: from stravinsky.debian.org (stravinsky.debian.org [82.195.75.108]) (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 88A563D1A9A; Fri, 15 May 2026 10:29:01 +0000 (UTC) Authentication-Results: smtp.subspace.kernel.org; arc=none smtp.client-ip=82.195.75.108 ARC-Seal:i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1778840943; cv=none; b=GyUohQNJeHWoVIsY+ZUBs7o/cbjGhv2djhlO72aP/eEVFblUfPg+RaWHAtuAtoLZuDVBw7iQtkqfa4sTwZoLXtCvrSHjZstKbS/k4chvmc4O+63BkSQLnpb5RqNqtvd/ZYPpBN9W5HTlft0RMk6Lg/U3Yva5DeSWTcqqKCzrvYU= ARC-Message-Signature:i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1778840943; c=relaxed/simple; bh=q2o9jgSNyuYPzly0nCT/XLRu8nBus4GRiO8EciABiP8=; h=From:Subject:Date:Message-Id:MIME-Version:Content-Type:To:Cc; b=AfKrEU2WFmYuYO9fJRiwEoSTDYuMeaTEx9rQerL5rLCeKXj8C0d1RzlH8ww7vNyiOfKDp4ZvQNEBstd+nWlEvA6+mwxrN3IsHFm7q9q4EFtpxgeD+B5WNZ7497w9p3FNGHUQfM7Ol1dIRC/eFedIDz069TvTad9yvrCo0UFnthw= ARC-Authentication-Results:i=1; smtp.subspace.kernel.org; dmarc=pass (p=none dis=none) header.from=debian.org; spf=pass smtp.mailfrom=debian.org; dkim=pass (2048-bit key) header.d=debian.org header.i=@debian.org header.b=iRnpxd+T; arc=none smtp.client-ip=82.195.75.108 Authentication-Results: smtp.subspace.kernel.org; dmarc=pass (p=none dis=none) header.from=debian.org Authentication-Results: smtp.subspace.kernel.org; spf=pass smtp.mailfrom=debian.org Authentication-Results: smtp.subspace.kernel.org; dkim=pass (2048-bit key) header.d=debian.org header.i=@debian.org header.b="iRnpxd+T" DKIM-Signature: v=1; a=rsa-sha256; q=dns/txt; c=relaxed/relaxed; d=debian.org; s=smtpauto.stravinsky; h=X-Debian-User:Cc:To:Content-Transfer-Encoding: Content-Type:MIME-Version:Message-Id:Date:Subject:From:Reply-To:Content-ID: Content-Description:In-Reply-To:References; bh=L/nYxV95FX7ES4SL/Qq7xlGA3XClDJwVpRV4zHEUrE0=; b=iRnpxd+TdBoKW3vZBf9UU1Rctg AvA6UVzdBPvMOP99c+peTc/by3iSheTQfcV9H8pgIDtTOXTQT34UEbRUv1qt1a3mtfECrmGNeXZ3O g+IdL5/xhHRsctpV6H+nixGv3oohy+2Ks0xysOI+D0GvdCRV0qQtWNcOu0o+pbW84C9GWZxclxzTX sUGrWzqu+YHTSoD+a7B768bcHGrr2C+gDdjmOBvXaewxULzCih8u9fj1IpDJztEL7LzPEVEungy+a CxUG60KLMNYxZJih5OIMX8OXze1dzbhGG6FFRoEP8C1R+RtNU2owl54Kf4ExVS7u+hTJCywMLaO8K N3LDnJNA==; Received: from authenticated user by stravinsky.debian.org with esmtpsa (TLS1.3:ECDHE_X25519__RSA_PSS_RSAE_SHA256__AES_256_GCM:256) (Exim 4.96) (envelope-from ) id 1wNpmp-004fTS-13; Fri, 15 May 2026 10:28:56 +0000 From: Breno Leitao Subject: [PATCH 0/2] fs/pipe: reduce pipe->mutex contention by bulk-allocating outside the lock Date: Fri, 15 May 2026 03:28:43 -0700 Message-Id: <20260515-fix_pipe-v1-0-b14c840c7555@debian.org> Precedence: bulk X-Mailing-List: linux-kernel@vger.kernel.org List-Id: List-Subscribe: List-Unsubscribe: MIME-Version: 1.0 Content-Type: text/plain; charset="utf-8" Content-Transfer-Encoding: 7bit X-B4-Tracking: v=1; b=H4sIAFz1BmoC/yXMQQqDMBBG4asM/9pAImhqriIibTq240JDoiUQc vdSu3yL7xUkjsIJjgoifyTJvsGRaQj+fd9erOQJR2h12+vOdGqRPAcJrPxgemu9uVm2aAgh8iL 5Wo3Tv9P5WNkfP49av4XLYolsAAAA X-Change-ID: 20260515-fix_pipe-c91677c187e7 To: Alexander Viro , Christian Brauner , Jan Kara , Shuah Khan Cc: linux-fsdevel@vger.kernel.org, linux-kernel@vger.kernel.org, linux-kselftest@vger.kernel.org, Breno Leitao , usama.arif@linux.dev, kernel-team@meta.com X-Mailer: b4 0.16-dev-d5d98 X-Developer-Signature: v=1; a=openpgp-sha256; l=4165; i=leitao@debian.org; h=from:subject:message-id; bh=q2o9jgSNyuYPzly0nCT/XLRu8nBus4GRiO8EciABiP8=; b=owEBbQKS/ZANAwAIATWjk5/8eHdtAcsmYgBqBvVixZflaGpM36w7fVPS2wgS53pKnlLbstfSZ nIUfeYc512JAjMEAAEIAB0WIQSshTmm6PRnAspKQ5s1o5Of/Hh3bQUCagb1YgAKCRA1o5Of/Hh3 bWVdD/9U7suOdLRHi2NK2+jhadxzdjKCc2V3e5NHz/VUQxbQcIpoD9Us4l+gQtiqRYSJpVQ6hRR hy/niqZ3TFYUAz89IXIVZ2R3np8QtlZ1Y8TPQy2dosyB9ABBDfTPWHT7t+kzcUR9ZMUASR80aj2 CggD2968vouqJyxl1kgJURC0wFGXFJp9lFi1PVbeLHQDBdw69QRvIf/haFs2Esu6MQ5LHpI0gLW OBPU4LIBicvq+fKYjB9AvPQFHqsiUl35uAvXD6UkxjxD1TrICTOlvv3iKN6oia8ZTj9C0pyrKyq yaqmIepHkzh/3w1IlQw+fxjE+U4EW5UdSPpQTQE6bT/lTBQxPPNhPQ95mWWp6tf0IR4xl+gS/X/ ffHXtizjTEHUUc916JqhQhjxChFQNI7EzYTcavB+SVegIxMG7tzVMLPgFpc3/I+513iIYwt7Gc9 QP2S2z3hAe7qRYhrMvjKspNMU9Vy0rXZeQoNhaoH3zRgtbnRrrihIX3a4LnLAgx6VULmAFx59sr xhIzFQJVjFGpUqR+m97KN9C/qDCPEgnuOE/4e9Ao7bQPBNLmZaQa9ToJruVnoH0smgDnmtETvWD p7PmLM7cWtWuJYHwuh20FZ0e37yPuMxe5jeePJyy792CLNWhyiDJVNn3624/OAtbYo+dF9MWssa 0APOGcRpT2LXLfA== X-Developer-Key: i=leitao@debian.org; a=openpgp; fpr=AC8539A6E8F46702CA4A439B35A3939FFC78776D X-Debian-User: leitao While profiling kernel code on Meta's caching code[1], I found some lock contention on pipe hot path, and I decide to investigate, and found that anon_pipe_write() currently calls alloc_page() once per page while holding pipe->mutex. The allocation can sleep doing direct reclaim and runs memcg charging, which extends the critical section and stalls any concurrent reader on the same mutex. I would like to propose that we bulk pre-allocate pages outside pipe->mutex in anon_pipe_write -- pre-allocates up to PIPE_PREALLOC_MAX (8) pages with alloc_pages_bulk() before taking the lock * the get-page helper then consumes from tmp_page[] / the prealloc array first and only falls back to in-lock alloc_page() for writes larger than PIPE_PREALLOC_MAX (8) pages, which is rare. I also vibe coded a microbenchmark to test the pipe benchmark. Basically it wweeps writers x readers over {1,2,5} x {1,5,10} with 64KB writes against a 1 MB pipe and prints throughput + latency percentiles per config. Measured on arm64 in virtme-ng (16 vCPUs, 64KB writes, 1 MB pipe). == No memory pressure (10s per config) == Throughput in MB/s (baseline -> patched, delta): writers readers=1 readers=5 readers=10 1 1119 -> 1354 (+21%) 1132 -> 1195 (+6%) 1060 -> 1240 (+17%) 2 1162 -> 1487 (+28%) 1034 -> 1285 (+24%) 1069 -> 1213 (+14%) 5 1152 -> 1357 (+18%) 1021 -> 1164 (+14%) 997 -> 1239 (+24%) Avg write latency in ns (baseline -> patched, delta): writers readers=1 readers=5 readers=10 1 55786 -> 46103 (-17%) 55164 -> 52260 (-5%) 58906 -> 50370 (-14%) 2 107546 -> 84011 (-22%) 120837 -> 97206 (-20%) 116860 -> 103036 (-12%) 5 271293 -> 230170 (-15%) 306089 -> 268429 (-12%) 313300 -> 252232 (-19%) Throughput improves +6% to +28% and average write latency drops 5% to 22% across every configuration. == Under memory pressure (--memory-pressure, 6s per config) == stress-ng --vm 2 --vm-bytes 50% --vm-keep is forked alongside the sweep so the alloc_page() calls inside anon_pipe_write() routinely hit direct reclaim -- exactly the regime the patch targets. Throughput in MB/s (baseline -> patched, delta): writers readers=1 readers=5 readers=10 1 1088 -> 1438 (+32%) 996 -> 1477 (+48%) 989 -> 1194 (+21%) 2 1076 -> 1378 (+28%) 1007 -> 1269 (+26%) 1018 -> 1234 (+21%) 5 1052 -> 1311 (+25%) 986 -> 1225 (+24%) 972 -> 1249 (+29%) Avg write latency in ns (baseline -> patched, delta): writers readers=1 readers=5 readers=10 1 57397 -> 43406 (-24%) 62690 -> 42272 (-33%) 63136 -> 52272 (-17%) 2 116121 -> 90700 (-22%) 124098 -> 98481 (-21%) 122754 -> 101217 (-18%) 5 297122 -> 238322 (-20%) 316836 -> 255095 (-19%) 321496 -> 250189 (-22%) Throughput improves +21% to +48% and average write latency drops 17% to 33% -- a noticeably bigger win than the no-pressure run. That tracks: when alloc_page() has to dip into reclaim, the cost of holding pipe->mutex across it is highest, and pulling the allocation out of the critical section pays the most. Link: https://www.usenix.org/system/files/conference/atc13/atc13-bronson.pdf [1] Signed-off-by: Breno Leitao --- Breno Leitao (2): fs/pipe: bulk pre-allocate pages outside pipe->mutex in anon_pipe_write selftests/pipe: add pipe_bench microbenchmark fs/pipe.c | 40 +++- tools/testing/selftests/Makefile | 1 + tools/testing/selftests/pipe/.gitignore | 1 + tools/testing/selftests/pipe/Makefile | 9 + tools/testing/selftests/pipe/pipe_bench.c | 351 ++++++++++++++++++++++++++++++ 5 files changed, 400 insertions(+), 2 deletions(-) --- base-commit: e98d21c170b01ddef366f023bbfcf6b31509fa83 change-id: 20260515-fix_pipe-c91677c187e7 Best regards, -- Breno Leitao