From mboxrd@z Thu Jan 1 00:00:00 1970 Authentication-Results: smtp.subspace.kernel.org; arc=none smtp.remote-ip=100.103.45.18 ARC-Seal: i=1; d=subspace.kernel.org; s=arc20261015; a=rsa-sha256; cv=none; t=1794693544; b=cwkJCnDlQ0btxiDvbsg/r3KYQEI483m07BgdsRT1s82a0cZr+0fmStCl1AJpHHJWyake SM0Hwu9o7FjUIJBHGm6tLZLiDDbLMYsMx8iQQ+9y/5ify6zYoKxDAEwWIDrQ4dD+eFin6 8eWk8J/M73cJrdp4/7AsmeBVlqFqMy5hoFmbi6/34N3wEvcSp6DPZTIfNNRxPlCXfSO7M 7W9n3iZWCS0CpuATvY/dXyPHqips81ct8aI8plU4Yh2gNe114fKm6MEk8CB5l16jCf6j/ QjeQjD3unO1UM7C8zmVioB/wKE+QIcrH8mK5OdDWnLavza0EsoibS2kYsHxcTSaG5iw== ARC-Message-Signature: i=1; d=subspace.kernel.org; s=arc20261015; a=rsa-sha256; c=relaxed/relaxed; t=1794693544; h=Received:DKIM-Signature:Date:To:From:Subject:Message-Id; bh=NQ/4aKLJpsGdnJW7yki1N5slGMs9Hm086N/fsBOIXF4=; b=Z83mSeDT01ModCdfuUvyGI0M7k/TA3kqkcawjX9ifq3dP3pmqVMKCE5qyRBTAteyPl9S 8pZzxJUoQYrlT3l3mjUP3I+KHfY+8JWDqnw/HVAdVOsm/VESVIIjrXfXZKmvao5IZUqPG yBZSCuG8ejzj17egpmIQIfe6BWuu+mtkf1LV2B89sA+xou8i5KaMmn/1DUiww0ZEJv4aZ SHaGdO9ee6fPWCyvjWokyylpsaWsdpLnZDE92OEWFmz5Q+qYy+xEHhCEuce2q1lXeLIEX lArBrKn9lLimX5O6TJDa6hcEZSHyufgEv1mT+4dO7ahSpPvopJNw1Zte8rsAnQDJEpg== ARC-Authentication-Results: i=1; smtp.subspace.kernel.org; dkim=pass header.d=linux-foundation.org header.i=@linux-foundation.org header.a=rsa-sha256 header.s=korg header.b=QPDWUCOs; arc=none smtp.remote-ip=100.103.45.18 Received: from smtp.kernel.org (quasi.space.kernel.org [100.103.45.18]) (using TLSv1.3 with cipher TLS_AES_256_GCM_SHA384 (256/256 bits) key-exchange X25519 server-signature ECDSA (prime256v1)) (No client certificate requested) by smtp.subspace.kernel.org (Postfix) with ESMTPS id 23705606A323 for ; Sat, 14 Nov 2026 21:59:03 +0000 (UTC) Authentication-Results: smtp.subspace.kernel.org; dkim=pass (1024-bit key, unprotected) header.d=linux-foundation.org header.i=@linux-foundation.org header.a=rsa-sha256 header.s=korg header.b=QPDWUCOs Received: by smtp.kernel.org (Postfix) with ESMTPSA id B37651F000C4; Sat, 14 Nov 2026 21:59:03 +0000 (UTC) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=linux-foundation.org; s=korg; t=1794693543; bh=NQ/4aKLJpsGdnJW7yki1N5slGMs9Hm086N/fsBOIXF4=; h=Date:To:From:Subject; b=QPDWUCOsmz1iVd9HNoZg0rSrhXmyxsB4nP3dkCrWMwHdaraqdPoMC249weAAEsdas 44Pgy4sXMBAPGGyjcOV5E6VDPaf4fWi0GbaTaoE76E9Fy68zsAUo/IblMcFGwh7tYw Dce6rexUOHBJ7+6gg12F1iIegSjqZxuWnABH8YN4= Date: Sat, 14 Nov 2026 13:59:03 -0800 To: mm-commits@vger.kernel.org,kasong@tencent.com,akpm@linux-foundation.org From: Andrew Morton Subject: [to-be-updated] mm-mglru-report-evictable-sizes-per-type.patch removed from -mm tree Message-Id: <20261114215903.B37651F000C4@smtp.kernel.org> X-Mailing-List: mm-commits@vger.kernel.org List-Id: List-Post: List-Help: List-Subscribe: List-Unsubscribe: List-Owner: Precedence: list The quilt patch titled Subject: mm/mglru: report evictable sizes per type has been removed from the -mm tree. Its filename was mm-mglru-report-evictable-sizes-per-type.patch This patch was dropped because an updated version will be issued ------------------------------------------------------ From: Kairui Song Subject: mm/mglru: report evictable sizes per type Date: Sat, 14 Nov 2026 02:55:26 +0800 Patch series "mm: mglru: fix swappiness behavior", v8. Classic LRU respects swappiness, while MGLRU only weakly honors it when selecting the scan type. The fallback logic can easily override the bias established by get_type_to_scan(). As a result, swappiness has a much smaller overall impact when changing from 1 to 200, as shown by the data presented later in this cover letter. In this patchset, patches 1-8 from Kairui introduce a model that uses refaults to determine nr_to_scan[] for both file and anon in MGLRU. For each reclaim operation, we calculate how many file and anon folios to scan, similar to CLRU, rather than relying on get_type_to_scan() and fallback mechanisms to decide what to reclaim, which have proven rather unreliable in honoring swappiness. This model also allows scanning and reclaiming from the two youngest generations, including the youngest generation itself. This can help resolve OOM situations[1] and reduce the need for aging. As Kairui mentioned, the OOM reproducer was demonstrated previously [2], and that series was merged in v7 [3]. The problem was largely alleviated as described, but not completely fixed. Under higher memory pressure, the system could still hit OOM. Before this series, Kairui could still reproduce OOM after hundreds of iterations. With the fixing patch in this series applied, the problem no longer occurs. Patch 9 from Barry fixes a cold/hot inversion exacerbated by patches 1–8 (which also exists in mainline) and improves reclaim efficiency. Patches 10-15 from Gaofei and Barry optimize aging based on folio distribution imbalance and improve reclaim behavior at extreme swappiness values such as 1 and 200. Patch 16 from Bo Zhang addresses the GFP_NOIO issue in MGLRU. After the patchset, the results track CLRU across the full swappiness range (see table below), with more file scanning at low swappiness and more anon scanning at high swappiness. pgsteal_file swappiness CLRU MGLRU MGLRU+patches 1 6,620,680 745,968 6,190,575 36 807,807 508,974 525,304 71 553,144 417,700 405,545 106 402,880 402,474 348,365 141 240,293 337,797 305,170 176 187,682 330,045 231,038 200 0 343,949 256 pgsteal_anon swappiness CLRU MGLRU MGLRU+patches 1 4,436,199 2,671,934 5,103,813 36 2,858,117 3,032,747 3,134,511 71 3,042,392 2,827,735 3,170,171 106 3,292,622 3,184,314 3,225,293 141 3,612,869 2,999,000 3,590,478 176 3,827,154 3,134,127 3,873,163 200 13,825,283 3,269,753 14,399,074 pgscan_file swappiness CLRU MGLRU MGLRU+patches 1 11,853,625 877,311 12,715,103 36 1,016,826 582,783 612,867 71 662,823 474,772 443,149 106 496,374 451,285 364,203 141 277,109 382,604 327,444 176 206,261 372,059 236,838 200 0 393,608 256 pgscan_anon swappiness CLRU MGLRU MGLRU+patches 1 20,804,386 5,847,747 7,142,640 36 17,830,330 6,740,075 6,297,912 71 18,357,293 6,126,194 7,046,149 106 19,938,920 6,431,355 7,876,121 141 19,609,579 5,997,762 9,672,762 176 21,612,749 6,071,032 11,195,357 200 44,776,474 6,544,125 30,225,030 refault_file swappiness CLRU MGLRU MGLRU+patches 1 6,523,070 667,302 6,103,539 36 722,110 431,585 448,161 71 477,062 340,241 331,108 106 327,610 324,747 272,266 141 161,827 265,959 228,015 176 115,551 258,515 172,882 200 0 268,049 212 refault_anon swappiness CLRU MGLRU MGLRU+patches 1 867,728 552,829 1,415,594 36 419,635 657,745 668,238 71 536,299 611,345 672,096 106 580,742 693,689 728,319 141 706,151 639,850 817,954 176 706,499 685,086 949,643 200 4,693,850 733,273 5,475,622 With a normal swappiness setting (without extreme bias), I see almost no noticeable performance difference between the two versions. For example, with `swappiness=60`, the average results over 5 rounds are: metric W/o patch W/ patch real 1m49.273s 1m49.051s user 25m33.186s 25m31.778s sys 3m41.851s 3m40.721s This patch (of 16): Change lruvec_evictable_size() to return the number of evictable anonymous and file pages separately instead of a single total, so that callers can weigh the two types independently. Update lruvec_is_sizable() and get_nr_to_scan() accordingly; the summed totals are unchanged, so there is no functional change. Link: https://lore.kernel.org/20261113185541.70203-1-baohua@kernel.org Link: https://lore.kernel.org/20261113185541.70203-2-baohua@kernel.org Link: https://github.com/ryncsn/emm-test-project/tree/master/file-anon-mix-pressure [1] Link: https://lore.kernel.org/all/20260318-mglru-reclaim-v1-0-2c46f9eb0508@tencent.com/ [2] Link: https://lore.kernel.org/linux-mm/20260428-mglru-reclaim-v7-0-02fabb92dc43@tencent.com/ [3] Signed-off-by: Kairui Song Signed-off-by: Barry Song (Xiaomi) Signed-off-by: Andrew Morton Reviewed-by: Kunwu Chan Reviewed-by: Baolin Wang Cc: Axel Rasmussen Cc: Baoquan He Cc: Johannes Weiner Cc: Cc: Liam R. Howlett Cc: wang lian Cc: Cc: Cc: Michal Hocko Cc: Qi Zheng Cc: Ridong Chen Cc: Mike Rapoport Cc: Kairui Song Cc: Shakeel Butt Cc: Suren Baghdasaryan Cc: wangzicheng Cc: Wei Xu Cc: Yuanchu Xie Cc: Bo Zhang Cc: Hui Zhu Cc: Siddharth Chintamaneni Cc: Kunwu Chan Cc: Bo Zhang --- mm/vmscan.c | 22 +++++++++++++--------- 1 file changed, 13 insertions(+), 9 deletions(-) --- a/mm/vmscan.c~mm-mglru-report-evictable-sizes-per-type +++ a/mm/vmscan.c @@ -4193,28 +4193,31 @@ static void set_initial_priority(struct sc->priority = clamp(priority, DEF_PRIORITY / 2, DEF_PRIORITY); } -static unsigned long lruvec_evictable_size(struct lruvec *lruvec, int swappiness) +static void lruvec_evictable_size(struct lruvec *lruvec, int swappiness, + unsigned long nr[]) { int type; - unsigned long seq, total = 0; + unsigned long seq; struct lru_gen_folio *lrugen = &lruvec->lrugen; DEFINE_MAX_SEQ(lruvec); DEFINE_MIN_SEQ(lruvec); + nr[LRU_GEN_ANON] = 0; + nr[LRU_GEN_FILE] = 0; + for_each_evictable_type(type, swappiness) { for (seq = min_seq[type]; seq <= max_seq; seq++) - total += lruvec_gen_size(lrugen, type, seq); + nr[type] += lruvec_gen_size(lrugen, type, seq); } - - return total; } static bool lruvec_is_sizable(struct lruvec *lruvec, struct scan_control *sc) { - unsigned long total; + unsigned long total, sizes[ANON_AND_FILE]; int swappiness = get_swappiness(lruvec, sc); - total = lruvec_evictable_size(lruvec, swappiness); + lruvec_evictable_size(lruvec, swappiness, sizes); + total = sizes[LRU_GEN_ANON] + sizes[LRU_GEN_FILE]; /* whether the size is big enough to be helpful */ return total >> sc->priority; @@ -5028,7 +5031,7 @@ static bool should_run_aging(struct lruv static long get_nr_to_scan(struct lruvec *lruvec, struct scan_control *sc, struct mem_cgroup *memcg, int swappiness) { - unsigned long nr_to_scan, evictable; + unsigned long nr_to_scan, evictable, sizes[ANON_AND_FILE]; struct pglist_data *pgdat = lruvec_pgdat(lruvec); /* @@ -5044,7 +5047,8 @@ static long get_nr_to_scan(struct lruvec return 0; } - evictable = lruvec_evictable_size(lruvec, swappiness); + lruvec_evictable_size(lruvec, swappiness, sizes); + evictable = sizes[LRU_GEN_ANON] + sizes[LRU_GEN_FILE]; nr_to_scan = apply_proportional_protection(memcg, sc, evictable); nr_to_scan >>= sc->priority; _ Patches currently in -mm which might be from kasong@tencent.com are mm-mglru-extract-lruvec_populated_min_seq-helper.patch mm-mglru-reclaim-from-the-oldest-populated-gen.patch mm-mglru-lift-the-forced-protection-of-reclaimer.patch mm-mglru-skip-zones-above-reclaim_idx-instead-of-rotating-them.patch mm-mglru-return-for-unavailable-anon-reclaim-earlier.patch mm-mglru-balance-anon-and-file-scan-budget-by-refault-rate.patch mm-mglru-lift-youngest-gen-protection-for-higher-priority.patch