On Thu, Dec 5, 2024 at 8:19 AM liuye <liuye@xxxxxxxxxx> wrote: > > > Friendly ping. > > Thanks. Hugh has responded on your "v2 RESEND": https://lore.kernel.org/linux-mm/dae8ea77-2bc1-8ee9-b94b-207e2c8e1b8d@xxxxxxxxxx/ > On 2024/9/6 上午9:16, liuye wrote: > > > > > > On 2024/8/23 上午10:04, liuye wrote: > >> I'm sorry to bother you about that, but it looks like the following email send 7 days ago, > >> did not receive a response from you. Do you mind having a look at this > >> when you have a bit of free time please? > >> > >>>>> Fixes: b2e18757f2c9 ("mm, vmscan: begin reclaiming pages on a per-node basis") > >>>> > >>>> Merged in 2016. > >>>> > >>>> Under what circumstances does it occur? > >>> > >>> User processe are requesting a large amount of memory and keep page active. > >>> Then a module continuously requests memory from ZONE_DMA32 area. > >>> Memory reclaim will be triggered due to ZONE_DMA32 watermark alarm reached. > >>> However pages in the LRU(active_anon) list are mostly from > >>> the ZONE_NORMAL area. > >>> > >>>> Can you please describe how to reproduce this? > >>> > >>> Terminal 1: Construct to continuously increase pages active(anon). > >>> mkdir /tmp/memory > >>> mount -t tmpfs -o size=1024000M tmpfs /tmp/memory > >>> dd if=/dev/zero of=/tmp/memory/block bs=4M > >>> tail /tmp/memory/block > >>> > >>> Terminal 2: > >>> vmstat -a 1 > >>> active will increase. > >>> procs -----------memory---------- ---swap-- -----io---- -system-- -------cpu------- > >>> r b swpd free inact active si so bi bo in cs us sy id wa st gu > >>> 1 0 0 1445623076 45898836 83646008 0 0 0 0 1807 1682 0 0 100 0 0 0 > >>> 1 0 0 1445623076 43450228 86094616 0 0 0 0 1677 1468 0 0 100 0 0 0 > >>> 1 0 0 1445623076 41003480 88541364 0 0 0 0 1985 2022 0 0 100 0 0 0 > >>> 1 0 0 1445623076 38557088 90987756 0 0 0 4 1731 1544 0 0 100 0 0 0 > >>> 1 0 0 1445623076 36109688 93435156 0 0 0 0 1755 1501 0 0 100 0 0 0 > >>> 1 0 0 1445619552 33663256 95881632 0 0 0 0 2015 1678 0 0 100 0 0 0 > >>> 1 0 0 1445619804 31217140 98327792 0 0 0 0 2058 2212 0 0 100 0 0 0 > >>> 1 0 0 1445619804 28769988 100774944 0 0 0 0 1729 1585 0 0 100 0 0 0 > >>> 1 0 0 1445619804 26322348 103222584 0 0 0 0 1774 1575 0 0 100 0 0 0 > >>> 1 0 0 1445619804 23875592 105669340 0 0 0 4 1738 1604 0 0 100 0 0 0 > >>> > >>> cat /proc/meminfo | head > >>> Active(anon) increase. > >>> MemTotal: 1579941036 kB > >>> MemFree: 1445618500 kB > >>> MemAvailable: 1453013224 kB > >>> Buffers: 6516 kB > >>> Cached: 128653956 kB > >>> SwapCached: 0 kB > >>> Active: 118110812 kB > >>> Inactive: 11436620 kB > >>> Active(anon): 115345744 kB > >>> Inactive(anon): 945292 kB > >>> > >>> When the Active(anon) is 115345744 kB, insmod module triggers the ZONE_DMA32 watermark. > >>> > >>> perf show nr_scanned=28835844. > >>> 28835844 * 4k = 115343376KB approximately equal to 115345744 kB. > >>> > >>> perf record -e vmscan:mm_vmscan_lru_isolate -aR > >>> perf script > >>> isolate_mode=0 classzone=1 order=1 nr_requested=32 nr_scanned=2 nr_skipped=2 nr_taken=0 lru=active_anon > >>> isolate_mode=0 classzone=1 order=1 nr_requested=32 nr_scanned=0 nr_skipped=0 nr_taken=0 lru=active_anon > >>> isolate_mode=0 classzone=1 order=0 nr_requested=32 nr_scanned=28835844 nr_skipped=28835844 nr_taken=0 lru=active_anon > >>> isolate_mode=0 classzone=1 order=1 nr_requested=32 nr_scanned=28835844 nr_skipped=28835844 nr_taken=0 lru=active_anon > >>> isolate_mode=0 classzone=1 order=0 nr_requested=32 nr_scanned=29 nr_skipped=29 nr_taken=0 lru=active_anon > >>> isolate_mode=0 classzone=1 order=0 nr_requested=32 nr_scanned=0 nr_skipped=0 nr_taken=0 lru=active_anon > >>> > >>> If increase Active(anon) to 1000G then insmod module triggers the ZONE_DMA32 watermark. hard lockup will occur. > >>> > >>> In my device nr_scanned = 0000000003e3e937 when hard lockup. Convert to memory size 0x0000000003e3e937 * 4KB = 261072092 KB. > >>> > >>> #5 [ffffc90006fb7c28] isolate_lru_folios at ffffffffa597df53 > >>> ffffc90006fb7c30: 0000000000000020 0000000000000000 > >>> ffffc90006fb7c40: ffffc90006fb7d40 ffff88812cbd3000 > >>> ffffc90006fb7c50: ffffc90006fb7d30 0000000106fb7de8 > >>> ffffc90006fb7c60: ffffea04a2197008 ffffea0006ed4a48 > >>> ffffc90006fb7c70: 0000000000000000 0000000000000000 > >>> ffffc90006fb7c80: 0000000000000000 0000000000000000 > >>> ffffc90006fb7c90: 0000000000000000 0000000000000000 > >>> ffffc90006fb7ca0: 0000000000000000 0000000003e3e937 > >>> ffffc90006fb7cb0: 0000000000000000 0000000000000000 > >>> ffffc90006fb7cc0: 8d7c0b56b7874b00 ffff88812cbd3000 > >>> > >>>> Why do you think it took eight years to be discovered? > >>> > >>> The problem requires the following conditions to occur: > >>> 1. The device memory should be large enough. > >>> 2. Pages in the LRU(active_anon) list are mostly from the ZONE_NORMAL area. > >>> 3. The memory in ZONE_DMA32 needs to reach the watermark. > >>> > >>> If the memory is not large enough, or if the usage design of ZONE_DMA32 area memory is reasonable, this problem is difficult to detect. > >>> > >>> notes: > >>> The problem is most likely to occur in ZONE_DMA32 and ZONE_NORMAL, but other suitable scenarios may also trigger the problem. > >>> > >>>> It looks like that will fix, but perhaps something more fundamental > >>>> needs to be done - we're doing a tremendous amount of pretty pointless > >>>> work here. Answers to my above questions will help us resolve this. > >>>> > >>>> Thanks. > >>> > >>> Please refer to the above explanation for details. > >>> > >>> Thanks. > >> > >> Thanks. > >> > > Friendly ping. > > >
