linux-kernel.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Mike Galbraith <efault@gmx.de>
To: lkml <linux-kernel@vger.kernel.org>
Cc: Mel Gorman <mgorman@techsingularity.net>
Subject: mm: LTP/memcg testcase regression induced by  8cd7c588decf..66ce520bb7c2 series
Date: Sun, 21 Nov 2021 11:57:20 +0100	[thread overview]
Message-ID: <99e779783d6c7fce96448a3402061b9dc1b3b602.camel@gmx.de> (raw)

Greetings,

FYI, something in this series causes LTP controllers::memcg_regression
testcase to hang forever.  Verified via brute force revert of the lot.

After letting box moan for 4.5 hours, I poked ^C repeatedly, but runltp
didn't exit/recover gracefully, and ps hung, so I nuked the box.  All
memcg_test_1 instances were stuck in reclaim_throttle().

crash> ps | grep UN
  31458      1   5  ffff88e9c8ded100  UN   0.0    7620   1156  memcg_test_1
  31459      1   6  ffff88e9c8de8000  UN   0.0    7620   1156  memcg_test_1
  31460      1   4  ffff88e9cbdd0000  UN   0.0    7620   1156  memcg_test_1
  31461      1   2  ffff88ea41502880  UN   0.0    7620   1156  memcg_test_1
  31462      1   4  ffff88ea12750000  UN   0.0    7620   1156  memcg_test_1
  31463      1   7  ffff88ea12752880  UN   0.0    7620   1156  memcg_test_1
  31464      1   3  ffff88ea01eb8000  UN   0.0    7620   1156  memcg_test_1
  31465      1   6  ffff88e9c2bca880  UN   0.0    7620   1156  memcg_test_1
  31466      1   7  ffff88e9c2bc8000  UN   0.0    7620   1156  memcg_test_1
  31467      1   2  ffff88ea41e82880  UN   0.0    7620   1156  memcg_test_1
  31476   2834   2  ffff88ea1174d100  UN   0.0   38868   3744  ps
crash> bt -sx ffff88e9c8ded100
PID: 31458  TASK: ffff88e9c8ded100  CPU: 5   COMMAND: "memcg_test_1"
 #0 [ffffb36648bc79a0] __schedule+0x2c3 at ffffffffb72636e3
 #1 [ffffb36648bc7a60] schedule+0x3a at ffffffffb72644ba
 #2 [ffffb36648bc7a70] schedule_timeout+0x1f3 at ffffffffb7268d03
 #3 [ffffb36648bc7ae8] reclaim_throttle+0xd0 at ffffffffb6a69ab0
 #4 [ffffb36648bc7b50] do_try_to_free_pages+0x160 at ffffffffb6a6bab0
 #5 [ffffb36648bc7ba8] try_to_free_mem_cgroup_pages+0xf4 at ffffffffb6a6d264
 #6 [ffffb36648bc7c40] try_charge_memcg+0x19f at ffffffffb6b03b6f
 #7 [ffffb36648bc7ce0] obj_cgroup_charge_pages+0x27 at ffffffffb6b043a7
 #8 [ffffb36648bc7d08] obj_cgroup_charge+0x6f at ffffffffb6b0605f
 #9 [ffffb36648bc7d28] kmem_cache_alloc+0x86 at ffffffffb6ae7686
#10 [ffffb36648bc7d80] vm_area_alloc+0x1a at ffffffffb689aa5a
#11 [ffffb36648bc7d90] mmap_region+0x32f at ffffffffb6a9ee1f
#12 [ffffb36648bc7df8] do_mmap+0x392 at ffffffffb6a9f492
#13 [ffffb36648bc7e50] vm_mmap_pgoff+0xd5 at ffffffffb6a75125
#14 [ffffb36648bc7ed8] do_syscall_64+0x58 at ffffffffb7256138
#15 [ffffb36648bc7f28] exc_page_fault+0x67 at ffffffffb7259c97
#16 [ffffb36648bc7f50] entry_SYSCALL_64_after_hwframe+0x44 at ffffffffb740007c
    RIP: 00007f7b95ad9743  RSP: 00007ffe12089b08  RFLAGS: 00000246
    RAX: ffffffffffffffda  RBX: 0000000000000000  RCX: 00007f7b95ad9743
    RDX: 0000000000000003  RSI: 0000000000001000  RDI: 0000000000000000
    RBP: 0000000000000000   R8: 0000000000000000   R9: 0000000000000000
    R10: 0000000000002022  R11: 0000000000000246  R12: 0000000000000003
    R13: 0000000000001000  R14: 0000000000002022  R15: 0000000000000000
    ORIG_RAX: 0000000000000009  CS: 0033  SS: 002b
crash> bt -sx ffff88ea1174d100
PID: 31476  TASK: ffff88ea1174d100  CPU: 2   COMMAND: "ps"
 #0 [ffffb3664883fba8] __schedule+0x2c3 at ffffffffb72636e3
 #1 [ffffb3664883fc68] schedule+0x3a at ffffffffb72644ba
 #2 [ffffb3664883fc78] rwsem_down_read_slowpath+0x1bf at ffffffffb7266c8f
 #3 [ffffb3664883fd08] down_read_killable+0x5c at ffffffffb7266f3c
 #4 [ffffb3664883fd18] down_read_killable+0x5c at ffffffffb7266f3c
 #5 [ffffb3664883fd28] __access_remote_vm+0x4a at ffffffffb6a9795a
 #6 [ffffb3664883fd98] proc_pid_cmdline_read+0x16c at ffffffffb6bc3acc
 #7 [ffffb3664883fe00] vfs_read+0x9a at ffffffffb6b1d49a
 #8 [ffffb3664883fe30] ksys_read+0xa1 at ffffffffb6b1d891
 #9 [ffffb3664883fe70] do_syscall_64+0x58 at ffffffffb7256138
#10 [ffffb3664883fec0] do_sys_openat2+0x1cd at ffffffffb6b1913d
#11 [ffffb3664883ff00] do_sys_open+0x57 at ffffffffb6b1a7e7
#12 [ffffb3664883ff28] do_syscall_64+0x67 at ffffffffb7256147
#13 [ffffb3664883ff50] entry_SYSCALL_64_after_hwframe+0x44 at ffffffffb740007c
    RIP: 00007f192fb5cb5e  RSP: 00007ffc611e0ee8  RFLAGS: 00000246
    RAX: ffffffffffffffda  RBX: 00007f19303de010  RCX: 00007f192fb5cb5e
    RDX: 0000000000020000  RSI: 00007f19303de010  RDI: 0000000000000006
    RBP: 0000000000020000   R8: 0000000000000007   R9: 00000000ffffffff
    R10: 0000000000000000  R11: 0000000000000246  R12: 00007f19303de010
    R13: 0000000000000000  R14: 0000000000000006  R15: 0000000000000000
    ORIG_RAX: 0000000000000000  CS: 0033  SS: 002b


             reply	other threads:[~2021-11-21 10:57 UTC|newest]

Thread overview: 11+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2021-11-21 10:57 Mike Galbraith [this message]
2021-11-21 13:51 ` Thorsten Leemhuis
2021-11-22  6:46   ` Mike Galbraith
2021-11-22  7:41     ` Mike Galbraith
2021-11-23  9:13 ` Mel Gorman
2021-11-23 11:06   ` Mike Galbraith
2021-11-23 11:18   ` Mike Galbraith
2021-11-23 13:12     ` Mike Galbraith
2021-11-23 14:28       ` Mike Galbraith
2021-11-24 14:56     ` Mel Gorman
2021-11-24 16:21       ` Mike Galbraith

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=99e779783d6c7fce96448a3402061b9dc1b3b602.camel@gmx.de \
    --to=efault@gmx.de \
    --cc=linux-kernel@vger.kernel.org \
    --cc=mgorman@techsingularity.net \
    --subject='Re: mm: LTP/memcg testcase regression induced by  8cd7c588decf..66ce520bb7c2 series' \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link

This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).