[LU-18169] Better support memcg for new kernels

• Type: Bug
• Resolution: Unresolved
• Priority: Minor
• Severity: 3
• Assignee: Qian Yingjin
• Reporter: Qian Yingjin

Description

EXA performance test script hanged on SLES15sp3 on NUMA system.
Found that once we disabled unstable_check, the test can pass.

lctl set_param llite.*.unstable_stats=0 # disable unstable check

Finally found the root reason: we are using NR_UNSTABLE_NFS wrongly, it was deprecated (DO NOT USE) on the SLES15sp3:

NR_UNSTABLE_NFS,        /* NFS unstable pages - DEPRECATED DO NOT USE */

Moreover, the cgroups (memcg) does not work for the newer kernel,
the reason is that NR_UNSTABLE_NFS was removed, and it is wrongly
using NR_ZONE_WRITE_PENDING for memory accounting.
According to the kernel patch:

"mm/writeback: discard NR_UNSTABLE_NFS, use NR_WRITEBACK instead"
kernel v5.8-rc1 commit: 8d92890bd6b8502d6aee4b37430ae6444ade7a8c

it should account unstable pages in NR_WRITEBACK and WB_WRITEBACK.
We should fix these accordingly.

Comments

[Gerrit Updater]

"Qian Yingjin <[e-mail]>" uploaded a new patch: https://review.whamcloud.com/c/fs/lustre-release/+/56722
Subject: LU-18169 osc: CL_FSYNC_RECLAIM not need to wait fsync RPC finished
Project: fs/lustre-release
Branch: master
Current Patch Set: 1
Commit: 95639ad79867ecd599b46be4c0a1944ad6bfc4a2

[Gerrit Updater]

"Qian Yingjin <[e-mail]>" uploaded a new patch: https://review.whamcloud.com/c/fs/lustre-release/+/56710
Subject: LU-18169 llite: wait unstable pages to be committed during umount
Project: fs/lustre-release
Branch: master
Current Patch Set: 1
Commit: bd9591dfa5356110d195430cab5391e09144c9a1

[Gerrit Updater]

"Oleg Drokin <[e-mail]>" merged in patch https://review.whamcloud.com/c/fs/lustre-release/+/56162/
Subject: LU-18169 osc: do not use deprecated NR_UNSTABLE_NFS
Project: fs/lustre-release
Branch: master
Current Patch Set:
Commit: 39a465f6b3c11cbd892d456f68fdb867044d693c

[Gerrit Updater]

"Qian Yingjin <[e-mail]>" uploaded a new patch: https://review.whamcloud.com/c/fs/lustre-release/+/56197
Subject: LU-18169 osc: add accounting for WB_WRITEBACK for memcg
Project: fs/lustre-release
Branch: master
Current Patch Set: 1
Commit: 09ba9727e32121b06e5904fae5a244d592ea4c1b

[Gerrit Updater]

"Qian Yingjin <[e-mail]>" uploaded a new patch: https://review.whamcloud.com/c/fs/lustre-release/+/56162
Subject: LU-18169 osc: do not use deprecated NR_UNSTABLE_NFS
Project: fs/lustre-release
Branch: master
Current Patch Set: 1
Commit: 731d06c3ec25054c32b237cec97c97d31215f448