[LU-7988] HSM: high lock contention for cdt_llog_lock

• Type: Bug
• Resolution: Fixed
• Priority: Critical
• Fix Version/s: Lustre 2.11.0, Lustre 2.10.4, Lustre 2.10.7
• Labels: cea
• Severity: 3
• Assignee: Frank Zago (Inactive)
• Reporter: Frank Zago (Inactive)

Description

There is an important locking issue around cdt_llog_lock when adding new HSM requests.

# time wc -l /proc/fs/lustre/mdt/snx11133-MDT0000/hsm/actions
219759 /proc/fs/lustre/mdt/snx11133-MDT0000/hsm/actions

real    11m45.068s
user    0m0.020s
sys     0m21.372s

11 minutes to cat the list is too high. Such operation should take a couple seconds at most.

The contention appears to come from the coordinator. Every time a new request is posted, the whole list of request is browsed, under that lock. That's not a problem when there is only a handful of request, but it doesn't scale when there is hundreds of thousands of them.

I recompiled a centos 7 kernel with CONFIG_LOCK_STAT on a VM. I ran test creating 10000 files and archiving them without a copytool present. Total time was 146 seconds. Lock contention result:

lock_stat version 0.3
-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------
                              class name    con-bounces    contentions   waittime-min   waittime-max waittime-total    acq-bounces   acquisitions   holdtime-min   holdtime-max holdtime-total
-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------

[...]

                     &cdt->cdt_llog_lock:          6296           6296          15.45       23074.17    43436574.06          17791          27134          25.09       37745.03   138558199.24
                     -------------------
                     &cdt->cdt_llog_lock           6296          [<ffffffffa0fb096d>] cdt_llog_process+0x9d/0x3a0 [mdt]
                     -------------------
                     &cdt->cdt_llog_lock           6296          [<ffffffffa0fb096d>] cdt_llog_process+0x9d/0x3a0 [mdt]
[...]

(time units are micro-seconds).

With waittime-total=43 seconds and holdtime-total=138s, this is a very contentious lock, way above the other locks in Lustre or the whole system.

AFAICS, contention is between these mechanisms:

• adding a new request (lfs hsm_archive, ...)
• changing a request status (WAITING->STARTED->SUCCEED)
• removing a request (archive completed)
• housekeeping (coordinator loop every 10 seconds)
• dumping the list of actions from /proc

The net result is that when there is a lot of requests, they trickle down to the copytool, exacerbating the problem by increasing the number in the list.

Issue Links

• is related to: LU-9959 hsm: cannot schedule two different requests on the same fid
• is related to: LU-8626 limit number of items in HSM action queue

Comments

[Gerrit Updater]

Oleg Drokin ([e-mail]) merged in patch https://review.whamcloud.com/28908/
Subject: LU-7988 hsm: added coordinator housekeeping flag
Project: fs/lustre-release
Branch: b2_10
Current Patch Set:
Commit: 387dca70723affc0b45b87730e994395b9627eef

[Aurelien Degremont (Inactive)]

It seems this ticket was wrongly flagged to 2.10.6.

The last patch being landed on b2_10 from this series was landed for 2.10.4

There is still one backport which was not landed and is interesting: https://review.whamcloud.com/#/c/28908/2