[SERVER-31359] when large inserts into mongo, lots of global lock occur Created: 03/Oct/17 Updated: 08/Feb/23 Resolved: 07/Nov/17 |
|
| Status: | Closed |
| Project: | Core Server |
| Component/s: | None |
| Affects Version/s: | None |
| Fix Version/s: | None |
| Type: | Question | Priority: | Major - P3 |
| Reporter: | shawn | Assignee: | Mark Agarunov |
| Resolution: | Done | Votes: | 0 |
| Labels: | MAREF | ||
| Remaining Estimate: | Not Specified | ||
| Time Spent: | Not Specified | ||
| Original Estimate: | Not Specified | ||
| Attachments: |
|
||||||||||||||||
| Issue Links: |
|
||||||||||||||||
| Participants: | |||||||||||||||||
| Description |
|
hi my applicaton use secondary as a read concern of mongodb.
we can see locks section, timeAcquiringMicros is 12923929. wait time is so long. As we known lock of WiredTiger is document level , why a query wait so long . seeing from db.currentOp(), as following:
the rssync thead holds a global lock, and lockstats.Global.acquireCount.W is bigger and bigger。 so , the root case is the rssync thead holds global lock . I use ycsb to benchmark a new replset reproduce this case. And monitor of global lock is high. |
| Comments |
| Comment by Mark Agarunov [ 07/Nov/17 ] |
|
Hello shawn_001, Thank you for the additional information. After investigating, I believe this behavior is due to the same underlying issue as Thanks, |
| Comment by shawn [ 04/Oct/17 ] |
|
Hi I hope that we could resovle this question. Thanks. |
| Comment by Mark Agarunov [ 03/Oct/17 ] |
|
Hello shawn_001, Thank you for the report. To get a better idea of what may be causing this, could you please provide the following:
This should give us a better look into what may be causing this lock to be held open. Thanks, |