[SERVER-18375] High CPU during insert-only stress test due to heap contention on Windows Created: 07/May/15 Updated: 09/Apr/20 |
|
| Status: | Open |
| Project: | Core Server |
| Component/s: | Storage, WiredTiger |
| Affects Version/s: | None |
| Fix Version/s: | Needs Further Definition |
| Type: | Bug | Priority: | Critical - P2 |
| Reporter: | Eitan Klein | Assignee: | DO NOT USE - Backlog - Platform Team |
| Resolution: | Unresolved | Votes: | 0 |
| Labels: | 32qa, WTmem, move-sa | ||
| Remaining Estimate: | Not Specified | ||
| Time Spent: | Not Specified | ||
| Original Estimate: | Not Specified | ||
| Attachments: |
|
||||||||
| Issue Links: |
|
||||||||
| Operating System: | Windows | ||||||||
| Steps To Reproduce: | Hammer.mongo insert only workload for long period of time, |
||||||||
| Sprint: | Platform 4 06/05/15, Platform 5 06/26/16, Platform 6 07/17/15, Platform 7 08/10/15 | ||||||||
| Participants: | |||||||||
| Description |
|
Configuration: Problem:
I think it's early in the 3.2 cycle that we can implement a full solution and stabilize it. This happened b/c we implemented the TCMalloc 1/2 way (only for WT) so the heap contention is still around , see profiler information about the % of the time around new/free functions |
| Comments |
| Comment by Alessandro Gherardi [ 21/Sep/16 ] |
|
Related ticket has been closed. This issue is 1 year+ old. Can it be resolved? |
| Comment by Alessandro Gherardi [ 18/Dec/15 ] |
|
Is this still an issue in 3.2.0/3.2.1? |
| Comment by Eitan Klein [ 18/May/15 ] |
|
50% of CPU time on WT secondary has been spent on free memory (See profile output on the attached file) Repro:
|
| Comment by Eitan Klein [ 07/May/15 ] |
|
See |