[SERVER-36936] Mongos memory usage is too large(>7G) Created: 30/Aug/18 Updated: 25/Oct/18 Resolved: 25/Oct/18 |
|
| Status: | Closed |
| Project: | Core Server |
| Component/s: | None |
| Affects Version/s: | 3.4.16 |
| Fix Version/s: | None |
| Type: | Question | Priority: | Major - P3 |
| Reporter: | lkx | Assignee: | Kelsey Schubert |
| Resolution: | Incomplete | Votes: | 0 |
| Labels: | None | ||
| Remaining Estimate: | Not Specified | ||
| Time Spent: | Not Specified | ||
| Original Estimate: | Not Specified | ||
| Attachments: |
|
| Participants: |
| Description |
|
Test mongodb cluster performance with ycsb: mongodb version: 3.4.0 or 3.4.16; mongodb sharded cluster : 3 shardSver; ycsb version: 0.12.0; system : centos7; memory: 48G; CPU: 24 core; Operation sequence: 1. start sharded cluster; 2. sh.enableSharding('ycsb'); 3. sh.shardCollection('ycsb.usertable',{_id:"hashed"}); 4. ycsb load data ( recordcount=20000, operationcount=20000, threads=64); 5. ycsb run scan (recordcount=20000, operationcount=20000, **scanproportion=1, threads=64), At this time, it will occupy 7G of memory and will not be released for a long time. 6. drop collection(ycsb.usertable), and drop database(ycsb) Memory usage still has not decreased; |
| Comments |
| Comment by Kelsey Schubert [ 25/Oct/18 ] | |
|
Hi lkx, We haven’t heard back from you for some time, so I’m going to mark this ticket as resolved. If this is still an issue for you, please provide additional information and we will reopen the ticket. Regards, | |
| Comment by Nick Brewer [ 01/Oct/18 ] | |
|
lkx Have you had a chance to collect the diagnostic.data with the heap profiler enabled? Thanks, | |
| Comment by Nick Brewer [ 17/Sep/18 ] | |
|
lkx Based on the information you've provided, we're not seeing the sort of memory utilization that was described previously - memory usage appears to be roughly 2GB. To investigate this, we'll need the diagnostic.data information requested previously, once the heap profiler has been enabled on the mongos via:
Thanks, | |
| Comment by lkx [ 15/Sep/18 ] | |
|
Yes! I added the result of serverStatus to the attachment. | |
| Comment by Nick Brewer [ 14/Sep/18 ] | |
|
lkx Are you still experiencing this issue? If so, we'll need the heap profiler information requested previously, so that we can better diagnose the cause. Thanks, |