[GODRIVER-2526] Heavy allocations in selectByKind Created: 16/Aug/22 Updated: 28/Oct/23 Resolved: 08/Sep/22 |
|
| Status: | Closed |
| Project: | Go Driver |
| Component/s: | None |
| Affects Version/s: | 1.9.1 |
| Fix Version/s: | 1.11.0 |
| Type: | Improvement | Priority: | Unknown |
| Reporter: | Peter Ivanov | Assignee: | Qingyang Hu |
| Resolution: | Fixed | Votes: | 0 |
| Labels: | None | ||
| Remaining Estimate: | Not Specified | ||
| Time Spent: | Not Specified | ||
| Original Estimate: | Not Specified | ||
| Attachments: |
|
||||||||||||||||
| Issue Links: |
|
||||||||||||||||
| Description |
|
This is how the top of allocation profile looks like in one of our batch processing services. We use sharded cluster, pool of mongos services, and drvier 1.9.1. It seems that, in our case at least, this selection in a no-op (all candidates are Mongos), but the allocation burden is very considerable. |
| Comments |
| Comment by Githook User [ 07/Sep/22 ] |
|
Author: {'name': 'Qingyang Hu', 'email': '103950869+qingyang-hu@users.noreply.github.com', 'username': 'qingyang-hu'}Message:
Co-authored-by: Benjamin Rewis <32186188+benjirewis@users.noreply.github.com> |
| Comment by Peter Ivanov [ 29/Aug/22 ] |
|
Hi! Out setup implies autoscaling of mongos instances according to load, but here's some numbers I can share:
|
| Comment by Qingyang Hu [ 25/Aug/22 ] |
|
Hi, petr.ivanov.s@gmail.com, can you please let us know how many mongos instances are running? Maybe the cluster topology as well? |