[SERVER-4756] mongos should be a smarter load balancer Created: 24/Jan/12 Updated: 06/Dec/22 Resolved: 05/Nov/21 |
|
| Status: | Closed |
| Project: | Core Server |
| Component/s: | Sharding |
| Affects Version/s: | 2.0.2 |
| Fix Version/s: | None |
| Type: | Improvement | Priority: | Major - P3 |
| Reporter: | Jon Hoffman | Assignee: | [DO NOT USE] Backlog - Sharding Team |
| Resolution: | Done | Votes: | 2 |
| Labels: | lamont-triage, mongos, performance | ||
| Remaining Estimate: | Not Specified | ||
| Time Spent: | Not Specified | ||
| Original Estimate: | Not Specified | ||
| Issue Links: |
|
||||||||
| Assigned Teams: |
Sharding
|
||||||||
| Participants: | |||||||||
| Description |
|
The mongos currently does very basic round robin query distribution across replica secondaries. Due to degraded hardware, we sometimes have replicas which answer queries much slower than other replicas, and ideally the mongos should that and balance appropriately. |
| Comments |
| Comment by Lamont Nelson [ 05/Nov/21 ] |
|
server selection algorithm takes latency into account. |