[SERVER-84449] High load can cause replication lag leads to write latency Created: 29/Dec/23 Updated: 02/Feb/24 |
|
| Status: | Open |
| Project: | Core Server |
| Component/s: | None |
| Affects Version/s: | None |
| Fix Version/s: | None |
| Type: | Task | Priority: | Major - P3 |
| Reporter: | Moustafa Maher | Assignee: | Backlog - Replication Team |
| Resolution: | Unresolved | Votes: | 0 |
| Labels: | None | ||
| Remaining Estimate: | Not Specified | ||
| Time Spent: | Not Specified | ||
| Original Estimate: | Not Specified | ||
| Issue Links: |
|
||||||||||||||||||||||||
| Assigned Teams: |
Replication
|
||||||||||||||||||||||||
| Participants: | |||||||||||||||||||||||||
| Case: | (copied to CRM) | ||||||||||||||||||||||||
| Description |
|
For WT to calculate all_durable and advance the stable_timestamp, it has to walk all opened sessions. In high load scenarios and connection storms this can lead to contention on the ReplicationCoordinator mutex, slowing replication and inducing read/write concern majority lag. |