[SERVER-21226] investigate possible starvation in acquiring log sync mutex Created: 30/Oct/15  Updated: 06/Dec/22  Resolved: 15/Apr/19

Status: Closed
Project: Core Server
Component/s: Storage
Affects Version/s: 3.2.0-rc1
Fix Version/s: None

Type: Bug Priority: Major - P3
Reporter: Geert Bosch Assignee: Backlog - Storage Execution Team
Resolution: Won't Fix Votes: 0
Labels: None
Remaining Estimate: Not Specified
Time Spent: Not Specified
Original Estimate: Not Specified

Assigned Teams:
Storage Execution
Operating System: ALL
Steps To Reproduce:

Only theoretical now. Try evoking this behavior with a test case (may need fail point).

Participants:

 Description   

The mutex used for syncing the WT journal is not necessarily fair and could lead to starvation. If confirmed, could be fixed by using two mutexes and alternating. (Even/odd number of syncs.)


Generated at Thu Feb 08 03:56:42 UTC 2024 using Jira 9.7.1#970001-sha1:2222b88b221c4928ef0de3161136cc90c8356a66.