-
Type: Bug
-
Resolution: Duplicate
-
Priority: Major - P3
-
None
-
Affects Version/s: 4.4.0
-
Component/s: None
-
ALL
-
Service Arch 2021-06-28, Service Arch 2021-07-12, Service Arch 2021-08-09, Service Arch 2021-08-23, Service Arch 2021-10-04, Service Arch 2022-1-24, Service Arch 2022-2-07, Service Arch 2022-2-21, Service Arch 2022-03-07, Service Arch 2022-03-21, Service Arch 2022-04-04
-
(copied to CRM)
-
5
In v4.2, mongos correctly balanced outgoing read requests to secondary nodes by randomizing the connection order when we issued requests here. In v4.4, the introduction of either hedged reads, opportunistic reads, or changes to ConnectionPool have made it such that one of these connections now consistently resolves first, effectively starving one of the secondaries of any reads and unbalancing our read requests. In this ticket, create a unit or integration test to capture this behavior and fix it.
- depends on
-
SERVER-65131 Disable opportunistic read targeting (except for hedged reads)
- Closed
- duplicates
-
SERVER-57232 Increase in slow queries in ConnectionsBuildup case in Mongos on v4.4
- Closed
- is duplicated by
-
SERVER-65131 Disable opportunistic read targeting (except for hedged reads)
- Closed