[SERVER-13748] Global Lock in Reduce Phase of Map/Reduce Created: 25/Apr/14  Updated: 10/Dec/14  Resolved: 25/Apr/14

Status: Closed
Project: Core Server
Component/s: MapReduce
Affects Version/s: 2.4.9, 2.6.0
Fix Version/s: None

Type: Question Priority: Major - P3
Reporter: Andre Spiegel Assignee: Mathias Stearn
Resolution: Duplicate Votes: 0
Labels: None
Remaining Estimate: Not Specified
Time Spent: Not Specified
Original Estimate: Not Specified

Issue Links:
Duplicate
duplicates SERVER-7831 m/r: reduce post processing: reduce l... Backlog
Related
related to SERVER-13552 remove unnecessary global lock during... Backlog
Participants:

 Description   

When writing results to an output collection, the map/reduce engine acquires a global write lock, effectively blocking the server for all other operations. Even when the nonAtomic option is used, the global lock is acquired for every single document that is written, and since this happens pre-emptively, the effect is very much the same.

This effectively prevents any kind of concurrency while doing map/reduce computations and should therefore be changed.


Generated at Thu Feb 08 03:32:45 UTC 2024 using Jira 9.7.1#970001-sha1:2222b88b221c4928ef0de3161136cc90c8356a66.