[SERVER-12304] Query concurrency regression on windows Created: 09/Jan/14 Updated: 27/Apr/15 Resolved: 08/Feb/15 |
|
| Status: | Closed |
| Project: | Core Server |
| Component/s: | Concurrency, Querying |
| Affects Version/s: | 2.5.4 |
| Fix Version/s: | None |
| Type: | Bug | Priority: | Critical - P2 |
| Reporter: | Davide Italiano | Assignee: | Mark Benvenuto |
| Resolution: | Won't Fix | Votes: | 1 |
| Labels: | 26qa | ||
| Remaining Estimate: | Not Specified | ||
| Time Spent: | Not Specified | ||
| Original Estimate: | Not Specified | ||
| Environment: |
Windows Server 2008 R2/Linux Red Hat 6.4 |
||
| Issue Links: |
|
||||
| Backwards Compatibility: | Fully Compatible | ||||
| Operating System: | ALL | ||||
| Sprint: | Server 2.7.5, Server 2.7.6, Platform 00 2/20/15 | ||||
| Participants: | |||||
| Description |
|
The concurrency of query subsystem is somewhat lower in 2.6. Example queries that show the slowdown in throughput (ops/s):
githash of master: 06851f4859a61019a17147ea96c4e6d9462f354b |
| Comments |
| Comment by Daniel Pasette (Inactive) [ 08/Feb/15 ] |
|
Closing as there is no specific information or next steps to work with. |
| Comment by Daniel Pasette (Inactive) [ 27/Feb/14 ] |
|
This was partially fixed, but leaving this open for further investigation as outlined in previous ticket. |
| Comment by Mark Benvenuto [ 27/Feb/14 ] |
|
I evaluated Native Windows Condition Variables with Critical Sections, and Reader-Writer locks. Both have worse performance then our existing implementation. I have code for various changes to try: They do not make a measurable impact on the micro benchmarks but may have a larger impact on QA-408. I am willing to try with a patch. |
| Comment by Githook User [ 18/Feb/14 ] |
|
Author: {u'username': u'markbenvenuto', u'name': u'Mark Benvenuto', u'email': u'mark.benvenuto@mongodb.com'}Message: |
| Comment by Daniel Pasette (Inactive) [ 10/Jan/14 ] |
|
mark.benvenuto, can you take a look at the most simple example of a regression on windows? |