[SERVER-45458] Test mapReduce performance without $_internalJsEmit Created: 09/Jan/20 Updated: 27/Oct/23 Resolved: 28/Feb/20 |
|
| Status: | Closed |
| Project: | Core Server |
| Component/s: | None |
| Affects Version/s: | None |
| Fix Version/s: | None |
| Type: | Task | Priority: | Major - P3 |
| Reporter: | David Percy | Assignee: | Eric Cox (Inactive) |
| Resolution: | Works as Designed | Votes: | 0 |
| Labels: | qopt-team | ||
| Remaining Estimate: | Not Specified | ||
| Time Spent: | Not Specified | ||
| Original Estimate: | Not Specified | ||
| Issue Links: |
|
||||||||
| Sprint: | Query 2020-01-27, Query 2020-02-10, Query 2020-02-24, Query 2020-03-09 | ||||||||
| Participants: | |||||||||
| Description |
|
Compare legacy mapReduce performance (on 4.2) to equivalent aggregation pipeline which uses a normal $project stage rather than one with $_internalJsEmit (replica set only).
|
| Comments |
| Comment by Eric Cox (Inactive) [ 28/Feb/20 ] | ||||||||||||||||||||||||||||
|
It looks like we have a consistent ~8.x speed improvement for the various $out replacement strategies
Evergreen run is here.
| ||||||||||||||||||||||||||||
| Comment by David Percy [ 11/Feb/20 ] | ||||||||||||||||||||||||||||
|
A good starting point would probably be one of these benchmarks: https://jira.mongodb.org/browse/SERVER-42695?focusedCommentId=2602350&page=com.atlassian.jira.plugin.system.issuetabpanels%3Acomment-tabpanel#comment-2602350 |