[SERVER-44502] Create a performance test that can verify that moving chunks back and forth with a steady stream of update operations is faster with the new changes. Created: 08/Nov/19 Updated: 05/Dec/22 Resolved: 25/Nov/22 |
|
| Status: | Closed |
| Project: | Core Server |
| Component/s: | Sharding |
| Affects Version/s: | None |
| Fix Version/s: | None |
| Type: | Task | Priority: | Major - P3 |
| Reporter: | Blake Oler | Assignee: | [DO NOT USE] Backlog - Sharding EMEA |
| Resolution: | Won't Do | Votes: | 0 |
| Labels: | sharding-common-backlog | ||
| Remaining Estimate: | Not Specified | ||
| Time Spent: | Not Specified | ||
| Original Estimate: | Not Specified | ||
| Assigned Teams: |
Sharding EMEA
|
| Sprint: | Sharding 2020-01-27, Sharding 2020-02-10, Sharding 2020-02-24, Sharding 2020-03-09, Sharding 2020-03-23, Sharding 2020-04-06 |
| Participants: |
| Description |
|
This could be done by creating a multi-shard environment and having one empty chunk move back and forth. |
| Comments |
| Comment by Blake Oler [ 08/Apr/20 ] |
|
Putting this back on the backlog to get picked up by whoever needs it. The last-known iteration of this workload-in-progress is linked in the document for WRITING-5357. |
| Comment by Blake Oler [ 11/Nov/19 ] |
|
This will be much less work if I create a targeted test and run it locally to prove the performance changes exist. The ticket becomes more complicated once I want to patch Genny up to do what's required here. |