[SERVER-36875] Compare Performance between 3.4 and 4.0 Created: 27/Aug/18 Updated: 06/Dec/22 Resolved: 18/Sep/18 |
|
| Status: | Closed |
| Project: | Core Server |
| Component/s: | Performance |
| Affects Version/s: | 4.0.1 |
| Fix Version/s: | None |
| Type: | Question | Priority: | Major - P3 |
| Reporter: | Jun Kim (Inactive) | Assignee: | Backlog - Performance Team |
| Resolution: | Won't Fix | Votes: | 1 |
| Labels: | None | ||
| Remaining Estimate: | Not Specified | ||
| Time Spent: | Not Specified | ||
| Original Estimate: | Not Specified | ||
| Attachments: |
|
||||||||||||
| Issue Links: |
|
||||||||||||
| Assigned Teams: |
Product Performance
|
||||||||||||
| Participants: | |||||||||||||
| Linked BF Score: | 0 | ||||||||||||
| Description |
|
There is a mongoDB community In Korea. I attached the tested result image . Here is the test env. Workload A: 50/50% Mix of Reads/Writes |
| Comments |
| Comment by Chad Kreimendahl [ 26/Feb/19 ] |
|
Even then. Seems like a 10% regression on a point release is a major issue. |
| Comment by Asya Kamsky [ 26/Feb/19 ] |
|
sallgeud our measures showed significantly lower regression (closer to 10% and no where near 50%). |
| Comment by Chad Kreimendahl [ 20/Feb/19 ] |
|
We saw something similar in 3.6. I'm curious why you'd "Won't fix" a 10-50% performance regression? How much were you able to reclaim? How much was left? |
| Comment by David Daly [ 18/Sep/18 ] |
|
We're aware of regressions since 3.4 on YCSB. We run YCSB as part of our performance regression environment. We've reclaimed some of the regression, and have accepted the remaining regressions at this point. I'm going to close this ticket as Won't Fix for now. If you disagree and would like to discuss more, please feel free to reopen. |
| Comment by Jun Kim (Inactive) [ 07/Sep/18 ] |
|
thanks for the comment. I am just on boarding at MongoDB ( one month ). I really don't know what kind of process we have to fix the regression. Could you let me know there is a process to fix the regression now or future release. |
| Comment by Jun Kim (Inactive) [ 27/Aug/18 ] |
|
Also I tested by own env. |