[CONTROLLER-573] Improve the scale & performance of the MD-SAL in-memory data store. Created: 20/Jun/14 Updated: 19/Oct/17 Resolved: 13/Nov/15 |
|
| Status: | Resolved |
| Project: | controller |
| Component/s: | mdsal |
| Affects Version/s: | Helium |
| Fix Version/s: | None |
| Type: | Improvement | ||
| Reporter: | Jan Medved | Assignee: | Unassigned |
| Resolution: | Cannot Reproduce | Votes: | 0 |
| Labels: | None | ||
| Remaining Estimate: | Not Specified | ||
| Time Spent: | Not Specified | ||
| Original Estimate: | Not Specified | ||
| Environment: |
Operating System: Mac OS |
||
| Description |
|
The system performance for Service chaining objects is as follows: Performance was around 400 req/sec the entire time and CPU only 4%. After all GC was done it took heap memory for 1M simple objects was around 1.5GB. The controller was run with the following JVM parameters: -Xmx4G -XX:+UseG1GC -XX:MaxPermSize=512m -Xms4G We need to optimize the memory utilization. Also, the low memory utilization may indicate contention. Needs to be profiled and potential bottlenecks identified and removed. |
| Comments |
| Comment by Robert Varga [ 02/Jul/14 ] |
|
Please provide coordinates of the benchmark used. |
| Comment by Carol Sanders [ 04/May/15 ] |
|
This bug is part of the project to Move all ADSAL associated component bugs to ADSAL |
| Comment by Robert Varga [ 04/May/15 ] |
|
This is actually MD-SAL |
| Comment by Robert Varga [ 13/Nov/15 ] |
|
This has been addressed. |