Details
-
Type:
Story
-
Status: Done
-
Resolution: Done
-
Fix Version/s: None
-
Component/s: None
-
Labels:None
-
Story Points:20
-
Epic Link:
-
Sprint:AP S22-6 (May)
-
Team:Alert Production
-
Urgent?:No
Description
This is an umbrella ticket for technical tasks related to the AP performance tuning sprint in May 2022.
Goals include:
- update profiling and identify future areas for performance tuning
- make AP-specific pipeline & configurations
- think about how to project timing scenarios more accurately in steady state operations.
We will test on DC2 data to capture scaling with pixels and image depth most accurately.
Attachments
Issue Links
- is triggering
-
DM-34993 Investigate failed detector-visit in DC2 4 patch run
- To Do
- relates to
-
DM-35158 Investigate scaling of DIAForcedSource
- To Do
-
DM-31653 Reprocess a subset of DC2 with profiling
- Done
-
DM-34845 Create ap_verify dataset for DC2
- Done
-
DM-34976 Prepare presentation on the performance tuning sprint
- Done
-
DM-34993 Investigate failed detector-visit in DC2 4 patch run
- To Do
-
DM-32838 AP pipeline performance characterization
- Done
-
DM-34865 Script for looking at ap_verify metrics
- Done
-
DM-34896 Collate timing metrics from run on 4-patch >200 visit DC2 dataset
- Done
Confluence summary page: https://confluence.lsstcorp.org/display/DM/May+2022+Performance+Sprint+Summary