[SERVER-44928] Add the large scale model to system_perf.yml Created: 03/Dec/19  Updated: 03/Dec/19  Resolved: 03/Dec/19

Status: Closed
Project: Core Server
Component/s: None
Affects Version/s: None
Fix Version/s: None

Type: Improvement Priority: Major - P3
Reporter: Donald Anderson Assignee: Donald Anderson
Resolution: Won't Do Votes: 0
Labels: None
Remaining Estimate: Not Specified
Time Spent: Not Specified
Original Estimate: Not Specified

Sprint: Storage Engines 2019-12-16
Participants:

 Description   

The large scale model is the basic workload for the Large Scale Workload Automation project. In its current form, it runs under genny for 70 minutes (after populating data sets) and genny will process metrics which can take a few hours. All told, anywhere from 2 to 7 hours (as genny can OOM during the process). Still, this is valuable for the storage team when WiredTiger metrics are captured. And as genny becomes more capable, we will extend the run time to many hours or days. So clearly, this needs to be its own workload job. Piggybacking onto genny_auto_tasks or genny_patch_tasks would be wasteful and confusing when selected.



 Comments   
Comment by Donald Anderson [ 03/Dec/19 ]

ryan.timmons and I discussed this, and decided that we'll put this into the genny AutoRun mechanism.  Even though it may run many hours, and may fail a lot, we hope to have enough successes to find what our baseline and variance is.  See https://jira.mongodb.org/browse/TIG-2201 .

Generated at Thu Feb 08 05:07:23 UTC 2024 using Jira 9.7.1#970001-sha1:2222b88b221c4928ef0de3161136cc90c8356a66.