[SERVER-20534] Add analysis comparing mongo-perf throughput with oplog versus standalone Created: 17/Sep/15  Updated: 29/Nov/16  Resolved: 08/Oct/15

Status: Closed
Project: Core Server
Component/s: Testing Infrastructure
Affects Version/s: None
Fix Version/s: 3.2.0-rc0

Type: Task Priority: Major - P3
Reporter: Ian Whalen (Inactive) Assignee: David Daly
Resolution: Done Votes: 0
Labels: None
Remaining Estimate: Not Specified
Time Spent: Not Specified
Original Estimate: Not Specified

Backwards Compatibility: Fully Compatible
Sprint: Performance A (10/08/15)
Participants:

 Description   

Scope includes any work needed to be done to get to a fully implemented test with pass/fail analysis phase running in EVG.

Workloads:

mongo-perf insert/updates	WT	standalone + oplog
mongo-perf insert/updates	MMAPV1	standalone + oplog

Analysis phase: Confirm throughput with oplog >= 75% of standalone

these might be too short-lived to be useful tests though. maybe bump to ~30-60 secs?



 Comments   
Comment by Githook User [ 08/Oct/15 ]

Author:

{u'username': u'dalyd', u'name': u'dalyd', u'email': u'david.daly@mongodb.com'}

Message: SERVER-20534: Add analysis comparing mongo-perf throughput with oplog versus standalone
Branch: master
https://github.com/mongodb/mongo/commit/83bc35d2c76d167eec057de8b7764e3788e93a92

Comment by Ian Whalen (Inactive) [ 23/Sep/15 ]

Relevant work is tracked here: CAP-2544. And apologies: Dan asked me about this offline and I misunderstood the question so only pointed him to this at first.

Comment by Daniel Pasette (Inactive) [ 23/Sep/15 ]

I don't think mongo-perf tests will be enough. I'd like to be able to compare YCSB load and 50-50 on standalone WT with and without oplog using the same setup as our regular system perf tests.

Generated at Thu Feb 08 03:54:31 UTC 2024 using Jira 9.7.1#970001-sha1:2222b88b221c4928ef0de3161136cc90c8356a66.