[SERVER-85014] Analyze error distribution of operations involving storage engine and compare it with some other operations Created: 22/Aug/22  Updated: 12/Jan/24  Resolved: 20/Sep/22

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

Type: Task Priority: Major - P3
Reporter: Alexander Ignatyev Assignee: Ruoxin Xu
Resolution: Fixed Votes: 0
Labels: M4
Remaining Estimate: Not Specified
Time Spent: Not Specified
Original Estimate: Not Specified

Attachments: HTML File Distribution analysis.html    
Sprint: QO 2022-09-05, QO 2022-09-19, QO 2022-10-03
Participants:

 Description   

Analyse error distributions for ABT nodes representing storage engine (WT) operations:

  • Index Seek
  • Seek
  • Scan

And some non-disk operations, e.g. filter.

1. Run an experiment with about 40 queries for every run
2. Calculate observational statistics of execution time parameter: median, mean, standard deviation, correlation with number of processed rows
3. Check the hypothesis that the distribution of execution time values is close to normal distribution using Kolmogorov-Smirnov test (scipy.stats.kstest). One way is to calculate z-scores= (value - media)/stddev and compare with standard distribution.
4. Create a table with results.


Generated at Thu Feb 08 06:56:35 UTC 2024 using Jira 9.7.1#970001-sha1:2222b88b221c4928ef0de3161136cc90c8356a66.