Throughput mode rework #52
Merged
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Rework execution loops to use iozone's own functionality Enable spreadsheet-friendly output Use spreadsheet-friendly output to generate more postprocessing-friendly CSV files
dvalinrh
added
the
group_review_lgtm
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Description
This reworks the use of iozone's throughput mode by:
--enabling spreadsheet-friendly output
--reworking the assembly of the iozone command line to facilitate the use of spreadsheet mode
--replacing the data reduction methodology for throughput mode to handle spreadsheet-friendly output and eliminate the problem of not handling multiple iterations in one run (only the most recent run is preserved)
--Makes the final CSV file more post-processing friendly
Before/After Comparison
Before:
Only the most recent filesystem/testmode run is preserved, and only certain subtests are handled correctly (and those by brute force)
CSV file isn't post-processing friendly
Ex:
processes:test_type:file_sze:record_size:Total_througput
1:initial writers:10485760 kB:Record Size 1024 kB: 1186870.25 kB/sec
1:readers:10485760 kB:Record Size 1024 kB: 3683637.25 kB/sec
2:initial writers:5242880 kB:Record Size 1024 kB: 1200949.69 kB/sec
2:readers:5242880 kB:Record Size 1024 kB: 3711953.50 kB/sec
4:initial writers:2097152 kB:Record Size 1024 kB: 1211215.00 kB/sec
4:readers:2097152 kB:Record Size 1024 kB: 3724389.06 kB/sec
After:
Spreadsheet-friendlyoutput is enabled
All run results are processed into a consolidated CSV
CSV file is post-processing friendly
Ex:
filesys:mode:op:1proc:2proc:4proc
xfs:incache:Initialwrite:13009629.00:12969813.50:12874782.50
xfs:incache:Rewrite:13283659.00:13076599.50:13061553.50
xfs:incache:Read:10675931.00:10447949.00:10391854.00
xfs:incache:Re-read:10757681.00:10449202.00:10254559.75
Clerical Stuff
This closes #28
Relates to JIRA: RPOPC-296