Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

Reduce fletcher4 and raidz benchmark times #11282

Merged
merged 1 commit into from
Dec 6, 2020
Merged

Reduce fletcher4 and raidz benchmark times #11282

merged 1 commit into from
Dec 6, 2020

Conversation

behlendorf
Copy link
Contributor

Motivation and Context

Reduce module load time and thereby total boot time.

Description

During module load time all of the available fetcher4 and raidz
implementations are benchmarked for a fixed amount of time to determine
the fastest available. Manual testing has shown that this time can
be significantly reduced with negligible effect on the final results.

This commit changes the benchmark time to 1ms which can reduce the
module load time by over a second on x86_64. On an x86_64 system
with sse3, ssse3, and avx2 instructions the benchmark times are:

Fletcher4    603ms   -> 15ms
RAIDZ        1,322ms -> 64ms

How Has This Been Tested?

Instrumented the code to measure the benchmark run time.
Then loaded the module and inspected the benchmark results
to confirm they were effectively the same with both the previous
and reduced run times.

Types of changes

  • Bug fix (non-breaking change which fixes an issue)
  • New feature (non-breaking change which adds functionality)
  • Performance enhancement (non-breaking change which improves efficiency)
  • Code cleanup (non-breaking change which makes code smaller or more readable)
  • Breaking change (fix or feature that would cause existing functionality to change)
  • Documentation (a change to man pages or other documentation)

Checklist:

@behlendorf
Reduce fletcher4 and raidz benchmark times
87ce679 
During module load time all of the available fetcher4 and raidz
implemenations are benchmarked for a fixed amount of time to determine
the fastest available.  Manual testing has shown that this time can
be significantly reduced with negligible effect on the final results.

This commit changes the benchmark time to 1ms which can reduce the
module load time by over a second on x86_64.  On an x86_64 system
with sse3, ssse3, and avx2 instructions the benchmark times are:

    Fletcher4    603ms   -> 15ms
    RAIDZ        1,322ms -> 64ms

Signed-off-by: Brian Behlendorf <[email protected]>
@behlendorf behlendorf added the Status: Code Review Needed Ready for review and testing label Dec 4, 2020
@ghost ghost added Status: Accepted Ready to integrate (reviewed, tested) and removed Status: Code Review Needed Ready for review and testing labels Dec 5, 2020
@behlendorf behlendorf merged commit 83b698d into openzfs:master Dec 6, 2020
sterlingjensen pushed a commit to sterlingjensen/zfs that referenced this pull request Dec 7, 2020
@behlendorf @sterlingjensen
Reduce fletcher4 and raidz benchmark times
6333c4b 
During module load time all of the available fetcher4 and raidz
implementations are benchmarked for a fixed amount of time to
determine the fastest available.  Manual testing has shown that this
time can be significantly reduced with negligible effect on the final
results.

This commit changes the benchmark time to 1ms which can reduce the
module load time by over a second on x86_64.  On an x86_64 system
with sse3, ssse3, and avx2 instructions the benchmark times are:

    Fletcher4    603ms   -> 15ms
    RAIDZ        1,322ms -> 64ms

Reviewed-by: Matthew Macy <[email protected]>
Reviewed-by: George Melikov <[email protected]>
Reviewed-by: Ryan Moeller <[email protected]>
Signed-off-by: Brian Behlendorf <[email protected]>
Closes openzfs#11282
ghost pushed a commit to zfsonfreebsd/ZoF that referenced this pull request Dec 23, 2020
@behlendorf
Reduce fletcher4 and raidz benchmark times
6406573 
During module load time all of the available fetcher4 and raidz
implementations are benchmarked for a fixed amount of time to
determine the fastest available.  Manual testing has shown that this
time can be significantly reduced with negligible effect on the final
results.

This commit changes the benchmark time to 1ms which can reduce the
module load time by over a second on x86_64.  On an x86_64 system
with sse3, ssse3, and avx2 instructions the benchmark times are:

    Fletcher4    603ms   -> 15ms
    RAIDZ        1,322ms -> 64ms

Reviewed-by: Matthew Macy <[email protected]>
Reviewed-by: George Melikov <[email protected]>
Reviewed-by: Ryan Moeller <[email protected]>
Signed-off-by: Brian Behlendorf <[email protected]>
Closes openzfs#11282
behlendorf added a commit that referenced this pull request Dec 23, 2020
@behlendorf
Reduce fletcher4 and raidz benchmark times
07ca433 
During module load time all of the available fetcher4 and raidz
implementations are benchmarked for a fixed amount of time to
determine the fastest available.  Manual testing has shown that this
time can be significantly reduced with negligible effect on the final
results.

This commit changes the benchmark time to 1ms which can reduce the
module load time by over a second on x86_64.  On an x86_64 system
with sse3, ssse3, and avx2 instructions the benchmark times are:

    Fletcher4    603ms   -> 15ms
    RAIDZ        1,322ms -> 64ms

Reviewed-by: Matthew Macy <[email protected]>
Reviewed-by: George Melikov <[email protected]>
Reviewed-by: Ryan Moeller <[email protected]>
Signed-off-by: Brian Behlendorf <[email protected]>
Closes #11282
jsai20 pushed a commit to jsai20/zfs that referenced this pull request Mar 30, 2021
@behlendorf @jsai20
Reduce fletcher4 and raidz benchmark times
6efa8f8 
During module load time all of the available fetcher4 and raidz
implementations are benchmarked for a fixed amount of time to
determine the fastest available.  Manual testing has shown that this
time can be significantly reduced with negligible effect on the final
results.

This commit changes the benchmark time to 1ms which can reduce the
module load time by over a second on x86_64.  On an x86_64 system
with sse3, ssse3, and avx2 instructions the benchmark times are:

    Fletcher4    603ms   -> 15ms
    RAIDZ        1,322ms -> 64ms

Reviewed-by: Matthew Macy <[email protected]>
Reviewed-by: George Melikov <[email protected]>
Reviewed-by: Ryan Moeller <[email protected]>
Signed-off-by: Brian Behlendorf <[email protected]>
Closes openzfs#11282
@behlendorf behlendorf deleted the benchmark branch April 19, 2021 19:21
sempervictus pushed a commit to sempervictus/zfs that referenced this pull request May 31, 2021
@behlendorf
Reduce fletcher4 and raidz benchmark times
a79faac 
During module load time all of the available fetcher4 and raidz
implementations are benchmarked for a fixed amount of time to
determine the fastest available.  Manual testing has shown that this
time can be significantly reduced with negligible effect on the final
results.

This commit changes the benchmark time to 1ms which can reduce the
module load time by over a second on x86_64.  On an x86_64 system
with sse3, ssse3, and avx2 instructions the benchmark times are:

    Fletcher4    603ms   -> 15ms
    RAIDZ        1,322ms -> 64ms

Reviewed-by: Matthew Macy <[email protected]>
Reviewed-by: George Melikov <[email protected]>
Reviewed-by: Ryan Moeller <[email protected]>
Signed-off-by: Brian Behlendorf <[email protected]>
Closes openzfs#11282
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Reviewers

@mattmacy mattmacy mattmacy approved these changes

@gmelikov gmelikov gmelikov approved these changes

Assignees
No one assigned
Labels
Status: Accepted Ready to integrate (reviewed, tested)
Projects
None yet
Milestone
No milestone
Development

Successfully merging this pull request may close these issues.
3 participants
@behlendorf @gmelikov @mattmacy