2.5.73-bk3, -bk4, -mjb1 regression test results
Nightly Regression Summary
for
2.5.73-bk2 vs 2.5.73-bk3
Benchmark Pass/Fail Improvements Regressions Results Results Summary --------------- --------- ------------ ----------- ----------- ----------- -------
dbench.ext2 P N N 2.5.73-bk2 2.5.73-bk3 report dbench.ext3 P Y N 2.5.73-bk2 2.5.73-bk3 report dbench.jfs P N N 2.5.73-bk2 2.5.73-bk3 report dbench.reiser P N N 2.5.73-bk2 2.5.73-bk3 report dbench.xfs P N N 2.5.73-bk2 2.5.73-bk3 report kernbench P N N 2.5.73-bk2 2.5.73-bk3 report lmbench P Y Y 2.5.73-bk2 2.5.73-bk3 report rawiobench P Y Y 2.5.73-bk2 2.5.73-bk3 report specjbb P Y N 2.5.73-bk2 2.5.73-bk3 report specsdet P N N 2.5.73-bk2 2.5.73-bk3 report tbench P Y Y 2.5.73-bk2 2.5.73-bk3 report tiobench.ext2 P N N 2.5.73-bk2 2.5.73-bk3 report tiobench.ext3 P N Y 2.5.73-bk2 2.5.73-bk3 report tiobench.jfs P N N 2.5.73-bk2 2.5.73-bk3 report tiobench.reiser P N Y 2.5.73-bk2 2.5.73-bk3 report tiobench.xfs P N N 2.5.73-bk2 2.5.73-bk3 report volanomark P N N 2.5.73-bk2 2.5.73-bk3 report
http://ltcperf.ncsa.uiuc.edu/data/2.5.73-bk3/2.5.73-bk2-vs-2.5.73-bk3/
Nightly Regression Summary
for
2.5.73 vs 2.5.73-bk3
Benchmark Pass/Fail Improvements Regressions Results Results Summary --------------- --------- ------------ ----------- ----------- ----------- -------
dbench.ext2 P N N 2.5.73 2.5.73-bk3 report dbench.ext3 P N N 2.5.73 2.5.73-bk3 report dbench.jfs P N N 2.5.73 2.5.73-bk3 report dbench.reiser P N N 2.5.73 2.5.73-bk3 report dbench.xfs P N N 2.5.73 2.5.73-bk3 report kernbench P N N 2.5.73 2.5.73-bk3 report lmbench P Y Y 2.5.73 2.5.73-bk3 report rawiobench P Y Y 2.5.73 2.5.73-bk3 report specjbb P Y Y 2.5.73 2.5.73-bk3 report specsdet P Y N 2.5.73 2.5.73-bk3 report tbench P N Y 2.5.73 2.5.73-bk3 report tiobench.ext2 P N N 2.5.73 2.5.73-bk3 report tiobench.ext3 P Y N 2.5.73 2.5.73-bk3 report tiobench.jfs P N N 2.5.73 2.5.73-bk3 report tiobench.reiser P N N 2.5.73 2.5.73-bk3 report tiobench.xfs P N N 2.5.73 2.5.73-bk3 report volanomark P N N 2.5.73 2.5.73-bk3 report
http://ltcperf.ncsa.uiuc.edu/data/2.5.73-bk3/2.5.73-vs-2.5.73-bk3/
Nightly Regression Summary
for
2.5.73-bk3 vs 2.5.73-bk4
Benchmark Pass/Fail Improvements Regressions Results Results Summary --------------- --------- ------------ ----------- ----------- ----------- -------
dbench.ext2 P N N 2.5.73-bk3 2.5.73-bk4 report dbench.ext3 P N Y 2.5.73-bk3 2.5.73-bk4 report dbench.jfs P N N 2.5.73-bk3 2.5.73-bk4 report dbench.reiser P N N 2.5.73-bk3 2.5.73-bk4 report dbench.xfs P N N 2.5.73-bk3 2.5.73-bk4 report kernbench P N N 2.5.73-bk3 2.5.73-bk4 report lmbench P Y Y 2.5.73-bk3 2.5.73-bk4 report rawiobench P Y Y 2.5.73-bk3 2.5.73-bk4 report specjbb P N Y 2.5.73-bk3 2.5.73-bk4 report specsdet P N N 2.5.73-bk3 2.5.73-bk4 report tbench P Y Y 2.5.73-bk3 2.5.73-bk4 report tiobench.ext2 P N N 2.5.73-bk3 2.5.73-bk4 report tiobench.ext3 P N Y 2.5.73-bk3 2.5.73-bk4 report tiobench.jfs P N Y 2.5.73-bk3 2.5.73-bk4 report tiobench.reiser P N Y 2.5.73-bk3 2.5.73-bk4 report tiobench.xfs P N Y 2.5.73-bk3 2.5.73-bk4 report volanomark P N N 2.5.73-bk3 2.5.73-bk4 report
http://ltcperf.ncsa.uiuc.edu/data/2.5.73-bk4/2.5.73-bk3-vs-2.5.73-bk4/
Nightly Regression Summary
for
2.5.73 vs 2.5.73-bk4
Benchmark Pass/Fail Improvements Regressions Results Results Summary --------------- --------- ------------ ----------- ----------- ----------- -------
dbench.ext2 P N N 2.5.73 2.5.73-bk4 report dbench.ext3 P N N 2.5.73 2.5.73-bk4 report dbench.jfs P N N 2.5.73 2.5.73-bk4 report dbench.reiser P N N 2.5.73 2.5.73-bk4 report dbench.xfs P N N 2.5.73 2.5.73-bk4 report kernbench P N N 2.5.73 2.5.73-bk4 report lmbench P Y Y 2.5.73 2.5.73-bk4 report rawiobench P Y Y 2.5.73 2.5.73-bk4 report specjbb P Y Y 2.5.73 2.5.73-bk4 report specsdet P Y N 2.5.73 2.5.73-bk4 report tbench P Y Y 2.5.73 2.5.73-bk4 report tiobench.ext2 P N Y 2.5.73 2.5.73-bk4 report tiobench.ext3 P N Y 2.5.73 2.5.73-bk4 report tiobench.jfs P N Y 2.5.73 2.5.73-bk4 report tiobench.reiser P N Y 2.5.73 2.5.73-bk4 report tiobench.xfs P N Y 2.5.73 2.5.73-bk4 report volanomark P N N 2.5.73 2.5.73-bk4 report
http://ltcperf.ncsa.uiuc.edu/data/2.5.73-bk4/2.5.73-vs-2.5.73-bk4/
Nightly Regression Summary
for
2.5.73 vs 2.5.73-mjb1
Benchmark Pass/Fail Improvements Regressions Results Results Summary --------------- --------- ------------ ----------- ----------- ----------- -------
dbench.ext2 P N N 2.5.73 2.5.73-mjb1 report dbench.ext3 P N Y 2.5.73 2.5.73-mjb1 report dbench.jfs P N N 2.5.73 2.5.73-mjb1 report dbench.reiser P Y N 2.5.73 2.5.73-mjb1 report dbench.xfs P N N 2.5.73 2.5.73-mjb1 report kernbench P N N 2.5.73 2.5.73-mjb1 report lmbench P Y Y 2.5.73 2.5.73-mjb1 report rawiobench P Y Y 2.5.73 2.5.73-mjb1 report specjbb P N Y 2.5.73 2.5.73-mjb1 report specsdet P Y N 2.5.73 2.5.73-mjb1 report tbench P N Y 2.5.73 2.5.73-mjb1 report tiobench.ext2 P Y N 2.5.73 2.5.73-mjb1 report tiobench.ext3 P Y Y 2.5.73 2.5.73-mjb1 report tiobench.jfs P N Y 2.5.73 2.5.73-mjb1 report tiobench.reiser P N N 2.5.73 2.5.73-mjb1 report tiobench.xfs P Y Y 2.5.73 2.5.73-mjb1 report volanomark P N N 2.5.73 2.5.73-mjb1 report
http://ltcperf.ncsa.uiuc.edu/data/2.5.73-mjb1/2.5.73-vs-2.5.73-mjb1/
Mark
Quoted 3 lines · Mark Peloquin
Nightly Regression Summary
for
2.5.73-bk2 vs 2.5.73-bk3
This is very cool stuff.
Thanks!
Jeff
Quoted 10 lines · Jeff Garzik
Quoted 5 lines · Mark Peloquin
Nightly Regression Summary
for
2.5.73-bk2 vs 2.5.73-bk3
Quoted 6 lines
This is very cool stuff.
Thanks!
Jeff
Glad you like it!
Mark
Quoted 2 lines · Mark Peloquin
Nightly Regression Summary
for
...
Have you ever had these regression tests run against the same kernel? say, 2.5.73 vs 2.5.73
How often do you see improvements or regressions reported then?
Signature · 2 lines
Dave Hansen [email protected]
Quoted 7 lines · Dave Hansen
Quoted 4 lines · Mark Peloquin
Nightly Regression Summary
for
Quoted 7 lines
...
Have you ever had these regression tests run against the same kernel? say, 2.5.73 vs 2.5.73
How often do you see improvements or regressions reported then?
Its benchmark specific. Currently dbench, specjbb, and lmbench have a few problematic data points that aren't terribly repeatable. So on the same kernel, one can see improvements and regressions. That said, the majority of data points are very repeatable and give good indications of real change. We will continue to tweak things here and there to reduce the number of false positives.
Mark