3.28 - 108.5% allrecipes / allrecipes fcp / allrecipes loadtime / amazon-search / amazon-search fcp / amazon-search loadtime (android-hw-g5-7-0-arm7-api-16-shippable) regression on push 741ea917c5e87c86e37c43f2a4c92858df8fee7b (Wed December 2 2020)
Categories
(Testing :: Raptor, defect)
Tracking
(firefox85 affected)
Tracking | Status | |
---|---|---|
firefox85 | --- | affected |
People
(Reporter: Bebe, Unassigned)
References
(Regression)
Details
(Keywords: perf, perf-alert, regression)
Perfherder has detected a browsertime performance regression from push 741ea917c5e87c86e37c43f2a4c92858df8fee7b. As author of one of the patches included in that push, we need your help to address this regression.
Regressions:
Ratio | Suite | Test | Platform | Options | Absolute values (old vs new) |
---|---|---|---|---|---|
109% | allrecipes | fcp | android-hw-g5-7-0-arm7-api-16-shippable | nocondprof warm | 416.25 -> 867.88 |
108% | allrecipes | fcp | android-hw-g5-7-0-arm7-api-16-shippable | nocondprof warm | 419.38 -> 871.71 |
27% | allrecipes | android-hw-g5-7-0-arm7-api-16-shippable | nocondprof warm | 1,033.11 -> 1,308.11 | |
7% | amazon-search | fcp | android-hw-g5-7-0-arm7-api-16-shippable | nocondprof warm | 826.23 -> 881.21 |
6% | amazon-search | android-hw-g5-7-0-arm7-api-16-shippable | nocondprof warm | 983.80 -> 1,041.29 | |
5% | allrecipes | loadtime | android-hw-g5-7-0-arm7-api-16-shippable | nocondprof warm | 4,397.83 -> 4,607.46 |
3% | amazon-search | loadtime | android-hw-g5-7-0-arm7-api-16-shippable | nocondprof warm | 1,666.06 -> 1,720.79 |
Improvements:
Ratio | Suite | Test | Platform | Options | Absolute values (old vs new) |
---|---|---|---|---|---|
9% | android-hw-g5-7-0-arm7-api-16-shippable | nocondprof warm webrender | 242.08 -> 220.49 | ||
9% | loadtime | android-hw-g5-7-0-arm7-api-16-shippable | nocondprof warm webrender | 242.83 -> 221.54 | |
9% | fcp | android-hw-g5-7-0-arm7-api-16-shippable | nocondprof warm webrender | 236.38 -> 215.79 |
Details of the alert can be found in the alert summary, including links to graphs and comparisons for each of the affected tests. Please follow our guide to handling regression bugs and let us know your plans within 3 business days, or the offending patch(es) will be backed out in accordance with our regression policy.
For more information on performance sheriffing please see our FAQ.
Reporter | ||
Updated•4 years ago
|
Comment 1•4 years ago
|
||
It's really interesting that it only regressed the warm pageload. We'll accept these as they are more realistic and I don't see any issues in the videos either. cc'ed :acreskey in case he's interested.
Comment 2•4 years ago
|
||
That is interesting.
I'm also surprised that more tests were not affected by this in general.
Comment 3•4 years ago
|
||
:acreskey, I'm going to close this as wontfix. If you think we should look into this some more though feel free to file a bug about it and we can discuss further there.
Comment 4•4 years ago
|
||
I agree with closing as wontfix - this change is a big step towards capturing a more representative codepath.
Description
•