Friday night MP scaling reduces capacity too quickly, resulting in pending time alerts |
||
Issue description^^^ We currently scale back linux GCE instances provided by MP at 8 PM PDT / 7 PM PST. The CQ is often still working through a nontrivial (though hardly peak) load at that time. I'm going to step us down to 1000 at 8 PM PDT / 7 PST before dropping to the weekend level at 1 AM PDT / 12 AM PST.
,
Dec 20 2017
Tweaking scaling in https://chrome-internal-review.googlesource.com/c/infradata/config/+/533759
,
Dec 20 2017
The following revision refers to this bug: https://chrome-internal.googlesource.com/infradata/config/+/32291bae4bb1121100335d634386af7c470cf57d commit 32291bae4bb1121100335d634386af7c470cf57d Author: John Budorick <jbudorick@google.com> Date: Wed Dec 20 22:51:37 2017
,
Dec 20 2017
,
Dec 22 2017
Issue 793561 has been merged into this issue.
,
Dec 22 2017
Issue 793562 has been merged into this issue.
,
Dec 22 2017
Issue 793563 has been merged into this issue.
,
Dec 22 2017
Issue 793564 has been merged into this issue.
,
Dec 22 2017
Issue 793565 has been merged into this issue. |
||
►
Sign in to add a comment |
||
Comment 1 by jbudorick@chromium.org
, Dec 20 2017