421524 - 25ms (2%) Tdhtml blip on qm-pxp-fast01

Status: NEW

(Core :: General, defect)

Description

[Steve England [:stevee]]

Attachment: gain 25ms, loose 25ms

It looks like one checkin gave us a 25ms Tdhtml win, and then another checkin cancelled this gain out. Maybe it was something to do with the testbox or something, but I'm filing anyway since I went and found ranges and we might want a 2% win if we can get it.

WINNT 5.1 mini talos trunk fast qm-pxp-fast01

build start 2008/03/05 12:08:47 tdhtml: 1290.59
build start 2008/03/05 13:59:38 tdhtml: 1265.53

Checkins to module PhoenixTinderbox between 2008-03-05 12:08 and 2008-03-05 13:59 : 

http://bonsai.mozilla.org/cvsquery.cgi?treeid=default&module=PhoenixTinderbox&branch=HEAD&branchtype=match&dir=&file=&filetype=match&who=&whotype=match&sortby=Date&hours=2&date=explicit&mindate=2008-03-05+12%3A08&maxdate=2008-03-05+13%3A59&cvsroot=%2Fcvsroot


build start 2008/03/05 22:03:54 tdhtml: 1267.50
build start 2008/03/05 23:33:56 tdhtml: 1298.18

Checkins to module PhoenixTinderbox between 2008-03-05 22:03 and 2008-03-05 23:33 :

http://bonsai.mozilla.org/cvsquery.cgi?treeid=default&module=PhoenixTinderbox&branch=HEAD&branchtype=match&dir=&file=&filetype=match&who=&whotype=match&sortby=Date&hours=2&date=explicit&mindate=2008-03-05+22%3A03&maxdate=2008-03-05+23%3A33&cvsroot=%2Fcvsroot

Comment 1

[Steve England [:stevee]]

http://graphs.mozilla.org/graph.html#spst=range&spstart=0&spend=1204778167&bpst=cursor&bpstart=0&bpend=1204778167&m1tid=148125&m1bl=0&m1avg=0

Comment 2

[Mike Schroepfer]

Looks like bug 415854 might be the culprit.  When we have time we should investigate if that is intentional.