- linux-release-hardy/v8_benchmark/score/score
  - vista-release-single-core/morejs/times/t
  - vista-release-single-core/moz/times/t
  - xp-release-single-core/intl1/times/t
  - xp-release-single-core/intl2/times/t
  - xp-release-single-core/morejs/times/t
  - xp-release-single-core/moz/times/t

BUG=none
TEST=perf steps are green
TBR=nsylvain@chromium.org

Review URL: http://codereview.chromium.org/6007008

git-svn-id: svn://svn.chromium.org/chrome/trunk/src@70594 0039d316-1c4b-4281-b951-d872f2087c98

  mac-release-10.5/intl1/times/t
  mac-release-10.5/intl2/times/t
  mac-release-10.5/startup/times/t
  mac-release-10.5/v8_benchmark/score/score
  mac-release-10.6/v8_benchmark/score/score
  vista-release-dual-core/v8_benchmark/score/score
  xp-release-dual-core/intl1/times/t
  xp-release-dual-core/intl2/times/t
  xp-release-dual-core/morejs/times/t
  xp-release-dual-core/v8_benchmark/score/score

BUG=none
TEST=perf steps are green
TBR=nsylvain@chromium.org

Review URL: http://codereview.chromium.org/5781007

git-svn-id: svn://svn.chromium.org/chrome/trunk/src@69078 0039d316-1c4b-4281-b951-d872f2087c98

  mac-release-10.5/morejs/times/t
  mac-release-10.6/dhtml/times/t
  mac-release-10.6/morejs/times/t
  mac-release-10.6/moz/times/t
  vista-release-dual-core/intl1/times/t
  vista-release-dual-core/morejs/times/t
  vista-release-dual-core/moz/times/t
  xp-release-dual-core/moz/times/t
  xp-release-dual-core/moz/total_byte_b/IO_b
  xp-release-dual-core/moz/total_byte_r/IO_r
  xp-release-dual-core/moz/total_op_b/IO_op_b
  xp-release-dual-core/moz/total_op_r/IO_op_r
  xp-release-dual-core/moz/vm_peak_b/vm_pk_b
  xp-release-dual-core/moz/vm_peak_r/vm_pk_r

BUG=none
TEST=perf waterfall steps are green
TBR=nsylvain@chromium.org

Review URL: http://codereview.chromium.org/5782002

git-svn-id: svn://svn.chromium.org/chrome/trunk/src@69056 0039d316-1c4b-4281-b951-d872f2087c98

These changed after the v8 and ref build updates.

  linux-release-hardy/dhtml/times/t
  linux-release-hardy/dhtml/total_byte_b/IO_b
  linux-release-hardy/dhtml/total_byte_r/IO_r
  linux-release-hardy/dhtml/total_op_b/IO_op_b
  linux-release-hardy/dhtml/total_op_r/IO_op_r
  linux-release-hardy/dhtml/vm_rss_final_b/vm_rss_f_b
  linux-release-hardy/dhtml/vm_rss_final_r/vm_rss_f_r
  linux-release-hardy/dhtml/vm_rss_final_t/vm_rss_f_t
  linux-release-hardy/dhtml/vm_size_final_b/vm_size_f_b
  linux-release-hardy/dhtml/vm_size_final_r/vm_size_f_r
  linux-release-hardy/dhtml/vm_size_final_t/vm_size_f_t
  linux-release-hardy/intl1/times/t
  linux-release-hardy/intl2/times/t
  linux-release-hardy/morejs/times/t
  linux-release-hardy/moz/times/t
  linux-release-hardy/v8_benchmark/score/score

BUG=none
TEST=linux steps are green
TBR=nsylvain@chromium.org

Review URL: http://codereview.chromium.org/5731002

git-svn-id: svn://svn.chromium.org/chrome/trunk/src@68815 0039d316-1c4b-4281-b951-d872f2087c98

v8_benchmark improved on the following platforms
after r68477:

  - linux-release-hardy v8_benchmark
  - mac-release-10.5 v8_benchmark
  - mac-release-10.6 v8_benchmark
  - vista-release-dual-core v8_benchmark
  - xp-release-dual-core v8_benchmark

We should be curious about the linux-release-hardy
results, which don't show a score increase like the
other platforms.

BUG=none
TEST=v8_benchmark is green
TBR=nsylvain@chromium.org

Review URL: http://codereview.chromium.org/5573012

git-svn-id: svn://svn.chromium.org/chrome/trunk/src@68551 0039d316-1c4b-4281-b951-d872f2087c98

BUG=63267
TEST=v8 benchmark step is green
TBR=nsylvain@chromium.org

Review URL: http://codereview.chromium.org/5030004

git-svn-id: svn://svn.chromium.org/chrome/trunk/src@66200 0039d316-1c4b-4281-b951-d872f2087c98

  - total_op_b went up around r65182, bug for that
    is 62272

  - total_byte_r and total_byte_b went up around r64763,
    bug for that is 62274.

BUG=62272, 62274
TEST=xp perf is green
TBR=nsylvain@chromium.org

Review URL: http://codereview.chromium.org/4652001

git-svn-id: svn://svn.chromium.org/chrome/trunk/src@65343 0039d316-1c4b-4281-b951-d872f2087c98

We improved some on intl1/times/t.  Update expectations
to match.

BUG=none
TEST=xp perf/intl1 is green
TBR=nsylvain@chromium.org

Review URL: http://codereview.chromium.org/4133008

git-svn-id: svn://svn.chromium.org/chrome/trunk/src@64352 0039d316-1c4b-4281-b951-d872f2087c98

  - linux-release-hardy/dhtml
  - linux-release-hardy/intl1/times/t
  - linux-release-hardy/morejs/times/t

The dhtml vm_rss_final_b increase appears due to r64072.

BUG=none
TEST=linux perf is green
TBR=nsylvain@chromium.org

Review URL: http://codereview.chromium.org/4133007

git-svn-id: svn://svn.chromium.org/chrome/trunk/src@64343 0039d316-1c4b-4281-b951-d872f2087c98

These new expectations match what's present on the new
perf dashboard.

BUG=none
TEST=perf steps are green
TBR=nsylvain@chromium.org

Review URL: http://codereview.chromium.org/4138007

git-svn-id: svn://svn.chromium.org/chrome/trunk/src@64033 0039d316-1c4b-4281-b951-d872f2087c98

  - linux-release-hardy/intl1/times/t
  - linux-release-hardy/dhtml/commit_charge/cc
  - linux-release-hardy/dhtml/total_op_b/IO_op_b
  - xp-release-dual-core/intl1/times/t
  - xp-release-dual-core/morejs/times/t
  - xp-release-dual-core/moz/times/t
  - xp-release-dual-core/moz/total_byte_r/IO_r

BUG=59985
TEST=perf steps are green
TBR=nsylvain@chromium.org

Review URL: http://codereview.chromium.org/3962002

git-svn-id: svn://svn.chromium.org/chrome/trunk/src@63339 0039d316-1c4b-4281-b951-d872f2087c98

BUG=none
TEST=vistadual/morejs is green
TBR=nsylvain@chromium.org

Review URL: http://codereview.chromium.org/3750016

git-svn-id: svn://svn.chromium.org/chrome/trunk/src@62917 0039d316-1c4b-4281-b951-d872f2087c98

  - linux-release-hardy/intl2/times/t
  - mac-release-10.5/startup/warm/t improvement due
    to WebKit roll at r61094
  - mac-release-10.6/morejs/times/t
  - xp-release-dual-core/intl2/times/t
  - xp-release-dual-core/moz/total_byte_r/IO_r big
    decrease at 61200:61205.
  - xp-release-dual-core/startup/warm/t speedup from r61096

BUG=none
TEST=perf steps are green
TBR=nsylvain@chromium.org

Review URL: http://codereview.chromium.org/3601005

git-svn-id: svn://svn.chromium.org/chrome/trunk/src@61235 0039d316-1c4b-4281-b951-d872f2087c98

  - linux-release-hardy/dhtml/total_byte_b/IO_b
  - linux-release-hardy/dhtml/total_byte_r/IO_r
  - linux-release-hardy/dhtml/total_op_b/IO_op_b
  - linux-release-hardy/dhtml/total_op_r/IO_op_r
  - linux-release-hardy/dhtml/vm_rss_final_b/vm_rss_f_b
  - linux-release-hardy/dhtml/vm_rss_final_r/vm_rss_f_r
  - linux-release-hardy/dhtml/vm_rss_final_t/vm_rss_f_t
  - linux-release-hardy/dhtml/vm_size_final_b/vm_size_f_b
  - linux-release-hardy/dhtml/vm_size_final_r/vm_size_f_r
  - linux-release-hardy/dhtml/vm_size_final_t/vm_size_f_t
  - linux-release-hardy/dhtml/commit_charge/cc
  - linux-release-hardy/dhtml/processes/proc_
  - linux-release-hardy/v8_benchmark/score/score
  - mac-release-10.5/intl2/vm_rss_final_b
  - mac-release-10.5/intl2/vm_rss_final_r
  - mac-release-10.5/intl2/vm_rss_final_t
  - mac-release-10.5/intl2/vm_size_final_b
  - mac-release-10.5/intl2/vm_size_final_r
  - mac-release-10.5/intl2/vm_size_final_t
  - mac-release-10.5/v8_benchmark/score/score
  - mac-release-10.6/v8_benchmark/score/score
  - vista-release-dual-core/v8_benchmark/score/score
  - xp-release-dual-core/v8_benchmark/score/score

BUG=none
TEST=perf steps are green
TBR=nsylvain@chromium.org

Review URL: http://codereview.chromium.org/3585006

git-svn-id: svn://svn.chromium.org/chrome/trunk/src@61194 0039d316-1c4b-4281-b951-d872f2087c98

Most changes are to avoid false positives.  There's a
small regression somewhere in the intl page cyclers
which I filed a bug on.

  - linux-release-hardy/dhtml/times/t
  - mac-release-10.6/intl1/times/t
  - mac-release-10.6/intl2/times/t
  - vista-release-dual-core/intl1/times/t
  - xp-release-dual-core/intl1/times/t
  - xp-release-dual-core/intl2/times/t
  - xp-release-dual-core/morejs/times/t
  - xp-release-dual-core/startup/warm/t

BUG=57447
TEST=perf steps are green
TBR=nsylvain@chromium.org

Review URL: http://codereview.chromium.org/3572005

git-svn-id: svn://svn.chromium.org/chrome/trunk/src@61093 0039d316-1c4b-4281-b951-d872f2087c98

Adjust after a slight intl1/intl2 perf improvement,
and avoid false alarms on other tests.

  - linux-release-hardy/startup/warm/t
  - mac-release-10.5/intl2/times/t
  - mac-release-10.6/intl1/times/t
  - mac-release-10.6/moz/times/t
  - vista-release-dual-core/dhtml/times/t
  - vista-release-dual-core/intl1/times/t

BUG=none
TEST=perf steps are green
TBR=nsylvain@chromium.org

Review URL: http://codereview.chromium.org/3441023

git-svn-id: svn://svn.chromium.org/chrome/trunk/src@60134 0039d316-1c4b-4281-b951-d872f2087c98

This widens or otherwise adjust perf expectations to
avoid false negatives:

  - linux-release-hardy/dhtml/times/t
  - mac-release-10.6/dhtml/times/t
  - mac-release-10.6/intl1/times/t
  - mac-release-10.6/intl2/times/t
  - vista-release-dual-core/dhtml/times/t
  - xp-release-dual-core/moz/times/t
  - xp-release-dual-core/moz/total_byte_r/IO_r
  - xp-release-dual-core/startup/warm/t

BUG=none
TEST=perf steps are green
TBR=nsylvain@chromium.org

Review URL: http://codereview.chromium.org/3466004

git-svn-id: svn://svn.chromium.org/chrome/trunk/src@59968 0039d316-1c4b-4281-b951-d872f2087c98

Following upstream WebKit perf slowdown and possible
V8 regression.

 - mac-release-10.5/morejs/times/t
 - mac-release-10.6/morejs/times/t
 - xp-release-dual-core/morejs/times/t

BUG=none
TEST=mac10.5, mac10.6, and xpdual morejs is green
TBR=nsylvain@chromium.org

Review URL: http://codereview.chromium.org/3367027

git-svn-id: svn://svn.chromium.org/chrome/trunk/src@59282 0039d316-1c4b-4281-b951-d872f2087c98

slowed due to WebKit bug 45524.

Hopefully I am adjusting the expectations correctly.

BUG=https://bugs.webkit.org/show_bug.cgi?id=45524
TEST=page cycle bots green up
TBR=chase@chromium.org

Review URL: http://codereview.chromium.org/3306017

git-svn-id: svn://svn.chromium.org/chrome/trunk/src@59206 0039d316-1c4b-4281-b951-d872f2087c98

  - mac-release-10.5/intl1/times/t
  - mac-release-10.5/startup/warm/t
  - mac-release-10.6/intl2/times/t
  - xp-release-dual-core/intl2/times/t
  - xp-release-dual-core/moz/total_byte_r/IO_r
  - xp-release-dual-core/moz/total_op_r/IO_op_r
  - xp-release-dual-core/moz/vm_peak_r/vm_pk_r

BUG=none
TEST=these are green: mac10.5 perf (1) intl1 and
startup, mac10.6 (perf) intl2, xp perf(1) intl2 and moz
TBR=nsylvain@chromium.org

Review URL: http://codereview.chromium.org/3328007

git-svn-id: svn://svn.chromium.org/chrome/trunk/src@58435 0039d316-1c4b-4281-b951-d872f2087c98

BUG=none
TEST=vistadual/intl2 is green
TBR=nsylvain@chromium.org

Review URL: http://codereview.chromium.org/3325003

git-svn-id: svn://svn.chromium.org/chrome/trunk/src@58222 0039d316-1c4b-4281-b951-d872f2087c98

  - vista-release-dual-core/dhtml/times
  - vista-release-dual-core/intl1/times
  - xp-release-dual-core/moz/times

BUG=none
TEST=tests are green
TBR=nsylvain@chromium.org

Review URL: http://codereview.chromium.org/3349002

git-svn-id: svn://svn.chromium.org/chrome/trunk/src@58202 0039d316-1c4b-4281-b951-d872f2087c98

  - mac-release-10.6/morejs/times
  - vista-release-dual-core/intl2/times
  - vista-release-dual-core/moz/times.
  - xp-release-dual-core/moz/vm_peak_r

BUG=none
TEST=perf is green
TBR=nsylvain@chromium.org

Review URL: http://codereview.chromium.org/3217017

git-svn-id: svn://svn.chromium.org/chrome/trunk/src@58076 0039d316-1c4b-4281-b951-d872f2087c98

These metrics are being updated to note improvements:

- xp-release-dual-core/intl1/times
- xp-release-dual-core/morejs/times
- xp-release-dual-core/moz/vm_peak_b
- xp-release-dual-core/moz/vm_peak_r
- vista-release-dual-core/intl1/times
- vista-release-dual-core/morejs/times
- vista-release-dual-core/moz/times
- vista-release-dual-core/intl2/times
- mac-release-10.5/morejs/times
- mac-release-10.5/intl2/times
- mac-release-10.6/morejs/times

BUG=none
TEST=listed perf steps are green
TBR=nsylvain@chromium.org

Review URL: http://codereview.chromium.org/3244008

git-svn-id: svn://svn.chromium.org/chrome/trunk/src@58061 0039d316-1c4b-4281-b951-d872f2087c98

- linux-release-hardy/dhtml/times
- linux-release-hardy/morejs/times
- mac10.6/morejs/times
- mac10.6/dhtml/times
- vista-release-dual-core/morejs/times
- xpdual/moz/total_byte_b
- xpdual/moz/total_op_b
- xpdual/startup/times

BUG=none
TEST=tests are green
TBR=nsylvain@chromium.org

Review URL: http://codereview.chromium.org/3270006

git-svn-id: svn://svn.chromium.org/chrome/trunk/src@57835 0039d316-1c4b-4281-b951-d872f2087c98

The regression from the WebKit roll looks worse than
originally seen.

BUG=none
TEST=linux-release-hardy/intl* is green
TBR=nsylvain@chromium.org

Review URL: http://codereview.chromium.org/3248004

git-svn-id: svn://svn.chromium.org/chrome/trunk/src@57832 0039d316-1c4b-4281-b951-d872f2087c98

This vm_peak_b increase is still under investigation.  Mark
it as expected while that work happens.

BUG=53619
TEST=xpdual/moz is green
TBR=nsylvain@chromium.org

Review URL: http://codereview.chromium.org/3286003

git-svn-id: svn://svn.chromium.org/chrome/trunk/src@57830 0039d316-1c4b-4281-b951-d872f2087c98

Regression appeared in r57724 (WebKit 66079:66240).
Tony Chang identified it as caused by WebKit r66115.
Update expectations for now.

BUG=none
TEST=intl steps are green
TBR=tony@chromium.org

Review URL: http://codereview.chromium.org/3226013

git-svn-id: svn://svn.chromium.org/chrome/trunk/src@57769 0039d316-1c4b-4281-b951-d872f2087c98

Looks like a regression introduced somewhere between
r55576 and r55952.

BUG=none
TEST=mac10.6/moz is green
TBR=nsylvain@chromium.org

Review URL: http://codereview.chromium.org/3180030

git-svn-id: svn://svn.chromium.org/chrome/trunk/src@57546 0039d316-1c4b-4281-b951-d872f2087c98

This looks like a local system change after a reboot
since t_ref changed, too.

BUG=none
TEST=xpdual/moz is green
TBR=nsylvain@chromium.org

Review URL: http://codereview.chromium.org/3190015

git-svn-id: svn://svn.chromium.org/chrome/trunk/src@57091 0039d316-1c4b-4281-b951-d872f2087c98

This updates the following systems to use the new improve/regress
format:
  - linux-release
  - linux-release-hardy
  - mac10.5
  - mac10.6
  - vista-release-dual-core
  - vista-release-single-core
  - xp-release-dual-core
  - xp-release-single-core

BUG=none
TEST=perf steps run correctly

Review URL: http://codereview.chromium.org/3148028

git-svn-id: svn://svn.chromium.org/chrome/trunk/src@56872 0039d316-1c4b-4281-b951-d872f2087c98

BUG=none
TEST=linux-hardy/moz is green
TBR=nsylvain@chromium.org

Review URL: http://codereview.chromium.org/3146017

git-svn-id: svn://svn.chromium.org/chrome/trunk/src@56274 0039d316-1c4b-4281-b951-d872f2087c98

This is a test.  If this test passes, I'll convert the
rest of the measures.  It includes a change to the
expectations to account for this test's new performance.
If it didn't include that change, the line would be
improve: -9, regress: 9.

BUG=none
TEST=linux/moz is green

Review URL: http://codereview.chromium.org/3115012

git-svn-id: svn://svn.chromium.org/chrome/trunk/src@56267 0039d316-1c4b-4281-b951-d872f2087c98

Review URL: http://codereview.chromium.org/3119015

git-svn-id: svn://svn.chromium.org/chrome/trunk/src@56178 0039d316-1c4b-4281-b951-d872f2087c98

Review URL: http://codereview.chromium.org/3108021

git-svn-id: svn://svn.chromium.org/chrome/trunk/src@56177 0039d316-1c4b-4281-b951-d872f2087c98

Most of the errors look like it came from the V8 merge a while back, but the perf expectations were a little bit too strict.

2 new perf regressions, both fairly small:

xp perf intl2: http://build.chromium.org/buildbot/perf/xp-release-dual-core/intl2/report.html?history=140&rev=55952
Blame: 55671 (ananta)

xp perf intl1: http://build.chromium.org/buildbot/perf/xp-release-dual-core/intl1/report.html?history=100&rev=56174
Only 0.5%. Blame: Possibly 56044 (WebKit merge 65180:65318)

Review URL: http://codereview.chromium.org/3121018

git-svn-id: svn://svn.chromium.org/chrome/trunk/src@56176 0039d316-1c4b-4281-b951-d872f2087c98

  - xpdual/dhtml/times - dhtml speedup
  - xpdual/intl1/times - slowdown (unknown cause)
  - xpdual/moz results - new variability in results

BUG=51863
TEST=xpdual/dhtml, intl1, and moz are green
TBR=nsylvain@chromium.org

Review URL: http://codereview.chromium.org/3172007

git-svn-id: svn://svn.chromium.org/chrome/trunk/src@55833 0039d316-1c4b-4281-b951-d872f2087c98

This reverts r55769.

BUG=none
TEST=mac10.6/dhtml passes
TBR=nsylvain@chromium.org

Review URL: http://codereview.chromium.org/3151009

git-svn-id: svn://svn.chromium.org/chrome/trunk/src@55779 0039d316-1c4b-4281-b951-d872f2087c98

Update unit tests.

BUG=none
TEST=mac10.6/dhtml is orange

Review URL: http://codereview.chromium.org/3180002

git-svn-id: svn://svn.chromium.org/chrome/trunk/src@55769 0039d316-1c4b-4281-b951-d872f2087c98

Looks like this result can be flaky, so give it a new
delta and var to keep the step green most of the time.

BUG=none
TEST=xpdual/moz is green
TBR=nsylvain@chromium.org

Review URL: http://codereview.chromium.org/3158003

git-svn-id: svn://svn.chromium.org/chrome/trunk/src@55623 0039d316-1c4b-4281-b951-d872f2087c98