summaryrefslogtreecommitdiff
path: root/cmds/cmd/cmd.cpp
diff options
context:
space:
mode:
author Robert Carr <racarr@google.com> 2017-12-04 13:51:20 -0800
committer Robert Carr <racarr@google.com> 2017-12-04 15:58:07 -0800
commit29abff83bb6e148961c2319add7bd72eb76af3d4 (patch)
tree9f950fd297c5fa57aa1b28c4172ff75640095b17 /cmds/cmd/cmd.cpp
parent13dd603c8e138d670bd2ef5a02bda0b059f6eb67 (diff)
Optimize layer traversal
I found when investigating traces with reported jank from P there was a large amount of time in handleMessageInvalidate but before latchBuffer. The only culprit here could be layer traversal itself. The current algorithm is quite costy requiring producing copies of sp, allocating a new vector, etc (see makeTraversalList). This CL optimizes the case where there are no relatives of the current layer. I found that this does in fact eliminate the new time in handleMessageInvalidate and also reduces onPreComposition. Bug:69852584 Test: Manual, comparison of systrace, relative Z still works. Change-Id: I2d942c1987087aae85decc0480d3622204ed665d
Diffstat (limited to 'cmds/cmd/cmd.cpp')
0 files changed, 0 insertions, 0 deletions