duflu | This is odd. Why is Xorg slower on Haswell than Sandybridge?! | 01:49 |
---|---|---|
duflu | Mir has no such problems | 01:50 |
RAOF | duflu: What test? | 02:06 |
RAOF | duflu: Also, fast Sandybridge vs slow Haswell? | 02:06 |
duflu | RAOF: I swapped my drive out of an HD2000 system into an HD4400 | 02:07 |
duflu | And it stutters quite a bit | 02:07 |
duflu | Oops... HD4600 | 02:08 |
duflu | I'm suspicious of: [ 1.949] (**) intel(0): "Tear free" disabled | 02:09 |
duflu | But can't remember what it used to be | 02:09 |
=== chihchun_afk is now known as chihchun | ||
mlankhorst | there didn't used to be a tear free option | 09:14 |
mlankhorst | and it was always disabled :p | 09:14 |
duflu | mlankhorst: Just guessing... | 09:57 |
duflu | But if I wanted a real answer I would debug Compiz | 09:57 |
duflu | trying to avoid that | 09:57 |
duflu | alan_g: Any hints as to how to force gmock to match 16 elements passed to a GLfloat* parameter? :) | 09:58 |
alan_g | duflu: write a bespoke matcher? | 09:59 |
duflu | alan_g: That's what I thought, but attempts so far don't even compile | 09:59 |
duflu | And the docs are too vague to explain why | 10:00 |
alan_g | racarr has written quite a few around the input tests | 10:00 |
duflu | On second thoughts, this test probably should not exist using mocks. It assumes too much about the internals of the class | 10:05 |
alan_g | Talking about assuming implementation details: Does anyone think SocketSessionTest.basic_msg is a readable or useful test? | 10:25 |
* alan_g wants to delete it | 10:25 | |
duflu | alan_g: If you can't read it then that doesn't bode well. I though you knew that stuff better than most | 10:28 |
duflu | +t | 10:28 |
* duflu wanders off | 10:28 | |
=== chihchun is now known as chihchun_afk | ||
ricmm | kdub: asleep? ;) | 11:10 |
=== chihchun_afk is now known as chihchun | ||
alan_g | alf_: can you take a look? I'm getting happier with it (but it may be just that I'm getting used to it): https://code.launchpad.net/~alan-griffiths/mir/spike-exposing-rpc-in-frontend/+merge/202351 | 13:02 |
=== alan_g is now known as alan_g|lunch | ||
alf_ | alan_g|lunch: sure | 13:03 |
=== alan_g|lunch is now known as alan_g | ||
=== chihchun is now known as chihchun_afk | ||
kgunn | alf_: a matter of curiosity, we don't have triple buffering on at the client level do we ? | 14:11 |
=== dandrader is now known as dandrader|afk | ||
alan_g | kgunn: we don't | 14:17 |
=== alan_g is now known as alan_g|afk | ||
alf_ | kgunn: alan_g: AFAIK, the code supports triple buffering for client surfaces. What is blocking it? | 14:17 |
kgunn | alf_: so i was just thinking, wrt side stage, where the code relies on snapshotting when "closing"/"revealing" | 14:21 |
kgunn | and that the pipeline is stalling | 14:21 |
kgunn | e.g. its gotta read from the buff | 14:21 |
kgunn | before it let's it continue rendering | 14:21 |
kgunn | & swapping buffs | 14:21 |
kgunn | whereas, triple buffering would at least help alleviate | 14:21 |
kgunn | this getting in at least one extra render while you're still reading | 14:22 |
kgunn | (all theory of course) | 14:22 |
kgunn | ricmm: ^ | 14:22 |
=== dandrader|afk is now known as dandrader | ||
alf_ | kgunn: are we seeing an actual slowdown when the sidestage is revealed/closed? | 14:26 |
kgunn | alf_: yeah there's definitely some stall/jank at times | 14:26 |
kgunn | if you flash devel-proposed, it has sidestage...N10 of course | 14:27 |
alf_ | kgunn: And I am assuming that snapshotting been identified as the culprit or is this a theory? | 14:28 |
kgunn | alf_: all theory | 14:28 |
ricmm | alf_: do you have a N10? | 14:32 |
alf_ | ricmm: yes | 14:33 |
ricmm | can you give it a go with the latest image | 14:33 |
ricmm | you'll have the feel of whats happening | 14:33 |
alf_ | ricmm: ok | 14:33 |
=== alan_g|afk is now known as alan_g | ||
=== chihchun_afk is now known as chihchun | ||
alan_g | alf_: sorted tabs (and placated valgrind over the SocketSessionTest.basic_msg_is_received_and_dispatched test) | 15:19 |
alf_ | alan_g: ok | 15:20 |
=== alan_g is now known as alan_g|tea | ||
=== alan_g|tea is now known as alan_g | ||
=== dandrader is now known as dandrader|lunch | ||
=== dandrader_ is now known as dandrader | ||
=== alan_g is now known as alan_g|EOD | ||
=== chihchun is now known as chihchun_afk | ||
=== dandrader is now known as dandrader|afk | ||
=== dandrader|afk is now known as dandrader | ||
dandrader | do you guys have trouble getting useful backtraces out of gdb on the device (arm)? | 20:16 |
kdub | dandrader, sometimes | 20:22 |
dandrader | kdub, any trick I can do to improve it? | 20:23 |
kdub | dandrader, unfortunately no, havent spent a lot of time looking | 20:26 |
Generated by irclog2html.py 2.7 by Marius Gedminas - find it at mg.pov.lt!