1517355 - Add CONTENT_FRAME_TIME variant that uses the vsync time as the start point

Status: RESOLVED FIXED

(Core :: Graphics: WebRender, enhancement)

Description

[Matt Woodrow (:mattwoodrow)]

The current CONTENT_FRAME_TIME uses the start of display list building, which means that we don't know the exact point at which we miss a frame (since it depends on how long pre-DL building tasks took).

We're currently assuming 200 (and that DL building started immediately after vsync), but that's probably often not correct.

If the 200 marks ends up being after the 'missed' vsync point, then there's a chance that a late composite might end up being done, and will show up as not being late by this metric.

We're going to add a new variant that times from vsync, so that 200 becomes much more meaningful.

Comment 1

[Matt Woodrow (:mattwoodrow)]

Attachment: request.md

Comment 2

[Matt Woodrow (:mattwoodrow)]

Attachment: Bug 1517355 - Add CONTENT_FRAME_TIME variant that records from the vsync time. data-review=rrayborn, r?jrmuizel

Comment 3

[Robert (rrayborn, he/him)]

Comment on attachment 9034039 [details]
request.md

General Notes: Straightforward, iterative change

1) Is there or will there be **documentation** that describes the schema for the ultimate data set available publicly, complete and accurate?
Yes, Histograms.json, relatively straightforward.

2) Is there a control mechanism that allows the user to turn the data collection on and off?
Yes, Telemetry Defaults

3) If the request is for permanent data collection, is there someone who will monitor the data over time?
Yes, [e-mail] + [e-mail]

4) Using the category system of data types (https://wiki.mozilla.org/Firefox/Data_Collection), what collection type of data do the requested measurements fall under?
Category 1

5) Is the data collection request for default-on or default-off?
Telemetry Defaults

6) Does the instrumentation include the addition of any *new* identifier* (whether anonymous or otherwise; e.g., username, random IDs, etc.  See the appendix for more details)?
No

7) Is the data collection covered by the existing Firefox privacy notice?
Yes, standard Telemetry

8) Does there need to be a check-in in the future to determine whether to renew the data?
No

Comment 4

[Jeff Muizelaar [:jrmuizel]]

https://treeherder.mozilla.org/#/jobs?repo=try&revision=651c7c1897ec5ec76f3946f5ed358ea321809bac

Comment 5

[Pulsebot]

Pushed by [e-mail]:
https://hg.mozilla.org/integration/autoland/rev/4a8c79b919b2
Add CONTENT_FRAME_TIME variant that records from the vsync time. data-review=rrayborn, r=jrmuizel

Comment 6

[Andrei Ciure[:aciure]]

https://hg.mozilla.org/mozilla-central/rev/4a8c79b919b2