New issue
Advanced search Search tips

Issue 613569 link

Starred by 5 users

Issue metadata

Status: Assigned
Owner:
EstimatedDays: ----
NextAction: ----
OS: Windows
Pri: 3
Type: Bug



Sign in to add a comment

Timer frequency raised by browsing to arstechnica.com, not always reset

Project Member Reported by brucedaw...@chromium.org, May 20 2016

Issue description

Something on arstechnica.com (ads?) causes Chrome to raise the timer frequency to 1 kHz (from the default 64 Hz) even when arstechnica is not visible. It also appears (hard to tell for sure) that the timer frequency sometimes stays raised after the arstechnica.com tab is closed.

Both issues are worth investigating.

The timer frequency can easily be seen by running the sysinternals clockres tool.

The cause of the raised frequency can be seen by running "powercfg /energy /duration 1" in an administrator command prompt and then searching the energy-report.html that is created for Platform Timer Resolution:Timer Request Stack.
 
audiodg sometimes raises the timer frequency, especially on Windows 8.1, which can make these investigations more difficult. "stop and disable audiosrv service will keep it out of your way" (https://twitter.com/mvaneerde/status/733513965964165121)

Ping! This bug is assigned and has an owner, but hasn't been updated in over 180 days. Is this still something we want to do?
It's not clear whether this is really a page-specific bug or, more likely, just a general instance of  crbug.com/153139 .  crbug.com/153139  is tagged as fixed and a fix which improved its behavior was certainly landed but it did not fully avoid raising the timer frequency. It just ensured that the frequency was not always raised.

Some investigation of this should be done but it may end up being better tagged as part of another bug.

Sign in to add a comment