Bug 13454
| Summary: | i915-related page allocation failure in Xorg | ||
|---|---|---|---|
| Product: | Drivers | Reporter: | James Ettle (james) |
| Component: | Video(DRI - Intel) | Assignee: | drivers_video-dri-intel (drivers_video-dri-intel) |
| Status: | RESOLVED CODE_FIX | ||
| Severity: | normal | CC: | chris, gordon.jin |
| Priority: | P1 | ||
| Hardware: | All | ||
| OS: | Linux | ||
| Kernel Version: | Subsystem: | ||
| Regression: | No | Bisected commit-id: | |
| Attachments: | syslog excerpt with page allocation failure backtraces | ||
Does this still exist in 2.6.31? I've just seen page allocation failures in 2.6.31, but this time in a number of processes. Ironically, Xorg wasn't one of them and there was no mention of i915 in the backtraces, so maybe this is symptomatic of a wider memory management problem. It happened during a kernel compile, but I think I've seen it happen in the past whenever a lot of stuff gets swapped out to make way for file cache. Those spurious warnings were just a silly use of NORETRY in the drm code and have since been removed. |
Created attachment 21747 [details] syslog excerpt with page allocation failure backtraces I have witnessed a number of (sporadic) page allocation failures in Xorg. This normally happens after some moderate stress (e.g. playing videos with Compiz enabled), possibly following a few suspend/resume cycles (although this may be just be due to a long uptime). This is with Intel X3100 graphics using: kernel-2.6.29.4-167.fc11.x86_64 xorg-x11-drv-intel-2.7.0-7.fc11.x86_64 libdrm-2.4.6-7.fc11.x86_64 Attached is a syslog excerpt with the backtraces.