Messages in this thread | | | From | Paul Turner <> | Date | Mon, 4 Apr 2011 16:10:11 -0700 | Subject | Re: [patch 00/15] CFS Bandwidth Control V5 |
| |
On Thu, Mar 31, 2011 at 12:57 AM, Xiao Guangrong <xiaoguangrong@cn.fujitsu.com> wrote: > On 03/23/2011 11:03 AM, Paul Turner wrote: >> Hi all, >> >> Please find attached the latest version of bandwidth control for the normal >> scheduling class. This revision has undergone fairly extensive changes since >> the previous version based largely on the observation that many of the edge >> conditions requiring special casing around update_curr() were a result of >> introducing side-effects into that operation. By introducing an interstitial >> state, where we recognize that the runqueue is over bandwidth, but not marking >> it throttled until we can actually remove it from the CPU we avoid the >> previous possible interactions with throttled entities which eliminates some >> head-scratching corner cases. >> > > Hi Paul, > > I have wrote some codes to test this patchset. While run attached test case, > the test program is blocked, it seams the children tasks can not be killed, > after one or two hours, the watchdog is expired and triggers box crashed. >
Sorry, I was out last week.
I'm taking a look at this now, I believe the interaction lies somewhere within the quota return paths.
Thanks for taking the time to test!
- Paul -- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/
| |