Messages in this thread | | | Subject | Re: [BISECTED] 2.6.35.*: horrible (exponential? >linear) slowdown to unusability (HPET) | From | Nix <> | Date | Fri, 10 Sep 2010 21:13:19 +0100 |
| |
On 10 Sep 2010, Artur Skawina outgrape:
> On 09/10/10 11:41, Jiri Slaby wrote: >> AFAIU, clocksource=jiffies shouldn't fix this issue. If that's the case >> we have another 2.6.32->2.6.33 regression (and I will report it >> separately). People report the system is unusable (sleepers are not >> woken), unless clocksource=jiffies, clocksource=tsc or nolapic_timer is >> used or a key pressed (i.e. some HW interrupt): >> https://bugzilla.novell.com/show_bug.cgi?id=579932 >> (there is also a report with 2.6.35.3 vanilla) > > I saw this first in v2.6.35-rc4. The symptom is that suddenly everything > stops and the only way to make things progress is to generate some events. > Apps that are waiting for a timeout aren't woken up unless you press a key > etc. After a few minutes (and lots of key presses ;) ) the machine usually > recovers, leaving no trace in logs.
In NOHZ mode, my (consistently affected) system never recovers. In !NOHZ mode, it never locks up, although timings are shot all to hell.
| |