Messages in this thread | | | Subject | Re: kmemleak disabled itself in 2.6.36 | From | Catalin Marinas <> | Date | Thu, 28 Oct 2010 14:33:22 +0100 |
| |
On Thu, 2010-10-28 at 14:13 +0100, Toralf Förster wrote: > Catalin Marinas wrote at 10:33:09 > > On Wed, 2010-10-27 at 20:12 +0100, Toralf Förster wrote: > > > I'm unsure whether this happens due to a > > > $> sudo su -c "echo clear > /sys/kernel/debug/kmemleak" > > > or while regular scanning, but anyway seems not to be normal, or ? > > > > > > 2010-10-27T20:42:21.697+02:00 n22 kernel: flush-254:0: page allocation > > > failure. order:0, mode:0x0 > > [...] > > > 2010-10-27T20:42:21.699+02:00 n22 kernel: kmemleak: Cannot allocate a > > > kmemleak_object structure 2010-10-27T20:42:21.699+02:00 n22 kernel: Pid: > > > 15475, comm: flush-254:0 Not tainted 2.6.36 #2 > > [...] > > > 2010-10-27T20:42:21.700+02:00 n22 kernel: kmemleak: Kernel memory leak > > > detector disabled > > > > Are you running out of memory on your system? Kmemleak tried to allocate > > a structure but the slab allocator failed to get page. Kmemleak disables > > itself in such situations but the problem is somewhere else (not enough > > memory?). > > I don't think so - no big load to that system, no excessive compiler runs ...
What does /proc/meminfo say after you got this error?
Which slab allocator are you using?
Catalin
-- 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/
| |