Messages in this thread | | | From | (Eric W. Biederman) | Date | Wed, 15 Sep 2010 14:34:12 -0700 | Subject | Re: [RFC][PATCH] update /proc/sys/vm/drop_caches documentation |
| |
Dave Hansen <dave@linux.vnet.ibm.com> writes:
> On Wed, 2010-09-15 at 11:37 -0700, Eric W. Biederman wrote: >> > I'm worried that there are users out there experiencing real problems >> > that aren't reporting it because "workarounds" like this just paper over >> > the issue. >> >> For what it is worth. I had a friend ask me about a system that had 50% >> of it's memory consumed by slab caches. 20GB out of 40GB. The kernel >> was suse? 2.6.27 so it's old, but if you are curious. >> /proc/sys/vm/drop_caches does nothing in that case. > > Was it the reclaimable caches doing it, though? The other really common > cause is kmalloc() leaks.
It was reclaimable caches. He kept seeing the cache sizes of the problem caches shrink. On an idle system he said he was seeing about 16MB/min getting free or something like that. Something that would take hours and hours before things freed up.
I asked and my friend told me that according to slabtop the slab with the most memory used kept changing dramatically and he could not see a pattern.
So at least on one old kernel on one strange workload there was a problem.
Eric
| |