Re: Unbounded growth of slab caches and how to shrink them

From	Christoph Lameter <cl@linux.com>
Newsgroups	linux.kernel
Subject	Re: Unbounded growth of slab caches and how to shrink them
Date	2016-06-29 16:40 +0200
Message-ID	<rPoOK-5l8-5@gated-at.bofh.it> (permalink)
References	<rPl4t-336-3@gated-at.bofh.it> <rPolI-5aS-13@gated-at.bofh.it> <rPoF4-5hL-15@gated-at.bofh.it>
Organization	linux.* mail to news gateway

Show all headers | View raw

On Wed, 29 Jun 2016, Nikolay Borisov wrote:

> Right, so what debugging concretely do you have in mind. So far what I
> did was reboot the machine with SLUB merging disabled, since there are
> quite a lot of slabs being merged into that particular one:
>
> :t-0000192   <- cred_jar pid_3 inet_peer_cache request_sock_TCPv6
> kmalloc-192 file_lock_cache bio-0 ip_dst_cache key_jar
>
> I'm quite sure it's likely it's one of the either networking or bio-0
> slab cache, since the others seems generally not very used.

Reboot the box with "slub_debug" on the kernel command line. Then post
the output of /sys/kernel/slab/kmalloc-128/alloc_calls and free_call after
you have recreated the situation.

Back to linux.kernel | Previous | Next — Previous in thread | Find similar | Unroll thread

Thread

Unbounded growth of slab caches and how to shrink them Nikolay Borisov <kernel@kyup.com> - 2016-06-29 12:40 +0200
  Re: Unbounded growth of slab caches and how to shrink them Christoph Lameter <cl@linux.com> - 2016-06-29 16:10 +0200
    Re: Unbounded growth of slab caches and how to shrink them Nikolay Borisov <kernel@kyup.com> - 2016-06-29 16:30 +0200
      Re: Unbounded growth of slab caches and how to shrink them Christoph Lameter <cl@linux.com> - 2016-06-29 16:40 +0200

csiph-web