From: Mike Kazantsev <mk.fraggod@gmail.com>
To: linux-mm@kvack.org
Cc: paul@paul-moore.com, netdev@vger.kernel.org
Subject: Re: PROBLEM: Memory leak (at least with SLUB) from "secpath_dup" (xfrm) in 3.5+ kernels
Date: Fri, 19 Oct 2012 23:36:32 +0600 [thread overview]
Message-ID: <20121019233632.26cf96d8@sacrilege> (raw)
In-Reply-To: <20121019205055.2b258d09@sacrilege>
[-- Attachment #1: Type: text/plain, Size: 2261 bytes --]
On Fri, 19 Oct 2012 20:50:55 +0600
Mike Kazantsev <mk.fraggod@gmail.com> wrote:
> slabtop showed "kmalloc-64" being the 99% offender in the past, but
> with recent kernels (3.6.1), it has changed to "secpath_cache"
To be more specific, on 3.5.4 kernel leak looks like this:
Active / Total Objects (% used) : 19971419 / 20084060 (99.4%)
Active / Total Slabs (% used) : 318645 / 318645 (100.0%)
Active / Total Caches (% used) : 79 / 121 (65.3%)
Active / Total Size (% used) : 1285299.85K / 1307992.83K (98.3%)
Minimum / Average / Maximum Object : 0.01K / 0.06K / 8.00K
OBJS ACTIVE USE OBJ SIZE SLABS OBJ/SLAB CACHE SIZE NAME
19678272 19678272 100% 0.06K 307473 64 1229892K kmalloc-64
159198 95262 59% 0.10K 4082 39 16328K buffer_head
32865 17515 53% 0.19K 1565 21 6260K dentry
20480 19456 95% 0.02K 80 256 320K ext4_io_page
16896 10380 61% 0.03K 132 128 528K kmalloc-32
16164 16164 100% 0.11K 449 36 1796K sysfs_dir_cache
15980 15980 100% 0.02K 94 170 376K fsnotify_event_holder
14742 9205 62% 0.87K 819 18 13104K ext4_inode_cache
13916 5494 39% 0.55K 497 28 7952K radix_tree_node
10030 5172 51% 0.05K 118 85 472K anon_vma_chain
10020 10020 100% 0.13K 334 30 1336K ext4_allocation_context
9486 9398 99% 0.04K 93 102 372K Acpi-Namespace
8192 8192 100% 0.01K 16 512 64K kmalloc-8
6960 6016 86% 0.25K 435 16 1740K kmalloc-256
6641 5412 81% 0.55K 229 29 3664K inode_cache
5124 4333 84% 0.19K 244 21 976K kmalloc-192
Unfortunately, kernel on this machine isn't booted with slub_debug
options (yet), so there're no specific on whether it's allocated (as I
understand it) in the same call or a different one.
Not sure if it's even possible that it might be the same call.
--
Mike Kazantsev // fraggod.net
[-- Attachment #2: signature.asc --]
[-- Type: application/pgp-signature, Size: 198 bytes --]
next prev parent reply other threads:[~2012-10-19 17:36 UTC|newest]
Thread overview: 21+ messages / expand[flat|nested] mbox.gz Atom feed top
2012-10-19 14:50 PROBLEM: Memory leak (at least with SLUB) from "secpath_dup" (xfrm) in 3.5+ kernels Mike Kazantsev
2012-10-19 17:36 ` Mike Kazantsev [this message]
2012-10-20 12:42 ` Paul Moore
2012-10-20 14:49 ` Mike Kazantsev
2012-10-20 22:45 ` Mike Kazantsev
2012-10-21 0:24 ` Mike Kazantsev
2012-10-21 13:29 ` Eric Dumazet
2012-10-21 13:57 ` Mike Kazantsev
2012-10-21 18:43 ` Mike Kazantsev
2012-10-21 19:51 ` Mike Kazantsev
2012-10-21 21:47 ` Eric Dumazet
2012-10-21 22:58 ` Mike Kazantsev
2012-10-22 8:15 ` Eric Dumazet
2012-10-22 12:06 ` Mike Kazantsev
2012-10-22 15:16 ` Eric Dumazet
2012-10-22 15:22 ` Eric Dumazet
2012-10-22 15:28 ` Eric Dumazet
2012-10-22 16:59 ` Mike Kazantsev
2012-10-22 17:24 ` Eric Dumazet
2012-10-22 19:03 ` [PATCH] net: fix secpath kmemleak Eric Dumazet
2012-10-22 19:17 ` David Miller
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20121019233632.26cf96d8@sacrilege \
--to=mk.fraggod@gmail.com \
--cc=linux-mm@kvack.org \
--cc=netdev@vger.kernel.org \
--cc=paul@paul-moore.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).