[squid-users] Slowly rising CPU load (eventually hits 100)

[Yuri Voinov]

-----BEGIN PGP SIGNED MESSAGE-----
Hash: SHA256
 
Looks like permanently running clients, which is exausted network
resources and then initiating connection abort.

Try to add

client_persistent_connections off

to squid.conf.

Then observe.

31.03.16 19:53, squid at peralex.com пишет:
> Hi,
>
> I'm running:
>
> Squid Cache: Version 3.5.15  (including patches up to revision 14000)
>
> on FreeBSD 9.3-STABLE (recently updated)
>
> Every week or so I run into a problem where squid's CPU usage starts
> growing slowly, reaching 100% over the course of a day or so.  When
> running normally its CPU usage is usually less than 5%.  Restarting
> squid fixes the problem.
>
> Memory usage is about 2 GBytes (on a system with 8 GBytes of RAM).
>
> The number of socket connections (from clients and to servers) is about
> the same (roughly 500) when I have the problem as when I don't have the
> problem.
>
> Attaching GDB and getting a stack trace while squid is stuck at 100%
> generally gives me this:
>
> #0  0x00000000005deef4 in mem_node::end ()
> #1  0x00000000005df076 in mem_node::dataRange ()
> #2  0x0000000000625d34 in mem_hdr::NodeCompare ()
> #3  0x0000000000628ad1 in SplayNode<mem_node*>::splay<mem_node*> ()
> #4  0x0000000000628b85 in Splay<mem_node*>::find<mem_node*> ()
> #5  0x0000000000625f8e in mem_hdr::getBlockContainingLocation ()
> #6  0x0000000000625ff8 in mem_hdr::hasContigousContentRange ()
> #7  0x00000000005e00fe in MemObject::isContiguous ()
> #8  0x0000000000649d05 in StoreEntry::mayStartSwapOut ()
> #9  0x0000000000648b96 in StoreEntry::swapOut ()
> #10 0x0000000000639e87 in StoreEntry::invokeHandlers ()
> #11 0x0000000000633e09 in StoreEntry::write ()
> #12 0x000000000079caa1 in Client::storeReplyBody ()
> #13 0x000000000059c0bf in HttpStateData::writeReplyBody ()
> #14 0x00000000005a18fd in HttpStateData::processReplyBody ()
> #15 0x00000000005a41ce in HttpStateData::processReply ()
> #16 0x00000000005a4408 in HttpStateData::readReply ()
> #17 0x00000000005ab6df in JobDialer<HttpStateData>::dial ()
> #18 0x00000000006fd81a in AsyncCall::make ()
> #19 0x0000000000701bc6 in AsyncCallQueue::fireNext ()
> #20 0x0000000000701ecf in AsyncCallQueue::fire ()
> #21 0x0000000000566621 in EventLoop::dispatchCalls ()
> #22 0x0000000000566930 in EventLoop::runOnce ()
> #23 0x0000000000566b18 in EventLoop::run ()
> #24 0x00000000005dbb73 in SquidMain ()
> #25 0x00000000005dc0fd in SquidMainSafe ()
> #26 0x00000000004cf401 in _start ()
> #27 0x0000000800ae4000 in ?? ()
> #28 0x0000000000000000 in ?? ()
>
>
> The cache.log file gets a few lines looking like this:
>
> 2016/03/31 11:51:04 kid1| local=192.168.1.15:3128
> remote=192.168.1.164:49540 FD 339 flags=1: read/write failure: (60)
> Operation timed out
>
> and some others looking like this:
>
> 2016/03/31 14:40:05 kid1|  FD 16, 192.168.1.15 [Stopped, reason:Listener
> socket closed job3132772]: (53) Software caused connection abort
>
>
> Does anybody have any suggestions on how to fix/improve this?  Currently
> I have cron restarting squid every morning.
>
> Should I file a bug?
>
> Thanks
> Mark
>
> _______________________________________________
> squid-users mailing list
> squid-users at lists.squid-cache.org
> http://lists.squid-cache.org/listinfo/squid-users

-----BEGIN PGP SIGNATURE-----
Version: GnuPG v2
 
iQEcBAEBCAAGBQJW/S8uAAoJENNXIZxhPexGg60H/i4QPMqNZtbZ+9Cw2RhBgLBy
PtW4A76bM8+Fdolgags28atI0IkZlmacLxzZDjKUKjxwP7j+QkMNToNpUcFVpN4g
zURmM1FqGbRtvIPsXeaExdo9oyl+qIVljtfBLaEwN85bT5SkIe79jNqpTb6SkJ/s
DdI5gZTZQG27Ix6Z2ajohVSYmAdNUl7CeM4bcGWlFXtDP80daeqC+EKlQACg+Lou
QyoVeJ/PSoLk+ecglIPObTrRHyhdpcacGWdd2p/TKiP0FppwxJGxPH/uxPJcBeHJ
iLHh4Irf0Fo9CvnqqcxZsxsqxrsXQ+rj5q/cB8G6My95Gy8jnkNstZtCtMmLx8I=
=H/Cg
-----END PGP SIGNATURE-----

-------------- next part --------------
A non-text attachment was scrubbed...
Name: 0x613DEC46.asc
Type: application/pgp-keys
Size: 2437 bytes
Desc: not available
URL: <http://lists.squid-cache.org/pipermail/squid-users/attachments/20160331/d8f7cbf9/attachment.key>