[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-Id: <20160309.121928.103638956202937455.davem@davemloft.net>
Date: Wed, 09 Mar 2016 12:19:28 -0500 (EST)
From: David Miller <davem@...emloft.net>
To: gorcunov@...il.com
Cc: eric.dumazet@...il.com, netdev@...r.kernel.org, solar@...nwall.com,
vvs@...tuozzo.com, avagin@...tuozzo.com, xemul@...tuozzo.com,
vdavydov@...tuozzo.com, khorenko@...tuozzo.com
Subject: Re: [RFC] net: ipv4 -- Introduce ifa limit per net
From: Cyrill Gorcunov <gorcunov@...il.com>
Date: Wed, 9 Mar 2016 19:39:19 +0300
> 9.21% [kernel] [k] nf_ct_iterate_cleanup
...
> Release
> -------
> 24.26% [kernel] [k] _raw_spin_lock
> 17.55% [kernel] [k] preempt_count_add
> 14.81% [kernel] [k] __local_bh_enable_ip
> 14.17% [kernel] [k] preempt_count_sub
> 10.10% [kernel] [k] nf_ct_iterate_cleanup
...
> The main problem still I think is that we allow to request
> as many inet addresses as there is enough free memory and
> of course kernel can't handle all in O(1) time, all resources
> must be released so there always be some lagging moment. Thus
> maybe introducing limits would be a good idea for sysadmins.
Primary problem seems to be netfilter conntrack.
It's at least 10 times more expensive than any of the other
operations and probably is where all of the lock banging is
coming from.
I'm not adding a limit when there is so much low hanging fruit
remaining, no way.
Powered by blists - more mailing lists