netdev.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Jesper Dangaard Brouer <brouer@redhat.com>
To: Eric Dumazet <eric.dumazet@gmail.com>
Cc: "David S. Miller" <davem@davemloft.net>,
	Hannes Frederic Sowa <hannes@stressinduktion.org>,
	netdev@vger.kernel.org
Subject: Re: [net-next PATCH 2/3] net: fix enforcing of fragment queue hash list depth
Date: Wed, 24 Apr 2013 15:35:23 +0200	[thread overview]
Message-ID: <1366810523.26911.495.camel@localhost> (raw)
In-Reply-To: <1366382991.16391.6.camel@edumazet-glaptop>

On Fri, 2013-04-19 at 07:49 -0700, Eric Dumazet wrote:
> On Fri, 2013-04-19 at 14:19 +0200, Jesper Dangaard Brouer wrote:
> 
> > When removing the LRU system (which is the real bottleneck, see perf
> > tests in cover mail), and doing direct hash cleaning we are trading-in
> > accuracy.
[...]
> > The reason I don't want a too big hash table is the following.
> > 
> > Worst case 1024 buckets * 130K bytes = 133 MBytes, which on smaller
> > embedded systems is a lot of kernel memory we are permitting a remote
> > host to "lock-down".
> 
> Thats pretty irrelevant, memory is limited by the total amount of memory
> used by fragments, not by hash table size.
>
> Its called /proc/sys/net/ipv4/ipfrag_high_thresh


I was talking about patch-03, where I do "direct hash cleaning", and
have moved the mem limit "ipfrag_high_thresh" into the hash cleaning
step.

It seems we are talking past each-other...

--Jesper

  reply	other threads:[~2013-04-24 13:35 UTC|newest]

Thread overview: 28+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2013-04-18 21:37 [net-next PATCH 0/3] net: frag code fixes and RFC for LRU removal Jesper Dangaard Brouer
2013-04-18 21:37 ` [net-next PATCH 1/3] net: fix race bug in fragmentation create code Jesper Dangaard Brouer
2013-04-19  1:00   ` Hannes Frederic Sowa
2013-04-19  8:09     ` Jesper Dangaard Brouer
2013-04-18 21:38 ` [net-next PATCH 2/3] net: fix enforcing of fragment queue hash list depth Jesper Dangaard Brouer
2013-04-19  0:52   ` Hannes Frederic Sowa
2013-04-19 10:11   ` Eric Dumazet
2013-04-19 10:41     ` David Laight
2013-04-19 11:14       ` Eric Dumazet
2013-04-19 12:19     ` Jesper Dangaard Brouer
2013-04-19 12:45       ` Hannes Frederic Sowa
2013-04-19 14:29         ` Jesper Dangaard Brouer
2013-04-19 15:06           ` Hannes Frederic Sowa
2013-04-19 19:44           ` Hannes Frederic Sowa
2013-04-22  9:10             ` Jesper Dangaard Brouer
2013-04-22 14:54               ` Hannes Frederic Sowa
2013-04-22 16:30                 ` Jesper Dangaard Brouer
2013-04-22 17:49                 ` Jesper Dangaard Brouer
2013-04-23  0:20                   ` Hannes Frederic Sowa
2013-04-23 14:19                     ` Jesper Dangaard Brouer
2013-04-23 20:54                       ` Hannes Frederic Sowa
2013-04-19 14:42       ` Eric Dumazet
2013-04-19 14:45       ` Eric Dumazet
2013-04-19 14:45       ` Eric Dumazet
2013-04-19 14:49       ` Eric Dumazet
2013-04-24 13:35         ` Jesper Dangaard Brouer [this message]
2013-04-24 15:05           ` Eric Dumazet
2013-04-18 21:39 ` [RFC net-next PATCH 3/3] net: remove fragmentation LRU list system Jesper Dangaard Brouer

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=1366810523.26911.495.camel@localhost \
    --to=brouer@redhat.com \
    --cc=davem@davemloft.net \
    --cc=eric.dumazet@gmail.com \
    --cc=hannes@stressinduktion.org \
    --cc=netdev@vger.kernel.org \
    /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).