From: Rik van Riel <riel@redhat.com>
To: David Miller <davem@davemloft.net>
Cc: a.p.zijlstra@chello.nl, johnpol@2ka.mipt.ru, linux-mm@kvack.org,
linux-kernel@vger.kernel.org, netdev@vger.kernel.org,
phillips@google.com
Subject: Re: [RFC][PATCH 0/9] Network receive deadlock prevention for NBD
Date: Sat, 12 Aug 2006 21:11:16 -0400 [thread overview]
Message-ID: <44DE7C34.4080909@redhat.com> (raw)
In-Reply-To: <20060812.174651.113732891.davem@davemloft.net>
David Miller wrote:
> From: Peter Zijlstra <a.p.zijlstra@chello.nl>
> Date: Sat, 12 Aug 2006 12:18:07 +0200
>
>> 65535 sockets * 128 packets * 16384 bytes/packet =
>> 1^16 * 1^7 * 1^14 = 1^(16+7+14) = 1^37 = 128G of memory per IP
>>
>> And systems with a lot of IP numbers are not unthinkable.
>
> TCP restricts the amount of global memory that may be consumed
> by all TCP sockets via the tcp_mem[] sysctl.
This is exactly why we need to be careful which sockets
we allocate memory for, when the system is about to run
out of memory.
--
"Debugging is twice as hard as writing the code in the first place.
Therefore, if you write the code as cleverly as possible, you are,
by definition, not smart enough to debug it." - Brian W. Kernighan
--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>
next prev parent reply other threads:[~2006-08-13 1:11 UTC|newest]
Thread overview: 140+ messages / expand[flat|nested] mbox.gz Atom feed top
2006-08-08 19:33 Peter Zijlstra
2006-08-08 19:33 ` [RFC][PATCH 1/9] pfn_to_kaddr() for UML Peter Zijlstra
2006-08-08 19:33 ` [RFC][PATCH 2/9] deadlock prevention core Peter Zijlstra
2006-08-08 20:57 ` Stephen Hemminger
2006-08-08 21:05 ` Peter Zijlstra
2006-08-09 1:33 ` Daniel Phillips
2006-08-09 1:38 ` David Miller, Daniel Phillips
2006-08-08 21:17 ` Thomas Graf
2006-08-09 1:34 ` Daniel Phillips
2006-08-09 1:39 ` David Miller, Daniel Phillips
2006-08-09 5:47 ` Daniel Phillips
2006-08-09 13:19 ` Thomas Graf
2006-08-09 14:07 ` Peter Zijlstra
2006-08-09 16:18 ` Thomas Graf
2006-08-09 16:19 ` Peter Zijlstra
2006-08-10 0:01 ` David Miller, Peter Zijlstra
2006-08-09 23:58 ` David Miller, Peter Zijlstra
2006-08-10 6:25 ` Peter Zijlstra
2006-08-11 4:24 ` Stephen Hemminger
2006-08-13 21:22 ` Daniel Phillips
2006-08-13 23:49 ` David Miller, Daniel Phillips
2006-08-14 1:15 ` Daniel Phillips
2006-08-11 2:37 ` Rik van Riel
2006-08-13 22:05 ` Daniel Phillips
2006-08-13 23:55 ` David Miller, Daniel Phillips
2006-08-14 1:31 ` Daniel Phillips
2006-08-14 1:53 ` Andrew Morton
2006-08-14 4:40 ` Peter Zijlstra
2006-08-14 4:58 ` Andrew Morton
2006-08-14 5:03 ` Peter Zijlstra
2006-08-14 5:22 ` Andrew Morton
2006-08-14 6:45 ` Peter Zijlstra
2006-08-14 7:07 ` Andrew Morton
2006-08-14 8:15 ` Peter Zijlstra
2006-08-14 8:25 ` Evgeniy Polyakov
2006-08-14 8:35 ` Peter Zijlstra
2006-08-14 8:33 ` David Miller, Andrew Morton
2006-08-17 4:27 ` Daniel Phillips
2006-08-14 7:17 ` Neil Brown
2006-08-14 7:31 ` Evgeniy Polyakov
2006-08-17 3:58 ` Daniel Phillips
2006-08-17 5:57 ` Andrew Morton
2006-08-17 23:53 ` Daniel Phillips
2006-08-18 0:24 ` Rik van Riel
2006-08-18 0:35 ` Daniel Phillips
2006-08-18 1:14 ` Neil Brown
2006-08-18 6:05 ` Andrew Morton
2006-08-18 21:22 ` Daniel Phillips
2006-08-18 22:34 ` Andrew Morton
2006-08-18 23:44 ` Daniel Phillips
2006-08-19 2:44 ` Andrew Morton
2006-08-19 4:14 ` Network receive stall avoidance (was [PATCH 2/9] deadlock prevention core) Daniel Phillips
2006-08-19 7:28 ` Andrew Morton
2006-08-19 15:06 ` [RFC][PATCH 2/9] deadlock prevention core Rik van Riel
2006-08-20 1:33 ` Andre Tomt
2006-08-19 16:53 ` Ray Lee
2006-08-21 13:27 ` Philip R. Auld
2006-08-25 10:47 ` Pavel Machek
2006-08-21 13:38 ` Jens Axboe
2006-08-08 22:10 ` David Miller
2006-08-09 1:35 ` Daniel Phillips
2006-08-09 1:41 ` David Miller, Daniel Phillips
2006-08-09 5:44 ` Daniel Phillips
2006-08-09 7:00 ` Peter Zijlstra
[not found] ` <42414.81.207.0.53.1155080443.squirrel@81.207.0.53>
2006-08-09 0:25 ` Daniel Phillips
2006-08-09 12:02 ` Indan Zupancic
2006-08-09 12:54 ` Peter Zijlstra
2006-08-09 13:48 ` Indan Zupancic
2006-08-09 14:00 ` Peter Zijlstra
2006-08-09 18:34 ` Indan Zupancic
2006-08-09 19:45 ` Peter Zijlstra
2006-08-09 20:19 ` Peter Zijlstra
2006-08-10 1:21 ` Indan Zupancic
2006-08-09 16:05 ` -v2 " Peter Zijlstra
2006-08-08 19:33 ` [RFC][PATCH 3/9] e1000 driver conversion Peter Zijlstra
2006-08-08 20:50 ` Auke Kok
2006-08-08 20:59 ` Peter Zijlstra
2006-08-08 22:32 ` David Miller, Auke Kok
2006-08-08 22:42 ` Auke Kok
2006-08-08 19:34 ` [RFC][PATCH 4/9] e100 " Peter Zijlstra
2006-08-08 20:13 ` Auke Kok
2006-08-08 20:18 ` Peter Zijlstra
2006-08-08 19:34 ` [RFC][PATCH 5/9] r8169 " Peter Zijlstra
2006-08-08 19:34 ` [RFC][PATCH 6/9] tg3 " Peter Zijlstra
2006-08-08 19:34 ` [RFC][PATCH 7/9] UML eth " Peter Zijlstra
2006-08-08 19:34 ` [RFC][PATCH 8/9] 3c59x " Peter Zijlstra
2006-08-08 23:07 ` Jeff Garzik
2006-08-09 5:51 ` Daniel Phillips
2006-08-09 5:55 ` David Miller, Daniel Phillips
2006-08-09 6:30 ` Jeff Garzik
2006-08-09 7:03 ` Peter Zijlstra
2006-08-09 7:20 ` Jeff Garzik
2006-08-13 19:38 ` Daniel Phillips
2006-08-13 19:53 ` Jeff Garzik
2006-08-08 19:34 ` [RFC][PATCH 9/9] deadlock prevention for NBD Peter Zijlstra
2006-08-09 5:46 ` [RFC][PATCH 0/9] Network receive " Evgeniy Polyakov
2006-08-09 5:52 ` Daniel Phillips
2006-08-09 5:56 ` David Miller, Daniel Phillips
2006-08-09 5:53 ` David Miller, Evgeniy Polyakov
2006-08-09 5:55 ` Evgeniy Polyakov
2006-08-09 12:37 ` Peter Zijlstra
2006-08-09 13:07 ` Evgeniy Polyakov
2006-08-09 13:32 ` Peter Zijlstra
2006-08-09 19:29 ` Evgeniy Polyakov
2006-08-09 23:54 ` David Miller, Peter Zijlstra
2006-08-10 6:06 ` Peter Zijlstra
2006-08-13 20:16 ` Daniel Phillips
2006-08-14 5:13 ` Evgeniy Polyakov
2006-08-14 6:45 ` Peter Zijlstra
2006-08-14 6:54 ` Evgeniy Polyakov
2006-08-17 4:49 ` Daniel Phillips
2006-08-17 4:48 ` Daniel Phillips
2006-08-17 5:36 ` Evgeniy Polyakov
2006-08-17 18:01 ` Daniel Phillips
2006-08-17 18:42 ` Evgeniy Polyakov
2006-08-17 19:15 ` Peter Zijlstra
2006-08-17 19:48 ` Evgeniy Polyakov
2006-08-17 23:24 ` Daniel Phillips
2006-08-18 7:16 ` Evgeniy Polyakov
2006-08-12 3:42 ` Rik van Riel
2006-08-12 8:47 ` Evgeniy Polyakov
2006-08-12 9:19 ` Peter Zijlstra
2006-08-12 9:37 ` Evgeniy Polyakov
2006-08-12 10:18 ` Peter Zijlstra
2006-08-12 10:42 ` Evgeniy Polyakov
2006-08-12 10:51 ` Evgeniy Polyakov
2006-08-12 11:40 ` Peter Zijlstra
2006-08-12 11:53 ` Evgeniy Polyakov
2006-08-13 0:46 ` David Miller, Peter Zijlstra
2006-08-13 1:11 ` Rik van Riel [this message]
2006-08-12 14:40 ` Rik van Riel
2006-08-12 14:49 ` Evgeniy Polyakov
2006-08-12 14:56 ` Rik van Riel
2006-08-12 15:08 ` Evgeniy Polyakov
2006-08-12 15:22 ` Peter Zijlstra
2006-08-14 0:56 ` Daniel Phillips
2006-08-13 0:46 ` David Miller, Evgeniy Polyakov
2006-08-13 9:06 ` Evgeniy Polyakov
2006-08-13 9:52 ` Evgeniy Polyakov
2006-08-15 19:17 ` Pavel Machek
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=44DE7C34.4080909@redhat.com \
--to=riel@redhat.com \
--cc=a.p.zijlstra@chello.nl \
--cc=davem@davemloft.net \
--cc=johnpol@2ka.mipt.ru \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=netdev@vger.kernel.org \
--cc=phillips@google.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