login
Login
/
Register
Search
Search this site:
Forums
News
Blogs
Features
Site
Home
»
Mailing list archives
»
linux-kernel
»
2007
»
November
»
14
Re: 2.6.24-rc2: Network commit causes SLUB performance regression with tbench
view
thread
Previous message: [
thread
] [
date
] [
author
]
Next message: [
thread
] [
date
] [
author
]
[view in full thread]
From: David Miller
Subject:
Re: 2.6.24-rc2: Network commit causes SLUB performance regression with tbench
Date: Wednesday, November 14, 2007 - 4:46 pm
From: Herbert Xu <herbert@gondor.apana.org.au> Date: Wed, 14 Nov 2007 19:48:44 +0800
quoted text
> [TCP]: Fix size calculation in sk_stream_alloc_pskb > > We round up the header size in sk_stream_alloc_pskb so that > TSO packets get zero tail room. Unfortunately this rounding > up is not coordinated with the select_size() function used by > TCP to calculate the second parameter of sk_stream_alloc_pskb. > > As a result, we may allocate more than a page of data in the > non-TSO case when exactly one page is desired. > > In fact, rounding up the head room is detrimental in the non-TSO > case because it makes memory that would otherwise be available to > the payload head room. TSO doesn't need this either, all it wants > is the guarantee that there is no tail room. > > So this patch fixes this by adjusting the skb_reserve call so that > exactly the requested amount (which all callers have calculated in > a precise way) is made available as tail room. > > Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Applied and I'll queue it up for -stable too. -
unsubscribe notice
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to
majordomo@vger.kernel.org
More majordomo info at
http://vger.kernel.org/majordomo-info.html
Please read the FAQ at
http://www.tux.org/lkml/
Previous message: [
thread
] [
date
] [
author
]
Next message: [
thread
] [
date
] [
author
]
Messages in current thread:
2.6.24-rc2 slab vs slob tbench numbers
, Nick Piggin
, (Fri Nov 9, 5:36 am)
Re: 2.6.24-rc2 slab vs slob tbench numbers
, Christoph Lameter
, (Fri Nov 9, 8:15 am)
Re: 2.6.24-rc2 slab vs slob tbench numbers
, Christoph Lameter
, (Fri Nov 9, 10:49 am)
2.6.24-rc2: Network commit causes SLUB performance regress ...
, Christoph Lameter
, (Fri Nov 9, 4:46 pm)
Re: 2.6.24-rc2: Network commit causes SLUB performance reg ...
, Nick Piggin
, (Fri Nov 9, 6:29 pm)
Re: 2.6.24-rc2: Network commit causes SLUB performance reg ...
, Nick Piggin
, (Fri Nov 9, 8:28 pm)
Re: 2.6.24-rc2: Network commit causes SLUB performance reg ...
, Christoph Lameter
, (Mon Nov 12, 12:44 pm)
Re: 2.6.24-rc2 slab vs slob tbench numbers
, Matt Mackall
, (Mon Nov 12, 1:13 pm)
Re: 2.6.24-rc2: Network commit causes SLUB performance reg ...
, Nick Piggin
, (Tue Nov 13, 4:41 am)
Re: 2.6.24-rc2 slab vs slob tbench numbers
, Nick Piggin
, (Tue Nov 13, 4:44 am)
Re: 2.6.24-rc2: Network commit causes SLUB performance reg ...
, Nick Piggin
, (Tue Nov 13, 10:36 am)
Re: 2.6.24-rc2: Network commit causes SLUB performance reg ...
, Nick Piggin
, (Tue Nov 13, 11:14 am)
Re: 2.6.24-rc2: Network commit causes SLUB performance reg ...
, Nick Piggin
, (Tue Nov 13, 3:27 pm)
Re: 2.6.24-rc2: Network commit causes SLUB performance reg ...
, Nick Piggin
, (Tue Nov 13, 3:55 pm)
Re: 2.6.24-rc2: Network commit causes SLUB performance reg ...
, Nick Piggin
, (Tue Nov 13, 4:39 pm)
Re: 2.6.24-rc2: Network commit causes SLUB performance reg ...
, Nick Piggin
, (Tue Nov 13, 5:02 pm)
Re: 2.6.24-rc2: Network commit causes SLUB performance reg ...
, David Miller
, (Tue Nov 13, 6:58 pm)
Re: 2.6.24-rc2: Network commit causes SLUB performance reg ...
, David Miller
, (Tue Nov 13, 11:12 pm)
Re: 2.6.24-rc2: Network commit causes SLUB performance reg ...
, David Miller
, (Tue Nov 13, 11:37 pm)
Re: 2.6.24-rc2: Network commit causes SLUB performance reg ...
, David Miller
, (Wed Nov 14, 4:10 am)
Re: 2.6.24-rc2: Network commit causes SLUB performance reg ...
, Herbert Xu
, (Wed Nov 14, 4:48 am)
Re: 2.6.24-rc2: Network commit causes SLUB performance reg ...
, David Miller
, (Wed Nov 14, 5:10 am)
Re: 2.6.24-rc2: Network commit causes SLUB performance reg ...
, Christoph Lameter
, (Wed Nov 14, 11:33 am)
Re: 2.6.24-rc2: Network commit causes SLUB performance reg ...
, David Miller
, (Wed Nov 14, 4:46 pm)
Re: 2.6.24-rc2: Network commit causes SLUB performance reg ...
, Nick Piggin
, (Wed Nov 14, 5:21 pm)
Re: 2.6.24-rc2: Network commit causes SLUB performance reg ...
, David Miller
, (Wed Nov 14, 5:27 pm)
Re: 2.6.24-rc2: Network commit causes SLUB performance reg ...
, Christoph Lameter
, (Wed Nov 14, 6:03 pm)
Re: 2.6.24-rc2: Network commit causes SLUB performance reg ...
, Herbert Xu
, (Wed Nov 14, 6:11 pm)
Re: 2.6.24-rc2: Network commit causes SLUB performance reg ...
, Nick Piggin
, (Wed Nov 14, 6:47 pm)
Navigation
Create content
Mailing list archives
Recent posts
Popular discussions
linux-kernel
:
Paul Turner
[tg_shares_up rewrite v4 11/11] sched: update tg->shares after cpu.shares write
Mr. James W. Laferriere
Re: Linux 2.6.25-rc1 , syntax error near unexpected token `;'
Linus Torvalds
Linux 2.6.34-rc4
David Miller
Re: 'global' rq->clock
Borislav Petkov
2.6.23-rc1: no setup signature found...
git
:
Len Brown
Re: fatal: unable to create '.git/index': File exists
Oliver Hoffmann
git init --bare versus git --bare init
Sam Vilain
Re: RFC: Flat directory for notes, or fan-out? Both!
Linus Torvalds
Re: git-diff should not fire up $PAGER, period!
Jonathan Nieder
Re: git-daemon serving repos with repo.git/git-daemon-export-ok
linux-netdev
:
Eric Dumazet
Re: [PATCH net-next-2.6] net: Introduce skb_orphan_try()
Jamie Lokier
Re: POHMELFS high performance network filesystem. Transactions, failover, performa...
William Allen Simpson
[net-next-2.6 PATCH v8 0/7] TCPCT part 1: cookie option exchange
Trond Myklebust
[PATCH] NET: Add the helper kernel_sock_shutdown()
Ron Mercer
[net-next PATCH 1/2] qlge: Add firmware info to ethtool get regs.
openbsd-misc
:
Sevan / Venture37
Re: This is what Linus Torvalds calls openBSD crowd
Netmaffia.hu
Tini Lányok AKCIÓBAN OTTHON
Siju George
This is what Linus Torvalds calls openBSD crowd
Darrin Chandler
Re: OT: Python (was Re: vi in /bin)
Gilles Chehade
Re: Longest Uptime?
git-commits-head
:
Linux Kernel Mailing List
ASoC: fix registration of the SoC card in the Freescale MPC8610 drivers
Linux Kernel Mailing List
drivers/acpi: use kasprintf
Linux Kernel Mailing List
V4L/DVB: xc3028: fix regression in firmware loading time
Linux Kernel Mailing List
V4L/DVB (10826): cx88: Add IR support to pcHDTV HD3000 & HD5500
Linux Kernel Mailing List
korina: do not use IRQF_SHARED with IRQF_DISABLED
Colocation donated by:
Syndicate