From: Peter Zijlstra <a.p.zijlstra@chello.nl>
To: Nick Piggin <nickpiggin@yahoo.com.au>
Cc: Linus Torvalds <torvalds@linux-foundation.org>,
Andrew Morton <akpm@linux-foundation.org>,
linux-kernel@vger.kernel.org, linux-mm@kvack.org,
netdev@vger.kernel.org, trond.myklebust@fys.uio.no
Subject: Re: [PATCH 03/33] mm: slub: add knowledge of reserve pages
Date: Wed, 31 Oct 2007 13:54:18 +0100 [thread overview]
Message-ID: <1193835258.27652.199.camel@twins> (raw)
In-Reply-To: <200710312225.07249.nickpiggin@yahoo.com.au>
[-- Attachment #1: Type: text/plain, Size: 1028 bytes --]
On Wed, 2007-10-31 at 22:25 +1100, Nick Piggin wrote:
> On Wednesday 31 October 2007 23:17, Peter Zijlstra wrote:
> > On Wed, 2007-10-31 at 21:46 +1100, Nick Piggin wrote:
>
> > > And I'd prevent these ones from doing so.
> > >
> > > Without keeping track of "reserve" pages, which doesn't feel
> > > too clean.
> >
> > The problem with that is that once a slab was allocated with the right
> > allocation context, anybody can get objects from these slabs.
>
> [snip]
>
> I understand that.
>
>
> > So we either reserve a page per object, which for 32 byte objects is a
> > large waste, or we stop anybody who doesn't have the right permissions
> > from obtaining objects. I took the latter approach.
>
> What I'm saying is that the slab allocator slowpath should always
> just check watermarks against the current task. Instead of this
> ->reserve stuff.
So what you say is to allocate a slab every time we take the slow path,
even when we already have one?
That sounds rather sub-optimal.
[-- Attachment #2: This is a digitally signed message part --]
[-- Type: application/pgp-signature, Size: 189 bytes --]
next prev parent reply other threads:[~2007-10-31 12:54 UTC|newest]
Thread overview: 72+ messages / expand[flat|nested] mbox.gz Atom feed top
2007-10-30 16:04 [PATCH 00/33] Swap over NFS -v14 Peter Zijlstra
2007-10-30 16:04 ` [PATCH 01/33] mm: gfp_to_alloc_flags() Peter Zijlstra
2007-10-30 16:04 ` [PATCH 02/33] mm: tag reseve pages Peter Zijlstra
2007-10-30 16:04 ` [PATCH 03/33] mm: slub: add knowledge of reserve pages Peter Zijlstra
2007-10-31 3:37 ` Nick Piggin
2007-10-31 10:42 ` Peter Zijlstra
2007-10-31 10:46 ` Nick Piggin
2007-10-31 12:17 ` Peter Zijlstra
2007-10-31 11:25 ` Nick Piggin
2007-10-31 12:54 ` Peter Zijlstra [this message]
2007-10-31 13:08 ` Peter Zijlstra
2007-10-30 16:04 ` [PATCH 04/33] mm: allow mempool to fall back to memalloc reserves Peter Zijlstra
2007-10-31 3:40 ` Nick Piggin
2007-10-30 16:04 ` [PATCH 05/33] mm: kmem_estimate_pages() Peter Zijlstra
2007-10-31 3:43 ` Nick Piggin
2007-10-31 10:42 ` Peter Zijlstra
2007-10-30 16:04 ` [PATCH 06/33] mm: allow PF_MEMALLOC from softirq context Peter Zijlstra
2007-10-31 3:51 ` Nick Piggin
2007-10-31 10:42 ` Peter Zijlstra
2007-10-31 10:49 ` Nick Piggin
2007-10-31 13:06 ` Peter Zijlstra
2007-10-30 16:04 ` [PATCH 07/33] mm: serialize access to min_free_kbytes Peter Zijlstra
2007-10-30 16:04 ` [PATCH 08/33] mm: emergency pool Peter Zijlstra
2007-10-30 16:04 ` [PATCH 09/33] mm: system wide ALLOC_NO_WATERMARK Peter Zijlstra
2007-10-31 3:52 ` Nick Piggin
2007-10-31 10:45 ` Peter Zijlstra
2007-10-30 16:04 ` [PATCH 10/33] mm: __GFP_MEMALLOC Peter Zijlstra
2007-10-30 16:04 ` [PATCH 11/33] mm: memory reserve management Peter Zijlstra
2007-10-30 16:04 ` [PATCH 12/33] selinux: tag avc cache alloc as non-critical Peter Zijlstra
2007-10-30 16:04 ` [PATCH 13/33] net: wrap sk->sk_backlog_rcv() Peter Zijlstra
2007-10-30 16:04 ` [PATCH 14/33] net: packet split receive api Peter Zijlstra
2007-10-30 16:04 ` [PATCH 15/33] net: sk_allocation() - concentrate socket related allocations Peter Zijlstra
2007-10-30 16:04 ` [PATCH 16/33] netvm: network reserve infrastructure Peter Zijlstra
2007-10-30 16:04 ` [PATCH 17/33] sysctl: propagate conv errors Peter Zijlstra
2007-10-30 16:04 ` [PATCH 18/33] netvm: INET reserves Peter Zijlstra
2007-10-30 16:04 ` [PATCH 19/33] netvm: hook skb allocation to reserves Peter Zijlstra
2007-10-30 16:04 ` [PATCH 20/33] netvm: filter emergency skbs Peter Zijlstra
2007-10-30 16:04 ` [PATCH 21/33] netvm: prevent a TCP specific deadlock Peter Zijlstra
2007-10-30 16:04 ` [PATCH 22/33] netfilter: NF_QUEUE vs emergency skbs Peter Zijlstra
2007-10-30 16:04 ` [PATCH 23/33] netvm: skb processing Peter Zijlstra
2007-10-30 21:26 ` Stephen Hemminger
2007-10-30 21:44 ` Peter Zijlstra
2007-10-30 21:26 ` Stephen Hemminger
2007-10-30 16:04 ` [PATCH 24/33] mm: prepare swap entry methods for use in page methods Peter Zijlstra
2007-10-30 16:04 ` [PATCH 25/33] mm: add support for non block device backed swap files Peter Zijlstra
2007-10-30 16:04 ` [PATCH 26/33] mm: methods for teaching filesystems about PG_swapcache pages Peter Zijlstra
2007-10-30 16:04 ` [PATCH 27/33] nfs: remove mempools Peter Zijlstra
2007-10-30 16:04 ` [PATCH 28/33] nfs: teach the NFS client how to treat PG_swapcache pages Peter Zijlstra
2007-10-31 8:52 ` Christoph Hellwig
2007-10-30 16:04 ` [PATCH 29/33] nfs: disable data cache revalidation for swapfiles Peter Zijlstra
2007-10-30 16:04 ` [PATCH 30/33] nfs: swap vs nfs_writepage Peter Zijlstra
2007-10-30 16:04 ` [PATCH 31/33] nfs: enable swap on NFS Peter Zijlstra
2007-10-30 16:04 ` [PATCH 32/33] nfs: fix various memory recursions possible with swap over NFS Peter Zijlstra
2007-10-30 16:04 ` [PATCH 33/33] nfs: do not warn on radix tree node allocation failures Peter Zijlstra
2007-10-31 3:26 ` [PATCH 00/33] Swap over NFS -v14 Nick Piggin
2007-10-31 4:37 ` David Miller, Nick Piggin
2007-10-31 4:04 ` Nick Piggin
2007-10-31 14:03 ` Byron Stanoszek
2007-10-31 8:50 ` Christoph Hellwig
2007-10-31 10:56 ` Peter Zijlstra
2007-10-31 11:18 ` NBD was " Pavel Machek
2007-10-31 11:24 ` Peter Zijlstra
2007-10-31 14:54 ` Mike Snitzer
2007-10-31 16:31 ` Evgeniy Polyakov
2007-10-31 9:53 ` Peter Zijlstra
2007-10-31 11:27 ` Peter Zijlstra
2007-10-31 12:16 ` Jeff Garzik
2007-10-31 12:56 ` Peter Zijlstra
2007-10-31 13:18 ` Arnaldo Carvalho de Melo
2007-10-31 13:44 ` Gregory Haskins
2007-11-02 8:54 ` Pavel Machek
2007-11-18 18:09 ` Robin Humble
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=1193835258.27652.199.camel@twins \
--to=a.p.zijlstra@chello.nl \
--cc=akpm@linux-foundation.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=netdev@vger.kernel.org \
--cc=nickpiggin@yahoo.com.au \
--cc=torvalds@linux-foundation.org \
--cc=trond.myklebust@fys.uio.no \
/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).