From: Daniel Phillips <phillips@bonn-fries.net>
To: Andrea Arcangeli <andrea@suse.de>
Cc: William Lee Irwin III <wli@holomorphy.com>,
linux-kernel@vger.kernel.org, rsf@us.ibm.com
Subject: Re: [TEST] page tables filling non-highmem
Date: Tue, 19 Feb 2002 01:06:14 +0100 [thread overview]
Message-ID: <E16cxnS-0000xk-00@starship.berlin> (raw)
In-Reply-To: <20020215045106.GB26322@holomorphy.com> <E16cnOQ-0000LC-00@starship.berlin> <20020218141545.P7940@athlon.random>
In-Reply-To: <20020218141545.P7940@athlon.random>
On February 18, 2002 02:15 pm, Andrea Arcangeli wrote:
> On Mon, Feb 18, 2002 at 01:59:42PM +0100, Daniel Phillips wrote:
> > Could you describe your page table deadlock-avoidance algorithm in more
> > detail please?
>
> There is nothing specific with the pagetables. If the lowmem was eat by
> skb instead of ptes you'd deadlock the very same way. The kernel will
> just see lots of cache in highmem and of swap available (not to tell the
> kernel never knows how much of such cache is really freeable or how much
> of the mappings are swappable and that's the very next problem that will
> leads to the same deadlock) and it will think there's "freeable" memory
> available and it will keep looping. That's simply plain broken. The
> only way if there's something freeable is to try to free it and if we
> fail we say "oom". You cannot say if there's something freeable by
> checking the cache size or the number of free swap pages, no-way.
>
> If in 2.5 we want perfect accounting of freeable resources instead, fine
> with me (that would math guarantee to never fail allocations if there's
> at least one page freeable, while right now you only can calculate a
> probabilistic measure), but it has to be _perfect_, and with 2.4 there
> isn't such perfect accounting, so we definitely cannot rely on cache
> size and swap available to know if to trigger oom or not. That's totally
> broken and it will deadlock. I care about those minor theorical things
> too, I want everything calculated and under control, I hate
> approximations that can leads to deadlocks, and it pays off eventually.
You're right, we have to get serious about doing what it takes to have a
precise accounting of pinned memory. What are we going to do, count the
number of 1->2 and 2->1 transitions on page->count? Or should we have a
pin/unpin_page(page) api? Or what?
--
Daniel
next prev parent reply other threads:[~2002-02-19 0:02 UTC|newest]
Thread overview: 15+ messages / expand[flat|nested] mbox.gz Atom feed top
2002-02-15 4:51 William Lee Irwin III
2002-02-15 8:59 ` Daniel Phillips
2002-02-15 8:56 ` William Lee Irwin III
2002-02-18 1:38 ` Andrea Arcangeli
2002-02-18 1:59 ` Daniel Phillips
2002-02-18 3:02 ` Marcelo Tosatti
2002-02-18 12:39 ` Andrea Arcangeli
2002-02-18 3:26 ` William Lee Irwin III
2002-02-18 12:27 ` Andrea Arcangeli
2002-02-18 12:59 ` Daniel Phillips
2002-02-18 13:15 ` Andrea Arcangeli
2002-02-19 0:06 ` Daniel Phillips [this message]
2002-02-18 4:25 ` William Lee Irwin III
2002-02-19 0:03 ` William Lee Irwin III
[not found] ` <Pine.LNX.4.33.0202181914350.5124-100000@coffee.psychology.mcmaster.ca>
2002-02-19 0:16 ` William Lee Irwin III
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=E16cxnS-0000xk-00@starship.berlin \
--to=phillips@bonn-fries.net \
--cc=andrea@suse.de \
--cc=linux-kernel@vger.kernel.org \
--cc=rsf@us.ibm.com \
--cc=wli@holomorphy.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
all inboxes | Powered by JetHome®