From: Stephen Lord <lord@sgi.com>
To: Andrew Morton <akpm@zip.com.au>
Cc: Robert Love <rml@tech9.net>, linux-kernel@vger.kernel.org
Subject: Re: [PATCH] only irq-safe atomic ops
Date: Sat, 23 Feb 2002 14:01:07 -0600 [thread overview]
Message-ID: <3C77F503.1060005@sgi.com> (raw)
In-Reply-To: <3C773C02.93C7753E@zip.com.au>, <1014444810.1003.53.camel@phantasy> <3C773C02.93C7753E@zip.com.au> <1014449389.1003.149.camel@phantasy> <3C774AC8.5E0848A2@zip.com.au>
Andrew Morton wrote:
>Robert Love wrote:
>
>>...
>>
>>Question: if (from below) you are going to use atomic operations, why
>>make it per-CPU at all? Just have one counter and atomic_inc and
>>atomic_read it. You won't need a spin lock.
>>
>
>Oh that works fine. But then it's a global counter, so each time
>a CPU marks a page dirty, the counter needs to be pulled out of
>another CPU's cache. Which is not a thing I *need* to do.
>
>As I said, it's a micro-issue. But it's a requirement which
>may pop up elsewhere.
>
>
I can tell you that Irix has just such a global counter for the amount of
delayed allocate pages - and it gets to be a major point of cache contention
once you get to larger cpu counts. So avoiding that from the start would
be good.
Steve
next prev parent reply other threads:[~2002-02-23 20:00 UTC|newest]
Thread overview: 36+ messages / expand[flat|nested] mbox.gz Atom feed top
2002-02-23 6:13 [PATCH] only irq-safe atomic ops Robert Love
2002-02-23 6:51 ` Andrew Morton
2002-02-23 7:29 ` Robert Love
2002-02-23 7:54 ` Andrew Morton
2002-02-23 11:38 ` yodaiken
2002-02-23 18:20 ` Robert Love
2002-02-23 19:06 ` yodaiken
2002-02-23 21:57 ` Roman Zippel
2002-02-23 22:10 ` Andrew Morton
2002-02-23 22:23 ` yodaiken
2002-02-23 22:40 ` Andrew Morton
2002-02-23 22:48 ` yodaiken
2002-02-23 23:13 ` Robert Love
2002-02-23 23:45 ` Robert Love
2002-02-23 23:56 ` Andrew Morton
2002-02-24 1:05 ` yodaiken
2002-02-24 1:08 ` Robert Love
2002-02-23 22:00 ` John Levon
2002-02-23 22:43 ` yodaiken
2002-02-23 20:01 ` Stephen Lord [this message]
2002-02-23 20:27 ` Andrew Morton
2002-02-23 9:38 ` Russell King
[not found] <1014444810.1003.53.camel@phantasy.suse.lists.linux.kernel>
[not found] ` <3C773C02.93C7753E@zip.com.au.suse.lists.linux.kernel>
[not found] ` <1014449389.1003.149.camel@phantasy.suse.lists.linux.kernel>
[not found] ` <3C774AC8.5E0848A2@zip.com.au.suse.lists.linux.kernel>
[not found] ` <3C77F503.1060005@sgi.com.suse.lists.linux.kernel>
[not found] ` <3C77FB35.16844FE7@zip.com.au.suse.lists.linux.kernel>
2002-02-23 20:56 ` Andi Kleen
2002-02-23 21:06 ` Andrew Morton
2002-02-23 21:17 ` Stephen Lord
2002-02-23 21:42 ` Andrew Morton
2002-02-23 22:10 ` Stephen Lord
2002-02-23 22:34 ` Andrew Morton
2002-02-23 23:07 ` Mike Fedyk
2002-02-23 23:47 ` Andrew Morton
2002-02-25 13:02 ` Stephen Lord
2002-02-25 13:12 ` Jens Axboe
2002-02-25 13:18 ` Stephen Lord
2002-02-25 19:42 ` Andrew Morton
2002-02-25 19:45 ` Steve Lord
2002-02-25 20:05 ` Andrew Morton
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=3C77F503.1060005@sgi.com \
--to=lord@sgi.com \
--cc=akpm@zip.com.au \
--cc=linux-kernel@vger.kernel.org \
--cc=rml@tech9.net \
/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