From: Andi Kleen <ak@muc.de>
To: Christoph Lameter <clameter@sgi.com>
Cc: linux-ia64@vger.kernel.org, linux-kernel@vger.kernel.org
Subject: Re: Page Fault Scalability patch V19 [4/4]: Drop use of
Date: Wed, 09 Mar 2005 22:56:14 +0000 [thread overview]
Message-ID: <m13bv4whrl.fsf@muc.de> (raw)
In-Reply-To: <20050309201344.29721.26698.sendpatchset@schroedinger.engr.sgi.com> (Christoph Lameter's message of "Wed, 9 Mar 2005 12:13:44 -0800 (PST)")
Christoph Lameter <clameter@sgi.com> writes:
> Do not use the page_table_lock in do_anonymous_page. This will significantly
> increase the parallelism in the page fault handler in SMP systems. The patch
> also modifies the definitions of _mm_counter functions so that rss and anon_rss
> become atomic.
I still think it's a bad idea to add arbitary process size limits like this:
>
> +#ifdef CONFIG_ATOMIC_TABLE_OPS
> +/*
> + * Atomic page table operations require that the counters are also
> + * incremented atomically
> +*/
> +#define set_mm_counter(mm, member, value) atomic_set(&(mm)->member, value)
> +#define get_mm_counter(mm, member) ((unsigned long)atomic_read(&(mm)->member))
> +#define update_mm_counter(mm, member, value) atomic_add(value, &(mm)->member)
> +#define MM_COUNTER_T atomic_t
Can you use atomic64_t on 64bit systems at least?
-Andi
WARNING: multiple messages have this Message-ID (diff)
From: Andi Kleen <ak@muc.de>
To: Christoph Lameter <clameter@sgi.com>
Cc: linux-ia64@vger.kernel.org, linux-kernel@vger.kernel.org
Subject: Re: Page Fault Scalability patch V19 [4/4]: Drop use of page_table_lock in do_anonymous_page
Date: Wed, 09 Mar 2005 23:56:14 +0100 [thread overview]
Message-ID: <m13bv4whrl.fsf@muc.de> (raw)
In-Reply-To: <20050309201344.29721.26698.sendpatchset@schroedinger.engr.sgi.com> (Christoph Lameter's message of "Wed, 9 Mar 2005 12:13:44 -0800 (PST)")
Christoph Lameter <clameter@sgi.com> writes:
> Do not use the page_table_lock in do_anonymous_page. This will significantly
> increase the parallelism in the page fault handler in SMP systems. The patch
> also modifies the definitions of _mm_counter functions so that rss and anon_rss
> become atomic.
I still think it's a bad idea to add arbitary process size limits like this:
>
> +#ifdef CONFIG_ATOMIC_TABLE_OPS
> +/*
> + * Atomic page table operations require that the counters are also
> + * incremented atomically
> +*/
> +#define set_mm_counter(mm, member, value) atomic_set(&(mm)->member, value)
> +#define get_mm_counter(mm, member) ((unsigned long)atomic_read(&(mm)->member))
> +#define update_mm_counter(mm, member, value) atomic_add(value, &(mm)->member)
> +#define MM_COUNTER_T atomic_t
Can you use atomic64_t on 64bit systems at least?
-Andi
next prev parent reply other threads:[~2005-03-09 22:56 UTC|newest]
Thread overview: 26+ messages / expand[flat|nested] mbox.gz Atom feed top
2005-03-09 20:13 Page Fault Scalabilty patch V19 [0/4]: Overview Christoph Lameter
2005-03-09 20:13 ` Christoph Lameter
2005-03-09 20:13 ` Page Fault Scalability patch V19 [1/4]: pte_cmpxchg and CONFIG_ATOMIC_TABLE_OPS Christoph Lameter
2005-03-09 20:13 ` Christoph Lameter
2005-03-09 23:01 ` Page Fault Scalability patch V19 [1/4]: pte_cmpxchg and Andi Kleen
2005-03-09 23:01 ` Page Fault Scalability patch V19 [1/4]: pte_cmpxchg and CONFIG_ATOMIC_TABLE_OPS Andi Kleen
2005-03-09 23:06 ` Page Fault Scalability patch V19 [1/4]: pte_cmpxchg and Christoph Lameter
2005-03-09 23:06 ` Page Fault Scalability patch V19 [1/4]: pte_cmpxchg and CONFIG_ATOMIC_TABLE_OPS Christoph Lameter
2005-03-09 20:13 ` Page Fault Scalability patch V19 [2/4]: Abstract mm_struct counter operations Christoph Lameter
2005-03-09 20:13 ` Christoph Lameter
2005-03-09 20:13 ` Page Fault Scalability patch V19 [3/4]: Drop use of page_table_lock in handle_mm_fault Christoph Lameter
2005-03-09 20:13 ` Christoph Lameter
2005-03-09 20:13 ` Page Fault Scalability patch V19 [4/4]: Drop use of page_table_lock in do_anonymous_page Christoph Lameter
2005-03-09 20:13 ` Christoph Lameter
2005-03-09 22:56 ` Andi Kleen [this message]
2005-03-09 22:56 ` Andi Kleen
2005-03-09 23:02 ` Page Fault Scalability patch V19 [4/4]: Drop use of page_table_lock Christoph Lameter
2005-03-09 23:02 ` Page Fault Scalability patch V19 [4/4]: Drop use of page_table_lock in do_anonymous_page Christoph Lameter
2005-03-09 23:14 ` Andi Kleen
2005-03-09 23:14 ` Andi Kleen
2005-03-09 23:17 ` Page Fault Scalability patch V19 [4/4]: Drop use of page_table_lock Christoph Lameter
2005-03-09 23:17 ` Page Fault Scalability patch V19 [4/4]: Drop use of page_table_lock in do_anonymous_page Christoph Lameter
2005-03-09 23:21 ` Andi Kleen
2005-03-09 23:21 ` Andi Kleen
2005-03-09 23:32 ` Page Fault Scalability patch V19 [4/4]: Drop use of page_table_lock Christoph Lameter
2005-03-09 23:32 ` Page Fault Scalability patch V19 [4/4]: Drop use of page_table_lock in do_anonymous_page Christoph Lameter
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=m13bv4whrl.fsf@muc.de \
--to=ak@muc.de \
--cc=clameter@sgi.com \
--cc=linux-ia64@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
/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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.