From: Momchil Velikov <velco@fadata.bg>
To: <mingo@elte.hu>
Cc: Anton Blanchard <anton@samba.org>,
Linus Torvalds <torvalds@transmeta.com>,
Andrea Arcangeli <andrea@suse.de>,
Rik van Riel <riel@conectiva.com.br>,
John Stoffel <stoffel@casc.com>,
linux-kernel <linux-kernel@vger.kernel.org>
Subject: Re: [PATCH] Radix-tree pagecache for 2.5
Date: 01 Feb 2002 17:26:42 +0200 [thread overview]
Message-ID: <87y9idusst.fsf@fadata.bg> (raw)
In-Reply-To: <Pine.LNX.4.33.0202011801260.11284-100000@localhost.localdomain>
In-Reply-To: <Pine.LNX.4.33.0202011801260.11284-100000@localhost.localdomain>
>>>>> "Ingo" == Ingo Molnar <mingo@elte.hu> writes:
Ingo> On 1 Feb 2002, Momchil Velikov wrote:
Ingo> files are used. With one big file (or a few big files), the i_shared_lock
Ingo> will always bounce between CPUs wildly in read() workloads, degrading
>>
>> Will there be difference between bounces of a rwlock in the radix tree
>> variant and the cache misses in hashed locks variant for the case of
>> concurrently accessed large file ?
Ingo> definitely, because in the case of page buckets there are many locks
Ingo> hashed in a mapping-neutral way. Ie. different parts of the same file will
Ingo> likely map to different spinlocks.
That's why it's likely to miss on each access.
Ingo> In the radix tree case all pages in the inode will map to the
Ingo> same spinlock.
That's why it's likely to bounce on each access.
So, is there any difference ? :)
Regards,
-velco
next prev parent reply other threads:[~2002-02-01 15:25 UTC|newest]
Thread overview: 87+ messages / expand[flat|nested] mbox.gz Atom feed top
2002-01-29 15:54 [PATCH] Radix-tree pagecache for 2.5 Christoph Hellwig
2002-01-29 19:27 ` Linus Torvalds
2002-01-29 21:40 ` David S. Miller
2002-01-29 22:07 ` Linus Torvalds
2002-01-29 23:01 ` Rik van Riel
2002-01-29 23:32 ` Alan Cox
2002-01-29 23:35 ` Rik van Riel
2002-01-30 3:00 ` Daniel Phillips
2002-01-31 23:44 ` Anton Blanchard
2002-02-01 0:34 ` Alan Cox
2002-02-01 11:04 ` Rik van Riel
2002-02-01 11:33 ` Arjan van de Ven
2002-02-02 18:57 ` Richard Henderson
2002-02-02 21:15 ` Rik van Riel
2002-01-29 23:02 ` Momchil Velikov
2002-01-29 23:33 ` Linus Torvalds
2002-01-29 23:45 ` Christoph Hellwig
2002-01-30 21:25 ` Momchil Velikov
2002-01-30 22:05 ` John Stoffel
2002-01-30 22:15 ` Momchil Velikov
2002-01-31 2:33 ` Andrea Arcangeli
2002-01-31 13:58 ` Rik van Riel
2002-01-31 14:36 ` Andrea Arcangeli
2002-01-31 15:32 ` Alan Cox
2002-01-31 16:39 ` William Lee Irwin III
2002-01-31 17:19 ` William Lee Irwin III
2002-01-31 17:21 ` Andrea Arcangeli
2002-01-31 17:50 ` William Lee Irwin III
2002-01-31 17:46 ` Linus Torvalds
2002-01-31 18:02 ` Andrea Arcangeli
2002-01-31 18:32 ` Linus Torvalds
2002-01-31 18:38 ` Rik van Riel
2002-01-31 18:49 ` Linus Torvalds
2002-01-31 19:09 ` Momchil Velikov
2002-01-31 19:26 ` Andrew Morton
2002-01-31 21:12 ` Momchil Velikov
2002-01-31 19:14 ` Andrea Arcangeli
2002-01-31 19:23 ` Linus Torvalds
2002-01-31 21:34 ` Ingo Molnar
2002-01-31 23:12 ` Anton Blanchard
2002-01-31 23:55 ` Andrea Arcangeli
2002-02-01 0:01 ` David S. Miller
2002-02-16 16:20 ` Andrea Arcangeli
2002-02-01 3:56 ` Anton Blanchard
2002-02-01 6:32 ` Momchil Velikov
2002-02-01 18:38 ` Anton Blanchard
2002-02-01 9:04 ` Ingo Molnar
2002-02-01 7:59 ` Momchil Velikov
2002-02-01 10:29 ` Ingo Molnar
2002-02-01 9:01 ` Momchil Velikov
2002-02-01 9:10 ` David S. Miller
2002-02-01 9:07 ` David S. Miller
2002-02-01 9:13 ` Momchil Velikov
2002-02-01 17:06 ` Linus Torvalds
2002-02-01 18:29 ` Jeff Garzik
2002-02-01 18:44 ` arjan
2002-02-01 19:47 ` Jeff Garzik
2002-02-02 15:39 ` Rik van Riel
2002-02-05 14:21 ` Pavel Machek
2002-02-05 18:45 ` Rik van Riel
2002-02-05 20:30 ` Eric Dumazet
2002-02-05 20:46 ` Pavel Machek
2002-02-06 9:07 ` Daniel Phillips
2002-02-05 9:19 ` Zdenek Kabelac
2002-02-01 23:49 ` Ingo Molnar
2002-02-01 14:44 ` Andrea Arcangeli
2002-02-01 14:59 ` Momchil Velikov
2002-02-01 17:03 ` Ingo Molnar
2002-02-01 15:26 ` Momchil Velikov [this message]
2002-02-01 23:45 ` Ingo Molnar
2002-01-31 10:41 ` Josh MacDonald
2002-01-31 14:00 ` Rik van Riel
2002-01-31 14:21 ` Momchil Velikov
2002-01-30 22:22 ` Christoph Hellwig
2002-01-30 3:02 ` Daniel Phillips
2002-01-29 23:00 ` William Lee Irwin III
-- strict thread matches above, loose matches on Subject: below --
2002-02-02 19:23 rwhron
2002-02-03 14:31 ` chris
2002-02-03 23:33 ` Momchil Velikov
2002-02-04 3:59 ` rwhron
2002-02-06 2:04 ` rwhron
2002-02-06 11:44 ` Rik van Riel
2002-02-06 21:34 rwhron
2002-02-06 21:37 ` Rik van Riel
2002-02-06 22:06 ` rwhron
2002-02-07 11:32 ` Daniel Phillips
2002-02-07 11:32 ` Daniel Phillips
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=87y9idusst.fsf@fadata.bg \
--to=velco@fadata.bg \
--cc=andrea@suse.de \
--cc=anton@samba.org \
--cc=linux-kernel@vger.kernel.org \
--cc=mingo@elte.hu \
--cc=riel@conectiva.com.br \
--cc=stoffel@casc.com \
--cc=torvalds@transmeta.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 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.