From: Manfred Spraul <manfred@colorfullife.com>
To: Andi Kleen <ak@suse.de>
Cc: linux-kernel@vger.kernel.org, Dave Hansen <haveblue@us.ibm.com>
Subject: Re: Horrible L2 cache effects from kernel compile
Date: Tue, 25 Feb 2003 19:37:34 +0100 [thread overview]
Message-ID: <3E5BB7EE.5090301@colorfullife.com> (raw)
Andi wrote:
>The reason:
>
>Dentry cache hash table entries: 131072 (order: 8, 1048576 bytes)
>Inode cache hash table entries: 65536 (order: 7, 524288 bytes)
>
>(1GB) I bet on your big memory box it is even worse. No cache
>in the world can cache that.
>
[snip]
>Try the appended experimental patch. It replaces the hash table madness
>with relatively small fixed tables.
>
>
Are you sure that this will help?
With a smaller table, you might cause fewer cache misses for the table
lookup. Instead you get longer hash chains. Walking linked lists
probably causes more cache line misses than the single array lookup.
Dave, how many entries are in the dcache?
Btw, has anyone tried to replaced the global dcache with something
local, perhaps a tree instead of d_child, and then lookup in d_child_tree?
--
Manfred
next reply other threads:[~2003-02-25 18:27 UTC|newest]
Thread overview: 27+ messages / expand[flat|nested] mbox.gz Atom feed top
2003-02-25 18:37 Manfred Spraul [this message]
2003-02-25 18:41 ` Horrible L2 cache effects from kernel compile Dave Hansen
2003-02-25 18:42 ` Andi Kleen
2003-02-25 19:29 ` Martin J. Bligh
2003-02-25 22:18 ` Linus Torvalds
2003-03-03 19:03 ` Benjamin LaHaise
2003-03-03 19:13 ` Linus Torvalds
2003-03-03 23:58 ` Alan Cox
2003-03-03 22:57 ` Andrew Morton
2003-03-03 23:01 ` Benjamin LaHaise
2003-03-03 23:09 ` Linus Torvalds
2003-03-05 20:19 ` dean gaudet
[not found] <3E5ABBC1.8050203@us.ibm.com.suse.lists.linux.kernel>
2003-02-25 16:16 ` Andi Kleen
2003-02-27 3:24 ` Dave Hansen
2003-02-27 16:36 ` Jan Harkes
[not found] ` <b3ekil$1cp$1@penguin.transmeta.com.suse.lists.linux.kernel>
[not found] ` <20030225170546.GA23772@morningstar.nowhere.lie.suse.lists.linux.kernel>
2003-02-25 17:20 ` Andi Kleen
2003-02-26 18:22 ` Jamie Lokier
-- strict thread matches above, loose matches on Subject: below --
2003-02-25 0:41 Dave Hansen
2003-02-25 0:59 ` William Lee Irwin III
2003-02-25 1:01 ` Dave Hansen
2003-02-25 3:15 ` John Levon
2003-02-25 3:15 ` William Lee Irwin III
2003-02-25 3:35 ` Andrew Morton
2003-02-25 4:13 ` Martin J. Bligh
2003-02-25 11:57 ` John Levon
2003-02-25 2:31 ` Linus Torvalds
2003-02-25 17:05 ` John W. M. Stevens
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=3E5BB7EE.5090301@colorfullife.com \
--to=manfred@colorfullife.com \
--cc=ak@suse.de \
--cc=haveblue@us.ibm.com \
--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 a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox