netdev.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Andi Kleen <ak@suse.de>
To: akepner@sgi.com
Cc: David Miller <davem@davemloft.net>,
	kuznet@ms2.inr.ac.ru, dev@sw.ru, netdev@vger.kernel.org
Subject: Re: [PATCH] limit rt cache size
Date: Wed, 9 Aug 2006 01:23:01 +0200	[thread overview]
Message-ID: <200608090123.01123.ak@suse.de> (raw)
In-Reply-To: <Pine.LNX.4.61.0608081316330.2452@localhost.localdomain>


> >
> > IMHO there needs to be a maximum size (maybe related to the sum of
> > caches of all CPUs in the system?)
> >
> > Best would be to fix this for all large system hashes together.
> 
> How about using an algorithm like this: up to a certain "size"
> (memory size, cache size,...), scale the hash tables linearly; 
> but for larger sizes, scale logarithmically (or approximately
> logarithmically)

I don't think it makes any sense to continue scaling at all after
some point - you won't get better shorter hash chains anymore and the 
large hash tables actually cause problems: e.g. there are situations where we walk
the complete tables and that takes longer and longer.

Also does a 1TB machine really need bigger hash tables than a 100GB one?

The problem is to find out what a good boundary is.

-Andi

  reply	other threads:[~2006-08-09  0:00 UTC|newest]

Thread overview: 28+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
     [not found] <44D75EF8.1070901@sw.ru>
2006-08-07 16:48 ` [PATCH] limit rt cache size Alexey Kuznetsov
2006-08-08  3:42   ` David Miller
2006-08-08  5:11     ` Andi Kleen
2006-08-08  6:18       ` David Miller
2006-08-08  6:53         ` Andi Kleen
2006-08-08  7:01           ` David Miller
2006-08-08 12:54             ` Kirill Korotaev
2006-08-08 12:58               ` Andi Kleen
2006-08-08 20:37       ` akepner
2006-08-08 23:23         ` Andi Kleen [this message]
2006-08-09  0:06           ` akepner
2006-08-09  0:11           ` David Miller
2006-08-09  0:11             ` akepner
2006-08-09  0:22               ` David Miller
2006-08-09  1:02               ` Andi Kleen
2006-08-09 16:16                 ` akepner
2006-08-09 16:32                   ` Andi Kleen
2006-08-10  0:02                     ` David Miller
2006-08-09  8:05               ` Kirill Korotaev
2006-08-09  0:24             ` Andi Kleen
2006-08-09  0:32               ` David Miller
2006-08-09  8:09               ` Kirill Korotaev
2006-08-09  8:53                 ` Eric Dumazet
2006-08-09  9:22                   ` David Miller
2006-08-08  8:17     ` Kirill Korotaev
2006-08-08  8:34       ` David Miller
2006-08-08  8:57     ` Eric Dumazet
2006-08-08  9:12       ` David Miller

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=200608090123.01123.ak@suse.de \
    --to=ak@suse.de \
    --cc=akepner@sgi.com \
    --cc=davem@davemloft.net \
    --cc=dev@sw.ru \
    --cc=kuznet@ms2.inr.ac.ru \
    --cc=netdev@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;
as well as URLs for NNTP newsgroup(s).