List:General Discussion« Previous MessageNext Message »
From:Jeremy Zawodny Date:November 7 2001 6:44am
Subject:Re: key cache optimization
View as plain text  
On Mon, Nov 05, 2001 at 10:58:56PM -0700, Michael Griffith wrote:
> > Even if all the key blocks where in memory (and not swapped
> > out--you're not using Linux 2.4.x, are you?), there's the data
> > itself.  The rows may not have been cached the first time, but the
> > second time they probably were.
> Actually I am using 2.4. MySQL 3.23.43 on RH 7.1 (2.4.3 SMP) 2 CPUs
> Is there something about linux 2.4 and the cache that I should be
> aware of?

Just that the 2.4 kernel's virtual memory management isn't all that
great (yet).  I run one of our with swap disabled just so it won't do
stupid things.

> I considered that the delay may be in the OS cache, but I really
> don't believe that is it. I have about 800MB of OS cache, and I
> don't have 800M of data files. If that is it then something is in
> the cache that should no be there otherwise I don't know why it
> would ever be swapped out.

But that data won't be in the cache *the first time*, right?  If I
recall, things sped up the 2nd time you ran the query.

Jeremy D. Zawodny, <jzawodn@stripped>
Technical Yahoo - Yahoo Finance
Desk: (408) 349-7878   Fax: (408) 349-5454   Cell: (408) 685-5936

MySQL 3.23.41-max: up 62 days, processed 1,355,040,969 queries (252/sec. avg)
key cache optimizationMichael Griffith6 Nov
  • Re: key cache optimizationJeremy Zawodny6 Nov
  • Re: key cache optimizationMichael Griffith6 Nov
    • Re: key cache optimizationJeremy Zawodny7 Nov
  • Re: key cache optimizationDan Nelson6 Nov