tech-userlevel archive

[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index][Old Index]

Re: Kernel VS application file caching

To: Steven Bellovin <smb%cs.columbia.edu@localhost>
Subject: Re: Kernel VS application file caching
From: David Holland <dholland-tech%netbsd.org@localhost>
Date: Sat, 23 Jan 2010 08:15:37 +0000

On Fri, Jan 22, 2010 at 08:56:07PM -0500, Steven Bellovin wrote:
 > The first lesson, of course, is that running accurate benchmarks is
 > hard.  If anyone has a way to invalidate the entire buffer cache,
 > it would certainly help.

The canonical way is to reboot between benchmark runs.

-- 
David A. Holland
dholland%netbsd.org@localhost

References:
- Kernel VS application file caching
  - From: Sad Clouds
- Re: Kernel VS application file caching
  - From: Steven Bellovin
- Re: Kernel VS application file caching
  - From: Sad Clouds
- Re: Kernel VS application file caching
  - From: Steven Bellovin
- Re: Kernel VS application file caching
  - From: Joerg Sonnenberger
- Re: Kernel VS application file caching
  - From: Steven Bellovin

Prev by Date: re: fetch_pkg_vulnerabilities enabled by default (was: CVS commit: src/etc)
Next by Date: Re: pthread_cond_signal() ambiguity
Previous by Thread: Re: Kernel VS application file caching
Next by Thread: Re: Kernel VS application file caching
Indexes:

Home | Main Index | Thread Index | Old Index