home *** CD-ROM | disk | FTP | other *** search
- Path: sparky!uunet!gatech!rpi!usc!hacgate!oracle!uhl
- From: uhl@oracle (Walter Uhl)
- Newsgroups: comp.os.linux
- Subject: Re: Benchmarking under Linux (was Re: New 486 Suggestions?
- Message-ID: <23101@hacgate.SCG.HAC.COM>
- Date: 1 Sep 92 13:50:19 GMT
- References: <ARL.92Sep1021727@cardhu.cs.hut.fi>
- Sender: news@hacgate.SCG.HAC.COM
- Lines: 28
- X-Newsreader: Tin 1.1 PL5
-
- Ari Lemmke (arl@cs.hut.fi) wrote:
- :
- : In article <1992Aug31.210041.21832@novell.com> bboerner@novell.com (Brendan B. Boerner) writes:
- : : I've got a 386/16Mhz w/a tad under 5MB of
- : : RAM and it takes me somewhere between 3-4hours to build the kernel. On
- : : my girlfriend's machine, a 486/33 w/8MB RAM, it takes under 10
- : : minutes. I'd like to get an idea of where I could improve
- : : performance.
- :
- :
- : But .. having faster disk, >2 MB swap, more memory (~8MB)
- : would make the kernel compile faster.
- :
- I did a bit of quick testing to determine the following;
- my machine 386-DX-33 with 387 and 8 meg of ram plus 64k cach
- sieve test under Linux 0.97pl1
- time 8.x
- user 4.x
- system 0.x
-
- this time was taken while building the kernel. With the system idle
- the only thing that changed was the time. Dropped to match user. What
- does it mean? 4 seconds to run sieve without having to access the
- disk drive, so I think that time shows processor & OS speed. Hope that
- this helps a little.
-
- Walter Paul Uhl
- uhl@solaria.hac.com
-