Return to BSD News archive
Newsgroups: comp.unix.bsd.freebsd.misc,comp.os.linux.development.system Path: euryale.cc.adfa.oz.au!newshost.anu.edu.au!harbinger.cc.monash.edu.au!newsroom.utas.edu.au!munnari.OZ.AU!spool.mu.edu!howland.reston.ans.net!gatech!news.sprintlink.net!news1!not-for-mail From: root@dyson.iquest.net (John S. Dyson) Subject: Re: The better (more suitable)Unix?? FreeBSD or Linux X-Nntp-Posting-Host: dyson.iquest.net Message-ID: <4g0pkb$ci@dyson.iquest.net> Sender: news@iquest.net (News Admin) Organization: John S. Dyson's home machine References: <4er9hp$5ng@orb.direct.ca> <311DA774.167EB0E7@FreeBSD.org> <31220995.C4C54C1@acm.org> <4g0sam$r6p@agate.berkeley.edu> Date: Fri, 16 Feb 1996 02:19:55 GMT Lines: 36 Xref: euryale.cc.adfa.oz.au comp.unix.bsd.freebsd.misc:14356 comp.os.linux.development.system:18008 In article <4g0sam$r6p@agate.berkeley.edu>, Nick Kralevich <nickkral@america.CS.Berkeley.EDU> wrote: > >The following benchmarks were done using a stabdalone i486DX33 with 16 >MB of RAM, and Western Digital Caviar IDE drives. The Linux kernel >which was used was Linux 1.1.62. The BSD kernel that was used was >FreeBSD 2.0 Alpha, based on the 4.4 BSD Lite distribution. The block >size used by the BSD FFS was 4k with 1k fragments; the block size used >by the Linux ext2fs was 1k blocks (the ext2fs cluster code provides most >of the performance gains of going to 4k blocks with 1k fragments, so >it's unlikely that ext2fs will actually implement support for >fragments). > For the best standard FreeBSD performance, use 8K/1K fragments, and also the async data is kind-of superfluous since FreeBSD V2.0 did not support async writes on FFS. I normally use 16K/2K on FreeBSD for my working filesystems that I don't use for publishing benchmarks (I use 8K/1K for those, even though perf is lower, it is more standard.) Note in 2.0 the extent of FFS async support was that the mount command did not return an error message. FreeBSD V2.0 was horrendously broken in both performance and algorithm. Both FreeBSD-current, FreeBSD-2.1 AND Linux 1.3.5x, 1.3.6x are much better than the performance figures that you have quoted. For example, the FreeBSD V2.0 paging code was so broken, it could do nothing but thrash. (Performance similar to LRU.) The clustering code was terrible, and the cache was limited in size. I (a major FreeBSD supporter) warned my friends away from 2.0 because I wanted to keep them friends (unless they simply wanted to experiment.) The FreeBSD team was forced into the 2.0 fiasco, but that is far far behind us. Once in a while, we get reminded though... :-). John Dyson dyson@freebsd.org