Andrej Podzimek <and...@podzimek.org> wrote:
> P. S. As far as Phoronix is concerned... Well, I remember how they once used
> a malfunctioning and crippled Reiser4 implementation (hacked by the people
> around the ZEN patchset so that it caused data corruption (!) and kernel
> crashes) and "compared" it to other file systems. (That foolish Reiser4
> "benchmark" can be found here:
> http://www.phoronix.com/scan.php?page=article&item=reiser4_benchmarks&num=1)
If you like to compare Solaris with Linux, it is hard to get comparable
constraints in order to comparable results.
Linux has different goals for data security at certain check points.
I know of ext* performance checks where people did run gtar to unpack a linux
kernel archive and these people did nothing but metering the wall clock time
for gtar.
I repeated this test and it turned out, that Linux did not even start to write
to the disk when gtar finished.
Then I checked what Solaris did on UFS with logging, Solaris did start
immediately with disk transfers, so could it be faster than Linux?
Well I switched to star that by default calls fsync() at the end of extracting
for every single file. Solaris was not slower than Linux with the speudo gtar
test, but when star finished the file system was in a consistent state. GOning
back to Linux but using star with fsync resulted in a comparable test but Linux
now was 4x slower than Solaris.
It seems that Linux is not designed to be fast but to create the impression of
being fast.
Jörg
--
EMail:jo...@schily.isdn.cs.tu-berlin.de (home) Jörg Schilling D-13353 Berlin
j...@cs.tu-berlin.de (uni)
joerg.schill...@fokus.fraunhofer.de (work) Blog:
http://schily.blogspot.com/
URL: http://cdrecord.berlios.de/private/ ftp://ftp.berlios.de/pub/schily
_______________________________________________
zfs-discuss mailing list
zfs-discuss@opensolaris.org
http://mail.opensolaris.org/mailman/listinfo/zfs-discuss
