On Wed, Jul 13, 2005 at 02:38:57PM +0200, vitko wrote: > >You could experiment with not using -o sync. Under 2.6.13-rc2 or later it > >may turn out to be just as reliable. > > Alan, I've run some preliminary 2.6.13-rc2 tests, but it seems that key > factor > is really -o sync. > > With -o sync I'm still getting cca 150 kb/s write speed, whereas without > -o sync I was able to copy 712000298 bytes in 68 s (including sync and > umount > commands, to be exact). This ammounts to some awesome 10 MB/s write speed, > while so far I've been able to get only cca 4 MB/s (yes, I've been mounting > with -o sync all the time until now). > > So now problem reduces to degraded write speeds with -o sync on kernel > > 2.6.11. > > Is it bug or feature? If the former, should I file a bug, if so, then is > it usb-storage, scsi, fat32 or some other issue?
I'd call this a fat32 or other filesystem-related issue. Neither SCSI nor
usb-storage knows about the -o sync option. That option is handled at the
filesystem layer.
Matt
--
Matthew Dharm Home: [EMAIL PROTECTED]
Maintainer, Linux USB Mass Storage Driver
Hi. I have my back hairs caught in my computer fan.
-- Customer
User Friendly, 8/20/1998
pgpgkYVrMYZwh.pgp
Description: PGP signature
