Date: Thu, 15 Feb 2007 13:03:27 -0800 From: "Kevin Oberman" <oberman@es.net> To: Ivan Voras <ivoras@fer.hr> Cc: freebsd-stable@freebsd.org Subject: Re: Very slow umass in 6.2-RC2 Message-ID: <20070215210327.E554E45053@ptavv.es.net> In-Reply-To: Your message of "Thu, 15 Feb 2007 11:55:03 PST." <20070215195503.18C3A45055@ptavv.es.net>
next in thread | previous in thread | raw e-mail | index | archive | help
--==_Exmh_1171573407_94867P Content-Type: text/plain; charset=us-ascii Content-Disposition: inline > Date: Thu, 15 Feb 2007 11:55:03 -0800 > From: "Kevin Oberman" <oberman@es.net> > Sender: owner-freebsd-stable@freebsd.org > > --==_Exmh_1171569303_99072P > Content-Type: text/plain; charset=us-ascii > Content-Disposition: inline > > > From: Ivan Voras <ivoras@fer.hr> > > Date: Thu, 15 Feb 2007 19:12:40 +0100 > > Sender: owner-freebsd-stable@freebsd.org > > > > Alexander Shikoff wrote: > > > > > umass0: vendor 0x1005 USB FLASH DRIVE, rev 2.00/1.00, addr 2 > > > da0 at umass-sim0 bus 0 target 0 lun 0 > > > da0: < USB FLASH DRIVE 34CH> Removable Direct Access SCSI-0 device > > > da0: 40.000MB/s transfers > > > da0: 3936MB (8060928 512 byte sectors: 255H 63S/T 501C) > > > > > > Writing to this device is very slooooow. > > > > > > Time taken to copy file of 1,4G is near 30 min. > > > > 1400/1800=0.77... which looks suspiciously like the rate I get while > > copying over USB 1 port. What does "iostat 1" say while you're copying > > the file? > > Looks a lot like a new 4GB drive I bought. It is painfully slow. > > Here is the result of iostat: > tty ad0 da0 pass0 cpu > tin tout KB/t tps MB/s KB/t tps MB/s KB/t tps MB/s us ni sy in id > 0 77 16.00 1 0.02 4.00 48 0.19 0.00 0 0.00 0 0 1 0 99 > 0 231 0.00 0 0.00 4.00 48 0.19 0.00 0 0.00 3 0 1 2 94 > 0 649 0.00 0 0.00 4.00 36 0.14 0.00 0 0.00 3 0 2 2 94 > 0 77 9.00 2 0.02 4.00 1 0.00 0.00 0 0.00 2 0 1 1 97 > 0 77 9.00 2 0.02 0.00 0 0.00 0.00 0 0.00 4 0 1 0 95 > > This is (obviously) from the end of the transfer. Transfer rate varies > from .14 to .19 MB/s. While I have not one statistical analysis, it is > clear that the mode is .14 and I'd guess the median is around 16 > KB/s. (I calculated it over 20 samples in the middle of the transfer.) > > To say that this is dreadful is a major understatement, but I suspect it > is an issue with the drive. I will try it on Windows and see it it works > any better there. It might be crappy hardware. (At $30 for a 4GB drive, > it was certainly cheap.) To followup on my own message, Ivan is doing GREAT! FreeBSD 312 seconds Windows 12 seconds Wow! To say that these numbers do not make FreeBSD look good would be a huge understatement. Is Hans new umass available? If so, I might give it a try when I have a chance. Also, I just realized that I am on the wrong list as the system I'm doing this on is running current, not stable. -- R. Kevin Oberman, Network Engineer Energy Sciences Network (ESnet) Ernest O. Lawrence Berkeley National Laboratory (Berkeley Lab) E-mail: oberman@es.net Phone: +1 510 486-8634 Key fingerprint:059B 2DDF 031C 9BA3 14A4 EADA 927D EBB3 987B 3751 --==_Exmh_1171573407_94867P Content-Type: application/pgp-signature -----BEGIN PGP SIGNATURE----- Version: GnuPG v1.4.6 (FreeBSD) Comment: Exmh version 2.5 06/03/2002 iD8DBQFF1Mqfkn3rs5h7N1ERAr7wAJ9bXJI6Dc2JLvGi1Ic67XomId4x3wCgg6T0 MET8BmkbhksE9aRiImKZw+0= =TOgP -----END PGP SIGNATURE----- --==_Exmh_1171573407_94867P--
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?20070215210327.E554E45053>