Date: Fri, 11 May 2001 20:08:13 -0500 From: Carroll Kong <damascus@home.com> To: Donn Miller <dmmiller@cvzoom.net> Cc: Lamont Granquist <lamont@scriptkiddie.org>, stable@FreeBSD.ORG Subject: Re: fat32 slower than dogshit? Message-ID: <5.1.0.14.0.20010511200505.027754a0@netmail.home.com> In-Reply-To: <3AFC7509.E0DAFE66@cvzoom.net> References: <20010511151056.J15049-100000@warez.scriptkiddie.org>
next in thread | previous in thread | raw e-mail | index | archive | help
At 07:26 PM 5/11/01 -0400, Donn Miller wrote: >Lamont Granquist wrote: > > > > Well, i think it is, i'm actually not too sure exactly how fast dogshit is > > in the first place. But in doing a simple untar on a fat32 partition > > using both 4-stable a couple days after release and a recently updated > > 4-stable as of yesterday (5/10) it goes about 20-30 times slower than an > > untar on a UFS partition. > >That sounds about right. This is one of many reasons I don't run WinDOS >anymore. > >To Unsubscribe: send mail to majordomo@FreeBSD.org >with "unsubscribe freebsd-stable" in the body of the message Actually, I think it has a lot to do with the way FreeBSD implemented the mount_msdos or whatever. I am a big unix fan myself, but I did these tests a while back on 4.0 maybe or even 3.X on a multibooting box. I was quite shocked to see that for some odd reason, fat32 and fat16 writes would max at around 400KB/sec as opposed to megabytes/sec (on UFS and EXT2FS). Of course rebooting into windows gave me back the write speeds of megabytes/second, like any normal fs should. Considering that Fat32 is so featureless compared to UFS, it does not seem to make any sense that it is slower. (no multiple inodes, and such). Oh yeah, these were on contiguous files, so it was not really due to fragmentation. The same files were moved at much faster speeds. -Carroll Kong To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-stable" in the body of the message
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?5.1.0.14.0.20010511200505.027754a0>