Date: Tue, 18 Jun 2002 21:40:54 -0400 From: "Remo Lacho" <Remo.Lacho@verizon.net> To: bob@immure.com Cc: stable@jnielsen.net, freebsd-stable@freebsd.org Subject: Re: the new ATA driver vs. vinum Message-ID: <200206182140540930.089E3C72@smtp.verizon.net> In-Reply-To: <20020619003131.GE9829@luke.immure.com> References: <DBEFLLCPEGLPEAGOPLIHIEEODKAA.patrick-fbsdstable@mindstep.com> <0fb301c2170c$df665ff0$0900a8c0@max> <20020618215151.GB9829@luke.immure.com> <108201c2171d$ea673d00$0900a8c0@max> <200206181948530523.0837ACB5@smtp.verizon.net> <20020619003131.GE9829@luke.immure.com>
next in thread | previous in thread | raw e-mail | index | archive | help
On 6/18/2002 at 7:31 PM Bob Willcox wrote: >What type of ata drives were you using? I am using IBM drives w/o any >problems (with DMA enabled). Most of my disks are the 80GB and 120GB >120GXP models. > As I said, this is not (yet) a production system. I have two Maxtor (Quantum) "throwaways" lc20s, 20GB, 5400 RPM (about 6 months old), set up as masters on each of the two ata channels. > >With one of my setups (a 3 80GB drive RAID0 array) I get up to 90MB/s >through put on reads and 70MB/s on writes. > That's impressive! My test box is a Gateway 6400 server with on board Symbios LVD 160 controllers (extremely fast with FBSD 4.6R). It would really be nice to have an ata array file server 2+2 RAID0+1 of 4 WD 80GB or 120GB drives with 8 MB cache and 7,200 RPM (from $95 to $120 each on sale with rebates). > >Bob > >On Tue, Jun 18, 2002 at 07:48:53PM -0400, Remo Lacho wrote: >> I too have set up a RAID0 array on a ServerWorks ROSB4 (non-raid) >controller >> (but not on a production machine!), that has worked flawlessly so far. >> >> However, prior to setting up the array (and until the drives' mode was >set to >> "PIO4") the ata sub-system kept crashing continuously. >> >> It would seem that if the atacontrol binary ever becomes stable -- and >can >> run ata disks at their top rated speed -- vinum will be getting a run >for its >> money. >> >> My experiences with vinum have all ended tragically. It has never been >> production level for my needs. >> >> When (and if) atacontrol becomes stable, you will be getting champagne >for >> the price of beer! >> >> *********** REPLY SEPARATOR *********** >> >> On 6/18/2002 at 5:14 PM John Nielsen wrote: >> >> >----- Original Message ----- >> >From: "Bob Willcox" <bob@immure.com> >> >To: "John Nielsen" <stable@jnielsen.net> >> >Cc: "stable list" <freebsd-stable@freebsd.org> >> >Sent: Tuesday, June 18, 2002 3:51 PM >> >Subject: Re: the new ATA driver vs. vinum >> > >> > >> >> On Tue, Jun 18, 2002 at 03:12:36PM -0600, John Nielsen wrote: >> >> > >> >> > Bear in mind that atacontrol is a utility to interact with a >hardware >> >ATA >> >> > raid controller, and doesn't do RAID itself. Vinum allows you to do >> >RAID >> >> > without any special hardware. ATA RAID was possible in 4.5, you >just >> >had to >> >> > rely on the RAID controller's BIOS to set it up and manage it if >there >> >was a >> >> > problem. >> >> >> >> Actually, with the new ata driver and atacontrol you can do raid w/o >an >> >> ata raid controller with some restrictions. From the atacontrol man >page: >> >> >> >> Allthough the ATA driver allows for creating an ATA >RAID on >> >> disks on any controller, there are restrictions. It is >only >> >pos- >> >> sible to boot on an array if its either located on a >"real" >> >ATA >> >> RAID controller like the Promise or Highpoint >controllers, >> >or if >> >> the RAID declared is of RAID1 or SPAN type, in case of a >> >SPAN >> >> the partition to boot must reside on the first disk in >the >> >SPAN. >> >> >> >> So as long as you don't want/need to boot from the RAID, any IDE >> >> controller should work. >> > >> >I stand corrected! I'll have to look into that some more. :) >> > >> >> I have several systems here runing both a RAID0 and a RAID0+1 array >> >> using a standard non-RAID promise IDE controllers (TX2's as I recall). >> >> Works fine! :-) >> >> >> >> Bob >> >> >> >> -- >> >> Bob Willcox Dealing with failure is easy: work hard to >> >improve. >> >> bob@vieo.com Success is also easy to handle: you've solved >the >> >> Austin, TX wrong problem. Work hard to improve. >> >> >> > >> > >> >To Unsubscribe: send mail to majordomo@FreeBSD.org >> >with "unsubscribe freebsd-stable" in the body of the message >> > >-- >Bob Willcox Dealing with failure is easy: work hard to improve. >bob@vieo.com Success is also easy to handle: you've solved the >Austin, TX wrong problem. Work hard to improve. 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?200206182140540930.089E3C72>