xfs
[Top] [All Lists]

RE: LVM on Linux

To: "'Simon Matter'" <simon.matter@xxxxxxxxxxxxxxxx>, Florin Andrei <florin@xxxxxxx>
Subject: RE: LVM on Linux
From: "Gonyou, Austin" <austin@xxxxxxxxxxxxxxx>
Date: Tue, 17 Jul 2001 13:38:59 -0500
Cc: linux-xfs@xxxxxxxxxxx
Sender: owner-linux-xfs@xxxxxxxxxxx
That is referred to as hardware RAID because most RAID card devices use an
ASIC programmed to do ONLY that. Think of it, if you like, as a RAID
appliance. :) 

-- 
Austin Gonyou
Systems Architect, CCNA
Coremetrics, Inc.
Phone: 512-796-9023
email: austin@xxxxxxxxxxxxxxx 

> -----Original Message-----
> From: Simon Matter [mailto:simon.matter@xxxxxxxxxxxxxxxx]
> Sent: Tuesday, July 17, 2001 1:38 AM
> To: Florin Andrei
> Cc: linux-xfs@xxxxxxxxxxx
> Subject: Re: LVM on Linux
> 
> 
> Florin Andrei schrieb:
> > 
> > On 16 Jul 2001 22:54:18 +0200, Ragnar Kjørstad wrote:
> > >
> > > Even for highend RAID's there are lots of reasons to use LVM/EVMS:
> > > * load balancing across multiple scsi-channels (not 
> implemented yet)
> > > * Dynamic partitioning
> > > * Volumes spanning multiple physical devices
> > > * snapshotting.
> > >
> > > Basicly handling this is software adds a lot of flexibility.
> > 
> > But how about performance?
> > Aren't these things supposed to be handled by the hardware?
> > It's the same thing as for soft vs hard RAID. Hard should be faster
> 
> I have never seen a true hardware RAID. I mean every RAID I saw
> was having its own CPU (be it i960 or any newer generation of
> microprocessor or microcontroller from different vendors) and
> small operating system (firmware). So in fact it's always
> software but not running on you main CPU. However
> mainstream CPU's became powerful and very cheap so it's not
> a bad idea to let this CPU work for your RAID funtionality. In
> fact software RAID on modern CPU's has exiting performance.
> 
> > (but, yeah, soft is easier to play with).
> 
> Another good reason to use the really soft version.
> 
> > 
> > --
> > Florin Andrei
> 
> 


<Prev in Thread] Current Thread [Next in Thread>