[Date Prev][Date Next]   [Thread Prev][Thread Next]   [Thread Index] [Date Index] [Author Index]

[dm-devel] RE: Is there a grand plan for FC failover?



I view port as a part of the path. I may have been a little loose on my
terms. I am describing paths that enter different ports on the device - not
the paths through the same port that you describe. Could be 1 adapter to a
switch with 2 switch connections to 2 ports on the target; or 2 adapters,
each with an independent path to a different port on the device.

Relative to a single port on the device - I agree with you. Simple
reservations only allow one initiator access. With multiple ports on the
device, each which may be on different and independent "bus", simple
reservation isn't sufficient.  (yes - I'm using "bus" loosely - it may be an
independent Parallel SCSI bus, or a independent fabric/zone, etc).

-- James

> -----Original Message-----
> From: Mike Anderson [mailto:andmike us ibm com]
> Sent: Thursday, January 29, 2004 1:31 PM
> To: Smart, James
> Cc: 'James Bottomley'; Philip R. Auld; 'Patrick Mansfield'; Simon
> Kelley; SCSI Mailing List; dm-devel sistina com
> Subject: Re: Is there a grand plan for FC failover?
> 
> 
> Smart, James [James Smart Emulex com] wrote:
> > 
> > 
> > > -----Original Message-----
> > > From: James Bottomley [mailto:James Bottomley SteelEye com]
> > > 
> > > On Thu, 2004-01-29 at 09:49, Philip R. Auld wrote:
> > > > It needs to be known to the pathing layer if you've got 
> > > load balancing. 
> > > > It has to know which path has the reservation and only 
> use that one.
> > > 
> > > Well, yes, but your multiple active path implementation 
> just collapsed
> > > back down to single path in the face of reservations, so it would
> > > probably be better simply to use failover in the face of 
> reservations
> > > and clustering.
> > 
> > Why do you imply that you're down to a single path ? With 
> multiple port
> > devices, and the T10 unclarity on multiport support, simple 
> reservations
> > didn't bring you down to the single port access you are 
> describing. Some
> > devices may have implemented it this way, but the standard 
> didn't say they
> > had to or even that they should.
> > 
> > And this picture changes significantly with the use of Persistent
> > Reservations and the use of keys.
> > 
> 
> It appears you are mixing port and path. If you have multiple 
> paths to a
> port created by multiple adapters connecting to this port 
> through a bus,
> fabric, etc. then simple reservations should restrict you to only one
> path to this port. Is there a device that implements simple 
> reservations
> and allows multiple initiators access?
> 
> -andmike
> --
> Michael Anderson
> andmike us ibm com
> 



[Date Prev][Date Next]   [Thread Prev][Thread Next]   [Thread Index] [Date Index] [Author Index]