Re: iSCSI:Request/Response Ordering

["John Hufferd" <hufferd@us.ibm.com>]

Sanjeev,
This is the purpose of Reserves.  Also, any application that performs this
type of operation to the very same device, from different systems, and has
not performed locking at the application level deserves what it gets.  If
the connections are from the same system, this is one of the purposes of
the Wedge Driver to coordinate I/O across different Connections.

Clustered Systems have had to deal with this for the last 35 years.  Shared
File Systems have a locking technique that spans the Cluster.  In Databases
they also have a locking technique that spans the Cluster.

.
.
.
John L. Hufferd
Senior Technical Staff Member (STSM)
IBM/SSG San Jose Ca
Main Office (408) 256-0403, Tie: 276-0403,  eFax: (408) 904-4688
Home Office (408) 997-6136
Internet address: hufferd@us.ibm.com


"Sanjeev Bhagat \(TRIPACE/Zoetermeer\)" <iscsi_t10@sanjeevbhagat.com>
@ece.cmu.edu on 09/29/2001 06:00:10 PM

Sent by:  owner-ips@ece.cmu.edu


To:   "'IPS Reflector'" <ips@ece.cmu.edu>, <T10@t10.org>
cc:
Subject:  iSCSI:Request/Response Ordering




Hello All (T10, IPS),

The SAM-2 specifications makes no assumption about,  or places any
requirement on the ordering of requests or responses between tasks  or task
management functions received from different SCSI initiator  ports.

In this scenario how can a SCSI target make  correctly handle the
read/write requests made on same blocks by different  intiators at the same
time.

Sanjeev