|
|
| [Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index] |
Sanjay, One of the reasons that I, for one, thought this approach was a good idea was that I felt that it was possible that a software version of iWARP could be made available. Even though it might not be appropriate for Server to Server communications, it might be very useful for workstations (desktops/laptops) to use software iWARP when communicating to a server that has and RNIC. In the workstation to iWARP server situation, the workstation often has all the MIPS it needs for this operation, and though not efficient for the workstation to use software iWARP (probably no one will notice anyway), it enables server efficiencies since the server can use iWARP via its RNIC. The same thought is appropriate when the workstation (Initiator) is contacting a Storage (Target) system that might have an RNIC. In that case the Initiator might prefer to use normal iSCSI, but the Target would prefer to use iSER. In other situations with RNICs, some vendors are producing RNICs that also support native iSCSI (especially if they want to sell product today). These RNICs can often support iSCSI as well as iSER. In some cases, the iSCSI path has been optimized for that specific task, and will operate as well as, or perhaps in some cases better than iSER (depending on the implementation and HW used). . . . John L Hufferd Sr. Executive Director of Technology Brocade Communications Systems, Inc jhufferd@brocade.com Office Phone: (408) 333-5244; eFAX: (408) 904-4688 Alt Office Phone: (408) 997-6136; Cell: (408) 627-9606 -----Original Message----- From: ips-bounces@ietf.org [mailto:ips-bounces@ietf.org] On Behalf Of Mike Ko Sent: Tuesday, November 29, 2005 11:15 AM To: Sanjay Goyal Cc: ips@ietf.org Subject: RE: iSER: draft-ietf-ips-iser-05.txt Sanjay, The initiator may well reject the RDMAExtensions offer from the target, but we don't want to preclude the possibility that the initiator might want to accommodate the target and choose to support iSER instead. Mike To: "Mike Ko" <mako@almaden.ibm.com> cc: <ips@ietf.org> Subject: RE: iSER: draft-ietf-ips-iser-05.txt Mike, I understand that, the point I was trying to make was if Initiator prefers iSCSI mode, why would it change its mind after it gets RDMAExtensions key from Target. -Sanjay _______________________________________________ Ips mailing list Ips@ietf.org https://www1.ietf.org/mailman/listinfo/ips _______________________________________________ Ips mailing list Ips@ietf.org https://www1.ietf.org/mailman/listinfo/ips
[IETF] [Linux iSCSI] [Linux SCSI] [Linux Resources] [Yosemite News] [IETF Announcements] [IETF Discussion] [SCSI]
![]() |
![]() |