[Ips] iSER Data-in clarification

Arne Redlich <arne.redlich@googlemail.com> Mon, 22 June 2009 17:24 UTC

DomainKey-Signature: a=rsa-sha1; c=nofws; d=googlemail.com; s=gamma; h=subject:from:reply-to:to:content-type:date:message-id:mime-version :x-mailer:content-transfer-encoding; b=enjz1MaMg6aAYR0AtqJ6cgC12D2SpKPy26cqU/eEcOW/C6gwH5buAVcCCcT8bsCkUx tN9hPU3OZdTC++ypep7ZILTg60qvvBoav3VpRaOdjT58ieu6BbJfJ6aRFFXhEZ4HQH9S SschKLtixJSzORsFYKge+MZe6o0LMo6CK18Os=
From: Arne Redlich <arne.redlich@googlemail.com>
To: ips@ietf.org
Content-Type: text/plain
Date: Mon, 22 Jun 2009 19:24:18 +0200
Message-Id: <1245691458.4513.269.camel@blackadder>
Mime-Version: 1.0
Content-Transfer-Encoding: 7bit
Subject: [Ips] iSER Data-in clarification
Precedence: list
Reply-To: arne.redlich@gmail.com

Hi,

I'm unclear on the granularity with which an iSER target is supposed to
transfer Data-In via RDMA writes. Here's the pieces of information I'm
trying to tie together:

(1) The iSER spec replaces the initiator's MaxRecvDataSegmentLength with
InitiatorMaxRecvDSL, but this only applies to control type PDUs
(2) MaxBurstLength limits the size of Data-{In,Out} sequences, however,
the iSER spec is silent about Data-In sequences.
(3) RFC 5046, 7.3.5 (SCSI Data-In):
 "2. It MUST generate and send an RDMA Write Message containing the read
data to the initiator [...]
  c. It MUST use DataSegmentLength from the SCSI Data-in PDU to
determine the amount of data to be sent in the RDMA Write Message."

What is the iSCSI layer at the target supposed to use as
DataSegmentLength? MaxBurstLength? The full Data-In length?

Thanks in advance,
Arne

[Ips] iSER Data-in clarification Arne Redlich