Re: iSCSI: error recovery

["Prasenjit Sarkar/Almaden/IBM" <psarkar@almaden.ibm.com>]

I think Matt's answer has gone the most about clarifying
the need for stat_rn.

I was concentrating more on the one connection case
(which I think we cannot ignore).

Let us assume that there is a facility for "quick" detection
of media failures.

In this situation, only the initiator can "quickly" detect a failed
connection and then build a separate new connection to
the target. (The opposite is not true as the intitiator
is not listening on any port). Moreover, if the target
has a limit of one connection per session and does
not also "quickly" detect a failed connection, it may think that the
old connection is still alive and reject the new connection.

In summary, while the stat_rn mechanism is useful
for the multiple connections per session model, I find its
use to be extremely limited in the one connection per session
model.

I leave it up to the authors whether they should make stat_rn
mandatory for the single connection per session model.

Prasenjit













   Prasenjit Sarkar
   Research Staff Member
   IBM Almaden Research
   San Jose


Matt Wakeley <matt_wakeley@agilent.com>@ece.cmu.edu on 10/24/2000 05:20:58
PM

Please respond to Matt Wakeley <matt_wakeley@agilent.com>

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


To:   IPS Reflector <ips@ece.cmu.edu>
cc:
Subject:  iSCSI: error recovery



There has been a lot of discussion on how the Status reference numbers are
(can be) used for error detection and recovery.  There is even a (optional)
method for numbering the Data PDUs now.

Let's clarify what "errors" we are trying to recover from, and how the RNs
are
meant to be used.  The example is as follows.  An iSCSI session has
multiple
TCP connections over *separate* physical links.  If one of the physical
links
fails, it is desirable to "recover" the SCSI I/Os that were occurring on
the
TCP connection(s) that were established over that link.  We should *not*
attempt to recover "errors" that are caused due to data being discarded
after
it has been delivered from TCP to the upper layers (iSCSI, SCSI, whatever).

Now there has already been discussion on how the TCP timeouts are
(generally)
longer than most SCSI command timeouts, so I'm only discussing link errors
that can be detected fairly quickly.  For example, if the physical link
gets
yanked, the MAC can relatively quickly determine the link is down and
notify
the appropriate management entity.

The goal is to have a mechanism for the initiator to determine what
commands
are outstanding on the failed connection. Likewise, it's desirable for the
target to retain the data and/or status of I/Os until they are acknowledged
by
the initiator, so that in the event of a link failure, the target can
"replay"
the I/O.

>From the ExpCmdRN, the initiator knows which commands it sent on the
failed
TCP connection where received by the target and those that were not.  Any
commands received by the target, but not completed (no status pdu received
before the failure) should be resent on another TCP connection with the
"retry" bit set.  Any commands not received by the target are resent on
another TCP connection without the "retry" bit.

The target keeps the context (status and maybe data) of SCSI I/Os it's
executed until it has positive acknowledgment from the initiator that the
I/O
is complete at the initiators end.  This acknowledgment is indicated in the
ExpStatRN received from the initiator.  Acknowledged I/Os are then
deallocated
in the target.

Now for some issues I have with the (current) iSCSI draft:

In section 2.2.2 it states "As the only cause for long delays in responses
can
be failed connections and received responses free-up resources, we felt
that
score boarding responses at the initiator could be accomplished by simple
bitmaps and there is no need to flow-control responses."

Score boarding, especially with bit maps,  is an operation that can be
somewhat CPU heavy in the normal "performance path" of the iSCSI layer. If
the
ExpStatRN was local to each TCP connection, rather than global across the
iSCSI session, then there would be no requirement for score boarding.  The
initiator would simply increment the StatRN received on each connection for
use in the ExpStatRN for that connection.

>From an earlier email: "1.1.1.3   Data PDU numbering
Incoming Data PDUs MAY be numbered by a target to enable fast recovery of
long
running READ commands. Data PDUs are numbered with DataRN.  NOP command
PDUs
carrying the same Initiator Tag as the Data PDUs are used to acknowledge
the
incoming Data PDUs."

Since the only "error" we are trying to recover from is the very rare event
that a physical link fails, I fail to see what the benefit is to be able to
"recover" at the PDU level.  Plus, you'll have to build into the protocol a
mechanism to request retransmission of particular data PDUs.  Let's
simplify
and just send the command with the "retry" bit set.

Also from an earlier email:


> >Mallikarjun,
> >
> >Thanks for your comments.
> >
> >Initiator scoreboarding is not considered. I will try to emphasize this
> >even more in the new draft.
> >The party responsible for reporting length is the target.  As
overlapping
> >ranges are not explicitly
> >forbidden this would be a harder task than apparent. Reporting counts
> >becomes entirely a question of faith!
>
> I didn't realize that (what FC calls as) data overlay is allowed, FCP
> requires this initiator capability to be explicitly stated in session
> establishment (process login).  Is there a particular reason why this
> is chosen to be allowed by default in iSCSI?
>

Again, in the interests of simplicity, I request that data overlay be
forbidden.  Period.  Otherwise, the initiator would have to perform score
boarding at the byte level to be positively sure that each byte was really
received.

>
> Given that the physical number of bytes transferred could be more (data
> overlay case) or less (command retry case), may I suggest that the
discussion
> about Residual under/overflow (section 3.3.1) and Residual Count (section
> 3.3.2) make it explicitly clear that it's the status of "logical" # of
> bytes that is being reported?  That way, initiator implementations can
> always rely on those fields regardless of the history of the task.
>
> I assume you took note of my comments on the need to change wording and
> payload definition of NOP PDU.
>
-Matt Wakeley