SORT BY:

LIST ORDER
THREAD
AUTHOR
SUBJECT


SEARCH

IPS HOME


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

    Re: iSCSI: need for new data SNACK code?



    Dave,
    
    I am glad that others are chiming in as well, :-)
    
    >It is free to segment
    > to any size <= to that and to change that size, for its own purposes, at
    > any point in time w/o notifying the initiator.
    
    That is correct for the general case, but not for the specific data SNACK
    case under discussion - the spec requires the retransmitted PDUs to be 
    "exact replicas" barring certain header fields, in the absence of a negotiated 
    max PDU size change.
    --
    Mallikarjun
    
    Mallikarjun Chadalapaka
    Networked Storage Architecture
    Network Storage Solutions
    Hewlett-Packard MS 5668 
    Roseville CA 95747
    cbm@rose.hp.com
    
    ----- Original Message ----- 
    From: "Dave Sheehy" <dbs@acropora.rose.agilent.com>
    To: "IETF IP SAN Reflector" <ips@ece.cmu.edu>
    Sent: Thursday, July 11, 2002 5:29 PM
    Subject: RE: iSCSI: need for new data SNACK code?
    
    
    > 
    > > > If the target makes
    > > > its own choice to resegment, and the initiator doesn't think the
    > > > target resegmented, there are error scenarios that combine this with
    > > > corrupt Data PDU headers to cause the initiator to successfully
    > > > complete a SCSI command that has not delivered all its data
    > > > (the resegmented PDUs caused the Data PDU count to match the ExpDataSN
    > > > value in the response that should have been discarded, but wasn't).
    > > > While these should be rare, their consequences can be catastrophic.
    > > 
    > > What do you mean by "if the target makes it's own choice to resegment"?
    > > Sounds like a target bug to me.  It feels like you're making this look more
    > > complicated than it really is.
    > 
    > The only promise the target has made to the initiator is that it will not
    > send a segment larger than MaxRecvDataSegmentLength. It is free to segment
    > to any size <= to that and to change that size, for its own purposes, at
    > any point in time w/o notifying the initiator. I don't think the spec says
    > anything about requiring the target to use a constant segment size. 
    > Therefore, the described behavior is perfectly legal and not a bug as you 
    > seem to believe.
    > 
    > Dave
    > 
    > 
    
    


Home

Last updated: Fri Jul 12 00:19:01 2002
11294 messages in chronological order