SORT BY:

LIST ORDER
THREAD
AUTHOR
SUBJECT


SEARCH

IPS HOME


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

    Re: Unsolicited Data.



    Sanjeev,
    
    You seem to restate what I proposed at the bottom of this email.
    
    Yes, the current draft doesn't talk about F-bit setting when immediate
    data is not present.  That's precisely what my proposal attempts to 
    make use of - to signal "no unsolicited data" if the F-bit is set.
    --
    Mallikarjun 
    
    
    Mallikarjun Chadalapaka
    Networked Storage Architecture
    Network Storage Solutions Organization
    MS 5668	Hewlett-Packard, Roseville.
    cbm@rose.hp.com
    
    
    >Mallkarjun,
    >
    >According to me it is possible for initiator **not** to send  unsolicited
    >data if we follow the latest changes on the section 2.3.1 posted at
    >
    >According to me
    >
    >When IntitialR2T= No, Immediate Data = Yes and target doesnt want to
    >send any immediate data but it does want to send unsolicited data it can be
    >done like this
    >Step 1
    >Send iSCSI CmdPDU and  Dont send F bit and Dont send any immediate data by
    >not including any extra length in datasegmentlength
    >Step 2
    >Send Unsolicited Data and set the F bit
    >
    >
    >When IntitialR2T= No, Immediate Data = Yes and target doesnt want to
    >send any immediate data nor does it want to send unsolicited data it can be
    >done as follows
    >
    >Set F bit in Task and Flag Attributes and dont send any immediate data
    >by not including any extra length in datasegmentlength .
    >
    >My only doubt here is that it is not any illegal condition to set this F bit
    >when there is no immediate data to be sent and no unsolicited data to be
    >sent. Current spec doesnt declare it illegal but it doesnt really suggest it
    >this way either.
    >
    >
    >PLEASE DO COMMENT ON THIS
    >
    >Regards,
    >Sanjeev
    >
    >
    >
    >
    >----- Original Message -----
    >From: "Mallikarjun C." <cbm@rose.hp.com>
    >To: <steph@cs.uchicago.edu>
    >Cc: <ips@ece.cmu.edu>
    >Sent: Thursday, June 07, 2001 8:04 PM
    >Subject: Re: Unsolicited Data.
    >
    >
    >> Steph,
    >>
    >> I agree with you that mandating unsolicited data to be sent always
    >> is limiting, even if InitialR2T=no is negotiated.
    >>
    >> I suggest the following for consideration -
    >> - If the command F-bit is set:
    >>        - if immediate data is present, it's all the data
    >>          for the command. (as in rev06)
    >>        - if immediate data is not present, there are no
    >>          unsolicited data PDUs following.
    >> - If the command F-bit is not set:
    >>        - if immediate is present, there is more solicited
    >>          data to follow.
    >>        - if immediate data is not present, there may be
    >>          solicited data depending on "Expected Data Transfer
    >>          Length".
    >>
    >> The only case this disallows is that of having _both_ unsolicited
    >> separate PDUs and immediate data for a command - which I personally
    >> am okay with.  This is disallowed in rev06 anyway, but for some
    >> reason seemed like was changed later.
    >> --
    >> Mallikarjun
    >>
    >>
    >> Mallikarjun Chadalapaka
    >> Networked Storage Architecture
    >> Network Storage Solutions Organization
    >> MS 5668 Hewlett-Packard, Roseville.
    >> cbm@rose.hp.com
    >>
    >> >
    >> >Sanjeev,
    >> >
    >> >> why would initiator choose not to send unsolicited immediate data when
    >> >> it has negotiated for IntialR2T= Yes??
    >> >
    >> >I assume you mean InitialR2T=no.
    >> >
    >> >I would do this because I think that the real benefit of unsolicited
    >> >data is for writes where ALL the write data can be sent unsolicited,
    >> >and I'm happy to have the target schedule the transfer of (ALL) data
    >> >for larger writes.  Of course, others would say I'm a moron.
    >> >
    >> >Assuming the overwhelming majority of storage use is file access,
    >> >small writes are exclusively file system metadata writes.  Unsolicited
    >> >data is a huge win for metadata writes because the latency of these
    >> >metadata writes is frequently not covered by transferring other data
    >> >(within a single access thread).  On the other hand, the file system
    >> >(usually) generates enough concurrent demand for real data writes that
    >> >the flow control (R2T) latency is well hidden.
    >> >
    >> >You might argue that if you're running a file system optimized fors
    >> >today's SANs over a link with a HUGE bandwidth * delay product
    >> >(greater than the expected demand created by the file system), sending
    >> >large amounts of unsolicited write data will substantially improve the
    >> >link utilization.  That is true, but I don't think many targets are
    >> >going to offer unsolicited data bursts remotely that large.
    >> >
    >> >In a hardware accelerate implementation, unsolicited data will be
    >> >handled differently than solicited data.  The target can chose where
    >> >the solicited data is delivered, but unsolicited data arrives through
    >> >a general-delivery path.  Therefore, if the offered unsolicited data
    >> >burst size approaches the regular burst size, an implementation will
    >> >need TWICE as much buffer memory (half in the general-delivery area
    >> >and half in the flow-controlled buffer area) to support the same
    >> >operation load.  Maybe this tradeoff is OK, but given the cost
    >> >sensitivity of storage targets, I doubt it.
    >> >
    >> >As always, I welcome comments from those who see things differently.
    >> >
    >> >Steph
    >> >
    >>
    >>
    >
    
    
    


Home

Last updated: Tue Sep 04 01:04:32 2001
6315 messages in chronological order