|
[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index] RE: A Transport Protocol Without ACK (resend)Julo, I agree, XON/XOFF would not work. A credit token scheme similar to FC Class 3 would. You may wish to review my draft as I have a simple scheme to illustrate the concept. This is also a genetic scheme proposed for SCTP as well. Doug > -----Original Message----- > From: owner-ips@ece.cmu.edu [mailto:owner-ips@ece.cmu.edu]On Behalf Of > julian_satran@il.ibm.com > Sent: Friday, September 29, 2000 6:49 AM > To: ips@ece.cmu.edu > Subject: RE: A Transport Protocol Without ACK (resend) > > > > > I don't doubt that such a mechanism could work and be somewhat useful. > Ordering between different XON/XOFFs is a bit more difficult > (the function can be easily piggybacked on R2T but R2Ts have no relative > ordering > or if we choose to do XON/XOFF at command boundary the command response > could > carry this information and responses are ordered). > > However I am under the impression that the TCP window (and in case of the > symmetrical > scheme or command sequence window) will perform the same function whenever > unsolicited data are enabled. > > Am I missing something? > > Julo > > Michael Krause <krause@cup.hp.com> on 23/09/2000 16:43:09 > > Please respond to Michael Krause <krause@cup.hp.com> > > To: ips@ece.cmu.edu > cc: (bcc: Julian Satran/Haifa/IBM) > Subject: RE: A Transport Protocol Without ACK (resend) > > > > > At 12:04 PM 9/22/00 -0600, HAAGENS,RANDY (HP-Roseville,ex1) wrote: > >Robert, > > > >The reason we proposed immediate write data for iSCSI was as an > optimization > >for short writes over "long" networks. As network diameter increases, > >minimizing round-trip signalling delays becomes important. Sending write > >data immediately following the command eliminates the need for > an RTT from > >the target, and thus eliminates a round-trip delay. > > > >If immediate data threatens to overflow the target's cache, the target > may, > >on an emergency basis, discard the data; and, when ready, request data > again > >using the RTT protocol. This behavior should be minimized, > however, as it > >will tend to congest the network. > > > >Note the use of SCSI-layer flow control (RTT mechanism). I agree with > those > >that say a controller must manage its cache, regardless of the > size of the > >cache. This is most apparent when one considers multiple hosts sharing a > >storage controller. In order to allocate performance between the hosts, > the > >controller must ensure that a write burst from a single host cannot fill > its > >cache. RTT provides a means for doing this that still allows other > commands > >(read commands, for example) from the same host to proceed. > > > >However, reserving a few MB of cache for each host, to accommodate > immediate > >writes, seems to me reasonable. The command windowing mechanism (another > >flow control mechanism) will prevent the overrunning of these immediate > >write buffers, assuming that the controller has reserved space in > proportion > >to the largest immediate buffer allowed (which is negotiated) x the > maximum > >number of commands. > > > >Upon writing this, it occurs to me that it may be useful to add an > >XOF/XON-like mechanism for temporarily disallowing immediate write data. > >This would give the controller another tool for cache management. When > its > >cache became congested, the controller could signal one or more of the > >requesting hosts to stop sending immediate write data with commands; > later, > >another message could allow immediate writes to resume. These messages > >would need to make it to the iSCSI layer in the hosts, as they > will affect > >how the host does DMA chain construction. > > Given the distances involved and the subsequent latency, I'd suggested > lifting the technique of issuing a RNR-NAK (receiver not ready) > with a time > period the sender should wait upon receiving the NAK before it retries the > operation (0 indicates immediate which may be acceptable if one knows the > sender is far away). Allows the receiver to allocate the requested buffer > space within what it believes to be a reasonable amount of time, > eliminates > the need for the receiver to track the sender's state for this > problem, and > eliminates the additional message associated with the XOFF/XON mechanism. > > In general, we should strive wherever possible to architect such that only > one side needs to track the state of a given attribute - this leads to > simplicity in implementation and future development of the architecture. > > Mike > > > >
Home Last updated: Tue Sep 04 01:06:57 2001 6315 messages in chronological order |