Re: [Scst-devel] Direct install on iscsi target

[Vladislav B. <vs...@vl...>]

Vladislav Bolkhovitin, on 12/09/2009 04:21 PM wrote:
> Vladislav Bolkhovitin, on 12/08/2009 11:19 PM wrote:
>> Benjamin Yates, on 12/08/2009 09:05 PM wrote:
>>> Vladislav Bolkhovitin wrote:
>>>> P.S. One more piece of IET code is going to be rewritten..
>>>     fwiw, iet works...
>> IET doesn't support MaxOutstandingR2T > 1.
> 
> Seems I should evaluate a bit more on this to remove very much possible 
> misunderstandings.
> 
> Let's consider we have a 1Gbps network between initiator and target with 
> 10ms latency (a good near distance WAN/Internet to another building in 
> the same town). We want to send backup from the initiator to a tape or 
> tape library on the target. Another possible task is a sync. 
> replication. We are limited to send only 1 write command at time, 
> because our tape doesn't allow more. We will send 2MB of data in each 
> command.
> 
> Our initiator and target negotiated typical values InitialR2T No, 
> ImmediateData Yes, FirstBurstLength 65536, MaxBurstLength 262144. Other 
> parameters don't matter for our task, except MaxOutstandingR2T. Let we 
> can run 2 pieces of iSCSI target software on the target: one supporting 
> only MaxOutstandingR2T 1 (e.g., IET) and another one supporting 
> MaxOutstandingR2T >1 (e.g., iSCSI-SCST). The first target negotiated 
> MaxOutstandingR2T 1, the second one - 16.
> 
> 10ms means that a 1 byte packet send from the initiator reaches the 
> target in 5ms time. Then 5ms in the opposite direction. 1Gbps bandwidth 
> means that 64K of data transferred from the initiator to the target in 
> about 0.5ms
> 
> Since each R2T request must contain less than MaxBurstLength data, we 
> need ((2MB - 64K)/256K) = 8 R2T requests to send. The first 64K will be 
> sent as immediate data without explicit R2T request.
> 
> 1. The first target with MaxOutstandingR2T 1.
> 
> MaxOutstandingR2T 1 means that only one R2T request can be active on 
> time. I.e., the next request for data transfer sent before the previous 
> one completed and all the data received.
> 
> Thus, on the first target each command will be completed on time:
> 
> 5 + 0.5 + (5 + 5 + 256K/64K * 0.5) * 7 + (5 + 5 + (256K - 64K)/64K * 
> 0.5) + 5 = 106ms, i.e. 9 IOPS, which is 18MB/s
> 
> 2. The second target with MaxOutstandingR2T 16.
> 
> With MaxOutstandingR2T 16 the second target can send all R2T requests at 
> once.
> 
> Thus, on the second target each command will be completed on time:
> 
> 5 + .5 + 5 + 5 + 256K/64K * 0.5 * 7 + (256K-64K)/64K * 0.5 + 5 = 36ms, 
> i.e. 27 IOPS, which is 54MB/s.
> 
> Thus, the second target will perform on 54/9 = 600% better that the 
> first target.

Oops, of course 54/18 = 300%. Impressive, anyway.

> So, iSCSI protocol isn't so bad for long latency links as many believe. 
> It is only needed to be implemented properly.
> 
> Vlad
>