A computer components & hardware forum. HardwareBanter

If this is your first visit, be sure to check out the FAQ by clicking the link above. You may have to register before you can post: click the register link above to proceed. To start viewing messages, select the forum that you want to visit from the selection below.

Go Back   Home » HardwareBanter forum » General Hardware & Peripherals » Storage & Hardrives
Site Map Home Register Authors List Search Today's Posts Mark Forums Read Web Partners

number of outstanding FCP transfer ready



 
 
Thread Tools Display Modes
  #1  
Old November 29th 06, 04:06 PM posted to comp.arch.storage
Granite Park
external usenet poster
 
Posts: 2
Default number of outstanding FCP transfer ready

Is there a limit to the number of outstanding FCP transfer ready IUs on
a single exchange? If the limit is 1 then is the limited negotiated?

Thanks
  #2  
Old December 1st 06, 03:30 PM posted to comp.arch.storage
TK
external usenet poster
 
Posts: 1
Default number of outstanding FCP transfer ready



On Nov 29, 8:06 am, Granite Park wrote:
Is there a limit to the number of outstanding FCP transfer ready IUs on
a single exchange? If the limit is 1 then is the limited negotiated?

In the case of FCP, the number of outstanding Transfer ready IUs is
one. However, there could be more number of transfer rdy's provided by
the device depending on various conditions of implementation for an I/O
depending on the size of the I/O. In the case of iSCSI,the outstanding
R2Ts which is equivalent to FCP Transfer rdy's is negotiable during the
login phase.

Hope this helps

TK

Thanks


  #3  
Old December 1st 06, 07:24 PM posted to comp.arch.storage
Granite Park
external usenet poster
 
Posts: 2
Default number of outstanding FCP transfer ready

Maybe the number of outstanding transfer ready's is exactly 1 due to the
transfer of sequence initiative to the other side in FCP. I agree
that iSCSI provides a mechanism to negotiate a number 1, and this will
be useful over high latency networks.


On Nov 29, 8:06 am, Granite Park wrote:
Is there a limit to the number of outstanding FCP transfer ready IUs on
a single exchange? If the limit is 1 then is the limited negotiated?

In the case of FCP, the number of outstanding Transfer ready IUs is
one. However, there could be more number of transfer rdy's provided by
the device depending on various conditions of implementation for an I/O
depending on the size of the I/O. In the case of iSCSI,the outstanding
R2Ts which is equivalent to FCP Transfer rdy's is negotiable during the
login phase.

Hope this helps

TK

Thanks


  #4  
Old December 8th 06, 05:00 AM posted to comp.arch.storage
Moojit
external usenet poster
 
Posts: 7
Default number of outstanding FCP transfer ready

The number of transfer readys are not negotiated. Transfer readys are a bi
product of SCSI WRITE operations. Transfer size is typically bounded by
the capabilities of the o/s kernel and HBA driver combination. Multiple
transfer readys may occur during a single fibre channel exchange.

The Moojit

"Granite Park" wrote in message
news:ceibh.15947$Uz.10868@trnddc05...
Is there a limit to the number of outstanding FCP transfer ready IUs on a
single exchange? If the limit is 1 then is the limited negotiated?

Thanks



  #5  
Old December 29th 06, 10:59 PM posted to comp.arch.storage
dbs
external usenet poster
 
Posts: 4
Default number of outstanding FCP transfer ready


Moojit wrote:
The number of transfer readys are not negotiated. Transfer readys are a bi
product of SCSI WRITE operations. Transfer size is typically bounded by
the capabilities of the o/s kernel and HBA driver combination. Multiple
transfer readys may occur during a single fibre channel exchange.


Transfer Ready's are issued by the target not the initiator. They are
therefore
NOT bounded by the OS/kernel or the HBA. Generally, they are bounded by
buffering strategy and available buffer resources in the target. A
useful (but
perhaps not very realistic) example would be to consider a disk drive
with
an 8MB cache. If it write for 16MB is issued to the drive it will have
to break
that write up into 8MB (max) or lesser transfers in order to process
the write
command.

Dave

The Moojit


 




Thread Tools
Display Modes

Posting Rules
You may not post new threads
You may not post replies
You may not post attachments
You may not edit your posts

vB code is On
Smilies are On
[IMG] code is On
HTML code is Off
Forum Jump

Similar Threads
Thread Thread Starter Forum Replies Last Post
On the brink of madness... I.C. Koets General 18 January 31st 05 10:49 PM
Number System rehhman Storage (alternative) 5 January 16th 05 08:34 AM
Number system rehhman Storage (alternative) 1 January 12th 05 03:33 PM
corrupted partition table - help needed! Justin Case General 0 August 3rd 04 09:22 AM


All times are GMT +1. The time now is 09:10 PM.


Powered by vBulletin® Version 3.6.4
Copyright ©2000 - 2024, Jelsoft Enterprises Ltd.
Copyright ©2004-2024 HardwareBanter.
The comments are property of their posters.