[Openib-windows] wsd over mt23108 data corruption issue (x64)

Guy Corem guyc at voltaire.com
Tue May 9 07:42:11 PDT 2006


Yes.

 

Also: it's a sender size problem (I've confirmed it by checking mt23108
host against mthca host)

 

________________________________

From: Tzachi Dar [mailto:tzachid at mellanox.co.il] 
Sent: Tuesday, May 09, 2006 5:20 PM
To: Guy Corem; openib-windows at openib.org
Cc: Erez Haba
Subject: RE: [Openib-windows] wsd over mt23108 data corruption issue
(x64)

 

Do you have the Microsoft patch for WSD installed on both machines?

 

(http://support.microsoft.com/?kbid=910481#EGADAAA)

 

Thanks

Tzachi

	 

	
________________________________


	From: openib-windows-bounces at openib.org
[mailto:openib-windows-bounces at openib.org] On Behalf Of Guy Corem
	Sent: Tuesday, May 09, 2006 5:13 PM
	To: openib-windows at openib.org
	Cc: Erez Haba
	Subject: [Openib-windows] wsd over mt23108 data corruption issue
(x64)

	 

	Hi Fab and Leonid,

	 

	While testing an MPI utility that uses large buffers (>= 64MB),
I've encountered a data corruption bug.

	I was able to reproduce it directly over WSD.

	 

	Simplest reproducing scenario: 

	 

	Use pcattcp from http://www.pcausa.com/Utilities/ttcpdown1.htm
(compiled to 32 bit or 64 bit)

	Use large file (>= 64MB)

	 

	I've used a 90MB text file

	 

	Receiver command line: pcattcp.exe -r -s > file2

	Sender command line: pcattcp.exe -s -l 150000000 -n 1 -t
receiver_ip < file

	 

	When comparing both files, I see that file2 has 512 bytes
misplace after about 45MB (512 bytes were sent twice)

	 

	The problem doesn't occur on 32 bit machines.

	The problem doesn't occur with new mthca low level driver.

	 

	I suspect a memory registration problem, but wasn't able to tack
it down, yet.

	 

	Did you encounter similar problems in the past with huge
buffers?

	 

	Thanks,

	Guy

	 

	 

	 

	 

	 

	 

	 

-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.openfabrics.org/pipermail/ofw/attachments/20060509/32fa01a7/attachment.html>


More information about the ofw mailing list