[openib-general] Problem with using krping

Tom Tucker tom at opengridcomputing.com
Wed Nov 22 23:15:33 PST 2006


Roland:

I'm a little stumped on the ALIGN macro change. The log entry implies that
the change was to fix the ALIGN macro so that it did NOT truncate to int,
but it seems to do exactly that. Do you have any insight into this. The file
I'm looking at is include/linux/kernel.h.

Thanks,
Tom


On 11/23/06 12:54 AM, "Tom Tucker" <tom at opengridcomputing.com> wrote:

> 
> It looks like this is an artifact of the ALIGN macro truncating to int (i.e.
> using - 1UL instead of -1). I believe that this was fixed on Sep 22 by Dave
> Miller. 
> 
> On 11/22/06 10:46 PM, "Krishna Kumar2" <krkumar2 at in.ibm.com> wrote:
> 
>> Hi,
>> 
>> While using amso cards and running krping with :
>> 
>> server: /bin/echo server,port=9999,verbose,addr=x.x.x.x > /proc/krping
>> client: /bin/echo client,port=9999,verbose,addr=x.x.x.x > /proc/krping
>> 
>> the client fails with (in /var/log/messages) :
>>         "c2_get_dma_mr:423
>>         couldn't vmalloc page_list of size 0
>>         krping: recv_buf reg_mr failed"
>> 
>> The problem (for me) happens since c2_reg_phys_mr() calculates page_shift
>> was as 15 and size is 0xffffffff resulting in pbl_depth getting set to
>> zero, and
>> vmalloc returns NULL. When I changed c2_get_dma_mr() on both server/client
>> to use address 0xefffffff, the tests works correctly.
>> 
>> What is the right fix for this problem ? I am using *rc3 bits and krping
>> is from
>> the gen2/*/utils directory, and at revision 10156.
>> 
>> Thanks,
>> 
>> - KK
>> 
>> 
>> _______________________________________________
>> openib-general mailing list
>> openib-general at openib.org
>> http://openib.org/mailman/listinfo/openib-general
>> 
>> To unsubscribe, please visit
>> http://openib.org/mailman/listinfo/openib-general
>> 
> 
> 
> 
> _______________________________________________
> openib-general mailing list
> openib-general at openib.org
> http://openib.org/mailman/listinfo/openib-general
> 
> To unsubscribe, please visit http://openib.org/mailman/listinfo/openib-general
> 






More information about the general mailing list