[openib-general] performance counters in /sys

[Mark Seger]

Hal Rosenstock wrote:

>On Thu, 2005-05-19 at 16:45, Yaron Haviv wrote:
>  
>
>>I believe you can use the per VL counters for that 
>>(IB allows counting traffic on a specific VL)
>>By matching ULPs to VLs (e.g. through the ib_at lib we suggested)
>>You can get both congestion isolation per traffic type as well as the
>>ability to count traffic per ULP 
>>(note that up to 8 VLs are supported in the Mellanox chips)
>>    
>>
>
>PortXmitDataVL[n], PortRcvDataVL[n], PortXmitPktVL[n], and
>PortRcvPktVL[n] are all IB optional. Do the Mellanox HCAs support these
>counters ?
>
>-- Hal
>
I didn't realize some counters are optional.  That kind of blows my 
notion of a fixed format, space separated output.  8-(

Perhaps a better way to focus this conversation is to see what the 
general feeling is towards statistics that are more oriented towards 
consumption by programs rather than humans and then discuss the details 
of format if some consensus can be reached.  I'm also wondering if data 
is to be combined for mulitple hcas/ports it may make more sense to put 
it into /proc where those types of structures appear, but that level of 
discussion should probably also be deferred.

-mark

-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.openfabrics.org/pipermail/general/attachments/20050520/948b51aa/attachment.html>