Gather HCA statistics

[guilbaults]

At the moment, only the statistics of the switches are collected. The original idea was to limit interaction with the compute nodes since every packets go to a switch, so the switch counters see all the traffic. This implementation does not capture errors that are localized on the HCA of a compute node, only the errors on the switches are seen.

ibqueryerrors is currently called with --switch, it should run without that flag, or run twice with the --ca flag on the second execution.

[gabrieleiannetti]

Hi,

I would prefer to just run ibqueryerrors one time with --switch and --ca flag enabled.

Looks like a more clear approach to me.

For instance

• errors on STDERR are not duplicated
• timeouts are not doubled retrieved on errors with bad status 110; Connection timed out
• process one input source, this is also beneficial for processing an input file

[guilbaults]

Thanks, merged