Re: [PATCH] IB/mad: Ensure fairness in ib_mad_completion_handler

["ira.weiny" <ira.weiny-ral2JQCrhuEAvxtiuMwx3w@public.gmane.org>]

On Mon, Dec 28, 2015 at 06:51:30PM +0200, Eli Cohen wrote:
> On Thu, Dec 10, 2015 at 04:52:30PM -0500, ira.weiny-ral2JQCrhuEAvxtiuMwx3w@public.gmane.org wrote:
> > From: Dean Luick <dean.luick-ral2JQCrhuEAvxtiuMwx3w@public.gmane.org>
> > 
> >  
> > @@ -2555,6 +2567,7 @@ static void ib_mad_completion_handler(struct work_struct *work)
> >  {
> >  	struct ib_mad_port_private *port_priv;
> >  	struct ib_wc wc;
> > +	int count = 0;
> >  
> >  	port_priv = container_of(work, struct ib_mad_port_private, work);
> >  	ib_req_notify_cq(port_priv->cq, IB_CQ_NEXT_COMP);
> 
> I think you shoudld push the call to ib_req_notify_cq outside the
> while loop. You don't need to arm the CQ if you re-queued the work.
> Only when you have drained the CQ should you re-arm.

Will it hurt to rearm?  The way the code stands I think the worse that will
happen is an extra work item scheduled and an ib_poll_cq call.

I'm not quite sure what you mean about moving the ib_req_notify_cq outside of
the while loop.  It seems like to do what you say we would need another work
item which just does ib_poll_cq.  Is that what you meant?

Ira

> 
> > @@ -2574,6 +2587,11 @@ static void ib_mad_completion_handler(struct work_struct *work)
> >  			}
> >  		} else
> >  			mad_error_handler(port_priv, &wc);
> > +
> > +		if (++count > MAD_COMPLETION_PROC_LIMIT) {
> > +			queue_work(port_priv->wq, &port_priv->work);
> > +			break;
> > +		}
> >  	}
> >  }
> >  
> > -- 
> > 1.8.2
> > 
> > --
> > To unsubscribe from this list: send the line "unsubscribe linux-rdma" in
> > the body of a message to majordomo-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
> > More majordomo info at  http://vger.kernel.org/majordomo-info.html
> --
> To unsubscribe from this list: send the line "unsubscribe linux-rdma" in
> the body of a message to majordomo-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
> More majordomo info at  http://vger.kernel.org/majordomo-info.html
--
To unsubscribe from this list: send the line "unsubscribe linux-rdma" in
the body of a message to majordomo-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html