[ewg] RE: sean_cm_limit_mra_timeout.patch

Hal Rosenstock hrosenstock at xsigo.com
Mon Dec 10 12:03:21 PST 2007


On Mon, 2007-12-10 at 11:20 -0800, Sean Hefty wrote:
> >The patch has:
> >+       if (cm_id_priv->timeout_ms > cm_convert_to_ms(max_timeout)) {
> >+               printk(KERN_WARNING PFX "req timeout_ms %d > %d, decreasing\n",
> >+                      cm_id_priv->timeout_ms, cm_convert_to_ms(max_timeout));
> >+               cm_id_priv->timeout_ms = cm_convert_to_ms(max_timeout);
> >+       }
> >
> >whereas cm.c has:
> >        cm_id_priv->timeout_ms = cm_convert_to_ms(
> >                                    param->primary_path->packet_life_time) * 2
> >+
> >                                 cm_convert_to_ms(
> >                                    param->remote_cm_response_timeout);
> >
> >This forces max_timeout to be set one higher than really needed. Should
> >the comparison in the patch also account for the packet life time ?
> 
> The intent is that the max_timeout is the absolute max, and does not adjust
> upward based on packet lifetime.  Otherwise there's no way to recover from a
> packet lifetime that was incorrectly set to an extremely large value.

Doesn't PLT come from the SM ? Was a large PLT the issue here (or ever
observed) ?

These questions should be moot (other than the fact this patch is in
OFED 1.3 and 1.2.5)...

-- Hal

> 
> - Sean



More information about the ewg mailing list