On Thu, Feb 23, 2023 at 04:36:25PM +0100, Ilya Maximets wrote:
> On 2/23/23 16:33, Simon Horman wrote:
> > On Thu, Feb 23, 2023 at 04:09:10PM +0100, Ilya Maximets wrote:
> >> On 2/23/23 15:19, Ilya Maximets wrote:
> >>> On 2/23/23 14:02, Simon Horman wrote:
> > 
> > ...
> > 
> >>>> +    AT_CHECK([
> >>>> +        if ! tc qdisc add dev veth0 handle ffff: ingress; then
> >>>> +            ip link del veth0
> >>>
> >>> Instead of deleting in every branch, we might add on_exit call somewhere
> >>> at the beginning of this function.  The port will stick around till the
> >>> end of the test, but I'm not sure if that's a problem if the name is
> >>> special enough.  Or we may keep one extra del at the very end.
> >>>
> >>> With on_exit, can probably be transformed into something like (untested):
> >>>
> >>>   AT_CHECK([tc qdisc add dev veth0 handle ffff: ingress || exit 77])
> >>
> >> Just AT_SKIP_IF([! tc qdisc add dev veth0 handle ffff: ingress]) should
> >> work, I guess.
> > 
> > The reason I used AT_CHECK rather than AT_SKIP_IF was to
> > capture stderr/stdout. Which serves two purposes:
> > 
> > 1. It avoids mess on the console - although that could also
> >    be avoided with something like >& /dev/null
> > 2. The capture output is useful in debugging
> >    e.g. when developing this script.
> > 
> > I can move to AT_SKIP_IF if you have a strong preference.
> > But AT_CHECK did seem a bit better to me - except the '77' bit.
> 
> Makes sense.  AT_CHECK is fine then.

Thanks, I'll prepare v2 with the other changes you suggested.
_______________________________________________
dev mailing list
[email protected]
https://mail.openvswitch.org/mailman/listinfo/ovs-dev

Reply via email to