"Bodireddy, Bhanuprakash" <bhanuprakash.bodire...@intel.com> writes:
> Hi Aaron, > >>> >>>I've been playing with this a little bit; is it too late to consider >>>tracking >>'threads' >>>instead of 'cores'? I'm not sure what it means for a particular core >>>ID to be 'healthy' - but I know what 'pmd24' not responding means. >> >>That's an interesting input. It's not late and all suggestions are >> most welcome. >>I will try doing this in the next series. > > I reworked and sent out V3 patch series here: > https://mail.openvswitch.org/pipermail/ovs-dev/2017-June/334229.html > In this series. > - Posix shared memory is removed. > - Logic has been changed to track threads as suggested in this > thread. I have used hash maps for this. > >> >>> >>>Additionally, I'd suggest keeping words like 'healthy', and 'unhealthy' >>>out of it. I'd basically just have this keepalive report things on the >>>thread you >>>*know* - last time it poked your status register (and you can also >>>track things like cpu utilization, etc, if you'd like). Then let your >>>higher level thing that reads ceilometer make those "healthy" >>>determinations. After all, sometimes 0% utilization is "healthy," and >>>sometimes it isn't. >> >>This makes sense. Infact It was the case in the beginning where only the core >>status was reported. >> Only recently I added this Datapath status row with the overall >> status. I shall >>remove this and leave it to external monitoring apps to parse the data and >>decide it. > > I have also removed this logic and now only the thread status is > shown. It's now the job of monitoring framework to read the thread > status and determine the health of the compute. Awesome to hear. I'm currently traveling with family (but it has been raining so I figured I'd do a quick check on INBOX), but will review next week. I like the direction it is going. > Bhanuprakash. _______________________________________________ dev mailing list d...@openvswitch.org https://mail.openvswitch.org/mailman/listinfo/ovs-dev
