Joe Handzik

@cathay4t Thanks for taking a look at Blaine's code. I agree that we should be able to get most of this information via standard methods as well as via hpssacli,...

I think that's fine, Gris. I saw some similar trickery in Ceph's spdk usage. Joe On May 2, 2016, at 7:21 AM, Gris Ge wrote: @joehandzikhttps://github.com/joehandzik @taslesonhttps://github.com/tasleson Currently, we are...

I guess we have three options (as far as I see): 1. Stick with the VPD83 string ID for all NVMe devices (I'm assuming they still expose it even with...

@cathay4t Ok, gotcha. It does sound complex and awfully in-flux. We'll see what @tasleson thinks, but for now I'm with you and leaning towards keeping NVMe unsupported. It could be...

@cathay4t Hey, sorry for the delay, back online after the holiday break. I'll take a look and see if I find anything. I assume all this code will be brought...

@cathay4t An initial pass through the source went fine, I think it looks really good actually! I may have more detailed feedback when we see how it fits in with...

I think that sounds like a reasonable plan. I've been tied up in another project lately, but let me see if I can carve out some time to get this...

@Zubrania Do you have any information about your cluster configuration? Is this happening on all nodes, or just some of them? Also, what version of Lustre are you using? Older...

There aren't any public dashboards at the moment, no. We're still trying to decide what our strategy is with that particular distribution option (we have some dashboards internally, but they...

Thanks for taking a look, @mjtrangoni! At a glance, it looks like we support most or all of those metrics, so t should be doable to emulate using our Prometheus...