Please don't reply to lustre-devel. Instead, comment in Bugzilla by using the 
following link:
https://bugzilla.lustre.org/show_bug.cgi?id=11089



(In reply to comment #17)

> The proc is organized as this
> 
> +- nid --> stats...
>     |
>     + exp#1 --> stats...
>     |
>     + exp#2 --> stats...
> 
> So it would avoid both situation you mentioned earlier with a little more 
> memory
> consumed for each NID. We considered it is worthwhile unless concrete numbers 
> on
> its weakness of scaling.
>       

Aha, so you want to destroy the export proc stats when the export disappears,
but _also_ keep a running total of per-nid stats, which lives for the life of
the server.  Is that right?
(I'm happier about that because it doesn't burn memory every time a client
restarts.)

Also, FYI, we're putting proc through a fairly major overhaul to deal with bug
10866, so we should wait for the dust to settle there before trying to land 
this.

_______________________________________________
Lustre-devel mailing list
[email protected]
https://mail.clusterfs.com/mailman/listinfo/lustre-devel

Reply via email to