[Swift-devel] mystery runs on ucanl & ncsa--warning very long email, sorry!

[Mihael Hategan]

On Thu, 2008-07-24 at 17:57 -0500, Michael Andric wrote:
> it's ucanl (not ncsa) that has been completing a few and declining,

Yes. I got that part.

>  e.g.
> 
> Progress:  Initializing:73 Selecting site:6922 Executing:5
[...]
> Progress:  Initializing:73 Selecting site:6916 Executing:5 Finished
> successfully:5 Failed but can retry:1
[...]

Seems time dependent rather than node dependent. Maybe something
happened to it.


> 
> on ncsa, it seems recently to either all-out work or not work.
> yesterday i got 73 jobs 'Finished successfully' on there and then it
> just hung, so i killed it (after letting it hang for a few hours).
> today, i couldn't get it to even start executing (re: the site is
> down).  
> 
> and this 'new site', it's been sitting at: 
> 
> Progress:  Selecting site:6994 Executing:6
> Progress:  Selecting site:6994 Executing:6
> Progress:  Selecting site:6994 Executing:6
> 
> since 2pm this afternoon, still with nothing finished, no errors, no
> indication of what's going on...
> woo grid computing! 

Can you give me more details about "new site"?