Hello,

Rachid sends us a list of questions below.

* Data loading :

   - Could  you  define  how   data  will  be  generated  and
     distributed on workers ?

   - Could  you begin  data  load testing  on  our 4  current
     machines at CC ?

   - How far are Qserv installation and data loading
     independent ?

* Production planning:

   - What happens if a worker crash ? What actions are needed
     ( error recovery ) ? How to exclude one worker node from
     Qserv ?

   - What exactly do you need to be monitored on workers ?

   - We propose to  begin installation on 4, then  10, 50 and
     finally 300 nodes. What  are the validation steps ? What
     will be the queries used ?


It would be good to have a wiki page for all these so that
we could refer to it.

We could discuss about this during our tomorrow meeting.

--

########################################################################
Use REPLY-ALL to reply to list

To unsubscribe from the QSERV-L list, click the following link:
https://listserv.slac.stanford.edu/cgi-bin/wa?SUBED1=QSERV-L&A=1