So we have o(10K) chunks --> ~400 chunks per worker. (but I have the feeling it is czar-related, not worker-related) We are getting two types of errors: - 1) unrecognized execution status - 2) error from provisioning ("Error accessing resource (delayed)") They are sprinkled between successful executions, pretty evenly. J. On 05/07/2015 11:24 PM, Serge Monkewitz wrote: > See /home/smm/in2p3_logs (@NCSA) for a copy of var/log from the in2p3 master run directory. > ######################################################################## 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