Kevin, The results of profiling pqact(1)'s processing of NEXRAD3 data-products are in. It spends most of it time in very low-level and highly-efficient routines that are called a lot -- just what I'd expect. There wasn't anything that indicated a possible inefficiency. One of our systems is experiencing a similar slowdown in pqact(1)'s processing of NEXRAD3 data. We reconfigured it to write all those data-products to /dev/null yet the NEXRAD3 pqact(1) process still, occasionally, processed the oldest product in the queue. Consequently, we're now beginning to suspect that the problem lies with the number of CPU-s and the load on the system. Can you correlate system-load (using "ldmadmin plotmetrics") with "Processed oldest" log messages on your system? You mentioned that the same system that's running the LDM is also running Cupid, which is used by almost everything in EDEX. Can you move Cupid to another system and, if so, does it help? Regards, Steve Emmerson Ticket Details =================== Ticket ID: KWB-851882 Department: Support LDM Priority: Normal Status: Closed
NOTE: All email exchanges with Unidata User Support are recorded in the Unidata inquiry tracking system and then made publicly available through the web. If you do not want to have your interactions made available in this way, you must let us know in each email you send to us.