[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

[LDM #KWB-851882]: pqact issues reading pq file

This archive contains answers to questions sent to Unidata support through mid-2025. Note that the archive is no longer being updated. We provide the archive for reference; many of the answers presented here remain technically correct, even if somewhat outdated. For the most up-to-date information on the use of NSF Unidata software and data services, please consult the Software Documentation first.

  • Subject: [LDM #KWB-851882]: pqact issues reading pq file
  • Date: Fri, 16 Aug 2013 15:35:45 -0600
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