NOTICE: This version of the NSF Unidata web site (archive.unidata.ucar.edu) is no longer being updated.
Current content can be found at unidata.ucar.edu.
To learn about what's going on, see About the Archive Site.
NOTICE: This version of the NSF Unidata web site (archive.unidata.ucar.edu) is no longer being updated.
Current content can be found at unidata.ucar.edu.
To learn about what's going on, see About the Archive Site.
Kind-of sounds like I/O contention... what's your disk configuration? Do you run RAID? If so, what kind? What do you observe if you monitor "iostat -x 5" while the problem is occuring?
Art, yes RAID-1
Do the relevant pqact(1) configuration-file entries use the "-flush" or "-close" option?
Steve, yes..except EXEC entries, are they needed there?
How are you dividing out the write tasks with LDM? Each pqact only has 32 pipes, so if you are attempting to fit too many products through those available pipes, there will be lags.Install system monitoring tools like 'dstat' and 'sysstat', monitor the disk IO rates before you do something drastic like reformatting or changing filesystems.
http://ldm01.michiganwxsystem.net/munin/localhost/localhost/index.html
When I have seen problems before, it is almost always a LDM configuration issue and not having enough pqacts running.daryl
hmm.. maybe I should look that over thanks to everyone .. gave me some food for thought.. -Jeff
ldm-users archives: