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 Note that the archive is no longer being updated. We provide the archive for reference; many of the answers presented here remain technically correct, even if somewhat outdated.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.
Kevin, That sounds like a good test. I wish the results were more definitive. All processes that share the LDM product-queue should share the same memory-segment (i.e., the product-queue should only be in one place in memory). > Steve > > Thanks for the feedback. A little update from yesterday on our end too. > Brad and I setup LDM to run on our second ingest server as well as the > primary Thursday night. We did this for two reasons: > > 1. Eliminate the overhead of qpidd on the same box > 2. Not use edexBridge, just FILE the products to /data_store > > We also created a separate, but equal, NFS partition for this test > /data_store > > Yesterday morning I investigated and saw the latency periods at the same > time as cpsbn1(which was running LDM + qpidd), but the severity was not as > bad. So, yesterday, we rebooted the DVB and I'll be checking on that > today. I'll let you know. Also, in case I wasn't clear before -- what > we're seeing isn't just with NEXRAD3, but also with other products at the > same time. We noticed it first and to the most extreme with that, but it > isn't isolated. > > However, it doesn't appear that the periods of latency are related to qpidd > or edexBridge,although I can't say we've 100% eliminated that. > > We have been focusing a little on our memory usage on these servers. How > many GB of RAM do you all suggest for a server running noaaportIngester + > pqact? I see they all read the ldm.pq into shared memory, and this gives > the impression that 5GB are used just by those processes -- although it > appears they all use the same shared memory segment, so it is really only > 1G -- correct? > > Thanks again in advance, > > Kevin > > -- > *Kevin P Johnson, RHCE™* > Principal Engineer with Honors > AWIPS Lead Systems Engineer > Mission Operations & Services > *Raytheon Company* > > +301-495-2257 (office) > +301-244-8575 (cell) > address@hidden > address@hidden > > > 8401 Colesville Road > Suite 800 > Silver Spring, MD 20910 > www.raytheon.com Regards, Steve Emmerson Ticket Details =================== Ticket ID: KWB-851882 Department: Support LDM Priority: Normal Status: Closed