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

[LDM #DSW-144649]: LDM 6.7.0.3 performance improvement with dcgrib2---just wondering

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 Note that the archive is no longer being updated. We provide the archive for reference; many of the answers presented here remain technically correct, even if somewhat outdated.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 #DSW-144649]: LDM 6.7.0.3 performance improvement with dcgrib2---just wondering
  • Date: Mon, 08 Sep 2008 16:38:53 -0600
Tom & Gilbert,

> Hmm...  It seems that the effect may for anything started by an EXEC
> in ldmd.conf (i.e., queue scanners), and this includes rtstats.

The only thing I've been able to think of is that, since dcgrib2(1)
(which is a CPU hog) is no longer being interrupted by SIGCONTs, it
continues on its merry way until the O/S decides to give some CPU
time to another process (such as rtstats(1)).  The result is much
better performance of dcgrib2(1) at the (very slight) expense of
processes like rtstats(1).

Or, it could be a brain tumor!  :-)

Regards,
Steve Emmerson

Ticket Details
===================
Ticket ID: DSW-144649
Department: Support LDM
Priority: Normal
Status: Closed