[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
- To: sebenste@xxxxxxxxxxxxxxxxxxxxx
- Subject: [LDM #DSW-144649]: LDM 6.7.0.3 performance improvement with dcgrib2---just wondering
- From: "Unidata LDM Support" <support-ldm@xxxxxxxxxxxxxxxx>
- Date: Mon, 08 Sep 2008 16:38:53 -0600
- Delivered-to: support-ldm@unidata.ucar.edu by laraine.unidata.ucar.edu (Postfix) with ESMTP id 34AE3CB186; Mon, 8 Sep 2008 16:38:54 -0600 (MDT) id 0B0EFD4FBA; Mon, 8 Sep 2008 16:38:53 -0600 (MDT)
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
