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

20031105: RPC cpu usage on new machine

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 Note that the archive is no longer being updated. We provide the archive for reference; many of the answers presented here remain technically correct, even if somewhat outdated.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: 20031105: RPC cpu usage on new machine
  • Date: Wed, 05 Nov 2003 12:04:46 -0700
>From: "Mark J. Laufersweiler" <address@hidden>
>Organization: OU
>Keywords: 200311051813.hA5IDvOb018345 LDM rpc.ldmd FreeBSD

Hi Mark,
>Any idea why rpc.ldm wuold be using between 20-50% of the cpu
>cycles? Internal nic?
>
>Or is this just an id10t error?
>
>  PID USER     PRI  NI  SIZE  RSS SHARE STAT %CPU %MEM   TIME COMMAND
>20660 ldm        9   0  1632 1308   800 S    48.3  0.0  1320m rpc.ldmd
>29010 ldm       15   0  9468 8944   772 R     7.5  0.4   3:25 dcgrib2
>20663 ldm       13   0 15300  11M   640 S     4.5  0.5 143:10 pqact
>    6 root      13   0     0    0     0 SW    2.9  0.0 224:59 kscand
>20662 ldm       11   0   792  732   648 S     2.3  0.0  73:38 pqbinstats
>20664 ldm        9   0   956  948   828 S     1.9  0.0  57:40 rtstats

What we don't know from this listing is:

- is this the lead rpc.ldmd
- is the CPU usage persistent

The other thing that is strange is the TIME field associated with
the listing.  This looks to be 1320 minutes, but that would be better
represented as HHH:MM.

Does the system responsiveness correspond to a process using a lot
of CPU, or is this some sort of a 'top' strangeness?

Tom