home *** CD-ROM | disk | FTP | other *** search
- Path: sparky!uunet!usc!sdd.hp.com!swrinde!elroy.jpl.nasa.gov!decwrl!csus.edu!nic.csu.net!cerritos.edu!orion.oac.uci.edu!draco.acs.uci.edu!iglesias
- From: iglesias@draco.acs.uci.edu (Mike Iglesias)
- Newsgroups: comp.sys.sun.admin
- Subject: Re: 690MP "pausing"
- Message-ID: <2A9FAAA9.2472@orion.oac.uci.edu>
- Date: 29 Aug 92 16:49:45 GMT
- References: <1992Aug18.222325.1509@puma.ATL.GE.COM> <1992Aug21.002326.27505@cybernet.cse.fau.edu>
- Organization: University of California, Irvine
- Lines: 22
- Nntp-Posting-Host: draco.acs.uci.edu
-
- In article <1992Aug21.002326.27505@cybernet.cse.fau.edu> steve@cse.fau.edu (Steve Smith) writes:
- >I have noticed that on our 690MP (4.1.2) the load seems to climb
- >intermittantly up to 8 or 10 -- sometimes causing pauses like Bob mentioned
- >and other times, I don't sense any delay in what I am doing. What is
- >going on here? I do a "ps axu" and there seem to be no cpu-hog type
- >processes... really nothing to explain it. The system serves as an NIS
- >server and NFS server but the files it serves via NFS are rarely used...
-
- Use ps to check for processes in D (disk wait) state. Our 690MP is used
- as a general timesharing system and as our campus news server. It's
- performance at times is pathetic, and when the load average is high
- there are almost as many nntpd processes in D state as the load average
- number.
-
- See the message I posted a few minutes ago for more info on our 690MP
- problems.
-
-
- Mike Iglesias Internet: iglesias@draco.acs.uci.edu
- University of California, Irvine BITNET: iglesias@uci
- Office of Academic Computing uucp: ...!ucbvax!ucivax!iglesias
- Distributed Computing Support phone: (714) 856-6926
-