[HPADM] hpux / linux nfs issues

From: Jeff Cleverley (jeff_cleverley_at_agilent.com)
Date: 04/14/05

  • Next message: mfearer_at_cox.net: "[HPADM] scsi devices not seen"
    Date: Thu, 14 Apr 2005 15:36:41 -0600
    To: hpux-admin@dutchworks.nl
    
    

    Greetings,

    We've been running hpux 11.00 nfs servers and linux compute boxes (RH7.3
    and 8.0) for a couple of years now with no serious side effects. We
    recently started rolling some hpux user workstations to linux boxes
    running RHEL Enterprise Workstation 3. These boxes have seen numerous
    timeout, slow transfer rates, etc. The hpux nfs servers have 64 nfsd
    processes running and most of the time they account for 45 of the top 50
    processes. The network switches never show the capacity of the servers
    maxed out, so we're leaning towards there being some type of nfs
    protocol differences between the two flavors. We're walking through
    Dave Olker's nfs guide also, but we can't be taking these servers up and
    down for reboots on a regular basis.

    This problem is obviously a big time drain and don't expect anyone to
    try and individually try and trouble shoot it. What I am asking for is
    1 of/or 2 things.

    1. Has anyone had any issues between hpux 11.00 and RHEL relating to
    nfs that you've been able to identify and fix?

    2. Are there any good software tools that we could install on either or
    both types of boxes that would effectively act as a packet sniffer and
    give us an idea of what is running through the network? Unfortunately
    our networking department has been outsourced and the contractors don't
    have access to a packet sniffer :-(

    Thanks,

    Jeff

    --
                 ---> Please post QUESTIONS and SUMMARIES only!! <---
            To subscribe/unsubscribe to this list, contact majordomo@dutchworks.nl
           Name: hpux-admin@dutchworks.nl     Owner: owner-hpux-admin@dutchworks.nl
     
     Archives:  ftp.dutchworks.nl:/pub/digests/hpux-admin       (FTP, browse only)
                http://www.dutchworks.nl/htbin/hpsysadmin   (Web, browse & search)
    

  • Next message: mfearer_at_cox.net: "[HPADM] scsi devices not seen"

    Relevant Pages

    • [HPADM] SUMMARY hpux/linux dns issues
      ... We've been running hpux 11.00 nfs servers and linux compute boxes (RH7.3 ...
      (HP-UX-Admin)
    • Re: Tools for FreeBSD development
      ... Most typically, the setup involves a central development server running -STABLE, with a private network link to a series of crash boxes. ... The development server NFS exports a file system to use as an NFS root and for file sharing, as well as running tftp and dhcp servers. ... Each test system has its own exported root, so I can use individual loader.conf's to tell test systems to boot off NFS, boot off local disks, etc. ...
      (freebsd-hackers)
    • Re: Tools for FreeBSD development
      ... Most typically, the setup involves a central development server running -STABLE, with a private network link to a series of crash boxes. ... The development server NFS exports a file system to use as an NFS root and for file sharing, as well as running tftp and dhcp servers. ... Each test system has its own exported root, so I can use individual loader.conf's to tell test systems to boot off NFS, boot off local disks, etc. ...
      (freebsd-questions)
    • Re: Recommendation please
      ... Problem is they're not my boxes. ... Check the full path of the perl executable with "which perl". ... >>but I cannot get the NFS side set up on the linux boxes. ... only groks NFSv2, and you set your server up with NFSv3 support, "mount ...
      (comp.os.linux.misc)
    • Re: RE:VM pager read error
      ... I'm not using NFS, so there should be no issues ... related to dropped packets. ... > I have also a network with many diskless boxes of 4.11 FreeBSD and every now ... > problem relies on poor hardware (my network has some low-end network cards). ...
      (freebsd-questions)