Re: [SLE] 9.1 is sloooooowwww

From: Sid Boyce (sboyce_at_blueyonder.co.uk)
Date: 06/29/04

  • Next message: James Golden: "[SLE] OpenOffice troubles"
    Date: Tue, 29 Jun 2004 16:16:09 +0100
    To: suse-linux-e@suse.com
    
    

    cincaipatron@gmx.net wrote:

    >>On Tue, 29 Jun 2004 03:40 pm, Fred Miller wrote:
    >>Good point, could the people who are getting good results
    >> post some more details?
    >>
    >>Processor, RAM, chipset, and output of lsmod
    >>
    >>
    >
    >Want to add one more thing: the IO scheduler. I remember
    >vaguely that on low-end machines (< P4), the CFQ IO scheduler
    >causes KDE applications to startup slower then the default
    >(anticipatory) IO scheduler.
    >
    >
    >
    >
    There was one earlier kernel 2.6.x-mm? from kernel.org that was very
    slow, can't remember which, there was frantic disk thrashing and top
    showed very high I/O wait. I reported it to the kernel mailing list and
    Andrew Morton had it fixed in the next update.
    See if there is anything like excessive memory or CPU usage in top, also
    I/O wait. I/O Wait doesn't show up now.

    Tasks: 182 total, 1 running, 179 sleeping, 0 stopped, 2 zombie
    Cpu(s): 9.1% us, 4.5% sy, 0.0% ni, 85.8% id, 0.0% wa, 0.6% hi, 0.0% si
    Mem: 514692k total, 510424k used, 4268k free, 53744k buffers
    Swap: 5373724k total, 268772k used, 5104952k free, 155232k cached

      PID USER PR NI VIRT RES SHR S %CPU %MEM TIME+ COMMAND
    14543 root 15 0 183m 15m 138m S 7.5 3.2 189:44.29 X
    14714 lancelot 15 0 31504 6168 25m S 1.9 1.2 0:20.47 kdeinit
    15201 root 15 0 51476 6380 37m S 1.6 1.2 30:49.66 epiphany-bin
     4732 root 17 0 1904 1004 1564 R 1.3 0.2 0:00.57 top
    14716 lancelot 16 0 59636 8816 39m S 0.6 1.7 10:02.60 kdeinit
    14705 lancelot 15 0 26760 2784 22m S 0.3 0.5 4:37.08 kdeinit
    14815 lancelot 16 0 32324 2328 23m S 0.3 0.5 0:20.31 suseplugger
    14837 lancelot 15 0 25524 10m 17m S 0.3 2.1 15:18.68 skype
    14982 root 15 0 70872 39m 32m S 0.3 7.9 6:23.53 thunderbird-bin
    15216 root 15 0 51476 6380 37m S 0.3 1.2 1:01.71 epiphany-bin
        1 root 16 0 588 72 444 S 0.0 0.0 0:04.25 init
        2 root 34 19 0 0 0 S 0.0 0.0 0:00.35 ksoftirqd/0
        3 root 5 -10 0 0 0 S 0.0 0.0 0:04.38 events/0
        4 root 5 -10 0 0 0 S 0.0 0.0 0:00.06 khelper
        5 root 5 -10 0 0 0 S 0.0 0.0 0:00.00 kacpid
       45 root 5 -10 0 0 0 S 0.0 0.0 1:19.82 kblockd/0
    <SNIP>

    Regards
    Sid.

    -- 
    Sid Boyce .... Hamradio G3VBV and keen Flyer
    ===== LINUX ONLY USED HERE =====
    -- 
    Check the headers for your unsubscription address
    For additional commands send e-mail to suse-linux-e-help@suse.com
    Also check the archives at http://lists.suse.com
    Please read the FAQs: suse-linux-e-faq@suse.com
    

  • Next message: James Golden: "[SLE] OpenOffice troubles"

    Relevant Pages

    • Re: [PATCH] cgroup: limit block I/O bandwidth
      ... solve the priority inversion problem you were seeing earlier. ... Thanks Naveen, I can test you scheduler if you want, but the priority ... inversion problem (or better we should call it a "bandwidth limiting" ... to the I/O scheduler. ...
      (Linux-Kernel)
    • Re: [RFC PATCH] block: Fix bio merge induced high I/O latency
      ... to create a fio job file. ... disconnect between 'ls' and the io scheduler at the bottom... ... system if doing heavy I/O. ... The behavior of an incoming ssh connexion after clearing the cache is ...
      (Linux-Kernel)
    • Re: pushing the envelope with sockets
      ... BeginReceiveFrom immediately in order to have an I/O ready to receive as ... but I find that my CPU usage will ... receiving into a large buffer, but less often -- while still not ...
      (microsoft.public.dotnet.languages.csharp)
    • Re: [PATCH] cgroup: limit block I/O bandwidth
      ... solve the priority inversion problem you were seeing earlier. ... Thanks Naveen, I can test you scheduler if you want, but the priority ... inversion problem (or better we should call it a "bandwidth limiting" ... to the I/O scheduler. ...
      (Linux-Kernel)
    • Re: [RFC PATCH] block: Fix bio merge induced high I/O latency
      ... to create a fio job file. ... disconnect between 'ls' and the io scheduler at the bottom... ... system if doing heavy I/O. ... The behavior of an incoming ssh connexion after clearing the cache is ...
      (Linux-Kernel)