newbie - just upgraded to RH9 from RH7.3 - any heads ups? - please help - Redhat

This is a discussion on newbie - just upgraded to RH9 from RH7.3 - any heads ups? - please help - Redhat ; Getting back to Linux after a hiatus ... I just upgraded to RH9 from RH7.3 for a better version of GCC. The upgrade "appears" to be successful. Any heads ups WRT RH9? What's the best version of GCC to use ...

+ Reply to Thread
Page 1 of 2 1 2 LastLast
Results 1 to 20 of 25

Thread: newbie - just upgraded to RH9 from RH7.3 - any heads ups? - please help

  1. newbie - just upgraded to RH9 from RH7.3 - any heads ups? - please help


    Getting back to Linux after a hiatus ...

    I just upgraded to RH9 from RH7.3 for a better version of GCC.
    The upgrade "appears" to be successful. Any heads ups WRT RH9?

    What's the best version of GCC to use with RH9?



  2. Re: newbie - just upgraded to RH9 from RH7.3 - any heads ups? - please help

    Roger wrote:
    > I just upgraded to RH9 from RH7.3 for a better version of GCC.
    > The upgrade "appears" to be successful. Any heads ups WRT RH9?


    Yes, it's obsolete. Get Fedora Core 2 or Red Hat Enterprise Linux
    instead.

    --
    Markku Kolkka
    markku.kolkka@iki.fi

  3. Re: newbie - just upgraded to RH9 from RH7.3 - any heads ups? - please help


    Oh-no, not RHEL. Can't afford anything too pricey.
    Is Red Hat trying to charge outrageously for
    software that is largely contributed? If so, BOOOO!!!



    "Markku Kolkka" wrote in message news:cje8tb$g84$2@phys-news1.kolumbus.fi...
    > Roger wrote:
    > > I just upgraded to RH9 from RH7.3 for a better version of GCC.
    > > The upgrade "appears" to be successful. Any heads ups WRT RH9?

    >
    > Yes, it's obsolete. Get Fedora Core 2 or Red Hat Enterprise Linux
    > instead.
    >
    > --
    > Markku Kolkka
    > markku.kolkka@iki.fi




  4. Re: newbie - just upgraded to RH9 from RH7.3 - any heads ups? - pleasehelp

    Roger top-posted:
    > Oh-no, not RHEL. Can't afford anything too pricey.
    > Is Red Hat trying to charge outrageously for
    > software that is largely contributed? If so, BOOOO!!!
    >

    No, Red Hat are not trying to charge outrageously for software that is
    largely contributed. What they charge for is support and maintenance. Some
    people find their support and maintenance to be worth what they charge.
    The rest can download the free source from Red Hat's web site and build it
    themselves.

    --
    .~. Jean-David Beyer Registered Linux User 85642.
    /V\ Registered Machine 241939.
    /( )\ Shrewsbury, New Jersey http://counter.li.org
    ^^-^^ 12:20:00 up 6 days, 23:24, 3 users, load average: 4.18, 4.27, 4.25


  5. Re: newbie - just upgraded to RH9 from RH7.3 - any heads ups? - please help

    On Wed, 29 Sep 2004 12:24:43 -0400, Jean-David Beyer wrote:

    > Roger top-posted:
    >> Oh-no, not RHEL. Can't afford anything too pricey. Is Red Hat trying
    >> to charge outrageously for software that is largely contributed? If
    >> so, BOOOO!!!
    >>

    > No, Red Hat are not trying to charge outrageously for software that is
    > largely contributed. What they charge for is support and maintenance.
    > Some people find their support and maintenance to be worth what they
    > charge. The rest can download the free source from Red Hat's web site
    > and build it themselves.


    Not to mention RedHat is one of the largest contributors to Linux and one
    of the companies chiefly responsible for its success. They should be
    allowed to keep themselves in business.


    --
    i.m.
    The USA Patriot Act is the most unpatriotic act in American history.


  6. Re: newbie - just upgraded to RH9 from RH7.3 - any heads ups? - pleasehelp

    Roger wrote:
    >
    > "Markku Kolkka" wrote in message news:cje8tb$g84$2@phys-news1.kolumbus.fi...
    >
    >>Roger wrote:
    >>
    >>>I just upgraded to RH9 from RH7.3 for a better version of GCC.
    >>>The upgrade "appears" to be successful. Any heads ups WRT RH9?

    >>
    >>Yes, it's obsolete. Get Fedora Core 2 or Red Hat Enterprise Linux
    >>instead.
    >>

    >
    > Oh-no, not RHEL. Can't afford anything too pricey.
    > Is Red Hat trying to charge outrageously for
    > software that is largely contributed? If so, BOOOO!!!
    >


    They're not charging for the software, they're charging for support.
    You can build it yourself, but there are also distributions that have
    done that already, such as White Box Enterprise Linux (which is what I
    run - http://www.whiteboxlinux.org). That's what I'm currently running.

    If you're interested, right now they're working on rebuilding all the
    SRPMs from RHEL 3.0 Update 3 - you can download "Respin 1" then use yum
    to update to "Respin 2", or you can hang out for a couple of weeks until
    the .iso files for "Respin 2" are done.


    --
    ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ ~~~~~~~~~~~~~
    ~ / \ / ~ Live from Montgomery, AL! ~
    ~ / \/ o ~ ~
    ~ / /\ - | ~ LXi0007@Netscape.net ~
    ~ _____ / \ | ~ http://www.knology.net/~mopsmom/daniel ~
    ~ ~ ~ ~ ~ ~ ~ ~ ~ ~ ~ ~ ~ ~ ~ ~ ~ ~ ~ ~ ~ ~ ~ ~ ~ ~ ~ ~ ~ ~ ~ ~
    ~ I do not read e-mail at the above address ~
    ~ Please see website if you wish to contact me privately ~
    ~ ~ ~ ~ ~ ~ ~ ~ ~ ~ ~ ~ ~ ~ ~ ~ ~ ~ ~ ~ ~ ~ ~ ~ ~ ~ ~ ~ ~ ~ ~ ~
    ~ GEEKCODE 3.12 GCS/IT d s-:+ a C++ L++ E--- W++ N++ o? K- w$ ~
    ~ !O M-- V PS+ PE++ Y? !PGP t+ 5? X+ R* tv b+ DI++ D+ G- e ~
    ~ h---- r+++ z++++ ~
    ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ ~~~~~~~~~~~~~


  7. Re: newbie - just upgraded to RH9 from RH7.3 - any heads ups? - please help


    Installed Fedora Core 2 earlier today. And, it does not
    leave a good impression. The install was successful.
    But, that's about it. It fails to boot. On boot,
    it had problems with the following:

    - my printer (HP LaserJet 5)
    - initializing USB (saying something about USB controller and dependencies)
    - hangs when starting "system logger"
    - fails to go into graphical login mode

    And, that's only what I remember. So, no thanks to Fedora Core 2.

    RH9 gave no problems whatsoever. I don't care if
    it's obsolete so long as it serves my needs.



    "Markku Kolkka" wrote in message news:cje8tb$g84$2@phys-news1.kolumbus.fi...
    > Roger wrote:
    > > I just upgraded to RH9 from RH7.3 for a better version of GCC.
    > > The upgrade "appears" to be successful. Any heads ups WRT RH9?

    >
    > Yes, it's obsolete. Get Fedora Core 2 or Red Hat Enterprise Linux
    > instead.
    >
    > --
    > Markku Kolkka
    > markku.kolkka@iki.fi




  8. Re: newbie - just upgraded to RH9 from RH7.3 - any heads ups? - please help


    If they're really only charging for support and maintenance,
    why have different versions of the software? Why can't
    everyone have access to just the software portion of RHEL?


    "Jean-David Beyer" wrote in message news:10lloec9tk0bff2@corp.supernews.com...
    > Roger top-posted:
    > > Oh-no, not RHEL. Can't afford anything too pricey.
    > > Is Red Hat trying to charge outrageously for
    > > software that is largely contributed? If so, BOOOO!!!
    > >

    > No, Red Hat are not trying to charge outrageously for software that is
    > largely contributed. What they charge for is support and maintenance. Some
    > people find their support and maintenance to be worth what they charge.
    > The rest can download the free source from Red Hat's web site and build it
    > themselves.
    >
    > --
    > .~. Jean-David Beyer Registered Linux User 85642.
    > /V\ Registered Machine 241939.
    > /( )\ Shrewsbury, New Jersey http://counter.li.org
    > ^^-^^ 12:20:00 up 6 days, 23:24, 3 users, load average: 4.18, 4.27, 4.25
    >




  9. Re: newbie - just upgraded to RH9 from RH7.3 - any heads ups? - please help


    "Roger" wrote in message
    news:XQH6d.21596$QJ3.5231@newssvr21.news.prodigy.c om...
    >
    > If they're really only charging for support and maintenance,
    > why have different versions of the software? Why can't
    > everyone have access to just the software portion of RHEL?
    >


    I think you can. Just download the source from ftp.redhat.com and you can
    compile your own RHEL. However, the support that RH sells is packaging it
    with a manual, CDs, painless install procedure and hotline to call when you
    need help.

    Fedora on the other hand is a permanent BETA for RHEL, and as the web site
    states there are new releases several times a year. IMHO I think it's great.
    I get something new to play with every couple of months and when the bugs
    are worked out corporate america gets a rock solid Linux - with support.

    >
    > "Jean-David Beyer" wrote in message
    > news:10lloec9tk0bff2@corp.supernews.com...
    >> Roger top-posted:
    >> > Oh-no, not RHEL. Can't afford anything too pricey.
    >> > Is Red Hat trying to charge outrageously for
    >> > software that is largely contributed? If so, BOOOO!!!
    >> >

    >> No, Red Hat are not trying to charge outrageously for software that is
    >> largely contributed. What they charge for is support and maintenance.
    >> Some
    >> people find their support and maintenance to be worth what they charge.
    >> The rest can download the free source from Red Hat's web site and build
    >> it
    >> themselves.
    >>
    >> --
    >> .~. Jean-David Beyer Registered Linux User 85642.
    >> /V\ Registered Machine 241939.
    >> /( )\ Shrewsbury, New Jersey http://counter.li.org
    >> ^^-^^ 12:20:00 up 6 days, 23:24, 3 users, load average: 4.18, 4.27,
    >> 4.25
    >>

    >
    >




  10. Re: newbie - just upgraded to RH9 from RH7.3 - any heads ups? - please help

    Roger wrote:

    >
    > Installed Fedora Core 2 earlier today. And, it does not
    > leave a good impression. The install was successful.
    > But, that's about it. It fails to boot. On boot,
    > it had problems with the following:


    Which is it: "it fails to boot" or "on boot ... "? They cannot both be true.

    >
    > - my printer (HP LaserJet 5)
    > - initializing USB (saying something about USB controller and
    > dependencies) - hangs when starting "system logger"
    > - fails to go into graphical login mode
    >
    > And, that's only what I remember. So, no thanks to Fedora Core 2.


    You don't say what resources your computer has. The FC2 documentation
    clearly specifies system requirements. But you don't.

    --
    Paul Lutus
    http://www.arachnoid.com


  11. Re: newbie - just upgraded to RH9 from RH7.3 - any heads ups? - please help


    "Roger" wrote in message
    news:BIH6d.21593$QJ3.16167@newssvr21.news.prodigy. com...
    >
    > Installed Fedora Core 2 earlier today. And, it does not
    > leave a good impression. The install was successful.
    > But, that's about it. It fails to boot. On boot,
    > it had problems with the following:
    >
    > - my printer (HP LaserJet 5)
    > - initializing USB (saying something about USB controller and
    > dependencies)
    > - hangs when starting "system logger"
    > - fails to go into graphical login mode
    >
    > And, that's only what I remember. So, no thanks to Fedora Core 2.
    >
    > RH9 gave no problems whatsoever. I don't care if
    > it's obsolete so long as it serves my needs.
    >


    I used FC1 for my servers. I have fewer problems if I stay back from the
    leading edge. FC1 has been around for a while longer than FC2 so has more
    bugs worked out. It also has an update source. There are no updates for
    security problems with RH9. Not that Linux has any gaping holes, but if
    others rely on it, it's better safe then sorry. It's also easier to apply a
    patch rather then update to a new version if you do find a hole.



  12. Re: newbie - just upgraded to RH9 from RH7.3 - any heads ups? - please help


    Replace "on boot" with "when trying to boot".

    It's the same hardware that both RH7.3 and RH9 works fine on.

    Motherboard: Asus A7V133 rev 1.05.
    CPU: AMD Athlon XP 1600+
    RAM: 512MB
    NIC: 3Com 3C905C-TXM
    Audio: Creative SoundBlaster Live! 5.1
    CD-ROM Burner: LiteOn 52x24x52x
    DVD Drive: Pioneer DVD-116
    Display Adapter: Leadtek WinFast GeForce256 DDR 32MB AGP
    Monitor: ViewSonic P815-4
    Printer: HP LaserJet 5

    Luckily, I installed FC2 on a spare HDD and didn't clobber RH9 with FC2.



    "Paul Lutus" wrote in message news:10lmnted46rtpf5@corp.supernews.com...
    > Roger wrote:
    >
    > >
    > > Installed Fedora Core 2 earlier today. And, it does not
    > > leave a good impression. The install was successful.
    > > But, that's about it. It fails to boot. On boot,
    > > it had problems with the following:

    >
    > Which is it: "it fails to boot" or "on boot ... "? They cannot both be true.
    >
    > >
    > > - my printer (HP LaserJet 5)
    > > - initializing USB (saying something about USB controller and
    > > dependencies) - hangs when starting "system logger"
    > > - fails to go into graphical login mode
    > >
    > > And, that's only what I remember. So, no thanks to Fedora Core 2.

    >
    > You don't say what resources your computer has. The FC2 documentation
    > clearly specifies system requirements. But you don't.
    >
    > --
    > Paul Lutus
    > http://www.arachnoid.com
    >




  13. Re: newbie - just upgraded to RH9 from RH7.3 - any heads ups? - pleasehelp

    m.marien wrote:
    > "Roger" wrote in message
    > news:XQH6d.21596$QJ3.5231@newssvr21.news.prodigy.c om...
    >
    >> If they're really only charging for support and maintenance, why have
    >> different versions of the software? Why can't everyone have access
    >> to just the software portion of RHEL?

    >
    > I think you can. Just download the source from ftp.redhat.com and you
    > can compile your own RHEL. However, the support that RH sells is
    > packaging it with a manual, CDs, painless install procedure and hotline
    > to call when you need help.


    Not only that, but included in the price is a Red Hat Network subscription
    and up2date program that gets security and bug-fix updates as fast as Red
    Hat can prepare them. I find that this, alone, is sufficient reason to go
    with RHEL 3. Someone must pay Red Hat to get those updates put in and tested.
    >
    > Fedora on the other hand is a permanent BETA for RHEL, and as the web
    > site states there are new releases several times a year. IMHO I think
    > it's great. I get something new to play with every couple of months and
    > when the bugs are worked out corporate america gets a rock solid Linux
    > - with support.
    >

    Right, and I, who do not want "something new to play with every couple of
    months" but something that just stays up and runs.

    My uptime below is so low because I deleted and added a partition to a
    hard drive, and I have not figured out the right way to get the partition
    table updated so I could format and use the new partition other than by
    rebooting. It looks like fdisk does this, but it does not. My old machine,
    running RHL 7.3 was up over 180 days and would still be up, but a power
    failure of 2.5 hours was longer than the UPSs on these machines could
    handle, so they did controlled shutdowns. This one has 68 minutes reserve,
    but is programmed to power down after an hour. I keep an eye on that, and
    will reduce it as the battery capacity diminishes with age.


    --
    .~. Jean-David Beyer Registered Linux User 85642.
    /V\ Registered Machine 241939.
    /( )\ Shrewsbury, New Jersey http://counter.li.org
    ^^-^^ 22:50:00 up 7 days, 9:54, 3 users, load average: 4.60, 4.35, 4.29


  14. Re: newbie - just upgraded to RH9 from RH7.3 - any heads ups? - please help


    "Jean-David Beyer" wrote in message
    news:10lmtiak15ph1c3@corp.supernews.com...
    >>


    [snip]

    > Right, and I, who do not want "something new to play with every couple of
    > months" but something that just stays up and runs.
    >
    > My uptime below is so low because I deleted and added a partition to a
    > hard drive, and I have not figured out the right way to get the partition
    > table updated so I could format and use the new partition other than by
    > rebooting. It looks like fdisk does this, but it does not. My old machine,
    > running RHL 7.3 was up over 180 days and would still be up, but a power
    > failure of 2.5 hours was longer than the UPSs on these machines could
    > handle, so they did controlled shutdowns. This one has 68 minutes reserve,
    > but is programmed to power down after an hour. I keep an eye on that, and
    > will reduce it as the battery capacity diminishes with age.
    >
    >
    > --
    > .~. Jean-David Beyer Registered Linux User 85642.
    > /V\ Registered Machine 241939.
    > /( )\ Shrewsbury, New Jersey http://counter.li.org
    > ^^-^^ 22:50:00 up 7 days, 9:54, 3 users, load average: 4.60, 4.35, 4.29
    >


    That's a fairly heavy load average. My K6II 400 system went way over 25 when
    I first upgraded but when I added memory it went back down to zero. If I
    understand it correctly, you have 4 threads waiting for processor time at
    any given time ? Are you running some SETI's or do you just type really fast
    ?

    21:45:43 up 54 days, 12:53, 1 user, load average: 0.04, 0.01, 0.00

    This is FC1 on a file server, but everybody has gone home. Last shutdown was
    to add the memory I think.



  15. Re: newbie - just upgraded to RH9 from RH7.3 - any heads ups? - pleasehelp

    m.marien wrote:
    > "Jean-David Beyer" wrote in message


    >> .~. Jean-David Beyer Registered Linux User 85642.
    >> /V\ Registered Machine 241939.
    >> /( )\ Shrewsbury, New Jersey http://counter.li.org
    >> ^^-^^ 22:50:00 up 7 days, 9:54, 3 users, load average: 4.60, 4.35, 4.29
    >>

    >
    >
    > That's a fairly heavy load average. My K6II 400 system went way over 25 when
    > I first upgraded but when I added memory it went back down to zero. If I
    > understand it correctly, you have 4 threads waiting for processor time at
    > any given time ? Are you running some SETI's or do you just type really fast
    > ?


    I type really fast! ;-)

    Actually, I am running BOINC that has two setiathome and two
    climateprediction running. Luckily at nice level 19. When it really gets
    hairy is when I populate an IBM DB2 UDB V8.1.7 database which runs over a
    dozen server processes at once. Then the load average can exceed 10. But
    the BOINC stuff tends to get out of the way at nice 19.

    The BOINC stuff screws up the processor caches, though, and makes the
    database slow down a lot, even though, nominally, it gets all the
    processor time it wants. But it does not get cache hit ratio it needs, so
    the disk IO goes at about half speed or a little less. With BOINC turned
    off, I get about 12 Megabytes/second to the hard drives, but it drops to
    around 4 when BOINC is running those applications, even though they are at
    nice 19.
    >
    > 21:45:43 up 54 days, 12:53, 1 user, load average: 0.04, 0.01, 0.00
    >
    > This is FC1 on a file server, but everybody has gone home. Last shutdown was
    > to add the memory I think.
    >
    >



    --
    .~. Jean-David Beyer Registered Linux User 85642.
    /V\ Registered Machine 241939.
    /( )\ Shrewsbury, New Jersey http://counter.li.org
    ^^-^^ 09:35:00 up 7 days, 20:39, 4 users, load average: 4.30, 4.23, 4.24


  16. Re: newbie - just upgraded to RH9 from RH7.3 - any heads ups? - please help


    "Jean-David Beyer" wrote in message
    news:10lo3c5gusobj9d@corp.supernews.com...
    > m.marien wrote:
    >> "Jean-David Beyer" wrote in message

    >
    >>> .~. Jean-David Beyer Registered Linux User 85642.
    >>> /V\ Registered Machine 241939.
    >>> /( )\ Shrewsbury, New Jersey http://counter.li.org
    >>> ^^-^^ 22:50:00 up 7 days, 9:54, 3 users, load average: 4.60, 4.35, 4.29
    >>>

    >>
    >>
    >> That's a fairly heavy load average. My K6II 400 system went way over 25
    >> when I first upgraded but when I added memory it went back down to zero.
    >> If I understand it correctly, you have 4 threads waiting for processor
    >> time at any given time ? Are you running some SETI's or do you just type
    >> really fast ?

    >
    > I type really fast! ;-)
    >
    > Actually, I am running BOINC that has two setiathome and two
    > climateprediction running. Luckily at nice level 19. When it really gets
    > hairy is when I populate an IBM DB2 UDB V8.1.7 database which runs over a
    > dozen server processes at once. Then the load average can exceed 10. But
    > the BOINC stuff tends to get out of the way at nice 19.
    >
    > The BOINC stuff screws up the processor caches, though, and makes the
    > database slow down a lot, even though, nominally, it gets all the
    > processor time it wants. But it does not get cache hit ratio it needs, so
    > the disk IO goes at about half speed or a little less. With BOINC turned
    > off, I get about 12 Megabytes/second to the hard drives, but it drops to
    > around 4 when BOINC is running those applications, even though they are at
    > nice 19.
    >>


    That would explain the load average. I run some SETI's on my dual celeron
    but only one per processor.

    08:55:50 up 48 days, 23:40, 1 user, load average: 2.00, 2.00, 2.00
    63 processes: 60 sleeping, 3 running, 0 zombie, 0 stopped
    CPU states: cpu user nice system irq softirq iowait idle
    total 1.4% 197.0% 1.2% 0.0% 0.0% 0.0% 0.0%
    cpu00 0.7% 98.4% 0.7% 0.0% 0.0% 0.0% 0.0%
    cpu01 0.7% 98.6% 0.5% 0.0% 0.0% 0.0% 0.0%
    Mem: 514220k av, 305372k used, 208848k free, 0k shrd, 126984k
    buff
    137988k active, 46540k inactive
    Swap: 1006952k av, 27280k used, 979672k free 16104k
    cached

    PID USER PRI NI SIZE RSS SHARE STAT %CPU %MEM TIME CPU COMMAND
    1410 root 39 19 16296 14M 1196 R N 99.0 2.9 70129m 0 setiathome
    26351 root 39 19 15884 15M 1152 R N 99.0 3.0 4050m 1 setiathome




  17. Re: newbie - just upgraded to RH9 from RH7.3 - any heads ups? - pleasehelp

    m.marien wrote:

    > That would explain the load average. I run some SETI's on my dual celeron
    > but only one per processor.


    My machine has two hyperthreaded Xeon processors, so they appear as four.
    >
    > 08:55:50 up 48 days, 23:40, 1 user, load average: 2.00, 2.00, 2.00
    > 63 processes: 60 sleeping, 3 running, 0 zombie, 0 stopped
    > CPU states: cpu user nice system irq softirq iowait idle
    > total 1.4% 197.0% 1.2% 0.0% 0.0% 0.0% 0.0%
    > cpu00 0.7% 98.4% 0.7% 0.0% 0.0% 0.0% 0.0%
    > cpu01 0.7% 98.6% 0.5% 0.0% 0.0% 0.0% 0.0%
    > Mem: 514220k av, 305372k used, 208848k free, 0k shrd, 126984k
    > buff
    > 137988k active, 46540k inactive
    > Swap: 1006952k av, 27280k used, 979672k free 16104k
    > cached
    >
    > PID USER PRI NI SIZE RSS SHARE STAT %CPU %MEM TIME CPU COMMAND
    > 1410 root 39 19 16296 14M 1196 R N 99.0 2.9 70129m 0 setiathome
    > 26351 root 39 19 15884 15M 1152 R N 99.0 3.0 4050m 1 setiathome
    >
    >
    >



    --
    .~. Jean-David Beyer Registered Linux User 85642.
    /V\ Registered Machine 241939.
    /( )\ Shrewsbury, New Jersey http://counter.li.org
    ^^-^^ 23:00:00 up 8 days, 10:04, 3 users, load average: 4.18, 4.20, 4.18


  18. Re: newbie - just upgraded to RH9 from RH7.3 - any heads ups? - please help


    "Jean-David Beyer" wrote in message
    news:10lpibs8bp5sc9f@corp.supernews.com...
    > m.marien wrote:
    >
    >> That would explain the load average. I run some SETI's on my dual celeron
    >> but only one per processor.

    >
    > My machine has two hyperthreaded Xeon processors, so they appear as four.
    >>


    Makes sense I guess. As you mentioned before, the low priority stuff still
    clobbers the cache once so it slows the priority stuff down. I guess anytime
    it gets processor time it reloads into cache.

    A question. SETI is a single thread process so when I run it on my quad it
    only takes 25% of the processor. Same on my dual, one SETI only takes 50% of
    the processing time. So how much processing time does a *single* SETI take
    on your dual hyperthreading system - 25% or 50%?

    Some pictures for your amusement. The first shows a quad with three SETI
    (75%) processes and a dual with a single SETI (50%) process. The second
    shows the quad with two SETI process but with the affinity set to specific
    processors. These two processors are at 100% while the other two are idling.
    I read somewhere that if you limit the SETI to one processor it will run
    faster as it stays in cache.

    http://www.digitalmapping.sk.ca/images/quad.gif
    http://www.digitalmapping.sk.ca/images/affinity.JPG

    I guess the thing to notice in the first picture is that while the SETI
    processes are passed back and forth among the processors, the processors
    aren't really equally used as shown by the graphs.




  19. Re: newbie - just upgraded to RH9 from RH7.3 - any heads ups? - pleasehelp

    m.marien wrote:
    > "Jean-David Beyer" wrote in message
    > news:10lpibs8bp5sc9f@corp.supernews.com...
    >
    >>m.marien wrote:
    >>
    >>
    >>>That would explain the load average. I run some SETI's on my dual celeron
    >>>but only one per processor.

    >>
    >>My machine has two hyperthreaded Xeon processors, so they appear as four.
    >>

    >
    > Makes sense I guess. As you mentioned before, the low priority stuff still
    > clobbers the cache once so it slows the priority stuff down. I guess anytime
    > it gets processor time it reloads into cache.
    >
    > A question. SETI is a single thread process so when I run it on my quad it
    > only takes 25% of the processor. Same on my dual, one SETI only takes 50% of
    > the processing time. So how much processing time does a *single* SETI take
    > on your dual hyperthreading system - 25% or 50%?


    I have my _top_ set the other way, so the total for my machine is 400%.

    10:50:36 up 8 days, 21:54, 3 users, load average: 4.17, 4.21, 4.18
    160 processes: 155 sleeping, 5 running, 0 zombie, 0 stopped
    CPU states: cpu user nice system irq softirq iowait idle
    total 29.6% 361.6% 7.6% 0.4% 0.0% 0.0% 0.0%
    cpu00 9.1% 87.8% 2.2% 0.5% 0.0% 0.0% 0.1%
    cpu01 5.8% 92.5% 1.6% 0.0% 0.0% 0.0% 0.0%
    cpu02 2.9% 95.6% 1.3% 0.0% 0.0% 0.0% 0.0%
    cpu03 11.7% 85.5% 2.4% 0.0% 0.0% 0.0% 0.1%
    Mem: 4100868k av, 4067544k used, 33324k free, 0k shrd, 70432k buff
    3168284k actv, 597020k in_d, 74444k in_c
    Swap: 8193076k av, 114616k used, 8078460k free 3636144k
    cached


    PID PPID USER PRI NI SIZE RSS SHARE STAT %CPU %MEM CTIME COMMAND
    1716 9896 boinc 39 19 46136 38M 3180 R N 94.5 0.9 5407m
    hadsm3um_4.04_i686-pc-lin
    19016 9895 boinc 39 19 15900 15M 916 R N 91.5 0.3 206:28
    setiathome_4.02_i686-pc-l
    4023 9912 boinc 39 19 46104 39M 3180 R N 90.2 0.9 3039m
    hadsm3um_4.04_i686-pc-lin
    20248 9895 boinc 39 19 15896 15M 904 R N 86.6 0.3 171:00
    setiathome_4.02_i686-pc-l

    So they are running around 90% each. You could divide all these by four if
    you wish to normalize to 100%. They normally run higher, around 98%, but
    some other stuff is going on now that makes them lower.

    When the machine is not running much else, a single setiathome takes 100%
    of one processor, or very near. And two take very nearly 100% of each of
    two processors, three take very nearly 100% of three processors, but with
    four, one of them gets only about 95% of a processor as the higher
    priority jobs take the rest.

    But remember, there are really only two clever processors in there. So
    even if they are all running 100%, the work done is not 4x the work of
    one. Running two insteances of setiathome, each one can do a work unit in
    a little less than 4 hours wall clock time. Running three does more
    overall work than two, but not 50% more, and running four definately does
    not do as much as 4x the amount of one.

    Now when running 4 setiathomes, they tend to take about 4.5 hours each.
    When running two setiathomes and 2 climatepredictors
    (hadsm3um_4.04_i686-pc-linux), the two setiathomes take a bit over 5 hours
    to do a work unit. I blame it on cache contention. These processors have
    three or four caches, depending how you count them. There is an L1
    instruction cache and an L1 data cache. These are around 16KBytes, IIRC.
    Each processor also has a 512KByte L2 cache and a 1024KByte L3 cache. But
    setiathome is a program that requires around 15Meg of memory (each) and
    hadsm3um_4.04_i686-pc-linux requires around 38 Meg of memory each. The
    working sets of each may be somewhat less, but they will never ever fit
    into the 1024KByte L3 caches.

    --
    .~. Jean-David Beyer Registered Linux User 85642.
    /V\ Registered Machine 241939.
    /( )\ Shrewsbury, New Jersey http://counter.li.org
    ^^-^^ 10:45:00 up 8 days, 21:49, 4 users, load average: 4.30, 4.27, 4.21


  20. Re: newbie - just upgraded to RH9 from RH7.3 - any heads ups? - please help


    "Jean-David Beyer" wrote in message
    news:10lqsg2hdk1n753@corp.supernews.com...
    > m.marien wrote:
    >> "Jean-David Beyer" wrote in message
    >> news:10lpibs8bp5sc9f@corp.supernews.com...
    >>
    >>>m.marien wrote:
    >>>
    >>>
    >>>>That would explain the load average. I run some SETI's on my dual
    >>>>celeron but only one per processor.
    >>>
    >>>My machine has two hyperthreaded Xeon processors, so they appear as four.
    >>>

    >>
    >> Makes sense I guess. As you mentioned before, the low priority stuff
    >> still clobbers the cache once so it slows the priority stuff down. I
    >> guess anytime it gets processor time it reloads into cache.
    >>
    >> A question. SETI is a single thread process so when I run it on my quad
    >> it only takes 25% of the processor. Same on my dual, one SETI only takes
    >> 50% of the processing time. So how much processing time does a *single*
    >> SETI take on your dual hyperthreading system - 25% or 50%?

    >
    > I have my _top_ set the other way, so the total for my machine is 400%.
    >
    > 10:50:36 up 8 days, 21:54, 3 users, load average: 4.17, 4.21, 4.18
    > 160 processes: 155 sleeping, 5 running, 0 zombie, 0 stopped
    > CPU states: cpu user nice system irq softirq iowait idle
    > total 29.6% 361.6% 7.6% 0.4% 0.0% 0.0% 0.0%
    > cpu00 9.1% 87.8% 2.2% 0.5% 0.0% 0.0% 0.1%
    > cpu01 5.8% 92.5% 1.6% 0.0% 0.0% 0.0% 0.0%
    > cpu02 2.9% 95.6% 1.3% 0.0% 0.0% 0.0% 0.0%
    > cpu03 11.7% 85.5% 2.4% 0.0% 0.0% 0.0% 0.1%
    > Mem: 4100868k av, 4067544k used, 33324k free, 0k shrd, 70432k
    > buff
    > 3168284k actv, 597020k in_d, 74444k in_c
    > Swap: 8193076k av, 114616k used, 8078460k free 3636144k
    > cached
    >
    >
    > PID PPID USER PRI NI SIZE RSS SHARE STAT %CPU %MEM CTIME
    > COMMAND
    > 1716 9896 boinc 39 19 46136 38M 3180 R N 94.5 0.9 5407m
    > hadsm3um_4.04_i686-pc-lin
    > 19016 9895 boinc 39 19 15900 15M 916 R N 91.5 0.3 206:28
    > setiathome_4.02_i686-pc-l
    > 4023 9912 boinc 39 19 46104 39M 3180 R N 90.2 0.9 3039m
    > hadsm3um_4.04_i686-pc-lin
    > 20248 9895 boinc 39 19 15896 15M 904 R N 86.6 0.3 171:00
    > setiathome_4.02_i686-pc-l
    >
    > So they are running around 90% each. You could divide all these by four if
    > you wish to normalize to 100%. They normally run higher, around 98%, but
    > some other stuff is going on now that makes them lower.
    >
    > When the machine is not running much else, a single setiathome takes 100%
    > of one processor, or very near. And two take very nearly 100% of each of
    > two processors, three take very nearly 100% of three processors, but with
    > four, one of them gets only about 95% of a processor as the higher
    > priority jobs take the rest.
    >
    > But remember, there are really only two clever processors in there. So
    > even if they are all running 100%, the work done is not 4x the work of
    > one. Running two insteances of setiathome, each one can do a work unit in
    > a little less than 4 hours wall clock time. Running three does more
    > overall work than two, but not 50% more, and running four definately does
    > not do as much as 4x the amount of one.
    >
    > Now when running 4 setiathomes, they tend to take about 4.5 hours each.
    > When running two setiathomes and 2 climatepredictors
    > (hadsm3um_4.04_i686-pc-linux), the two setiathomes take a bit over 5 hours
    > to do a work unit. I blame it on cache contention. These processors have
    > three or four caches, depending how you count them. There is an L1
    > instruction cache and an L1 data cache. These are around 16KBytes, IIRC.
    > Each processor also has a 512KByte L2 cache and a 1024KByte L3 cache. But
    > setiathome is a program that requires around 15Meg of memory (each) and
    > hadsm3um_4.04_i686-pc-linux requires around 38 Meg of memory each. The
    > working sets of each may be somewhat less, but they will never ever fit
    > into the 1024KByte L3 caches.
    >


    There is always a certain amount of overhead so the SETI processes will
    never get 100% of all the processing power. But it looks like one SETI
    process takes about 25% of the available processing power or 50% of one
    processor. So you need to run two processes per processor in order to
    maximize the processing power.

    I guess since the demise of DOS all o/s are multithreading. But it's still
    an interesting move on Intel's part, a processor built to take advantage of
    the software ??? It's usually the other way around.





+ Reply to Thread
Page 1 of 2 1 2 LastLast