Why use a check point file? was: Re: [RC5] client versions - AIX
jackb at guppy.us
Wed Oct 2 23:46:52 EDT 2002
Check point files are great for a machine with a harddrive.
I have machines that are nothing but a motherboard w/ a network boot rom.
They have enough memory to load a distro, a ram drive and dnet. By using
battery backup and smallest block sizes (think: check point file == micro
blocks), my network cranks and the power use is low... no drives spinning,
or monitor glowing. And no overhead of cluster software... each machine is
quiet little node, doing a single job.
Yes, I had some nodes checking in work even 6 minutes, but that is same
as a check point file, spinning up a hard drive, and writing data. But you see
I have one machine having to do that, the proxy server, and since multiple
machines are crunching - the drive does not spin down.
Now you say... use a network drive to write that check point file... Why? It is
faster to return and request a new block from proxy, and I do not have
support NFS mounts or SMB or worry about two machines sharing the same
To add a new machine, setup the rom, add to bootp/dhcp and away it goes.
> this is what checkpoint files are for... /ALL/ my machines use
> checkpoint files... all my machines are on UPS', too...
> Blain Nelson wrote:
> > 10/2/2002 7:59:54 AM, "Timothy Marsh" <Timothy.Marsh at usm.edu> wrote:
> > >
> > >----- Original Message -----
> > >From: "Jack Beglinger" <jackb at guppy.us>
> > >To: <rc5 at lists.distributed.net>
> > >Sent: Tuesday, October 01, 2002 3:32 PM
> > >Subject: RE: [RC5] client versions - AIX
> > >
> > >> First off, a week is too long for any work unit. It was also the most
> > >current
> > >> version available. OGR has no appeal to me - for this very reason.
> > >
> > >Since the same amount of credit is given no matter how long the unit is, it
> > >seems to me that the only problem with having a longer unit is that it
> > >delays the update of your stats until it is finished. I can see how stats
> > >junkies (I must admit I love stats too) would have a problem with this, but
> > >I imagine most stats junkies also have some faster machines that don't take
> > >more than a day to do an average OGR unit. I don't think a week is that
> > >long to wait.
> > >
> > The problem with taking a week is that, if your system crashes in that week, you lose the whole block.
> > My P90 took huge amounts of time to do OGR-25 blocks, and would crash before they were done semi-
> > consistently.
> > I recognize there are features which can mitigate this somewhat, but point it out as another problem
> > with work units that take too much time.
> > Take care,
> > Blain
> > --
> > ( ) ASCII ribbon campaign
> > X against HTML e-mail
> > / \
> > --
> > To unsubscribe, send 'unsubscribe rc5' to majordomo at lists.distributed.net
> > rc5-digest subscribers replace rc5 with rc5-digest
> (@@) Waldo Kitty, Waldo's Place USA
> __ooO_( )_Ooo_____________________ telnet://bbs.wpusa.dynip.com
> _|_____|_____|_____|_____|_____|_____ http://www.wpusa.dynip.com
> ____|_____|_____|_____|_____|_____|_____ ftp://ftp.wpusa.dynip.com
> _|_Eat_SPAM_to_email_me!_YUM!__|_____|_____ wkitty42 (at) alltel.net
> To unsubscribe, send 'unsubscribe rc5' to majordomo at lists.distributed.net
> rc5-digest subscribers replace rc5 with rc5-digest
To unsubscribe, send 'unsubscribe rc5' to majordomo at lists.distributed.net
rc5-digest subscribers replace rc5 with rc5-digest
More information about the rc5