-BEGIN PGP SIGNED MESSAGE-
Hash: SHA1
Brady Catherman wrote:
| BTW, are you guys looking for other commonly (or in some cases.. ultra
| rarely) used science/biology ebuilds? I have built something like a
| dozen for the utilities that we use in house here.
That might find more talk on
Eric Thibodeau wrote:
The way I see it, multiple Gentoo roots would be available (different
machine profiles/optimisation) and they would be specified in the DHCP server's
config file as simply as any PXE entry So I am not too sure I
understand your couple of ROOT=/foo _and_ the busybox
-BEGIN PGP SIGNED MESSAGE-
Hash: SHA1
Mathias Weigt wrote:
| Donnie Berkholz wrote:
| What exactly do you want more detail about?
|
|
| They boot to an initrd containing busybox, then proceed to mount
| necessary bits from a read-only NFS export and other bits via tmpfs
| where they need
-BEGIN PGP SIGNED MESSAGE-
Hash: SHA1
Stéphane Lacasse wrote:
| Like you said, it's beside the point, but I think you could take a look
| at their design and draw some inpirations from it. An easy install like
| Rock Cluster but instead of using Kickstart(tm) files, would use the
|
Brady Catherman wrote:
My next step was to take the live CD and try to modify it. The live CD
needs two things enabled in order to consider it ready for use on a
headless XServe G5. It needs to enable the serial console by default,
and it needs fusion MPT support.
Might be nice to search
Andrew D. Fant wrote:
I'll dig around and forward the ebuild to the list later tonight or
tomorrow. At the risk of going off on a rant, I think that the
/etc/env.d model is a core part of the problem. If two users want to
use two different mpi implementations, will eselect allow them to both
Ramon van Alteren wrote:
Suggest we pick one of the usual free licenses (maybe the same as the
gentoo documentation project uses ?)
Please! Otherwise we can never incorporate the material into any
official documentation.
Thanks,
Donnie
signature.asc
Description: OpenPGP digital signature
Brady Catherman wrote:
One last question for you all.. Why is distcc so popular? We used it on
our 134 node cluster and it actually made compiling much slower than
just running it on one of the nodes. The network overhead killed the
performance gain. The only way we found that it helped was
Brady Catherman wrote:
So the short of it is that higher is always better, and this is only a
'best as I personally' could do comparison.
OK, thanks for the clarification. Have you also run lmbench?
After our conversion things went together much smoother and now
maintenance is fairly
Donnie Berkholz wrote:
We used to have some documentation floating around, but it never got put
on the Gentoo site and converted to GuideXML. I think there was a
filesystem selection guide and a Heartbeat/DRBD howto, maybe something
else. I'm poking the author to see whether he can dig them up
This message about java-config just passed across gentoo-dev. Apparently
it can switch both on a system and a user level, so it may be worth
looking into for adapting to mpi-config.
Thanks,
Donnie
Original Message
Subject: [gentoo-dev] Changes to the way Java packages are built
Hanni Ali wrote:
I feel it would be sensible to have a gentoo cluster overlay for all
clustering and grid related software, would be useful for testing and
collaboration.
http://overlays.gentoo.org/ http://overlays.gentoo.org/
There's already some stuff in the gentoo science overlay [1].
Bryan Green wrote:
Thats great to hear. Consider them a work in progress. They work great for
me, and I've only tested them on amd64. I'd be happy to get feedback,
including fixes/additions.
Bug me on IRC sometime and I'll look them over with you. I'm pretty busy
today though.
Thanks,
Bryan Green wrote:
Yes, I actually used those ebuilds to test Lustre on our mini 3x3
hyperwall which runs Gentoo. I was able to get it working, but over here
they want the supported, released version, whereas those ebuilds are for the
beta. I tried to install the released version, but
Bryan Green wrote:
Donnie Berkholz writes:
I guess that means we should get in touch with them to get on the
supported systems list. =)
Sounds like a fine idea to me. :)
I talked to someone there at SC06, but they did not sound terribly open to
the idea of directing precious resources
John R. Dunning wrote:
From: Bryan Green [EMAIL PROTECTED]
A longer term solution is to do some combination of remodularizing vfs and
recasting the lustre stuff so as to depend less on getting its fingers into
the guts. I once spent some time looking into that, and I do believe it's
We might benefit from splitting the clustering packages into two
separate groups for high-availability and high-performance computing.
This will help to keep the bugs a bit cleaner so each group of folks
will have a clearer idea of what they need to do.
Does anyone else have thoughts on this?
Andrew D. Fant wrote:
Donnie Berkholz wrote:
We might benefit from splitting the clustering packages into two
separate groups for high-availability and high-performance computing.
This will help to keep the bugs a bit cleaner so each group of folks
will have a clearer idea of what they need
Philipp Riegger wrote:
On Dec 11, 2006, at 9:11 AM, Donnie Berkholz wrote:
Does anyone else have thoughts on this?
I think, hac-cluster and hpc-cluster sound strange, since c in hpc and
hac already stands for cluster.
or computing...
--
gentoo-cluster@gentoo.org mailing list
Hanni Ali wrote:
ok so follow the hpc how to: http://www.gentoo.org/doc/en/hpc-howto.xml
but modify for diskless which you seem to have got the hang of.
FWIW, I've got plans to put together a doc for a clean setup of a
diskless cluster. I'm unhappy with our clustering documentation,
although
Daniel van Ham Colchete wrote:
I would like the deployment and maintenance to be done as easily as
possible because this project needs to be scalable to more than 100
servers. Although we are going to install only 10 servers in the
beginning, my boss says that I should be prepared for this
C. Bergström wrote:
I've uploaded my rough outline of what I have so far to a google doc and
started #gentoo-deploy on freenode for anyone interested in working
together on this.
I'd like if you guys could stick in #gentoo-cluster instead of a new IRC
channel, it's relevant to everyone in
C. Bergström wrote:
Donnie Berkholz wrote:
C. Bergström wrote:
I've uploaded my rough outline of what I have so far to a google doc
and started #gentoo-deploy on freenode for anyone interested in
working together on this.
I'd like if you guys could stick in #gentoo-cluster instead of a new
C. Bergström wrote:
I'm trying to really clean up my cluster deployment and while looking at
GFS came across this.
http://people.redhat.com/rkenna/gfs-deploy-tool/html.doc/
My first thoughts are of course switching out the dependency to pull
rpms from the rh network to PORTAGE_BINHOST..
On 09:31 Fri 25 Jan , Ramon van Alteren wrote:
I remember seeing a demo from yamin at a gentoo UK conference demoing
netbooting with a genkernel kernel
That's the genkernel-4 code. I've used it for diskless setups and it
works quite nicely. It's living on gentooexperimental.org at the
: Darryl Coburn [EMAIL PROTECTED]
To: 'Donnie Berkholz' [EMAIL PROTECTED]
Subject: RE: Linux/Cluster/Grid Project Leader
Date: Sun, 8 Jun 2008 22:51:15 -0600
Thanks Donnie, that would be great.
Do you need anything from me?
Darryl Coburn
630-573-5050 ext. 340 office
708-767-6367
,
Donnie
Donnie Berkholz
Developer, Gentoo Linux
Blog: http://dberkholz.wordpress.com
pgpu0LiFmDtFM.pgp
Description: PGP signature
27 matches
Mail list logo