the original condor just forwarded system calls back to the node it
was started from. Thus all system calls were done in the context of
the originating node and user.
Not much good if you're migrating because the node's gone down. What
happens then? Sorry to ask, RTFM seems a bit beyond my
On Sat, Apr 18, 2009 at 12:16 AM, erik quanstrom quans...@quanstro.net wrote:
On Fri, Apr 17, 2009 at 11:37 PM, erik quanstrom quans...@quanstro.net
wrote:
I can imagine a lot of problems stemming from open files could be
resolved by first attempting to import the process's namespace at the
there's no guarantee to a process running in a conventional
environment that files won't change underfoot. why would
condor extend a new guarantee?
Because you have to migrate standard applications, not only
applications that allow for migration. Consider a word processing
session, for
On Sat, Apr 18, 2009 at 1:47 AM, lu...@proxima.alt.za wrote:
Every time I have to use something like
Linux or MS, I feel overwhelmed by the sheer complexity of it all.
Possibly OT, my main beef with Linux and Windows is that they keep
wanting to update themselves and the effort to manage
The update/installation process in Ubuntu sucks. If you try something
using BSD ports or Gentoo portage, you can fine tune things and have
explicit control over the update process.
I was specifically omitting BSD ports, as they are in a different
league. The point I _was_ making is that one
This thing about Windows updates, I think it's a non-issue. It's not like
updates are mandatory and, as a matter of fact, there's rather fine-grained
classification of them on Microsoft's knowledge base which can be used by
any more or less experienced user to identify exactly what they need
On Fri, Apr 17, 2009 at 03:15:25PM -0700, ron minnich wrote:
if you want to look at checkpointing, it's worth going back to look at
Condor, because they made it really work. There are a few interesting
issues that you need to get right. You can't make it 50% of the way
there; that's not
I assumed cloud computing means you can log into any node
that you are authorised to and your data and code will migrate
to you as needed.
The idea being the sam -r split is not only dynamic but on demand,
you may connect to the cloud from your phone just to read your email
so the editor session
* you can get the same effect by increasing the scale of your system.
* the reason conventional systems work is not, in my opinion, because
the collision window is small, but because one typically doesn't do
conflicting edits to the same file.
* saying that something isn't likely in
[I reply to myself because I was replying half on two distinct threads]
On Sat, Apr 18, 2009 at 01:59:03PM +0200, tlaro...@polynum.com wrote:
But my gut feeling, after reading about Mach or reading A. Tanenbaum
(that I find poor---but he is A. Tanenbaum, I'm only T. Laronde),
is that a
On Fri Apr 17 16:22:55 EDT 2009, blstu...@bellsouth.net wrote:
I often tell my students that every cycle used by overhead
(kernel, UI, etc) is a cycle taken away from doing the work
of applications. I'd much rather have my DNA sequencing
application finish in 25 days instead of 30 than to
On Sat, Apr 18, 2009 at 4:59 AM, tlaro...@polynum.com wrote:
But my gut feeling, after reading about Mach or reading A. Tanenbaum
(that I find poor---but he is A. Tanenbaum, I'm only T. Laronde),
is that a cluster is above the OS (a collection of CPUs), but a
NUMA is for the OS an atom, i.e.
On Sat, Apr 18, 2009 at 6:50 AM, erik quanstrom quans...@quanstro.net wrote:
in a plan 9 system, the only files that i can think of which many processes
have open at the same time are log files, append-only files. just reopening
log file would solve the problem.
you're not thinking in terms
I talked with a guy that's is doing parallel filesystem work, and
according to him 80% of all filesystem operations when running an HPC
job are for checkpointing (not that much restart). I just don't see
how checkpointing can scale knowing how bad the parallel fs are.
Lucho
On Fri, Apr 17,
On Sat, Apr 18, 2009 at 10:54:34AM -0400, erik quanstrom wrote:
as an old example, i think that the lab's use of worm storage
for the main file server was incredibly insightful.
what could we do today, but don't quite dare?
stop writing all programs in C, and start writing them in a
On Sat, Apr 18, 2009 at 9:50 AM, erik quanstrom quans...@quanstro.net wrote:
* you can get the same effect by increasing the scale of your system.
* the reason conventional systems work is not, in my opinion, because
the collision window is small, but because one typically doesn't do
On Sat, Apr 18, 2009 at 2:11 AM, lu...@proxima.alt.za wrote:
The update/installation process in Ubuntu sucks. If you try something
using BSD ports or Gentoo portage, you can fine tune things and have
explicit control over the update process.
I was specifically omitting BSD ports, as they are
On Sat, Apr 18, 2009 at 9:10 AM, J.R. Mauro jrm8...@gmail.com wrote:
I agree that generally only one process will be accessing a normal
file at once. I think an editor is not a good example, as you say.
I'll say it again. It does not matter what we think. It matters what
apps do. And some
On Sat, Apr 18, 2009 at 2:08 AM, Eris Discordia
eris.discor...@gmail.com wrote:
This thing about Windows updates, I think it's a non-issue. It's not like
updates are mandatory and, as a matter of fact, there's rather fine-grained
classification of them on Microsoft's knowledge base which can be
On Fri, Apr 17, 2009 at 6:00 AM, Eris Discordia
eris.discor...@gmail.com wrote:
It's like I'm seeing an apparition of myself back more than a year ago. No
wonder 9fans got to dislike me so much. Do 9fans get nuisances like me in
regular intervals?
yes, they come and they go. But there's
On Sat Apr 18 12:21:49 EDT 2009, rminn...@gmail.com wrote:
On Sat, Apr 18, 2009 at 9:10 AM, J.R. Mauro jrm8...@gmail.com wrote:
I agree that generally only one process will be accessing a normal
file at once. I think an editor is not a good example, as you say.
I'll say it again. It
Seriously, give Gentoo portage a try. There is a sane package
management system for Linux.
if you don't upgrade in lock step you will get into dependency hell.
portage is now exactly what its developers railed against — rpm
dependency hell. portage just kicks the can down the street a bit.
in
It's like I'm seeing an apparition of myself back more than a year ago. No
wonder 9fans got to dislike me so much. Do 9fans get nuisances like me in
regular intervals?
yes, they come and they go. But there's always one. Never more,
according to Yoda.
I think I can see why. In fact, Eris
On Sat, Apr 18, 2009 at 12:20 PM, erik quanstrom quans...@quanstro.net wrote:
Seriously, give Gentoo portage a try. There is a sane package
management system for Linux.
if you don't upgrade in lock step you will get into dependency hell.
portage is now exactly what its developers railed
On Sat, Apr 18, 2009 at 12:20 PM, ron minnich rminn...@gmail.com wrote:
On Sat, Apr 18, 2009 at 9:10 AM, J.R. Mauro jrm8...@gmail.com wrote:
I agree that generally only one process will be accessing a normal
file at once. I think an editor is not a good example, as you say.
I'll say it
On Sat, Apr 18, 2009 at 12:20 PM, ron minnich rminn...@gmail.com wrote:
I'll say it again. It does not matter what we think. It matters what
apps do. And some apps have multiple processes accessing one file.
As to the wisdom of such access, there are many opinions :-)
You really can not
Hi folks,
some time ago, we had several discussions about shared libraries,
mmap(), etc. One of the major arguments for shared libraries is
to share code pages between processes - and the traditional *nix
approach to do so is mmap() (at least on the systems I know).
Assuming statically
* erik quanstrom quans...@quanstro.net wrote:
Hi,
yes. there are several web servers, including one in the standard
dist. however, rails or merb might be something you'd have to do
yourself.
Did anyone already get java running on Plan9 ?
I dont know anything about ruby, but IMHO python
I _do_ think yours should come first! Having to say: yes to an user...
If you don't say 'yes' at some point, you won't have a system anyone
will want to use. Remember all those quotes about why Unix doesn't
prevent you from doing stupid things?
A checkpoint restart package.
https://ftg.lbl.gov/CheckpointRestart/CheckpointRestart.shtml
On Sat, Apr 18, 2009 at 07:05:07PM +0200, Enrico Weigelt wrote:
Assuming statically linked-in libraries are properly aligned,
we'll have lots of equal pages in the system, so the kernel could
find and automatically map them together.
Well that's one of the 3 classical options:
1) static
Devon H. O'Dell devon.od...@gmail.com wrote:
Given the feedback from the list, I've come up with two alternatives.
(Well, one of them was actually Mechiel's brainchild).
Idea #1 (From Mechiel)
[snipped]
Maybe it's just the packet shifter in me, but could not the ideas of
Token
That is a lie. There are updates which (at least on XP) you could
never refuse. Nevermind the fact that Windows would have to restart
more than once on a typical series of updates.
Windows isn't really the subject on this thread or this list. Except when
someone goes out of their way to
On Sat, Apr 18, 2009 at 2:29 PM, Eris Discordia
eris.discor...@gmail.com wrote:
That is a lie. There are updates which (at least on XP) you could
never refuse. Nevermind the fact that Windows would have to restart
more than once on a typical series of updates.
Windows isn't really the subject
Actually, I used Windows for years before discovering something
better. I explicitly disabled updates in XP, and it would insist on
looking for them and bothering me about them, anyway.
I put it here for I don't know what to call it--shall we say... historical
record?--how to turn off your
On Sat, Apr 18, 2009 at 3:34 PM, Eris Discordia
eris.discor...@gmail.com wrote:
Actually, I used Windows for years before discovering something
better. I explicitly disabled updates in XP, and it would insist on
looking for them and bothering me about them, anyway.
I put it here for I don't
While I think SQL *really* sucks (besides smelling too much of COBOL,
it pretends to be relational when it is not), that was not my point,
and I agree with you that relational databases don't store objects,
and that relational databases do have valid uses that are sadly often
overlooked (maybe
On Fri, Apr 17, 2009 at 2:45 PM, Rudolf Sykora rudolf.syk...@gmail.com wrote:
Writing the core of a blog engine in three lines of rc is hard to
beat, plus you get the benefit of being able to manipulate and manage
all your data using the tools any self respecting Unix user loves.
uriel
While I think SQL *really* sucks (besides smelling too much of COBOL,
it pretends to be relational when it is not),
your facts here are incorrect. clearly sql is relational, if you take
codd's meaning of the term. also sql as a language has nothing
to do with cobol. cobol, like fortran, c,
On Fri, Apr 17, 2009 at 2:45 PM, Rudolf Sykora rudolf.syk...@gmail.com
wrote:
Writing the core of a blog engine in three lines of rc is hard to
beat, plus you get the benefit of being able to manipulate and manage
all your data using the tools any self respecting Unix user loves.
uriel
On Sun, Apr 19, 2009 at 12:27 AM, erik quanstrom quans...@quanstro.net wrote:
While I think SQL *really* sucks (besides smelling too much of COBOL,
it pretends to be relational when it is not),
your facts here are incorrect. clearly sql is relational, if you take
codd's meaning of the term.
So, how hard is it to get werc running on real Plan 9? The readme was
for Plan 9 Ports last time I checked.
Shouldn't be hard, aside from a couple of paths that might need fixing
(perhaps using bind(1) will do), it should run out of the box.
The only issue is that it expects to run as a CGI,
this discussion of checkpoint/restart reminds me of
a hint i was given years ago: if you wanted to break into a system,
attack through the checkpoint/restart system. i won a jug of
beer for my subsequent successful attack which involved patching
the disc offset for an open file in a copy of the
On Sat, Apr 18, 2009 at 7:31 PM, Charles Forsyth fors...@terzarima.net wrote:
this discussion of checkpoint/restart reminds me of
a hint i was given years ago: if you wanted to break into a system,
attack through the checkpoint/restart system. i won a jug of
beer for my subsequent successful
I really didn't want to get into this debate, my point about COBOL was
more about the archaic syntax than anything else.
the way not to get into a debate is to not make controvertial
claims about the facts.
- erik
So, how hard is it to get werc running on real Plan 9? The readme was
for Plan 9 Ports last time I checked.
Shouldn't be hard, aside from a couple of paths that might need fixing
(perhaps using bind(1) will do), it should run out of the box.
The only issue is that it expects to run as a
I haven't responded yet to all the info and ideas in my earlier thread,
because I've been trying to get Plan 9 working in QEMU.
First, I tried using 9vx. I found these instructions at
http://swtch.com/9vx/ :
9vx-0.12.tar.bz2 is a binary distribution
containing a minimal plan 9 tree and binaries
*Challenge 4*: Display size
My Ubuntu display is 1024x768. The default size of the Plan 9 display is
much smaller, so it wasn't using all the available space on the Ubuntu
display.
Winning response: I re-installed Plan 9, changing the dimensions at the
prompt. I haven't learned yet
When I installed Plan 9, it took more than an hour to format 2GB.
the plan 9 ide driver will use pio unless you tell it to do otherwise.
i'm not sure if this applies to qemu, but assuming your emulated drive
is sdC0, you can turn on dma with
echo dma on /dev/sdC0/ctl
- erik
49 matches
Mail list logo
