* Distributed Linux
@ 2002-11-10 11:04 Prasad
2002-11-10 11:31 ` Hacksaw
2002-11-10 12:50 ` Lars Marowsky-Bree
0 siblings, 2 replies; 4+ messages in thread
From: Prasad @ 2002-11-10 11:04 UTC (permalink / raw)
To: lkml
Hi all,
the subject may be too ambitious, but thats not a prank i am
playing... As a graduation project i intended to make linux distributed...
by distributed i mean, enabling process migration, selecting eligible
nodes, and ofcourse selecting candidate processes which would be migrated
to the selected node. The following is the description of how i intended
to do and would like inputs/suggessions from the gurus here.
The processes would be dynamically migrated from one node to the other
based on the selections of local process (candidate) and the remote node.
The entire task along with its memory map will be migrated on to the other
system (This system however would be later changed to migrate only
referenced pages). The guest system (where the process originated) would
however have a pseudo process running on it, which would not take much
resources but would help in handling various signals/interrupts and in
handling system calls. This method of handling helps is in migrating the
user mode execution (which is on an average greater than 75%) to some
other system on the network thus reducing the load on the guest system.
As of now i am trying to device a migration system where the system mode
computation is mostly carried out on the tasks original system, as this
simplifies the implementation and helps maintaining the speed and
efficiency in cases where the distribution is not needed.
Prasad
--
Failure is not an option
^ permalink raw reply [flat|nested] 4+ messages in thread
* Re: Distributed Linux
2002-11-10 11:04 Distributed Linux Prasad
@ 2002-11-10 11:31 ` Hacksaw
2002-11-10 12:50 ` Lars Marowsky-Bree
1 sibling, 0 replies; 4+ messages in thread
From: Hacksaw @ 2002-11-10 11:31 UTC (permalink / raw)
To: Prasad; +Cc: lkml
> As a graduation project i intended to make linux distributed
You mean, like Mosix?
http://www.mosix.org/
--
Playing fast is easier than playing slow.
http://www.hacksaw.org -- http://www.privatecircus.com -- KB1FVD
^ permalink raw reply [flat|nested] 4+ messages in thread
* Re: Distributed Linux
2002-11-10 11:04 Distributed Linux Prasad
2002-11-10 11:31 ` Hacksaw
@ 2002-11-10 12:50 ` Lars Marowsky-Bree
1 sibling, 0 replies; 4+ messages in thread
From: Lars Marowsky-Bree @ 2002-11-10 12:50 UTC (permalink / raw)
To: Prasad, lkml
On 2002-11-10T16:34:10,
Prasad <prasad_s@gdit.iiit.net> said:
> As of now i am trying to device a migration system where the system mode
> computation is mostly carried out on the tasks original system, as this
> simplifies the implementation and helps maintaining the speed and
> efficiency in cases where the distribution is not needed.
Look at OpenMosix and the Compaq Single System Image cluster stuff.
Sincerely,
Lars Marowsky-Brée <lmb@suse.de>
--
Principal Squirrel
SuSE Labs - Research & Development, SuSE Linux AG
"If anything can go wrong, it will." "Chance favors the prepared (mind)."
-- Capt. Edward A. Murphy -- Louis Pasteur
^ permalink raw reply [flat|nested] 4+ messages in thread
* Re: Distributed Linux
@ 2002-11-13 5:13 Aneesh Kumar K.V
0 siblings, 0 replies; 4+ messages in thread
From: Aneesh Kumar K.V @ 2002-11-13 5:13 UTC (permalink / raw)
To: prasad_s; +Cc: linux-kernel, ssic-linux-devel
> As a graduation project i intended to make linux distributed
This is what exactly openSSI project does. http://ssic-linux.sf.net
>The processes would be dynamically migrated from one node to the other
>based on the selections of local process (candidate) and the remote
>node.
In the case of SSI the process to be migrated is selected by using
mosix algorithm. If mosix load balancer is not enabled automatic load
balancing doesn't work. But you can use the migrate() call with "best
node" argument so that the average load on the machine is used to
determine which node the process should migrate.
>The entire task along with its memory map will be migrated on to the
>other system
SSI even support mmap across cluster. That means you can even ask a
process that has done a mmap of file to migrate to another node.
>The guest system (where the process originated) would
>however have a pseudo process running on it, which would not take much
>resources but would help in handling various signals/
SSI support cluster wide signaling. That means you can send signal to a
process running on other node( you have cluster wide PID )
It also support cluster wide message queue, DLM , cluster wide device
access and cluster wide IP. The developers are working on cluster wide
support for semaphore shared memory
NOTE: it support three architectures. x86/IA64/Alpha
-aneesh
^ permalink raw reply [flat|nested] 4+ messages in thread
end of thread, other threads:[~2002-11-13 5:06 UTC | newest]
Thread overview: 4+ messages (download: mbox.gz follow: Atom feed
-- links below jump to the message on this page --
2002-11-10 11:04 Distributed Linux Prasad
2002-11-10 11:31 ` Hacksaw
2002-11-10 12:50 ` Lars Marowsky-Bree
-- strict thread matches above, loose matches on Subject: below --
2002-11-13 5:13 Aneesh Kumar K.V
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.