Computer Old Farts Forum
 help / color / mirror / Atom feed
* [COFF] how was TCF different or similar to Mosix
@ 2021-04-02 19:04 Clem Cole
  2021-04-02 20:09 ` Charles H Sauer
  0 siblings, 1 reply; 2+ messages in thread
From: Clem Cole @ 2021-04-02 19:04 UTC (permalink / raw)
  To: Theodore Ts'o; +Cc: TUHS main list, Josh Good


[-- Attachment #1.1: Type: text/plain, Size: 2423 bytes --]

On Fri, Apr 2, 2021 at 1:50 PM Theodore Ts'o <tytso@mit.edu> wrote:

> Out of curiousity, how was TCF different or similar to Mosix?
>
Many similar ideas.  TCF was basically the commercial implementation of the
Locus, which Jerry and students built at UCLA (one 11/70s original).  I
want to say the Locus papers are in some early SOSPs.

MOSIX was its own Unix-like OS, as was Locus [and some of this was in
Sprite too BTW].  TCF was a huge number of rewrites to BSD and was UNIX.
The local/remote restructuring was ad-hoc.   By the time Roman and I lead
TNF, we had created a formal VPROC layer as an analog to the VFS  layer
(more in a minute).   TNC was to be the gut of Intel's Paragon using OSF/1
as base OS.

The basic idea of all of them is that the cluster is looks like a single
protection domain with nodes contributing resources.   A Larry says a ps is
cluster-wide.  TCF had the idea of features that each node provides (ISA,
floating-point unit, AP, *etc*..) so if a process needed specific
resources, it would only run on a node that had those resources.   But it
also meant that processes could be migrated from a node that had the same
resources.

One of the coolest demos I ever saw was we took a new unconfigured PS/2 at
a trade show and connected the ethernet to it on the trade show network,
and put in a boot floppy. We dialed back into a system at an LCC, and
filled in some security things, details like the IP address of the new
system and soon it booted and joined the cluster.   It immediately started
to add services to the cluster, we walked away, and (overnight) the system
had set up the hard disk and started caching locally things that were
needed for speed.  Later I was editing a file and from another screen
migrated the process around the cluster while the editing was active.

The problem with VPROC (like VFS) is it takes surgery all over the kernel.
 In fact, for Linux 2.x kernel the OpenSSI
<https://sourceforge.net/projects/ssic-linux/> folks did all the kernel
work to virtualize the concept of process, which sadly never got picked up
as the kernel.org folks did not like it (a real shame IMO).   BTW, one of
the neat side effects of a layer like VPROC is things like
checkpoint/restart are free -- you are just migrating a process to the
storage instead of an active processor.

Anyway, Mosix has a lot of the same types of ideas.  I have much less
experience with it directly.

[-- Attachment #1.2: Type: text/html, Size: 4129 bytes --]

[-- Attachment #2: Type: text/plain, Size: 141 bytes --]

_______________________________________________
COFF mailing list
COFF@minnie.tuhs.org
https://minnie.tuhs.org/cgi-bin/mailman/listinfo/coff

^ permalink raw reply	[flat|nested] 2+ messages in thread

* Re: [COFF] how was TCF different or similar to Mosix
  2021-04-02 19:04 [COFF] how was TCF different or similar to Mosix Clem Cole
@ 2021-04-02 20:09 ` Charles H Sauer
  0 siblings, 0 replies; 2+ messages in thread
From: Charles H Sauer @ 2021-04-02 20:09 UTC (permalink / raw)
  To: coff

Amazon still carries the Popek/Walker LOCUS book 
https://smile.amazon.com/Distributed-System-Architecture-Computer-Systems/dp/0262517191/ 


I haven't cracked it open in years, but I assume it is still the best 
starting point.

On 4/2/2021 2:04 PM, Clem Cole wrote:
> On Fri, Apr 2, 2021 at 1:50 PM Theodore Ts'o <tytso@mit.edu 
> <mailto:tytso@mit.edu>> wrote:
> 
>     Out of curiousity, how was TCF different or similar to Mosix?
> 
> Many similar ideas.  TCF was basically the commercial implementation of 
> the Locus, which Jerry and students built at UCLA (one 11/70s 
> original).  I want to say the Locus papers are in some early SOSPs.
> 
> MOSIX was its own Unix-like OS, as was Locus [and some of this was in 
> Sprite too BTW].  TCF was a huge number of rewrites to BSD and was 
> UNIX.  The local/remote restructuring was ad-hoc.   By the time Roman 
> and I lead TNF, we had created a formal VPROC layer as an analog to the 
> VFS  layer (more in a minute). TNC was to be thegut of Intel's Paragon 
> using OSF/1 as base OS.
> 
> The basic idea of all of them is that the cluster is looks like a single 
> protection domain with nodes contributing resources.   A Larry says a ps 
> is cluster-wide.  TCF had the idea of features that each node provides 
> (ISA, floating-point unit, AP, /etc/..) so if a process needed specific 
> resources, it would only run on a node that had those resources.   But 
> it also meant that processes could be migrated from a node that had the 
> same resources.
> 
> One of the coolest demos I ever saw was we took a new unconfigured PS/2 
> at a trade show and connected the ethernet to it on the trade show 
> network, and put in a boot floppy. We dialed back into a system at an 
> LCC, and filled in some security things, details like the IP address of 
> the new system and soon it booted and joined the cluster.   It 
> immediately started to add services to the cluster, we walked away, and 
> (overnight) the system had set up the hard disk and started caching 
> locally things that were needed for speed.  Later I was editing a file 
> and from another screen migrated the process around the cluster while 
> the editing was active.
> 
> The problem with VPROC (like VFS) is it takes surgery all over the 
> kernel.   In fact, for Linux 2.x kernel the OpenSSI 
> <https://sourceforge.net/projects/ssic-linux/> folks did all the kernel 
> work to virtualize the concept of process, which sadly never got picked 
> up as the kernel.org <http://kernel.org> folks did not like it (a real 
> shame IMO).   BTW, one of the neat side effects of a layer like VPROC is 
> things like checkpoint/restart are free -- you are just migrating a 
> process to the storage instead of an active processor.
> 
> Anyway, Mosix has a lot of the same types of ideas.  I have much less 
> experience with it directly.
> 
> 
> 
> _______________________________________________
> COFF mailing list
> COFF@minnie.tuhs.org
> https://minnie.tuhs.org/cgi-bin/mailman/listinfo/coff
> 

-- 
voice: +1.512.784.7526       e-mail: sauer@technologists.com
fax: +1.512.346.5240         Web: https://technologists.com/sauer/
Facebook/Google/Skype/Twitter: CharlesHSauer
_______________________________________________
COFF mailing list
COFF@minnie.tuhs.org
https://minnie.tuhs.org/cgi-bin/mailman/listinfo/coff

^ permalink raw reply	[flat|nested] 2+ messages in thread

end of thread, other threads:[~2021-04-02 20:54 UTC | newest]

Thread overview: 2+ messages (download: mbox.gz / follow: Atom feed)
-- links below jump to the message on this page --
2021-04-02 19:04 [COFF] how was TCF different or similar to Mosix Clem Cole
2021-04-02 20:09 ` Charles H Sauer

Computer Old Farts Forum

This inbox may be cloned and mirrored by anyone:

	git clone --mirror https://inbox.vuxu.org/coff

	# If you have public-inbox 1.1+ installed, you may
	# initialize and index your mirror using the following commands:
	public-inbox-init -V1 coff coff/ https://inbox.vuxu.org/coff \
		coff@minnie.tuhs.org
	public-inbox-index coff

Example config snippet for mirrors.
Newsgroup available over NNTP:
	nntp://inbox.vuxu.org/vuxu.archive.coff


AGPL code for this site: git clone https://public-inbox.org/public-inbox.git