On Wednesday, 09/20/2006 at 07:23 MST, Adam Thornton
[EMAIL PROTECTED] wrote:
Where is my misunderstanding of the problem? Surely, if we know what
the S/390 or zSeries system does when it wants to put a packet on the
network via the OSA, and if we know what packet ultimately ends up on
the
I've always thought that on LPARs one has to deal in real DASD,
printers
etc.
If you look at it from the perspective of the OS in the Hercules
instance, you are.
With Herc under Linux, one has all the tools Linux provides at one's
disposal to clone Hercules/Linux systems. And there are
I do not know if there's a version of Flex-ES that's had its 64-bit
emulation recoded from x86 to x86-64. I would not be surprised if Hercules
compiled for x86-64 would outperform Flex-ES built for x86 for the same
64-bit workload, but I am not in a position to do more than guess at that.
For a
David Boyes
Sine Nomine Associates
and if you'd like to know more
http://www.bbc.co.uk/learnwelsh/..
OTOH I suspect Spanish is probably more useful in most of the world.
Remember, you're talking to a crowd that probably had to learn COBOL to
survive... 8-)
Spanish may be more useful,
Jay Maynard wrote:
A nice fast 8-way Opteron would probably outrun the average PartnerWorld
Flex-ES box, but that's hardly an apples-to-apples comparison. :-)
I'd be content to judge their finest against the finest alternative to
be a fair comparison.
If _I_ wanted the best possible box to
I don't really understand what Flex-ES is - I have some idea it's some
hardware-plus-software imitation mainframe.
FlexES is a software mainframe processor and I/O system emulation
product that has historically been the only emulated mainframe solution
blessed by IBM, ie that you could legally
On Wed, Sep 20, 2006 at 10:28:13PM +0800, John Summerfield wrote:
A nice fast 8-way Opteron would probably outrun the average PartnerWorld
Flex-ES box, but that's hardly an apples-to-apples comparison. :-)
I'd be content to judge their finest against the finest alternative to
be a fair
On Wed, Sep 20, 2006 at 10:38:14AM -0400, David Boyes wrote:
About the same, realistically (albeit throwing more hardware at a
Hercules solution is a LOT cheaper). The key issue is that you can
legally license IBM software on FlexES; you can't do that on Hercules.
I'd say it's not known
Well, if you're just doing z/Linux, you can throw one hell of a fast
box
at
the problem with Hercules for what you would spend on Flex-ES.
This is *very* true. A 8 core name-brand Opteron system with 16G of RAM
prices out at a little under $7K list. Whitebox Opteron systems are
about $1K
I'd say it's not known whether you can do that on Hercules. AFAIK,
nobody
has ever gotten a refusal to license on Hercules at any price from IBM
in
writing. If such a document exists, I'd appreciate seeing it; until I
do,
there's been enough FUD thrown around from one particular party that
Subject
Re: [LINUX-390] Getting to 64-bit
systems *legitimately*...
09/20/06 10:12 AM
Please respond to
Linux on 390 Port
[EMAIL PROTECTED
Jay Maynard clarified:
John Summerfield wrote:
In such an environment, lack of VM might not matter so much, the
virtualisation could be done natively rather than in the emulated
environment.
Indeed. Simply run multiple copies of Hercules. This only works, of
course,
as long as you're not
On Sep 20, 2006, at 8:12 AM, David Boyes wrote:
About
the only thing missing is OSA Express L2 support, AFAIK -- which is
really useful to support VSWITCHes.
Can Flex do this either, yet?
I would assume that since there's now an Open Source QDIO Ethernet
driver for Linux, that that gives
Jay Maynard wrote:
On Wed, Sep 20, 2006 at 10:28:13PM +0800, John Summerfield wrote:
A nice fast 8-way Opteron would probably outrun the average PartnerWorld
Flex-ES box, but that's hardly an apples-to-apples comparison. :-)
I'd be content to judge their finest against the finest alternative
David Boyes wrote:
In such an environment, lack of VM might not matter so much, the
virtualisation could be done natively rather than in the emulated
environment.
Indeed. Simply run multiple copies of Hercules. This only works, of
course,
as long as you're not doing things that depend on
Sadly no :(
The impression that I get is that even though the driver code is open
sourced (for Linux), there is enough of the function still proprietary
to prevent Fundamental from making anything useful from it. I keep
asking about it and hope is still alive... :)
Adam Thornton wrote:
On
On Sep 20, 2006, at 4:48 PM, John Summerfield wrote:
I don't expect one could run up Adam's 4 virtual Linuxes, but I'd
expect one to get more than two or three.
Er, those were David's, not mine.
Adam
--
For LINUX-390
loopback mount comes in handy for accessing zLinux filesystems
from the host.
-- R;
- Original Message -
From: John Summerfield [EMAIL PROTECTED]
Sent: 09/20/2006 07:48 PM
To: LINUX-390@VM.MARIST.EDU
Subject: Re: Getting to 64-bit systems *legitimately*...
David Boyes wrote
On Sep 20, 2006, at 4:54 PM, Rich Smrcina wrote:
Sadly no :(
The impression that I get is that even though the driver code is open
sourced (for Linux), there is enough of the function still proprietary
to prevent Fundamental from making anything useful from it. I keep
asking about it and hope
: Linux on 390 Port [mailto:[EMAIL PROTECTED] On Behalf Of
McKown, John
Sent: September 18, 2006 17:23
To: LINUX-390@VM.MARIST.EDU
Subject: Re: Getting to 64-bit systems *legitimately*...
-Original Message-
From: Linux on 390 Port [mailto:[EMAIL PROTECTED] On
Behalf Of David Boyes
Sent
On Sep 19, 2006, at 6:30 AM, Peter Webb, Toronto Transit Commission
wrote:
Well, we just had a techy from our local IBM reseller in here
yesterday,
and he said they could sell us a FLEX based system that would run z/VM
5.2. I'm going to keep my eyes open for a flock of pigs flying past
until
Adam Thornton [EMAIL PROTECTED] wrote
snip...
Yeah, Hercules would let us get around that for the pure-Linux stuff
(although for *that* we could also just cross-compile from Intel if
we wanted). It doesn't help for the z/VM-integrated-with-Linux or
for the Linux-under-z/VM cases.
...snip
64-bit guests run on Flex-ES.
If you can *get* the 64-bit zSeries enablement code. That's the first (and
more critical) problem.
Just much more slowly than they need
to.
Separate (but related) problem.
My understanding is that IBM refuses to allow Flex-ES to be licensed
on 64-bit host
Thanks. I appreciate the clarification.
Peter
-Original Message-
From: Linux on 390 Port [mailto:[EMAIL PROTECTED] On Behalf Of
Adam Thornton
Sent: September 19, 2006 14:11
To: LINUX-390@VM.MARIST.EDU
Subject: Re: Getting to 64-bit systems *legitimately*...
On Sep 19, 2006, at 6:30 AM
On Sep 19, 2006, at 11:35 AM, David Boyes wrote:
Hercules is also, as far as I know,
slower on the same hardware than Flex-ES; one of its design goals has
been portability, and it explicitly trades performance for
portability. Point is, it's a nonstarter for a shop that wants to do
On Monday, 09/18/2006 at 04:48 AST, David Boyes [EMAIL PROTECTED]
wrote:
FWIW, VSE/ESA 2.7 will be withdrawn from service on 02/28/2007. The
current z/VSE 3.1 is still 31-bit also, though. z/VSE 4.1 will be the
first 64-bit version, no availability date on that yet.
Given this, I'd like to
On Monday, 09/18/2006 at 04:48 AST, David Boyes [EMAIL PROTECTED]
wrote:
Could someone please find out what the hold-up is? We've been told one
rumor is that IBM thinks nobody wants it -- I'd like to shout call! on
that assertion.
Oh, and that rumor is false. I suppose if we plugged our ears,
Given this, I'd like to pose again the question of why IBM has not
approved the 64-bit version of FlexES for public sale.
It's a business decision, the details of which are unlikely to be
discussed outside the company and to which few outside of the Inner
Circle
are even privy. Sorry.
I
On Sep 19, 2006, at 1:13 PM, Alan Altmark wrote:
On Monday, 09/18/2006 at 04:48 AST, David Boyes
[EMAIL PROTECTED]
wrote:
FWIW, VSE/ESA 2.7 will be withdrawn from service on 02/28/2007. The
current z/VSE 3.1 is still 31-bit also, though. z/VSE 4.1 will be
the
first 64-bit version, no
Ar Maw, 2006-09-19 am 16:20 -0400, ysgrifennodd David Boyes:
It's annoying, but understandable. At least the requirement has been
voiced and heard, and I can correct the error of the field weenies' ways
that the requirement has not been voiced.
You can all buy one IBM share each and each go
I might regret this, but I'm curious as to how one might pronounce _any_
of that.
Mark Post
-Original Message-
From: Linux on 390 Port [mailto:[EMAIL PROTECTED] On Behalf Of
Alan Cox
Sent: Tuesday, September 19, 2006 5:44 PM
To: LINUX-390@VM.MARIST.EDU
Subject: Re: Getting to 64-bit
On Sep 19, 2006, at 2:35 PM, Post, Mark K wrote:
I might regret this, but I'm curious as to how one might pronounce
_any_
of that.
As if you've just been forced to eat someone's leek.
_Henry V_, Act 5, scene 1.
Adam
--
For
Ar Maw, 2006-09-19 am 17:35 -0400, ysgrifennodd Post, Mark K:
I might regret this, but I'm curious as to how one might pronounce _any_
of that.
This is getting off topic a little but for the curious:
Well Ar is like you'd expect Maw is short for Mawrth and I guess
Maw alone would be pronounced
Adam Thornton wrote:
Yeah, Hercules would let us get around that for the pure-Linux stuff
(although for *that* we could also just cross-compile from Intel if
we wanted). It doesn't help for the z/VM-integrated-with-Linux or
for the Linux-under-z/VM cases. Hercules is also, as far as I know,
On Wed, Sep 20, 2006 at 07:46:54AM +0800, John Summerfield wrote:
I don't really understand what Flex-ES is - I have some idea it's some
hardware-plus-software imitation mainframe.
As I understand it, it's a software emulator. Fundamental Software does have
parallel and ESCON channel hardware
study language kit
recently as well so your timing is perfect! ;)
-Sam
-Original Message-
From: Linux on 390 Port [mailto:[EMAIL PROTECTED] On Behalf Of
Alan Cox
Sent: Tuesday, September 19, 2006 7:56 PM
To: LINUX-390@VM.MARIST.EDU
Subject: Re: Getting to 64-bit systems *legitimately
FWIW, VSE/ESA 2.7 will be withdrawn from service on 02/28/2007. The
current z/VSE 3.1 is still 31-bit also, though. z/VSE 4.1 will be the
first 64-bit version, no availability date on that yet.
Given this, I'd like to pose again the question of why IBM has not
approved the 64-bit version of
-Original Message-
From: Linux on 390 Port [mailto:[EMAIL PROTECTED] On
Behalf Of David Boyes
Sent: Monday, September 18, 2006 3:48 PM
To: LINUX-390@VM.MARIST.EDU
Subject: Getting to 64-bit systems *legitimately*...
FWIW, VSE/ESA 2.7 will be withdrawn from service on 02/28
38 matches
Mail list logo