In 54be8afc026d0017f...@prv-mh.provo.novell.com, on 01/20/2015
at 03:06 PM, Mark Post mp...@suse.com said:
You have to understand, CP is the nucleus of z/VM.
I've understood for decades what CP was, TYVM.
There are pieces of it that do normal operating system things,
Just as there are
In 54bce8fd026d0017f...@prv-mh.provo.novell.com, on 01/19/2015
at 09:22 AM, Mark Post mp...@suse.com said:
Of course not, but the things you were talking about are not part of
the hypervisor features of CP, but the OS itself.
Untrue; CP includes code for error handling. and the port of,
On 1/19/2015 at 04:10 PM, Shmuel Metz (Seymour J.)
shmuel+ibm-m...@patriot.net wrote:
In 54bce8fd026d0017f...@prv-mh.provo.novell.com, on 01/19/2015
at 09:22 AM, Mark Post mp...@suse.com said:
Of course not, but the things you were talking about are not part of
the hypervisor features
On 1/18/2015 at 10:57 AM, Shmuel Metz (Seymour J.)
shmuel+ibm-m...@patriot.net wrote:
In 54bab26b026d0017f...@prv-mh.provo.novell.com, on 01/17/2015
at 05:05 PM, Mark Post mp...@suse.com said:
What you're talking about aren't features of a hypervisor, per se,
but operating systems in
was
several times larger effort than the straight-forward ports ... *AND*
hardware field support said they wouldn't maintain system w/o it.
re:
http://www.garlic.com/~lynn/2015.html#43 z13 new(?) characteristics from
RedBook
http://www.garlic.com/~lynn/2015.html#44 z13 new(?) characteristics from
In 54bab26b026d0017f...@prv-mh.provo.novell.com, on 01/17/2015
at 05:05 PM, Mark Post mp...@suse.com said:
What you're talking about aren't features of a hypervisor, per se,
but operating systems in general.
What is CP, chopped liver?
--
Shmuel (Seymour J.) Metz, SysProg and JOAT
In 54b8fa04026d0017e...@prv-mh.provo.novell.com, on 01/16/2015
at 09:46 AM, Mark Post mp...@suse.com said:
You'll need to be a little more verbose. What about error recovery?
Does KVM on a bare LPAR have code to recover from I/O, memory and
processor failures? Does it have code to record
On 1/17/2015 at 06:37 PM, Shmuel Metz (Seymour J.)
shmuel+ibm-m...@patriot.net wrote:
In 54b8fa04026d0017e...@prv-mh.provo.novell.com, on 01/16/2015
at 09:46 AM, Mark Post mp...@suse.com said:
You'll need to be a little more verbose. What about error recovery?
Does KVM on a bare
On Sat, 17 Jan 2015 17:05:15 -0700, Mark Post wrote:
So, we don't just do z/VM, KVM, or LPARs, we do them all.
Thank you Mark, nice synopsis of what's do-able.
Now, if I can just find a customer that would do likewise ... ;-)
Shane ...
Mark Post wrote:
I note a SoD to include KVM on the z13.
Hopefully this should allow configurations that make this debate
moot - z/VM should be not needed at all.
Dave Gibney wrote:
If you can live with 85 or less zLinux instances :)
You are not limited to 85 Linux instances with KVM in the
On Fri, 16 Jan 2015 19:51:29 +0800, Timothy Sipples wrote:
KVM is not PR/SM. PR/SM is always boss. Everything, including KVM, runs
within an LPAR.
Hmmm, that was my reading of the somewhat obtuse SoD in the announcement.
Timothy obviously has access to resources the rest of us would love.
I
On Thu, 15 Jan 2015 13:49:16 -0600, John McKown wrote:
5) SMT (hyperthreading) only on IFL and zIIP engines (not CPs). Apparently
when running SMT, the individual threads can't match the speed of a non-SMT
CP, but their aggregate power may.
I think of it this way. Remember in the old days when
In 4988215587123941.wa.m42tomibmmainyahoo@listserv.ua.edu, on
01/16/2015
at 07:16 AM, Tom Marchant
000a2a8c2020-dmarc-requ...@listserv.ua.edu said:
Remember in the old days when we ran uniprocessors.
Indeed.
Every time one job accessed DASD, it had to wait for the I/O
operation to
Tom Marchant wrote:
begin extract
In this way, at least some of the time that the processor is idle
waiting for data from memory, it is able to do useful work.
/end extract
and I should reformulate this as
In this way at least some of the time that the processor would
otherwise be idle waiting
On Fri, Jan 16, 2015 at 7:16 AM, Tom Marchant
000a2a8c2020-dmarc-requ...@listserv.ua.edu wrote:
On Thu, 15 Jan 2015 13:49:16 -0600, John McKown wrote:
5) SMT (hyperthreading) only on IFL and zIIP engines (not CPs). Apparently
when running SMT, the individual threads can't match the speed
So, as an extremely silly example. SMT will not help in the following
program: I.e. in a hard loop which uses data instructions
There are exceptions to every rule. If that’s the type of workload you run,
turn SMT off.
Bob Shannon
Rocket Software
Rocket
Good reminder, Shane. IBM has issued a Statement of Direction relating to
KVM on zSystems. IBM's plans could change.
Timothy Sipples
IT Architect Executive, Industry Solutions, IBM z Systems,
On 1/15/2015 at 06:02 PM, Shane Ginnane ibm-m...@tpg.com.au wrote:
I note a SoD to include KVM on the z13.
Hopefully this should allow configurations that make this debate moot - z/VM
should be not needed at all.
I wonder how that affects SUSE install scripts ...
SUSE has shipped KVM for
On Fri, Jan 16, 2015 at 8:24 AM, Bob Shannon bshan...@rocketsoftware.com
wrote:
So, as an extremely silly example. SMT will not help in the following
program: I.e. in a hard loop which uses data instructions
There are exceptions to every rule. If that’s the type of workload you
run, turn
On 1/16/2015 at 06:51 AM, Timothy Sipples sipp...@sg.ibm.com wrote:
Mark Post wrote:
I note a SoD to include KVM on the z13.
Hopefully this should allow configurations that make this debate
moot - z/VM should be not needed at all.
No, I didn't.
Mark Post
On 16/01/2015 11:16 PM, John McKown wrote:
On Fri, Jan 16, 2015 at 8:24 AM, Bob Shannon bshan...@rocketsoftware.com
wrote:
So, as an extremely silly example. SMT will not help in the following
program: I.e. in a hard loop which uses data instructions
There are exceptions to every rule. If
On Fri, Jan 16, 2015 at 9:38 AM, David Crayford dcrayf...@gmail.com wrote:
On 16/01/2015 11:16 PM, John McKown wrote:
On Fri, Jan 16, 2015 at 8:24 AM, Bob Shannon bshan...@rocketsoftware.com
wrote:
So, as an extremely silly example. SMT will not help in the following
program: I.e. in a
In 54b8e4c0026d0017e...@prv-mh.provo.novell.com, on 01/16/2015
at 08:15 AM, Mark Post mp...@suse.com said:
For shops that have never run z/VM before, KVM could very well be
good enough to get started with virtualizing guests on System z.
What about error recovery?
--
Shmuel
On 1/16/2015 at 11:29 AM, Shmuel Metz (Seymour J.)
shmuel+ibm-m...@patriot.net wrote:
In 54b8e4c0026d0017e...@prv-mh.provo.novell.com, on 01/16/2015
at 08:15 AM, Mark Post mp...@suse.com said:
For shops that have never run z/VM before, KVM could very well be
good enough to get started
000a2a8c2020-dmarc-requ...@listserv.ua.edu (Tom Marchant) writes:
Today's processors have cache because main memory is _really_ slow
compared to the processor. When the processor accesses something at a
memory address, if the data at that location is in the cache, the
processor can access
like Batman
http://www.garlic.com/~lynn/2015.html#43 z13 new(?) characteristics from
RedBook
--
virtualization experience starting Jan1968, online at home since Mar1970
--
For IBM-MAIN subscribe / signoff / archive access
On Fri, Jan 16, 2015 at 11:16 AM, Anne Lynn Wheeler l...@garlic.com
wrote:
snip
... snip ...
... this was pipelined so wasn't serialized ... so there has been
shrinking difference between popular cisc and risc for a couple decades.
http://en.wikipedia.org/wiki/Instruction_pipeline
of the executable on disk. Said compiled code is
foot printed and recompiled if the TIMI object is change or, sometimes,
when maintenance is applied to the i system software. I found the concept
fascinating.
re:
http://www.garlic.com/~lynn/2015.html#44 z13 new(?) characteristics from
RedBook
lowmid
On 1/15/2015 at 02:49 PM, John McKown john.archie.mck...@gmail.com wrote:
10) Curious statement:
quote
If only Linux on z Systems is to be run under z/VM, then a z/VM mode LPAR
is not required,
and we suggest that a Linux-only LPAR be used instead.
/quote
I would say that's true today,
On 1/15/2015 at 02:53 PM, Chase, John jch...@ussco.com wrote:
I believe that's because z/VM is significantly cheaper if run in an
IFL-only LPAR.
That certainly used to be true, but I'm not at all sure it still is the case.
If I'm remembering right, z/VM licensing is the same for both CPs
On Thu, Jan 15, 2015 at 1:53 PM, Chase, John jch...@ussco.com wrote:
-Original Message-
From: IBM Mainframe Discussion List On Behalf Of John McKown
Sent: Thursday, January 15, 2015 1:49 PM
I'm reading the Redbook mentioned by Timothy Stipples on the z13. Some
interesting
-Original Message-
From: IBM Mainframe Discussion List On Behalf Of John McKown
Sent: Thursday, January 15, 2015 1:49 PM
I'm reading the Redbook mentioned by Timothy Stipples on the z13. Some
interesting things, to me.
[ snip ]
10) Curious statement:
quote
If only Linux on z
On Thu, 15 Jan 2015 13:18:08 -0700, Mark Post wrote:
On 1/15/2015 at 02:53 PM, Chase, John jch...@ussco.com wrote:
I believe that's because z/VM is significantly cheaper if run in an
IFL-only LPAR.
That certainly used to be true, but I'm not at all sure it still is the case.
If I'm
-Original Message-
From: IBM Mainframe Discussion List [mailto:IBM-MAIN@LISTSERV.UA.EDU]
On Behalf Of Shane Ginnane
Sent: Thursday, January 15, 2015 3:03 PM
To: IBM-MAIN@LISTSERV.UA.EDU
Subject: Re: z13 new(?) characteristics from RedBook
On Thu, 15 Jan 2015 13:18:08 -0700, Mark
-302-7535 Office
323-715-0595 Mobile
jo.skip.robin...@sce.com
-Original Message-
From: IBM Mainframe Discussion List [mailto:IBM-MAIN@LISTSERV.UA.EDU] On Behalf
Of Mark Post
Sent: Thursday, January 15, 2015 12:18 PM
To: IBM-MAIN@LISTSERV.UA.EDU
Subject: Re: z13 new(?) characteristics from
fast enough.
-Original Message-
From: IBM Mainframe Discussion List [mailto:IBM-MAIN@LISTSERV.UA.EDU] On Behalf
Of J O Skip Robinson
Sent: Thursday, January 15, 2015 2:07 PM
To: IBM-MAIN@LISTSERV.UA.EDU
Subject: Re: z13 new(?) characteristics from RedBook
The Linux-only option is not new
W dniu 2015-01-15 o 23:07, J O Skip Robinson pisze:
The Linux-only option is not new. Our z12 and z196 Linux-under-VM LPARs are
defined with the 'LINUX only' option. I don't recall an explicit reason for the
recommendation.
IMHO Linux-only LPAR type is older than VM LPAR.
--
Radoslaw
I'm reading the Redbook mentioned by Timothy Stipples on the z13. Some
interesting things, to me.
1) No zAAPs. So it is Java on your zIIPs now. But up to 2 zIIPs per CP may
be ordered.
1.5) LPAR can exceed 2 zIIPs per assigned CP. I.e. a CEC with 2 CPs 4
zIIPs can have an LPAR with 1 CP and 3
John McKown writes:
2) new type of CP: IFP - Integrated Firmware Processor, like a SAP, but
for
the native PCIe features such as 10 Gb RoGE and zEDC Express
Yes, but you don't even have to think about it. The system comes
pre-configured with the IFP at no additional charge, it's invisible, and
39 matches
Mail list logo
