Vtam error code

[Jake Anderson]

Hello

One of our application was reporting the below error. I was looking through
the SNA and IP codes but not able to find or am ignorant about the below
code


VTAM error RtnCd:100900 Sense: Cmd:23

Where exactly I can find the explanation for 100900 ?

Jake

--
For IBM-MAIN subscribe / signoff / archive access instructions,
send email to lists...@listserv.ua.edu with the message: INFO IBM-MAIN

Re: Irish data centers....an opportunity?

[Bill Johnson]

Correct. I copied the article from the NYT & then reposted the paragraph in the 
article which discussed the study. 



Heh - I don't think those are rankings - just (former) links from the
article in whatever publication Bill copied from.


> >    ...
> >The largest cloud data centers, sometimes the size of football fields,
> are owned and operated by big tech companies like Google, Microsoft, Amazon
> and Facebook.
> >    ...
> >Over the years, data center electricity consumption has been a story of
> economic incentives and technology advances combining to tackle a problem.
> >
> Do they use:
> o IBM z?
> o IBM supercomputers?
> o Others, such as overseas-sourced (specify)?
>

At one time Facebook published detailed specs for its homegrown PC servers,
in contrast to the likes of Google, Amazon, and Microsoft, for whom it's
all trade secrets. I've no idea if they've kept the specs current. Lynn
Wheeler wrote about this stuff a number of times when he was active on
IBM-MAIN, though mostly from an available-compute-power perspective rather
than a power efficiency one.

Tony H.

--
For IBM-MAIN subscribe / signoff / archive access instructions,
send email to lists...@listserv.ua.edu with the message: INFO IBM-MAIN




--
For IBM-MAIN subscribe / signoff / archive access instructions,
send email to lists...@listserv.ua.edu with the message: INFO IBM-MAIN

Re: Irish data centers....an opportunity?

[Tony Harminc]

On Sat, 11 Feb 2023 at 13:22, Paul Gilmartin <
042bfe9c879d-dmarc-requ...@listserv.ua.edu> wrote:

> On Sat, 11 Feb 2023 17:40:21 +, Bill Johnson wrote:
> >...
> >The digital services churned out by the world’s computer centers are
> multiplying, but their energy use is not, thanks to cloud computing, a new
> study says.
> >
> >   - Share on Facebook
> >   - Share on WhatsApp
> >   - Post on Twitter
> >   - Mail
> >
> Are these ranked?  Actual numbers would be interesting.  "Mail" surprises
> me.  But I mail few
> resources and I don't quote attachments.  In fact, I prune quotations.
>

Heh - I don't think those are rankings - just (former) links from the
article in whatever publication Bill copied from.


> >...
> >The largest cloud data centers, sometimes the size of football fields,
> are owned and operated by big tech companies like Google, Microsoft, Amazon
> and Facebook.
> >...
> >Over the years, data center electricity consumption has been a story of
> economic incentives and technology advances combining to tackle a problem.
> >
> Do they use:
> o IBM z?
> o IBM supercomputers?
> o Others, such as overseas-sourced (specify)?
>

At one time Facebook published detailed specs for its homegrown PC servers,
in contrast to the likes of Google, Amazon, and Microsoft, for whom it's
all trade secrets. I've no idea if they've kept the specs current. Lynn
Wheeler wrote about this stuff a number of times when he was active on
IBM-MAIN, though mostly from an available-compute-power perspective rather
than a power efficiency one.

Tony H.

--
For IBM-MAIN subscribe / signoff / archive access instructions,
send email to lists...@listserv.ua.edu with the message: INFO IBM-MAIN

Re: Irish data centers....an opportunity?

[Charles Mills]

And it is called Z. O'Ess, after all.

Charles


-Original Message-
From: IBM Mainframe Discussion List [mailto:IBM-MAIN@LISTSERV.UA.EDU] On Behalf 
Of Bill Johnson
Sent: Saturday, February 11, 2023 2:52 PM
To: IBM-MAIN@LISTSERV.UA.EDU
Subject: Re: Irish data centersan opportunity?

This is an interesting piece by 2 people, Jonathan Koomey & Eric Masanet who 
appear to be experts in data center electrical usage. They point out the flaws  
in some analysis.

https://www.sciencedirect.com/science/article/pii/S2542435121002117

Their analysis was also in the NY Times.


Sent from Yahoo Mail for iPhone


On Saturday, February 11, 2023, 3:23 PM, Doug  wrote:

I'd love to see the raw data they based this "research" on.

I have ALWAYS found, "If it sounds too good to be true, its usually 
is"


Doug Fuerst

-- Original Message --
From: "Bill Johnson" <0047540adefe-dmarc-requ...@listserv.ua.edu>
To: IBM-MAIN@listserv.ua.edu
Sent: 11-Feb-23 13:50:52
Subject: Re: Irish data centersan opportunity?

>I don’t know, but I imagine there is more detail in the scientific study it’s 
>based on. I don’t have access to it.
>
>The study findings were published on Thursday in an article in the journal 
>Science. It was a collaboration of five scientists at Northwestern University, 
>the Lawrence Berkeley National Laboratory and an independent research firm. 
>The project was funded by the Department of Energy and by a grant from a 
>Northwestern alumnus who is an environmental philanthropist.
>
>
>Sent from Yahoo Mail for iPhone
>
>
>On Saturday, February 11, 2023, 1:22 PM, Paul Gilmartin 
><042bfe9c879d-dmarc-requ...@listserv.ua.edu> wrote:
>
>On Sat, 11 Feb 2023 17:40:21 +, Bill Johnson wrote:
>>...
>>The digital services churned out by the world’s computer centers are 
>>multiplying, but their energy use is not, thanks to cloud computing, a new 
>>study says.
>>
>>  - Share on Facebook
>>  - Share on WhatsApp
>>  - Post on Twitter
>>  - Mail
>>
>Are these ranked?  Actual numbers would be interesting.  "Mail" surprises me.  
>But I mail few
>resources and I don't quote attachments.  In fact, I prune quotations.
>
>>...
>>The largest cloud data centers, sometimes the size of football fields, are 
>>owned and operated by big tech companies like Google, Microsoft, Amazon and 
>>Facebook.
>>...
>>Over the years, data center electricity consumption has been a story of 
>>economic incentives and technology advances combining to tackle a problem.
>>
>Do they use:
>o IBM z?
>o IBM supercomputers?
>o Others, such as overseas-sourced (specify)?
>
>--
>gil
>
>--
>For IBM-MAIN subscribe / signoff / archive access instructions,
>send email to lists...@listserv.ua.edu with the message: INFO IBM-MAIN
>
>
>
>
>--
>For IBM-MAIN subscribe / signoff / archive access instructions,
>send email to lists...@listserv.ua.edu with the message: INFO IBM-MAIN

--
For IBM-MAIN subscribe / signoff / archive access instructions,
send email to lists...@listserv.ua.edu with the message: INFO IBM-MAIN




--
For IBM-MAIN subscribe / signoff / archive access instructions,
send email to lists...@listserv.ua.edu with the message: INFO IBM-MAIN

--
For IBM-MAIN subscribe / signoff / archive access instructions,
send email to lists...@listserv.ua.edu with the message: INFO IBM-MAIN

Re: Irish data centers....an opportunity?

[Bill Johnson]

This is an interesting piece by 2 people, Jonathan Koomey & Eric Masanet who 
appear to be experts in data center electrical usage. They point out the flaws  
in some analysis.

https://www.sciencedirect.com/science/article/pii/S2542435121002117

Their analysis was also in the NY Times.


Sent from Yahoo Mail for iPhone


On Saturday, February 11, 2023, 3:23 PM, Doug  wrote:

I'd love to see the raw data they based this "research" on.

I have ALWAYS found, "If it sounds too good to be true, its usually 
is"


Doug Fuerst

-- Original Message --
From: "Bill Johnson" <0047540adefe-dmarc-requ...@listserv.ua.edu>
To: IBM-MAIN@listserv.ua.edu
Sent: 11-Feb-23 13:50:52
Subject: Re: Irish data centersan opportunity?

>I don’t know, but I imagine there is more detail in the scientific study it’s 
>based on. I don’t have access to it.
>
>The study findings were published on Thursday in an article in the journal 
>Science. It was a collaboration of five scientists at Northwestern University, 
>the Lawrence Berkeley National Laboratory and an independent research firm. 
>The project was funded by the Department of Energy and by a grant from a 
>Northwestern alumnus who is an environmental philanthropist.
>
>
>Sent from Yahoo Mail for iPhone
>
>
>On Saturday, February 11, 2023, 1:22 PM, Paul Gilmartin 
><042bfe9c879d-dmarc-requ...@listserv.ua.edu> wrote:
>
>On Sat, 11 Feb 2023 17:40:21 +, Bill Johnson wrote:
>>    ...
>>The digital services churned out by the world’s computer centers are 
>>multiplying, but their energy use is not, thanks to cloud computing, a new 
>>study says.
>>
>>  - Share on Facebook
>>  - Share on WhatsApp
>>  - Post on Twitter
>>  - Mail
>>
>Are these ranked?  Actual numbers would be interesting.  "Mail" surprises me.  
>But I mail few
>resources and I don't quote attachments.  In fact, I prune quotations.
>
>>    ...
>>The largest cloud data centers, sometimes the size of football fields, are 
>>owned and operated by big tech companies like Google, Microsoft, Amazon and 
>>Facebook.
>>    ...
>>Over the years, data center electricity consumption has been a story of 
>>economic incentives and technology advances combining to tackle a problem.
>>
>Do they use:
>o IBM z?
>o IBM supercomputers?
>o Others, such as overseas-sourced (specify)?
>
>--
>gil
>
>--
>For IBM-MAIN subscribe / signoff / archive access instructions,
>send email to lists...@listserv.ua.edu with the message: INFO IBM-MAIN
>
>
>
>
>--
>For IBM-MAIN subscribe / signoff / archive access instructions,
>send email to lists...@listserv.ua.edu with the message: INFO IBM-MAIN

--
For IBM-MAIN subscribe / signoff / archive access instructions,
send email to lists...@listserv.ua.edu with the message: INFO IBM-MAIN




--
For IBM-MAIN subscribe / signoff / archive access instructions,
send email to lists...@listserv.ua.edu with the message: INFO IBM-MAIN

Re: Question on use of LPARNAME, SYSNAME and SMFID

[Radoslaw Skorupka]

To be honest I did.
In the past I used each id different, however naming convention allowed 
easily guess remaining names.

Example
sysname = HRET, HREV, HREM, etc. multiple systems, not sysplexed
SMF ID = RET1, REV1, REM1, etc.
NJE node = NRET, NREV, NREM, etc.
sysplex = HRETPLEX or HRET - that was future. And for future sysplex 
members HR2T, HR3T...

Standard LPAR for HRET was LHRET. XHRET for DRP machine.
(it is not full list)
It wasn't pretty, but it was well documented and only one letter was 
important.
Why not use same name whenever possible? Well, the idea was to know for 
sure which of the IDs is displayed. It was intuitive.


--
Radoslaw Skorupka
Lodz, Poland



W dniu 11.02.2023 o 21:00, Rob Schramm pisze:

oh.. on that I agree.  I have always thought that it was silly to have a
sysname that didn't match or in some cases is related to in any way the
SMFID... but I see it alot.

I would love a reason from someone that kept sysname <> smfid.

Rob

On Sat, Feb 11, 2023 at 2:44 PM Radoslaw Skorupka <
0471ebeac275-dmarc-requ...@listserv.ua.edu> wrote:


As far as I understand the question is "what is the difference between
SMF ID and SYSNAME".
Or rather "Why on Earth have two identifiers, while there is always 1:1
correlation".
I agree, I see no reason to have SMF ID and sysname independent.
Among meny identifiers I can explain the purpose of JES2 NODE name, MAS
member name, LPAR name, TCPIP hostname, sysplex name, etc.
However I would like to know the reason if it exist.

My €0.02


--
Radoslaw Skorupka
Lodz, Poland



W dniu 10.02.2023 o 17:15, Matt Hogstrom pisze:

I’m doing some research involving historical SMF data.  It’s caused me

to wonder how engineers use the ,  and  symbols.
 From what I can see is that in most instances they are the same.  LPARNAME
appears to me to have little value in that if may or may not have an
affinity for a z/OS guest in terms of naming.

 and  seem to generally correlate.  I’m curious if there

are use cases where these are different and what the purpose might be?

Appreciate any insight  / best parties that people are using.

Matt Hogstrom
m...@hogstrom.org




--
For IBM-MAIN subscribe / signoff / archive access instructions,
send email to lists...@listserv.ua.edu with the message: INFO IBM-MAIN

Z/OS jobs in Eastern and Western Europe

[rpinion865]

What is z/is sysprog job market like in Eastern and Western Europe?

Sent from Proton Mail mobile

--
For IBM-MAIN subscribe / signoff / archive access instructions,
send email to lists...@listserv.ua.edu with the message: INFO IBM-MAIN

Re: Irish data centers....an opportunity?

[Doug]

I'd love to see the raw data they based this "research" on.

I have ALWAYS found, "If it sounds too good to be true, its usually 
is"



Doug Fuerst

-- Original Message --
From: "Bill Johnson" <0047540adefe-dmarc-requ...@listserv.ua.edu>
To: IBM-MAIN@listserv.ua.edu
Sent: 11-Feb-23 13:50:52
Subject: Re: Irish data centersan opportunity?


I don’t know, but I imagine there is more detail in the scientific study it’s 
based on. I don’t have access to it.

The study findings were published on Thursday in an article in the journal 
Science. It was a collaboration of five scientists at Northwestern University, 
the Lawrence Berkeley National Laboratory and an independent research firm. The 
project was funded by the Department of Energy and by a grant from a 
Northwestern alumnus who is an environmental philanthropist.


Sent from Yahoo Mail for iPhone


On Saturday, February 11, 2023, 1:22 PM, Paul Gilmartin 
<042bfe9c879d-dmarc-requ...@listserv.ua.edu> wrote:

On Sat, 11 Feb 2023 17:40:21 +, Bill Johnson wrote:

...
The digital services churned out by the world’s computer centers are 
multiplying, but their energy use is not, thanks to cloud computing, a new 
study says.

  - Share on Facebook
  - Share on WhatsApp
  - Post on Twitter
  - Mail


Are these ranked?  Actual numbers would be interesting.  "Mail" surprises me.  
But I mail few
resources and I don't quote attachments.  In fact, I prune quotations.


...
The largest cloud data centers, sometimes the size of football fields, are 
owned and operated by big tech companies like Google, Microsoft, Amazon and 
Facebook.
...
Over the years, data center electricity consumption has been a story of 
economic incentives and technology advances combining to tackle a problem.


Do they use:
o IBM z?
o IBM supercomputers?
o Others, such as overseas-sourced (specify)?

--
gil

--
For IBM-MAIN subscribe / signoff / archive access instructions,
send email to lists...@listserv.ua.edu with the message: INFO IBM-MAIN




--
For IBM-MAIN subscribe / signoff / archive access instructions,
send email to lists...@listserv.ua.edu with the message: INFO IBM-MAIN


--
For IBM-MAIN subscribe / signoff / archive access instructions,
send email to lists...@listserv.ua.edu with the message: INFO IBM-MAIN

Re: Question on use of LPARNAME, SYSNAME and SMFID

[Rob Schramm]

oh.. on that I agree.  I have always thought that it was silly to have a
sysname that didn't match or in some cases is related to in any way the
SMFID... but I see it alot.

I would love a reason from someone that kept sysname <> smfid.

Rob

On Sat, Feb 11, 2023 at 2:44 PM Radoslaw Skorupka <
0471ebeac275-dmarc-requ...@listserv.ua.edu> wrote:

> As far as I understand the question is "what is the difference between
> SMF ID and SYSNAME".
> Or rather "Why on Earth have two identifiers, while there is always 1:1
> correlation".
> I agree, I see no reason to have SMF ID and sysname independent.
> Among meny identifiers I can explain the purpose of JES2 NODE name, MAS
> member name, LPAR name, TCPIP hostname, sysplex name, etc.
> However I would like to know the reason if it exist.
>
> My €0.02
>
>
> --
> Radoslaw Skorupka
> Lodz, Poland
>
>
>
> W dniu 10.02.2023 o 17:15, Matt Hogstrom pisze:
> > I’m doing some research involving historical SMF data.  It’s caused me
> to wonder how engineers use the ,  and  symbols.
> From what I can see is that in most instances they are the same.  LPARNAME
> appears to me to have little value in that if may or may not have an
> affinity for a z/OS guest in terms of naming.
> >
> >  and  seem to generally correlate.  I’m curious if there
> are use cases where these are different and what the purpose might be?
> >
> > Appreciate any insight  / best parties that people are using.
> >
> > Matt Hogstrom
> > m...@hogstrom.org
> >
> > A generalist knows less and less about more and more till he knows
> nothing about everything
> > A specialist knows more and more about less and less till he knows
> everything about nothing
>
> --
> For IBM-MAIN subscribe / signoff / archive access instructions,
> send email to lists...@listserv.ua.edu with the message: INFO IBM-MAIN
>

--
For IBM-MAIN subscribe / signoff / archive access instructions,
send email to lists...@listserv.ua.edu with the message: INFO IBM-MAIN

Re: Question on use of LPARNAME, SYSNAME and SMFID

[Radoslaw Skorupka]

As far as I understand the question is "what is the difference between 
SMF ID and SYSNAME".
Or rather "Why on Earth have two identifiers, while there is always 1:1 
correlation".

I agree, I see no reason to have SMF ID and sysname independent.
Among meny identifiers I can explain the purpose of JES2 NODE name, MAS 
member name, LPAR name, TCPIP hostname, sysplex name, etc.

However I would like to know the reason if it exist.

My €0.02


--
Radoslaw Skorupka
Lodz, Poland



W dniu 10.02.2023 o 17:15, Matt Hogstrom pisze:

I’m doing some research involving historical SMF data.  It’s caused me to wonder how 
engineers use the ,  and  symbols.  From what I can see 
is that in most instances they are the same.  LPARNAME appears to me to have little value 
in that if may or may not have an affinity for a z/OS guest in terms of naming.

 and  seem to generally correlate.  I’m curious if there are use 
cases where these are different and what the purpose might be?

Appreciate any insight  / best parties that people are using.

Matt Hogstrom
m...@hogstrom.org

A generalist knows less and less about more and more till he knows nothing 
about everything
A specialist knows more and more about less and less till he knows everything 
about nothing


--
For IBM-MAIN subscribe / signoff / archive access instructions,
send email to lists...@listserv.ua.edu with the message: INFO IBM-MAIN

Re: Irish data centers....an opportunity?

[Bob Bridges]

This is just a reflex, but that's VERY unlikely.  Such predictions are almost 
always based on "if this trend continues...".  But trends never continue - 
never.

Mind you, sometimes they change for the worse.  But 27% doesn't sound plausible.

---
Bob Bridges, robhbrid...@gmail.com, cell 336 382-7313

/* a dangerous ambition more often lurks behind the specious mask of zeal 
for the rights of the people than under the forbidden appearance of zeal for 
the firmness and efficiency of government.  History will teach us that the 
former has been found a much more certain road to the introduction of despotism 
than the latter, and that of those men who have overturned the liberties of 
republics, the greatest number have begun their career by paying an obsequious 
court to the people; commencing demagogues, and ending tyrants.  -Alexander 
Hamilton, _Federalist_ #1 */

-Original Message-
From: IBM Mainframe Discussion List  On Behalf Of 
Dave Jones
Sent: Saturday, February 11, 2023 11:26

All good questions, Paul. And you are correct about the URL, too, thanks for 
fixing that.
The article does claim that data centres (sp?) could take up 27% of the [Irish] 
national electricity output by 2029.

--
For IBM-MAIN subscribe / signoff / archive access instructions,
send email to lists...@listserv.ua.edu with the message: INFO IBM-MAIN

Re: Irish data centers....an opportunity?

[Bill Johnson]

I don’t know, but I imagine there is more detail in the scientific study it’s 
based on. I don’t have access to it.

The study findings were published on Thursday in an article in the journal 
Science. It was a collaboration of five scientists at Northwestern University, 
the Lawrence Berkeley National Laboratory and an independent research firm. The 
project was funded by the Department of Energy and by a grant from a 
Northwestern alumnus who is an environmental philanthropist.


Sent from Yahoo Mail for iPhone


On Saturday, February 11, 2023, 1:22 PM, Paul Gilmartin 
<042bfe9c879d-dmarc-requ...@listserv.ua.edu> wrote:

On Sat, 11 Feb 2023 17:40:21 +, Bill Johnson wrote:
>    ...
>The digital services churned out by the world’s computer centers are 
>multiplying, but their energy use is not, thanks to cloud computing, a new 
>study says.
>  
>  - Share on Facebook
>  - Share on WhatsApp
>  - Post on Twitter
>  - Mail
>
Are these ranked?  Actual numbers would be interesting.  "Mail" surprises me.  
But I mail few
resources and I don't quote attachments.  In fact, I prune quotations.

>    ...
>The largest cloud data centers, sometimes the size of football fields, are 
>owned and operated by big tech companies like Google, Microsoft, Amazon and 
>Facebook.
>    ...
>Over the years, data center electricity consumption has been a story of 
>economic incentives and technology advances combining to tackle a problem.
>
Do they use:
o IBM z?
o IBM supercomputers?
o Others, such as overseas-sourced (specify)?

-- 
gil

--
For IBM-MAIN subscribe / signoff / archive access instructions,
send email to lists...@listserv.ua.edu with the message: INFO IBM-MAIN




--
For IBM-MAIN subscribe / signoff / archive access instructions,
send email to lists...@listserv.ua.edu with the message: INFO IBM-MAIN

Re: Question on use of LPARNAME, SYSNAME and SMFID

[Rob Schramm]

Some of this used to be more helpful for the suplex data sets that were
tied to the hardware like the coupling facility stuff.  And it comes into
play when you restoring on hardware that you want to switch to a different
data set and have it automatically come up.  Brain cell too may have been
lost in in the years but it was done because the Dr hardware was different
than the production hardware.  So we used the LPARNAME to help resolve the
sysplex data sets by use of the CEC.  At least that's how I think it used
to work.

Me personally I never try to discount a symbol until I get stuck with
having to use it. VBG

Rob

On Sat, Feb 11, 2023, 08:26 Matt Hogstrom  wrote:

> In almost all instances I’ve seen the word ‘PLEX’ is in the 
> variable in some form or another.  PRODPLEX, PLEXA1, …
>
> Matt Hogstrom
> m...@hogstrom.org
> +1-919-656-0564
> PGP Key: 0x90ECB270
> Facebook   LinkedIn <
> https://linkedin/in/mhogstrom>  Twitter 
>
> “It may be cognitive, but, it ain’t intuitive."
> — Hogstrom
>
>
>
> > On Feb 11, 2023, at 1:46 PM, Scott Chapman <
> 03fffd029d68-dmarc-requ...@listserv.ua.edu> wrote:
> >
> > There's a whole lot of PRODPLEX and SYSA and similar out there. But
> there's also a fair number of more creative names too.
>
>
> --
> For IBM-MAIN subscribe / signoff / archive access instructions,
> send email to lists...@listserv.ua.edu with the message: INFO IBM-MAIN
>

--
For IBM-MAIN subscribe / signoff / archive access instructions,
send email to lists...@listserv.ua.edu with the message: INFO IBM-MAIN

Re: Irish data centers....an opportunity?

[Paul Gilmartin]

On Sat, 11 Feb 2023 17:40:21 +, Bill Johnson wrote:
>...
>The digital services churned out by the world’s computer centers are 
>multiplying, but their energy use is not, thanks to cloud computing, a new 
>study says.
>   
>   - Share on Facebook
>   - Share on WhatsApp
>   - Post on Twitter
>   - Mail
>
Are these ranked?  Actual numbers would be interesting.  "Mail" surprises me.  
But I mail few
resources and I don't quote attachments.  In fact, I prune quotations.

>...
>The largest cloud data centers, sometimes the size of football fields, are 
>owned and operated by big tech companies like Google, Microsoft, Amazon and 
>Facebook.
>...
>Over the years, data center electricity consumption has been a story of 
>economic incentives and technology advances combining to tackle a problem.
>
Do they use:
o IBM z?
o IBM supercomputers?
o Others, such as overseas-sourced (specify)?

-- 
gil

--
For IBM-MAIN subscribe / signoff / archive access instructions,
send email to lists...@listserv.ua.edu with the message: INFO IBM-MAIN

Re: Irish data centers....an opportunity?

[Bill Johnson]

Not as bad as feared. And I’m an environmentalist.




Cloud Computing Is Not the Energy Hog That Had Been Feared

The digital services churned out by the world’s computer centers are 
multiplying, but their energy use is not, thanks to cloud computing, a new 
study says.
   
   - Share on Facebook
   - Share on WhatsApp
   - Post on Twitter
   - Mail
ImageMajd Bakar, a Google vice president. The largest cloud data centers are 
owned and operated by big tech companies like Google.Credit...Josh 
Edelson/Agence France-Presse — Getty Images
By Steve Lohr
Feb. 27, 2020
The computer engine rooms that power the digital economy have become 
surprisingly energy efficient.

A new study of data centers globally found that while their computing output 
jumped sixfold from 2010 to 2018, their energy consumption rose only 6 percent. 
The scientists’ findings suggest concerns that the rise of mammoth data centers 
would generate a surge in electricity demand and pollution have been greatly 
overstated.

The major force behind the improving efficiency is the shift to cloud 
computing. In the cloud model, businesses and individuals consume computing 
over the internet as services, from raw calculation and data storage to search 
and social networks.

The largest cloud data centers, sometimes the size of football fields, are 
owned and operated by big tech companies like Google, Microsoft, Amazon and 
Facebook.

Each of these sprawling digital factories, housing hundreds of thousands of 
computers, rack upon rack, is an energy-hungry behemoth. Some have been built 
near the Arctic for natural cooling and others beside huge hydroelectric plants 
in the Pacific Northwest.




Still, they are the standard setters in terms of the amount of electricity 
needed for a computing task. “The public thinks these massive data centers are 
energy bad guys,” said Eric Masanet, the lead author of the study. “But those 
data centers are the most efficient in the world.”

The study findings were published on Thursday in an article in the journal 
Science. It was a collaboration of five scientists at Northwestern University, 
the Lawrence Berkeley National Laboratory and an independent research firm. The 
project was funded by the Department of Energy and by a grant from a 
Northwestern alumnus who is an environmental philanthropist.

The new research is a stark contrast to often-cited predictions that energy 
consumption in the world’s data centers is on a runaway path, perhaps set to 
triple or more over the next decade. Those worrying projections, the study 
authors say, are simplistic extrapolations and what-if scenarios that focus 
mainly on the rising demand for data center computing.

By contrast, the new research is a bottom-up analysis that compiles information 
on data center processors, storage, software, networking and cooling from a 
range of sources to estimate actual electricity use. Enormous efficiency 
improvements, they conclude, have allowed computing output to increase sharply 
while power consumption has been essentially flat.




“We’re hopeful that this research will reset people’s intuitions about data 
centers and energy use,” said Jonathan Koomey, a former scientist at the 
Berkeley lab who is an independent researcher.

Over the years, data center electricity consumption has been a story of 
economic incentives and technology advances combining to tackle a problem.

>From 2000 to 2005, energy use in computer centers doubled. In 2007, the 
>Environmental Protection Agency forecast another doubling of power consumed by 
>data centers from 2005 to 2010.

In 2011, at the request of The New York Times, Mr. Koomey made an assessment of 
how much data center electricity consumption actually did increase between 2005 
and 2010. He estimated the global increase at 56 percent, far less than 
previously expected. The recession after the 2008 financial crisis played a 
role, but so did gains in efficiency. The new study, with added data, lowered 
that 2005 to 2010 estimate further.




But the big improvements have come in recent years. Since 2010, the study 
authors write in Science, “the data center landscape has changed dramatically.”

The tectonic shift has been to the cloud. In 2010, the researchers estimated 
that 79 percent of data center computing was done in smaller traditional 
computer centers, largely owned and run by non-tech companies. By 2018, 89 
percent of data center computing took place in larger, utility-style cloud data 
centers.

The big cloud data centers use tailored chips, high-density storage, so-called 
virtual-machine software, ultrafast networking and customized airflow systems — 
all to increase computing firepower with the least electricity.

“The big tech companies eke out every bit of efficiency for every dollar they 
spend,” said Mr. Masanet, who left Northwestern last month to join the faculty 
of the University of California, Santa Barbara.




Google is at the forefront. Its data centers 

Re: Irish data centers....an opportunity?

[Joel C. Ewing]

Interesting that Ireland & concern for electric power consumption by 
computers should appear together in a new context.


In late 2017 there were articles widely quoted (and since questioned on 
accuracy) that use of computers for mining cryptocurrency was estimated 
to consume annually more electrical power world-wide than the entire 
annual electric power consumption of Ireland.  The assumptions made in 
that estimate have caused its accuracy to be questioned, but the usage 
by this activity is still considered sufficiently significant that an 
increasing number of countries with stressed electric power grids have 
put restrictions on cryptocurrency mining.


Cryptocurrency mining makes the most sense in locales where there is 
cheap electricity available, which I gather is not the case in Ireland, 
where electricity is reportedly among the most expensive in Europe; so 
presumably the concerns in this article are about more conventional data 
center power usage.


    Joel C. Ewing

On 2/11/23 09:40, Dave Jones wrote:

Recently the BBC posted an article about how the grow in Irish data centers (or "centres" 
for the Brits) is causing a possible power crises. See "Can we make the internet less 
power-thirsty?" (https://www.bbc.com/news/business-64429819). Sounds like a great opportunity 
for IBM to highlight the sustainability of large numbers of Linux on z servers running on a z16 box.
Hopefully somebody at IBM is taking a hard look at this now.

And the Brits seem to get it:
-
He points out that using the term "cloud" is highly misleading, as it is "a very 
physical thing".

The cloud does not float in the atmosphere, it consists of computer servers 
with a vast appetite for electricity.
The Irish example highlights how a combination of environmental concerns and 
worries about capacity in the grid have triggered a race to save the reputation 
of the data centre industry.
--
DJ

...


--
Joel C. Ewing

--
For IBM-MAIN subscribe / signoff / archive access instructions,
send email to lists...@listserv.ua.edu with the message: INFO IBM-MAIN

Re: Irish data centers....an opportunity?

[Dave Jones]

All good questions, Paul. And you are correct about the URL, too, thanks for 
fixing that.
The article does claim that data centres (sp?) could take up 27% of the [Irish] 
national electricity output by 2029.
DJ

--
For IBM-MAIN subscribe / signoff / archive access instructions,
send email to lists...@listserv.ua.edu with the message: INFO IBM-MAIN

Re: Irish data centers....an opportunity?

[Paul Gilmartin]

On Sat, 11 Feb 2023 09:40:30 -0600, Dave Jones wrote:

>Recently the BBC posted an article about how the grow in Irish data centers 
>(or "centres" for the Brits) is causing a possible power crises. See "Can we 
>make the internet less power-thirsty?" 
>(https://www.bbc.com/news/business-64429819). Sounds like a great opportunity 
>for IBM to highlight the sustainability of large numbers of Linux on z servers 
>running on a z16 box. 
>Hopefully somebody at IBM is taking a hard look at this now.
>
Link on listserv.ua gets 404.  Perhaps: 
?

Do z systems, like personal systems, operate at reduced energy consumption when 
idle?
It's only a partial answer that the z is optimized for peak performance 24*7*52.

Popular media, driven by sensation, emphasize the demands of crypto mining.  
How does that
compare?  And what fraction of total energy use, including domestic, 
agriculture, transportation,
manufacturing ...?

-- 
gil

--
For IBM-MAIN subscribe / signoff / archive access instructions,
send email to lists...@listserv.ua.edu with the message: INFO IBM-MAIN

Irish data centers....an opportunity?

[Dave Jones]

Recently the BBC posted an article about how the grow in Irish data centers (or 
"centres" for the Brits) is causing a possible power crises. See "Can we make 
the internet less power-thirsty?" (https://www.bbc.com/news/business-64429819). 
Sounds like a great opportunity for IBM to highlight the sustainability of 
large numbers of Linux on z servers running on a z16 box. 
Hopefully somebody at IBM is taking a hard look at this now.

And the Brits seem to get it:
-
He points out that using the term "cloud" is highly misleading, as it is "a 
very physical thing".

The cloud does not float in the atmosphere, it consists of computer servers 
with a vast appetite for electricity.
The Irish example highlights how a combination of environmental concerns and 
worries about capacity in the grid have triggered a race to save the reputation 
of the data centre industry.
--
DJ

--
For IBM-MAIN subscribe / signoff / archive access instructions,
send email to lists...@listserv.ua.edu with the message: INFO IBM-MAIN

Re: Question on use of LPARNAME, SYSNAME and SMFID

[Peter Relson]

> the ,  and  symbols.

FWIW, the latter two are not symbols that z/OS provides. Obviously a customer 
could create them.

The LPARNAME can be used as a filter in processing of the IEASYMxx parmlib 
member (and others), as can HWNAME and VMUSERID

Peter Relson
z/OS Core Technology Design


--
For IBM-MAIN subscribe / signoff / archive access instructions,
send email to lists...@listserv.ua.edu with the message: INFO IBM-MAIN

Re: Question on use of LPARNAME, SYSNAME and SMFID

[Matt Hogstrom]

In almost all instances I’ve seen the word ‘PLEX’ is in the  variable 
in some form or another.  PRODPLEX, PLEXA1, … 

Matt Hogstrom
m...@hogstrom.org
+1-919-656-0564
PGP Key: 0x90ECB270
Facebook   LinkedIn 
  Twitter 

“It may be cognitive, but, it ain’t intuitive."
— Hogstrom



> On Feb 11, 2023, at 1:46 PM, Scott Chapman 
> <03fffd029d68-dmarc-requ...@listserv.ua.edu> wrote:
> 
> There's a whole lot of PRODPLEX and SYSA and similar out there. But there's 
> also a fair number of more creative names too. 


--
For IBM-MAIN subscribe / signoff / archive access instructions,
send email to lists...@listserv.ua.edu with the message: INFO IBM-MAIN

Re: Question on use of LPARNAME, SYSNAME and SMFID

[Scott Chapman]

Having looked at data from a whole lot of customer systems, I can say that 
SMFID and SYSNAME are often (but not always) the same. LPARNAME is very often 
different, although I appreciate it when there's at least some sort of visual 
link between it and SMFID/SYSNAME. E.G. SYSA and C1SYSA vs SYSA and C1LP4. Most 
sites do tend to have that sort of link between them, but some don't. It seems 
like that would make it easier to make a mistake while working on the HMC. 

There's a whole lot of PRODPLEX and SYSA and similar out there. But there's 
also a fair number of more creative names too. 

--
For IBM-MAIN subscribe / signoff / archive access instructions,
send email to lists...@listserv.ua.edu with the message: INFO IBM-MAIN