Re: A Discussion about RLSE on RAID Drives with Chat GPT-4

2023-07-03 Thread Walt Farrell
Thanks, Hobart.

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


Re: A Discussion about RLSE on RAID Drives with Chat GPT-4

2023-07-02 Thread Hobart Spitz
Here goes:
Me: Describe the impacts of either disabling the RLSE subparameter of
SPACE= in z/OS JCL on RAID drives or having RLSE only release unused
extends on RAID drives. Consider the savings in avoiding unnecessary VTOC
updates. Which is better, changing RLSE to only release unused extends, or
disabling RLSE and running periodical utilities (vendor or site) to release
unused extends? Assume that the majority of dataset of the legacy type with
a limit of 16 extents. Consider and identify any program products or access
methods that already specify TYPE=T with the CLOSE macro. Consider, as an
alternative to the first cases, a new DISP= option, ASIS, which would
become OLD if the dataset exists and NEW if said dataset did not exist.

The Resource Limit Specification Exception (RLSE) subparameter of SPACE= in
z/OS Job Control Language (JCL) is designed to release any unused allocated
space when the data set is closed. This means that if your program
allocates more space than it uses, the RLSE option will make that unused
space available for other programs to use, which can be important in
ensuring efficient use of disk space.

Disabling RLSE can lead to wasted space if a job frequently over-allocates,
as unused allocated space remains assigned to the data set even after the
job has ended. On RAID drives, this can contribute to unnecessary
fragmentation and inefficient use of storage.

However, there can be a performance trade-off because releasing unused
space involves updating the Volume Table of Contents (VTOC), which is an
I/O operation that can impact system performance. Hence, in systems where
performance is critical and storage is less of a concern, you might prefer
to disable RLSE to avoid these VTOC updates.

In your scenario, where the majority of data sets are legacy types with a
limit of 16 extents, it may be advisable to consider how often these data
sets reach their maximum extent limit. If they often do, RLSE could
potentially result in many VTOC updates, affecting performance. Conversely,
if they rarely reach this limit, the impact of RLSE might be minimal.

As for the question of whether to change RLSE to release only unused
extends, or to disable RLSE and run periodic utilities to release unused
extends, this depends on your specific circumstances. The former approach
would likely lead to more frequent but smaller VTOC updates, while the
latter could result in less frequent but larger updates. In
high-performance, low-storage environments, the latter may be preferred. In
environments where storage is at a premium, the former may be the better
option.

If you're considering program products or access methods that already
specify TYPE=T with the CLOSE macro, this typically indicates that these
are temporary data sets. These data sets are usually deleted and their
space released automatically when the job ends, making RLSE redundant in
this context.

Lastly, regarding the new DISP= option, ASIS, which becomes OLD if the
dataset exists and NEW if it doesn't, this could offer more flexibility in
managing data sets. It could potentially reduce the need for JCL
modifications when rerunning jobs or handling rerun scenarios. However, it
would also require careful consideration of job flow and dependencies, as
it could have unexpected consequences if not properly managed.

In summary, the best approach depends on your specific circumstances, such
as the nature of your workloads, the typical size and number of extents in
your data sets, the performance and storage characteristics of your RAID
drives, and the specifics of your operating environment. It's advisable to
conduct performance and impact testing before making any significant
changes.
[image: User]
Me: In z/OS JCL RLSE is short for ReLeaSE.

Yes, you are correct. In IBM's z/OS Job Control Language (JCL), RLSE stands
for ReLeaSE. The RLSE keyword indicates that, when a job finishes, the
system should release all unused allocated space associated with a dataset.
This can be a useful strategy for managing disk space, especially in
situations where the exact amount of space needed may not be known in
advance and over-allocation might occur.

The impact of enabling or disabling RLSE really depends on the specific
context. For instance, if a dataset often ends up using less space than
allocated, having RLSE enabled can help save valuable disk space. However,
keep in mind that releasing space involves updating the Volume Table of
Contents (VTOC), which is an I/O operation and can potentially impact
system performance.

Therefore, deciding whether to use RLSE, or modify its behavior, or even to
run periodic utilities to manage unused space, should be based on an
assessment of your system's specific needs and constraints. It's all about
finding the right balance between efficient space utilization and system
performance.
[image: User]
Me: ASIS is a hypothetical proposal, not yet submited as a requirement.

I see, thank you for the clarification. The 

Re: A Discussion about RLSE on RAID Drives with Chat GPT-4

2023-07-01 Thread Walt Farrell
On Thu, 29 Jun 2023 18:10:06 -0500, Hobart Spitz  wrote:

>https://chat.openai.com/share/1718b445-7a89-47a3-ab23-b670aa8c2211

That URL gives a 404 error, for me.

Perhaps you could have your conversation again, and quote the conversation here 
directly next time?

-- 
Walt

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


Re: A Discussion about RLSE on RAID Drives with Chat GPT-4

2023-06-29 Thread Roger W Suhr
Would you rather pass data in move mode (*nix piping) or locate mode

Just remember, in LOCATE mode you can move your data once, in MOVE mode you'll 
have to move data twice!  But in the end it really depends on what you are 
going to do with the data record.

I know nothing about pipes.

Please let me know if you have any questions, or concerns!

Thank You!

Roger W Suhr

suhr...@gmail.com
563-581-9065

(from my personal laptop)

-Original Message-
From: IBM Mainframe Discussion List  On Behalf Of 
Hobart Spitz
Sent: Thursday, June 29, 2023 7:10 PM
To: IBM-MAIN@LISTSERV.UA.EDU
Subject: A Discussion about RLSE on RAID Drives with Chat GPT-4

https://chat.openai.com/share/1718b445-7a89-47a3-ab23-b670aa8c2211


OREXXMan
Q: What do you call the residence of the ungulate with the largest antlers?
A: A moose pad.
:-D
Would you rather pass data in move mode (*nix piping) or locate mode
(Pipes) or via disk (JCL)?  Why do you think you rarely see *nix commands with 
more than a dozen filters, while Pipelines specifications are commonly over 
100s of stages, and 1000s of stages are not uncommon.
REXX is the new C.

--
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


A Discussion about RLSE on RAID Drives with Chat GPT-4

2023-06-29 Thread Hobart Spitz
https://chat.openai.com/share/1718b445-7a89-47a3-ab23-b670aa8c2211


OREXXMan
Q: What do you call the residence of the ungulate with the largest antlers?
A: A moose pad.
:-D
Would you rather pass data in move mode (*nix piping) or locate mode
(Pipes) or via disk (JCL)?  Why do you think you rarely see *nix commands
with more than a dozen filters, while Pipelines specifications are commonly
over 100s of stages, and 1000s of stages are not uncommon.
REXX is the new C.

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