Jim,
I have not set up a memory shared pool in the hosting partition for virtualization I/O, but I will do that in my testing environment ASAP.
I found this Midrange archive post talking about that, so thanks for pointing me in that direction:
https://archive.midrange.com/midrange-l/201304/msg00907.html
+1
-------------
Jacob
-------------
From: Jim Oberholtzer <midrangel@xxxxxxxxxxxxxxxxx>
Sent: Thursday, August 22, 2024 9:42 AM
To: Midrange Systems Technical Discussion <midrange-l@xxxxxxxxxxxxxxxxxx>
Cc: Jacob Banda <jnbanda@xxxxxxxxxx>
Subject: Re: Memory and CPU Considerations for IBM i LPARs
Have you by chance set up a memory shared pool for your hosting environment, putting memory in there? That will force the I/O operations that IBM i virtualizes into that memory pool giving you significant control over it. Now you can size it large enough to avoid I/O issues with the hosted environments and isolate that activity away from *BASE.
If you have not moved the hosted environment into its own shared pool(s) then all that work and the work the host does in *BASE is mixed and interesting things can show up and hamper operations. I said "interesting" because hosting certainly can stay in *BASE successfully, but it's not in my view a best practice, unless that's the only thing IBM i does is host the other environments.
As to CPU and memory in the partitions you assign those in the HMC, so each partition has its own memory/CPU (Assuming you don't have memory sharing turned on) and CPU can vary if you have the processors set to uncapped.
--
Jim Oberholtzer
Chief Technical Architect
Agile Technology Architects
On Wed, Aug 21, 2024 at 4:08 PM Jacob Banda via MIDRANGE-L <midrange-l@xxxxxxxxxxxxxxxxxx <mailto:midrange-l@xxxxxxxxxxxxxxxxxx> > wrote:
So I have a new Power 10 set up with IBM i hosting i and Linux partitions,
managed with V10R3 vHMC. I have a good understanding of the workings of
Processing Units (PU) vs. Virtual Processor (vCPU) allotments in the
partition profiles and have been monitoring the workloads with the HMC
Performance Dashboard for Average and Maximum CPU consumption.
My questions are regarding assigning sufficient CPU resources to the client
partitions and identifying memory usage in the IBM i client partitions.
1. How the heck do I identify just how much memory is required for my
workloads in an IBM i partition? DSPSYSSTS just seems to dump the total
system main storage (memory), but I have a feeling that it's allocating
everything because we gave it a lot to begin with. How can I identify how
much I can cut back? I would REALLY like to cut back some memory on
partitions that we migrated from dedicated boxes with only 1 partition per
box.
2. Is there a rule of thumb for the PU to vCPU ratio on Power hardware? On
my x86 hosts I tend to shoot for 1:2. For mostly idle workloads, I use 1:4.
3. For Shared Processor Partitions, do you all try to set Entitled Capacity
(PU) to be close to average usage, and vCPU to peak usage, with the MAX PU
value set to match the vCPU max, or as close as possible? I read this on a
slidedeck published by Bjorn Roden during an IBM Edge 2015 conference.
Thanks,
-------------
Jacob
-------------
midrange.com
