On Monday, 08/03/2020 at 04:00 GMT, Mariusz Walczak
wrote:
> How to properly use zVM and zLinux virtualization technology to increase
> Openshift Cluster capacity from 12 vCPU to 24 vCPU, without degrading
> performance. Which of the approaches below is correct ?
> - to have 6 Worker Nodes (zLinu
I'd say have multiple guests. Let's NOT forget SPOF. (Well, you have a
SPOF if it's in only one z/VM LPAR but at least you have multiple guests
that can be serviced at different times.)
I usually like a number of small guests over a single large guest.
Especially when there are multiple guests
Hello,
I also thought that enabling SMT will degrade performance of a single
threaded process, but I could not find anyone to confirm that. Thank you
Christian.
Alan:
Postgres is not constrained by having only 4 cores. It's running fine with
1 vCPU. The problem is with overall Openshift Cluster C
On 02.08.20 06:36, Alan Altmark wrote:
>
> A physical core has a certain amount of “horsepower” in it. It can, at top
> speed do X amount of work.
>
> In SMT, you split the core in half, creating two execution contexts (CPUs)
> instead of just one. The two CPUs share resources on the physical c
On Sunday, 08/02/2020 at 06:46 GMT, Mariusz Walczak
wrote:
> The motivation to increase vCPU on zLinux was to increase the capacity
of
> Openshift Cluster. We have 3 worker nodes, 4 vCPU each = 12 vCPU on
> cluster. This allows us to run 7 Postgres databases in parallel (1 vCPU
> each). We would
The motivation to increase vCPU on zLinux was to increase the capacity of
Openshift Cluster. We have 3 worker nodes, 4 vCPU each = 12 vCPU on
cluster. This allows us to run 7 Postgres databases in parallel (1 vCPU
each). We would like to have 24 vCPU on the cluster, but not degrade
performance of
A physical core has a certain amount of “horsepower” in it. It can, at top
speed do X amount of work.
In SMT, you split the core in half, creating two execution contexts (CPUs)
instead of just one. The two CPUs share resources on the physical core,
but the total horsepower doesn’t increase. In
Mariusz,
Does your workload really require 16 virtual CPUs, or are you relying on a
vendor to drive your decision making?
A good performance monitor will be a big help.
Rich Smrcina
Sr. Systems Engineer
Velocity Software Inc.
Main: (650) 964-8867
Main: (877) 964-8867
r...@velocitysoftware.com
Hello Mark,
Yes, that is what I meant.
Is there a way to increase zLinux capacity without buying physical IFL on
Mainframe? Can I make use of LPAR and zVM virtualization features to
achieve this?
I already learnt that enabling SMT on zVM doubled our vCPU count (from 4 to
8) on Hypervisor. After e
On 7/31/20 7:46 PM, Mariusz Walczak wrote:
> We have 4 IFL on Mainframe box, 4 IFL on zVM and 4 cpu on zLinux. I'd like
> to gain zLinux capacity (run more processes) and increase to 16 cpu. Will I
> degrade performance of a single threaded workload if I do this?
Do you mean you want to specify 16
] Overcommitting zLinux CPU
Hello Group,
We have 4 IFL on Mainframe box, 4 IFL on zVM and 4 cpu on zLinux. I'd like
to gain zLinux capacity (run more processes) and increase to 16 cpu. Will I
degrade performance of a single threaded workload if I do this?
All the best,
Ma
Hello Group,
We have 4 IFL on Mainframe box, 4 IFL on zVM and 4 cpu on zLinux. I'd like
to gain zLinux capacity (run more processes) and increase to 16 cpu. Will I
degrade performance of a single threaded workload if I do this?
All the best,
Mariusz
--
12 matches
Mail list logo