You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@cloudstack.apache.org by "sftcloud (via GitHub)" <gi...@apache.org> on 2023/06/01 12:47:31 UTC
[GitHub] [cloudstack] sftcloud opened a new issue, #7581: Compute OverCommit
sftcloud opened a new issue, #7581:
URL: https://github.com/apache/cloudstack/issues/7581
##### ISSUE TYPE
<!-- Pick one below and delete the rest -->
* Bug Report
* Improvement Request
##### COMPONENT NAME
<!--
-->
~~~
OverCommiting CPU
~~~
##### CLOUDSTACK VERSION
<!--
-->
~~~
4.17
~~~
##### OS / ENVIRONMENT
<!--
-->
~~~
VMware, KVM
~~~
##### SUMMARY
<!-- Explain the problem/feature briefly -->
try to overcommit cpu on Cloudstack but only MHz can be overcommitted and can't overcommit on the CPU cores.
am I wrong or can't be an overcommitted CPU core?
this is OpenStack overcommitting
The formula for the number of virtual instances on a compute node is (OR*PC)/VC, where:
OR
CPU overcommit ratio (virtual cores per physical core)
PC
Number of physical cores
VC
Number of virtual cores per instance
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: commits-unsubscribe@cloudstack.apache.org.apache.org
For queries about this service, please contact Infrastructure at:
users@infra.apache.org
Re: [I] Compute OverCommit [cloudstack]
Posted by "DaanHoogland (via GitHub)" <gi...@apache.org>.
DaanHoogland closed issue #7581: Compute OverCommit
URL: https://github.com/apache/cloudstack/issues/7581
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: commits-unsubscribe@cloudstack.apache.org
For queries about this service, please contact Infrastructure at:
users@infra.apache.org
[GitHub] [cloudstack] boring-cyborg[bot] commented on issue #7581: Compute OverCommit
Posted by "boring-cyborg[bot] (via GitHub)" <gi...@apache.org>.
boring-cyborg[bot] commented on issue #7581:
URL: https://github.com/apache/cloudstack/issues/7581#issuecomment-1571990225
Thanks for opening your first issue here! Be sure to follow the issue template!
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: commits-unsubscribe@cloudstack.apache.org
For queries about this service, please contact Infrastructure at:
users@infra.apache.org
[GitHub] [cloudstack] rajujith commented on issue #7581: Compute OverCommit
Posted by "rajujith (via GitHub)" <gi...@apache.org>.
rajujith commented on issue #7581:
URL: https://github.com/apache/cloudstack/issues/7581#issuecomment-1586604609
@sftcloud If you are looking for creating VMs with more vCPUs than what is available on the hypervisor that could be restricted by the hypervisor itself. This could be the possible reason for not exploring such options in CloudStack. Currently, the host CPU count is used as a capability constraint.
https://docs.vmware.com/en/VMware-vSphere/7.0/com.vmware.vsphere.vm_admin.doc/GUID-13AD347E-3B77-4A67-B3F4-4AC2230E4509.html
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: commits-unsubscribe@cloudstack.apache.org
For queries about this service, please contact Infrastructure at:
users@infra.apache.org
Re: [I] Compute OverCommit [cloudstack]
Posted by "rajujith (via GitHub)" <gi...@apache.org>.
rajujith commented on issue #7581:
URL: https://github.com/apache/cloudstack/issues/7581#issuecomment-3095402865
> I wonder what this would accomplish [@rajujith](https://github.com/rajujith) . would a VM that asks for 5 cores be able to run on a host with only 4 cores? would that make sense? the overcommit is in my opinion not sensible. there will never be more than four truly parallel threads possible. I think we should close this as ‘rejected’/‘not planned’. Would you agree?
Yes, we can close this as ‘rejected’/‘not planned’.
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: commits-unsubscribe@cloudstack.apache.org
For queries about this service, please contact Infrastructure at:
users@infra.apache.org
[GitHub] [cloudstack] rajujith commented on issue #7581: Compute OverCommit
Posted by "rajujith (via GitHub)" <gi...@apache.org>.
rajujith commented on issue #7581:
URL: https://github.com/apache/cloudstack/issues/7581#issuecomment-1573246874
Hi @sftcloud here is the answer from the cloudstack admin guide, I hope it answers.
> Service offering limits (e.g. 1 GHz, 1 core) are strictly enforced for core count. For example, a guest with a service offering of one core will have only one core available to it regardless of other activity on the Host.
>
> Service offering limits for gigahertz are enforced only in the presence of contention for CPU resources. For example, suppose that a guest was created with a service offering of 1 GHz on a Host that has 2 GHz cores, and that guest is the only guest running on the Host. The guest will have the full 2 GHz available to it. When multiple guests are attempting to use the CPU a weighting factor is used to schedule CPU resources. The weight is based on the clock speed in the service offering. Guests receive a CPU allocation that is proportionate to the GHz in the service offering. For example, a guest created from a 2 GHz service offering will receive twice the CPU allocation as a guest created from a 1 GHz service offering.
http://docs.cloudstack.apache.org/en/latest/adminguide/hosts.html#over-provisioning-and-service-offering-limits
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: commits-unsubscribe@cloudstack.apache.org
For queries about this service, please contact Infrastructure at:
users@infra.apache.org
[GitHub] [cloudstack] sftcloud commented on issue #7581: Compute OverCommit
Posted by "sftcloud (via GitHub)" <gi...@apache.org>.
sftcloud commented on issue #7581:
URL: https://github.com/apache/cloudstack/issues/7581#issuecomment-1573324780
Hello and thanks for reply @rajujith
yes, I have already read these documents. my question is why do cant overcommit CPU cores In addition to GHz
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: commits-unsubscribe@cloudstack.apache.org
For queries about this service, please contact Infrastructure at:
users@infra.apache.org
Re: [I] Compute OverCommit [cloudstack]
Posted by "DaanHoogland (via GitHub)" <gi...@apache.org>.
DaanHoogland commented on issue #7581:
URL: https://github.com/apache/cloudstack/issues/7581#issuecomment-3061410420
I wonder what this would accomplish @rajujith . would a VM that asks for 5 cores be able to run on a host with only 4 cores? would that make sense? the overcommit is in my opinion not sensible. there will never be more than four truly parallel threads possible. I think we should close this as ‘rejected’/‘not planned’. Would you agree?
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: commits-unsubscribe@cloudstack.apache.org
For queries about this service, please contact Infrastructure at:
users@infra.apache.org