Re: CPU Overprovisioning
Assuming you are on KVM...total number of Shares = total number of Mhz (cores * Mhz) / cpuOverprovisioningFactor - cpu shares get changed (after changing cpu overprovisioning) only when you stop and start an existing VM. So i.e. 2 vCPU of 2000 MHz VM, with CPU overprovisioning of 2 will get (2*2000)/2= 2000 CPU shares In that regards, there are no "reservation" specifically, but cpu shares are "engaged" only when there is shortage of CPU cycles on the host, otherwise is not applicable. CPU cap has been implemented for KVM only in 4.12 (if not mistaken), but in general even if CPU cap has been set on the offerings, if changing cpu overprovisioning factor, cpu cap will NOT change on hypervisor side (can confirm for XS and VMware but expect same for KVM in 4.12) - i.e. it always stays the same. Hope that helps, Andrija On Sun, Jul 7, 2019, 18:04 Fariborz Navidan wrote: > Hello, > > How VMs receive CPU shares when cpu over provisioning factor is increased > and CPU cap is disabled for them? > > Thanks >
CPU Overprovisioning
Hello, How VMs receive CPU shares when cpu over provisioning factor is increased and CPU cap is disabled for them? Thanks
Re: Cpu Overprovisioning factor
No (currently). Perhaps in next year or so, we *might* have some changes around that, but atm - no. Andrija On Wed, 26 Jun 2019 at 14:52, Fariborz Navidan wrote: > Hello All, > > Is there any way to force ACS to take into consideration the new cpu > overprovision factor without having to shoutdown lots of VMs on the host? > > Thanks > -- Andrija Panić
Cpu Overprovisioning factor
Hello All, Is there any way to force ACS to take into consideration the new cpu overprovision factor without having to shoutdown lots of VMs on the host? Thanks
Re: AW: cpu overprovisioning
I can confirm that stopping the machines and then making them run again (not with the command reboot but first stop and then start) the percentage reflects the correct proportion of GHz GHz allocated to available for moltipliati factor overprovisioning. Thanks Il 22/04/2015 12:05, S. Brüseke - proIO GmbH ha scritto: Dashboard is not wrong. You only have these resources left in your CS. Here is an example as far as I remember: Dashboard shows 100 GHz / 180 Ghz (cpu over provisioning is 1 / 3 Hosts each 24x 2.5Ghz) You deploy 10 vms with 1 Ghz Dashboard shows 110 Ghz / 180 Ghz (cpu over provisioning is 1 / 3 Hosts each 24x 2.5Ghz) You change cpu over provisioning to 4 Dashboard shows 440 Ghz / 720 Ghz (cpu over provisioning is 4 / 3 Hosts each 24x 2.5Ghz) You stop and start all vms Dashboard shows 110 Ghz / 720 Ghz Mit freundlichen Grüßen / With kind regards, Swen Brüseke -Ursprüngliche Nachricht- Von: Abhinandan Prateek [mailto:abhinandan.prat...@shapeblue.com] Gesendet: Mittwoch, 22. April 2015 06:35 An: users@cloudstack.apache.org Betreff: Re: cpu overprovisioning Can we fix the dashboard to reflect the available capacity given an over commit ? On 22-Apr-2015, at 9:56 am, Bharat Kumar bharat.ku...@citrix.com wrote: Also In case of change in the overcommit value the total capacity will change instantaneously, but the used resource and the total available will change when the capacity checker thread runs. The interval at which this will run can be changed from the global settings. Thanks, Bharat. On 22-Apr-2015, at 9:50 am, Bharat Kumar bharat.ku...@citrix.com wrote: Hi, The change in cpu overcommit factor will not change the amount of resource that are available to you. It will change the way you want to use the free resource available at that time. It won't change what was already allocated. for example if you have deployed the VMs with overcommit say 2 and after a while you change the overcommit to 3, the used resource will be scaled based on the change. changing the overcommit cannot create resource. It can only change the way you want to use the free resource. So now after the change in overcommit you can deploy 3 times more VMs (of a given service offering) than usual using the the resource that is free at the time of changing the overcommit value. The perviously allocated resource cannot be freed until you restart the VMs. This link will tell you how resource allocation calculations are made. https://cwiki.apache.org/confluence/display/CLOUDSTACK/CPU+and+RAM+Ov ercommit Thanks, Bharat. On 21-Apr-2015, at 11:20 pm, Rafael Weingärtner rafaelweingart...@gmail.commailto:rafaelweingart...@gmail.com wrote: I have not looked at the code, but that seems odd. Restarting VMs instances to update the resource usage/resource availability when changing the overprovisioning factor. On Tue, Apr 21, 2015 at 12:51 PM, S. Brüseke - proIO GmbH s.brues...@proio.commailto:s.brues...@proio.com wrote: Please try to stop and start the vm. Maybe reboot is not working here. You should start to see more free CPU after the first vm. Mit freundlichen Grüßen / With kind regards, Swen Brüseke -Ursprüngliche Nachricht- Von: Ugo Vasi [mailto:ugo.v...@procne.it] Gesendet: Dienstag, 21. April 2015 16:40 An: users@cloudstack.apache.orgmailto:users@cloudstack.apache.org Betreff: Re: AW: cpu overprovisioning Hi Swen, I try rebboting 2 vm but the amount of cpu MHz is not changed. Do I have to restart all vm before you see a change? Il 21/04/2015 16:16, S. Brüseke - proIO GmbH ha scritto: This is because the factor of overprovisioning is attached to the instance too! And this factor is only changing after rebooting the instance. So after a change of cpu.overprovisioning.factor you need to reboot all instances on this cluster which were running before this change was made. Mit freundlichen Grüßen / With kind regards, Swen Brüseke -Ursprüngliche Nachricht- Von: Ugo Vasi [mailto:ugo.v...@procne.it] Gesendet: Dienstag, 21. April 2015 16:06 An: users@cloudstack.apache.orgmailto:users@cloudstack.apache.org Betreff: Re: cpu overprovisioning If I change the over-provisioning ratio in cluster-relative settings (infrastructure-cluser-cluster-name-settings) the dashboard show the sum of real GHz the overprovisioned amount of GHz (324GHz) as aspected, but after a while also the sum of Ghz is multiplied by the same factor making it unnecessary... Il 21/04/2015 15:26, Bharat Kumar ha scritto: In case of cloudstack, cpu capacity for host is total of cpus * no of Ghz * overporvisoning. total capacity = sum of capacities of individual hosts. Thanks, Bharat. On 21-Apr-2015, at 6:49 pm, Abhinandan Prateek abhinandan.prat...@shapeblue.commailto:abhinandan.prat...@shapeblue.com wrote: Available CPU will be 3 times the actual CPU when over provisioned by 3. The UI not showing the over provisioned value seems like a bug. -abhi On 21-Apr-2015, at 6:34 pm, Ugo Vasi ugo.v
Re: cpu overprovisioning
Thank you guys for your inputs, will check it out soon. Regards, -abhi On 22-Apr-2015, at 6:42 pm, Ugo Vasi ugo.v...@procne.it wrote: I can confirm that stopping the machines and then making them run again (not with the command reboot but first stop and then start) the percentage reflects the correct proportion of GHz GHz allocated to available for moltipliati factor overprovisioning. Thanks Il 22/04/2015 12:05, S. Brüseke - proIO GmbH ha scritto: Dashboard is not wrong. You only have these resources left in your CS. Here is an example as far as I remember: Dashboard shows 100 GHz / 180 Ghz (cpu over provisioning is 1 / 3 Hosts each 24x 2.5Ghz) You deploy 10 vms with 1 Ghz Dashboard shows 110 Ghz / 180 Ghz (cpu over provisioning is 1 / 3 Hosts each 24x 2.5Ghz) You change cpu over provisioning to 4 Dashboard shows 440 Ghz / 720 Ghz (cpu over provisioning is 4 / 3 Hosts each 24x 2.5Ghz) You stop and start all vms Dashboard shows 110 Ghz / 720 Ghz Mit freundlichen Grüßen / With kind regards, Swen Brüseke -Ursprüngliche Nachricht- Von: Abhinandan Prateek [mailto:abhinandan.prat...@shapeblue.com] Gesendet: Mittwoch, 22. April 2015 06:35 An: users@cloudstack.apache.org Betreff: Re: cpu overprovisioning Can we fix the dashboard to reflect the available capacity given an over commit ? On 22-Apr-2015, at 9:56 am, Bharat Kumar bharat.ku...@citrix.com wrote: Also In case of change in the overcommit value the total capacity will change instantaneously, but the used resource and the total available will change when the capacity checker thread runs. The interval at which this will run can be changed from the global settings. Thanks, Bharat. On 22-Apr-2015, at 9:50 am, Bharat Kumar bharat.ku...@citrix.com wrote: Hi, The change in cpu overcommit factor will not change the amount of resource that are available to you. It will change the way you want to use the free resource available at that time. It won't change what was already allocated. for example if you have deployed the VMs with overcommit say 2 and after a while you change the overcommit to 3, the used resource will be scaled based on the change. changing the overcommit cannot create resource. It can only change the way you want to use the free resource. So now after the change in overcommit you can deploy 3 times more VMs (of a given service offering) than usual using the the resource that is free at the time of changing the overcommit value. The perviously allocated resource cannot be freed until you restart the VMs. This link will tell you how resource allocation calculations are made. https://cwiki.apache.org/confluence/display/CLOUDSTACK/CPU+and+RAM+Ov ercommit Thanks, Bharat. On 21-Apr-2015, at 11:20 pm, Rafael Weingärtner rafaelweingart...@gmail.commailto:rafaelweingart...@gmail.com wrote: I have not looked at the code, but that seems odd. Restarting VMs instances to update the resource usage/resource availability when changing the overprovisioning factor. On Tue, Apr 21, 2015 at 12:51 PM, S. Brüseke - proIO GmbH s.brues...@proio.commailto:s.brues...@proio.com wrote: Please try to stop and start the vm. Maybe reboot is not working here. You should start to see more free CPU after the first vm. Mit freundlichen Grüßen / With kind regards, Swen Brüseke -Ursprüngliche Nachricht- Von: Ugo Vasi [mailto:ugo.v...@procne.it] Gesendet: Dienstag, 21. April 2015 16:40 An: users@cloudstack.apache.orgmailto:users@cloudstack.apache.org Betreff: Re: AW: cpu overprovisioning Hi Swen, I try rebboting 2 vm but the amount of cpu MHz is not changed. Do I have to restart all vm before you see a change? Il 21/04/2015 16:16, S. Brüseke - proIO GmbH ha scritto: This is because the factor of overprovisioning is attached to the instance too! And this factor is only changing after rebooting the instance. So after a change of cpu.overprovisioning.factor you need to reboot all instances on this cluster which were running before this change was made. Mit freundlichen Grüßen / With kind regards, Swen Brüseke -Ursprüngliche Nachricht- Von: Ugo Vasi [mailto:ugo.v...@procne.it] Gesendet: Dienstag, 21. April 2015 16:06 An: users@cloudstack.apache.orgmailto:users@cloudstack.apache.org Betreff: Re: cpu overprovisioning If I change the over-provisioning ratio in cluster-relative settings (infrastructure-cluser-cluster-name-settings) the dashboard show the sum of real GHz the overprovisioned amount of GHz (324GHz) as aspected, but after a while also the sum of Ghz is multiplied by the same factor making it unnecessary... Il 21/04/2015 15:26, Bharat Kumar ha scritto: In case of cloudstack, cpu capacity for host is total of cpus * no of Ghz * overporvisoning. total capacity = sum of capacities of individual hosts. Thanks, Bharat. On 21-Apr-2015, at 6:49 pm, Abhinandan Prateek abhinandan.prat
AW: cpu overprovisioning
Dashboard is not wrong. You only have these resources left in your CS. Here is an example as far as I remember: Dashboard shows 100 GHz / 180 Ghz (cpu over provisioning is 1 / 3 Hosts each 24x 2.5Ghz) You deploy 10 vms with 1 Ghz Dashboard shows 110 Ghz / 180 Ghz (cpu over provisioning is 1 / 3 Hosts each 24x 2.5Ghz) You change cpu over provisioning to 4 Dashboard shows 440 Ghz / 720 Ghz (cpu over provisioning is 4 / 3 Hosts each 24x 2.5Ghz) You stop and start all vms Dashboard shows 110 Ghz / 720 Ghz Mit freundlichen Grüßen / With kind regards, Swen Brüseke -Ursprüngliche Nachricht- Von: Abhinandan Prateek [mailto:abhinandan.prat...@shapeblue.com] Gesendet: Mittwoch, 22. April 2015 06:35 An: users@cloudstack.apache.org Betreff: Re: cpu overprovisioning Can we fix the dashboard to reflect the available capacity given an over commit ? On 22-Apr-2015, at 9:56 am, Bharat Kumar bharat.ku...@citrix.com wrote: Also In case of change in the overcommit value the total capacity will change instantaneously, but the used resource and the total available will change when the capacity checker thread runs. The interval at which this will run can be changed from the global settings. Thanks, Bharat. On 22-Apr-2015, at 9:50 am, Bharat Kumar bharat.ku...@citrix.com wrote: Hi, The change in cpu overcommit factor will not change the amount of resource that are available to you. It will change the way you want to use the free resource available at that time. It won't change what was already allocated. for example if you have deployed the VMs with overcommit say 2 and after a while you change the overcommit to 3, the used resource will be scaled based on the change. changing the overcommit cannot create resource. It can only change the way you want to use the free resource. So now after the change in overcommit you can deploy 3 times more VMs (of a given service offering) than usual using the the resource that is free at the time of changing the overcommit value. The perviously allocated resource cannot be freed until you restart the VMs. This link will tell you how resource allocation calculations are made. https://cwiki.apache.org/confluence/display/CLOUDSTACK/CPU+and+RAM+Ov ercommit Thanks, Bharat. On 21-Apr-2015, at 11:20 pm, Rafael Weingärtner rafaelweingart...@gmail.commailto:rafaelweingart...@gmail.com wrote: I have not looked at the code, but that seems odd. Restarting VMs instances to update the resource usage/resource availability when changing the overprovisioning factor. On Tue, Apr 21, 2015 at 12:51 PM, S. Brüseke - proIO GmbH s.brues...@proio.commailto:s.brues...@proio.com wrote: Please try to stop and start the vm. Maybe reboot is not working here. You should start to see more free CPU after the first vm. Mit freundlichen Grüßen / With kind regards, Swen Brüseke -Ursprüngliche Nachricht- Von: Ugo Vasi [mailto:ugo.v...@procne.it] Gesendet: Dienstag, 21. April 2015 16:40 An: users@cloudstack.apache.orgmailto:users@cloudstack.apache.org Betreff: Re: AW: cpu overprovisioning Hi Swen, I try rebboting 2 vm but the amount of cpu MHz is not changed. Do I have to restart all vm before you see a change? Il 21/04/2015 16:16, S. Brüseke - proIO GmbH ha scritto: This is because the factor of overprovisioning is attached to the instance too! And this factor is only changing after rebooting the instance. So after a change of cpu.overprovisioning.factor you need to reboot all instances on this cluster which were running before this change was made. Mit freundlichen Grüßen / With kind regards, Swen Brüseke -Ursprüngliche Nachricht- Von: Ugo Vasi [mailto:ugo.v...@procne.it] Gesendet: Dienstag, 21. April 2015 16:06 An: users@cloudstack.apache.orgmailto:users@cloudstack.apache.org Betreff: Re: cpu overprovisioning If I change the over-provisioning ratio in cluster-relative settings (infrastructure-cluser-cluster-name-settings) the dashboard show the sum of real GHz the overprovisioned amount of GHz (324GHz) as aspected, but after a while also the sum of Ghz is multiplied by the same factor making it unnecessary... Il 21/04/2015 15:26, Bharat Kumar ha scritto: In case of cloudstack, cpu capacity for host is total of cpus * no of Ghz * overporvisoning. total capacity = sum of capacities of individual hosts. Thanks, Bharat. On 21-Apr-2015, at 6:49 pm, Abhinandan Prateek abhinandan.prat...@shapeblue.commailto:abhinandan.prat...@shapeblue.com wrote: Available CPU will be 3 times the actual CPU when over provisioned by 3. The UI not showing the over provisioned value seems like a bug. -abhi On 21-Apr-2015, at 6:34 pm, Ugo Vasi ugo.v...@procne.itmailto:ugo.v...@procne.it wrote: Hi all, we have a cluster of three machines with 16 CPU at 2.2GHz each and we have set a cpu-overprovizioning to 3. I would expect that the CPU system capacity of the dashboard
Re: AW: cpu overprovisioning
I have not looked at the code, but that seems odd. Restarting VMs instances to update the resource usage/resource availability when changing the overprovisioning factor. On Tue, Apr 21, 2015 at 12:51 PM, S. Brüseke - proIO GmbH s.brues...@proio.com wrote: Please try to stop and start the vm. Maybe reboot is not working here. You should start to see more free CPU after the first vm. Mit freundlichen Grüßen / With kind regards, Swen Brüseke -Ursprüngliche Nachricht- Von: Ugo Vasi [mailto:ugo.v...@procne.it] Gesendet: Dienstag, 21. April 2015 16:40 An: users@cloudstack.apache.org Betreff: Re: AW: cpu overprovisioning Hi Swen, I try rebboting 2 vm but the amount of cpu MHz is not changed. Do I have to restart all vm before you see a change? Il 21/04/2015 16:16, S. Brüseke - proIO GmbH ha scritto: This is because the factor of overprovisioning is attached to the instance too! And this factor is only changing after rebooting the instance. So after a change of cpu.overprovisioning.factor you need to reboot all instances on this cluster which were running before this change was made. Mit freundlichen Grüßen / With kind regards, Swen Brüseke -Ursprüngliche Nachricht- Von: Ugo Vasi [mailto:ugo.v...@procne.it] Gesendet: Dienstag, 21. April 2015 16:06 An: users@cloudstack.apache.org Betreff: Re: cpu overprovisioning If I change the over-provisioning ratio in cluster-relative settings (infrastructure-cluser-cluster-name-settings) the dashboard show the sum of real GHz the overprovisioned amount of GHz (324GHz) as aspected, but after a while also the sum of Ghz is multiplied by the same factor making it unnecessary... Il 21/04/2015 15:26, Bharat Kumar ha scritto: In case of cloudstack, cpu capacity for host is total of cpus * no of Ghz * overporvisoning. total capacity = sum of capacities of individual hosts. Thanks, Bharat. On 21-Apr-2015, at 6:49 pm, Abhinandan Prateek abhinandan.prat...@shapeblue.com wrote: Available CPU will be 3 times the actual CPU when over provisioned by 3. The UI not showing the over provisioned value seems like a bug. -abhi On 21-Apr-2015, at 6:34 pm, Ugo Vasi ugo.v...@procne.it wrote: Hi all, we have a cluster of three machines with 16 CPU at 2.2GHz each and we have set a cpu-overprovizioning to 3. I would expect that the CPU system capacity of the dashboard appear with the sum of megahertz CPUs multiplied by three instead I get the real sum (108MHz). I do not understand if this overprovisioning allows me to allocate more MHz of real ones asthe documentation say since in reality the virtual machines occupy on average only 20% of the computing power. thanks in advance -- U g o V a s iugo.v...@procne.it P r o c n e s.r.l) via Cotonificio 45 33010 Tavagnacco IT phone: +390432486523 fax: +390432486523 Le informazioni contenute in questo messaggio sono riservate e confidenziali ed è vietata la diffusione in qualunque modo eseguita. Qualora Lei non fosse la persona a cui il presente messaggio è destinato, La invitiamo ad eliminarlo e a non leggerlo, dandocene gentilmente comunicazione. Per qualsiasi informazione si prega di contattare supp...@procne.it . Rif. D.L. 196/2003 Find out more about ShapeBlue and our range of CloudStack related services IaaS Cloud Design Buildhttp://secure-web.cisco.com/1Yol7cn0c4CnDObcpSirV3DCPZ0WVdvOa3L hGNjqR1LC8fdUx8eCLTnMMSoshd9HpKAnV6UPQ_yMd3M-1eZw2Ta-m7j5KgANh1cCgIkU g7gUvZUUMIkYZDZDpYP9IDOTuw6o3kuFAtJGiF0j7g8WWr6r9HIr7CqwJi047V_38MGrr r_r5JkLvVUoDdjYuhuBW/http%3A%2F%2Fshapeblue.com%2Fiaas-cloud-design-a nd-build%2F%2F CSForge - rapid IaaS deployment frameworkhttp://secure-web.cisco.com/1QG_8HfqAJxyrN85oTEHIYNcbRgpmjr Akp0COA-UIvjKFK3VDTqCkj9wp1e8W2JML6G56lRvuJpQMr5faxHOlQGVsy3eWivku7VX STR7Z_reGWbZS3mVJGbFxehTWTUAsA_HOfZ_i-dHdhIuYwCSXyx0PRQcIdyEE51ZlHghI wpl_CcVK4rj2EVlq5FWSNjbo/http%3A%2F%2Fshapeblue.com%2Fcsforge%2F CloudStack Consultinghttp://secure-web.cisco.com/1Jd9xC30lbTOK4Yz24hsK-SYyFxcaJ 15JHz5Aat3Lyd0qe4l_RGA3YuQAxdRlfgsKaT6hI61qwykCBNqiJRWwlaPIeK_FNJxaJt TYZ9o6c9gUZUI1GDDw2fGIesLOAjS5FnkfMjK4oqpmjkwKOCLxeXnBDDSoZhjQjyBB65K 27drcx_ll0lovUbqvBoz1HRfM/http%3A%2F%2Fshapeblue.com%2Fcloudstack-con sultancy%2F CloudStack Software Engineeringhttp://secure-web.cisco.com/10UUubQoT9nA8gFa_q8Qn0och7aMN dFTHV-Yar0Ga9h9N4I3YNAockHpCCMMiqhnaECX7ZcolpDZ0IWds3ca9SDAQ_9hoGadj_ YhjpPvW95NwJlv15UDNFNs8r99wke8pQl6BKjgzv94SQuWHueziP1J7X8G7uzAbyj7qqQ IjwV8qqxyV81xYENQyXC13qHt9/http%3A%2F%2Fshapeblue.com%2Fcloudstack-so ftware-engineering%2F CloudStack Infrastructure Supporthttp://secure-web.cisco.com/1tHfpu6yxqCTFv4ED5hd1IzUqlDUAasw9 gn30YT3ucOvb0PNffUKzHjrKXCpTie0_dZ2a1Veui99C8Qp-p9CiKkobjVQ7pQow2X2A6 AYXKH5HwcPQ4zvZuLr30h5QBdE3MjtkFm_PM2JKk7WRAhtnukS0nvUJnIY1CzNyvezE5Y Vmd8PpcV-eZRBptj4Mv_5i/http%3A%2F%2Fshapeblue.com%2Fcloudstack-infras
cpu overprovisioning
Hi all, we have a cluster of three machines with 16 CPU at 2.2GHz each and we have set a cpu-overprovizioning to 3. I would expect that the CPU system capacity of the dashboard appear with the sum of megahertz CPUs multiplied by three instead I get the real sum (108MHz). I do not understand if this overprovisioning allows me to allocate more MHz of real ones asthe documentation say since in reality the virtual machines occupy on average only 20% of the computing power. thanks in advance -- U g o V a s iugo.v...@procne.it P r o c n e s.r.l) via Cotonificio 45 33010 Tavagnacco IT phone: +390432486523 fax: +390432486523 Le informazioni contenute in questo messaggio sono riservate e confidenziali ed è vietata la diffusione in qualunque modo eseguita. Qualora Lei non fosse la persona a cui il presente messaggio è destinato, La invitiamo ad eliminarlo e a non leggerlo, dandocene gentilmente comunicazione. Per qualsiasi informazione si prega di contattare supp...@procne.it . Rif. D.L. 196/2003
Re: cpu overprovisioning
Available CPU will be 3 times the actual CPU when over provisioned by 3. The UI not showing the over provisioned value seems like a bug. -abhi On 21-Apr-2015, at 6:34 pm, Ugo Vasi ugo.v...@procne.it wrote: Hi all, we have a cluster of three machines with 16 CPU at 2.2GHz each and we have set a cpu-overprovizioning to 3. I would expect that the CPU system capacity of the dashboard appear with the sum of megahertz CPUs multiplied by three instead I get the real sum (108MHz). I do not understand if this overprovisioning allows me to allocate more MHz of real ones asthe documentation say since in reality the virtual machines occupy on average only 20% of the computing power. thanks in advance -- U g o V a s iugo.v...@procne.it P r o c n e s.r.l) via Cotonificio 45 33010 Tavagnacco IT phone: +390432486523 fax: +390432486523 Le informazioni contenute in questo messaggio sono riservate e confidenziali ed è vietata la diffusione in qualunque modo eseguita. Qualora Lei non fosse la persona a cui il presente messaggio è destinato, La invitiamo ad eliminarlo e a non leggerlo, dandocene gentilmente comunicazione. Per qualsiasi informazione si prega di contattare supp...@procne.it . Rif. D.L. 196/2003 Find out more about ShapeBlue and our range of CloudStack related services IaaS Cloud Design Buildhttp://shapeblue.com/iaas-cloud-design-and-build// CSForge – rapid IaaS deployment frameworkhttp://shapeblue.com/csforge/ CloudStack Consultinghttp://shapeblue.com/cloudstack-consultancy/ CloudStack Software Engineeringhttp://shapeblue.com/cloudstack-software-engineering/ CloudStack Infrastructure Supporthttp://shapeblue.com/cloudstack-infrastructure-support/ CloudStack Bootcamp Training Courseshttp://shapeblue.com/cloudstack-training/ This email and any attachments to it may be confidential and are intended solely for the use of the individual to whom it is addressed. Any views or opinions expressed are solely those of the author and do not necessarily represent those of Shape Blue Ltd or related companies. If you are not the intended recipient of this email, you must neither take any action based upon its contents, nor copy or show it to anyone. Please contact the sender if you believe you have received this email in error. Shape Blue Ltd is a company incorporated in England Wales. ShapeBlue Services India LLP is a company incorporated in India and is operated under license from Shape Blue Ltd. Shape Blue Brasil Consultoria Ltda is a company incorporated in Brasil and is operated under license from Shape Blue Ltd. ShapeBlue SA Pty Ltd is a company registered by The Republic of South Africa and is traded under license from Shape Blue Ltd. ShapeBlue is a registered trademark.
Re: AW: cpu overprovisioning
Hi Swen, I try rebboting 2 vm but the amount of cpu MHz is not changed. Do I have to restart all vm before you see a change? Il 21/04/2015 16:16, S. Brüseke - proIO GmbH ha scritto: This is because the factor of overprovisioning is attached to the instance too! And this factor is only changing after rebooting the instance. So after a change of cpu.overprovisioning.factor you need to reboot all instances on this cluster which were running before this change was made. Mit freundlichen Grüßen / With kind regards, Swen Brüseke -Ursprüngliche Nachricht- Von: Ugo Vasi [mailto:ugo.v...@procne.it] Gesendet: Dienstag, 21. April 2015 16:06 An: users@cloudstack.apache.org Betreff: Re: cpu overprovisioning If I change the over-provisioning ratio in cluster-relative settings (infrastructure-cluser-cluster-name-settings) the dashboard show the sum of real GHz the overprovisioned amount of GHz (324GHz) as aspected, but after a while also the sum of Ghz is multiplied by the same factor making it unnecessary... Il 21/04/2015 15:26, Bharat Kumar ha scritto: In case of cloudstack, cpu capacity for host is total of cpus * no of Ghz * overporvisoning. total capacity = sum of capacities of individual hosts. Thanks, Bharat. On 21-Apr-2015, at 6:49 pm, Abhinandan Prateek abhinandan.prat...@shapeblue.com wrote: Available CPU will be 3 times the actual CPU when over provisioned by 3. The UI not showing the over provisioned value seems like a bug. -abhi On 21-Apr-2015, at 6:34 pm, Ugo Vasi ugo.v...@procne.it wrote: Hi all, we have a cluster of three machines with 16 CPU at 2.2GHz each and we have set a cpu-overprovizioning to 3. I would expect that the CPU system capacity of the dashboard appear with the sum of megahertz CPUs multiplied by three instead I get the real sum (108MHz). I do not understand if this overprovisioning allows me to allocate more MHz of real ones asthe documentation say since in reality the virtual machines occupy on average only 20% of the computing power. thanks in advance -- U g o V a s iugo.v...@procne.it P r o c n e s.r.l) via Cotonificio 45 33010 Tavagnacco IT phone: +390432486523 fax: +390432486523 Le informazioni contenute in questo messaggio sono riservate e confidenziali ed è vietata la diffusione in qualunque modo eseguita. Qualora Lei non fosse la persona a cui il presente messaggio è destinato, La invitiamo ad eliminarlo e a non leggerlo, dandocene gentilmente comunicazione. Per qualsiasi informazione si prega di contattare supp...@procne.it . Rif. D.L. 196/2003 Find out more about ShapeBlue and our range of CloudStack related services IaaS Cloud Design Buildhttp://secure-web.cisco.com/1Yol7cn0c4CnDObcpSirV3DCPZ0WVdvOa3L hGNjqR1LC8fdUx8eCLTnMMSoshd9HpKAnV6UPQ_yMd3M-1eZw2Ta-m7j5KgANh1cCgIkU g7gUvZUUMIkYZDZDpYP9IDOTuw6o3kuFAtJGiF0j7g8WWr6r9HIr7CqwJi047V_38MGrr r_r5JkLvVUoDdjYuhuBW/http%3A%2F%2Fshapeblue.com%2Fiaas-cloud-design-a nd-build%2F%2F CSForge - rapid IaaS deployment frameworkhttp://secure-web.cisco.com/1QG_8HfqAJxyrN85oTEHIYNcbRgpmjr Akp0COA-UIvjKFK3VDTqCkj9wp1e8W2JML6G56lRvuJpQMr5faxHOlQGVsy3eWivku7VX STR7Z_reGWbZS3mVJGbFxehTWTUAsA_HOfZ_i-dHdhIuYwCSXyx0PRQcIdyEE51ZlHghI wpl_CcVK4rj2EVlq5FWSNjbo/http%3A%2F%2Fshapeblue.com%2Fcsforge%2F CloudStack Consultinghttp://secure-web.cisco.com/1Jd9xC30lbTOK4Yz24hsK-SYyFxcaJ 15JHz5Aat3Lyd0qe4l_RGA3YuQAxdRlfgsKaT6hI61qwykCBNqiJRWwlaPIeK_FNJxaJt TYZ9o6c9gUZUI1GDDw2fGIesLOAjS5FnkfMjK4oqpmjkwKOCLxeXnBDDSoZhjQjyBB65K 27drcx_ll0lovUbqvBoz1HRfM/http%3A%2F%2Fshapeblue.com%2Fcloudstack-con sultancy%2F CloudStack Software Engineeringhttp://secure-web.cisco.com/10UUubQoT9nA8gFa_q8Qn0och7aMN dFTHV-Yar0Ga9h9N4I3YNAockHpCCMMiqhnaECX7ZcolpDZ0IWds3ca9SDAQ_9hoGadj_ YhjpPvW95NwJlv15UDNFNs8r99wke8pQl6BKjgzv94SQuWHueziP1J7X8G7uzAbyj7qqQ IjwV8qqxyV81xYENQyXC13qHt9/http%3A%2F%2Fshapeblue.com%2Fcloudstack-so ftware-engineering%2F CloudStack Infrastructure Supporthttp://secure-web.cisco.com/1tHfpu6yxqCTFv4ED5hd1IzUqlDUAasw9 gn30YT3ucOvb0PNffUKzHjrKXCpTie0_dZ2a1Veui99C8Qp-p9CiKkobjVQ7pQow2X2A6 AYXKH5HwcPQ4zvZuLr30h5QBdE3MjtkFm_PM2JKk7WRAhtnukS0nvUJnIY1CzNyvezE5Y Vmd8PpcV-eZRBptj4Mv_5i/http%3A%2F%2Fshapeblue.com%2Fcloudstack-infras tructure-support%2F CloudStack Bootcamp Training Courseshttp://secure-web.cisco.com/1x7d61M2SDzx2SvrIj9y8lD6Eepy3dddj EIFHasGDV_PPBn4EwtHVaqqdWSD1VShX_OR-DKgxqKGgB-dO7jrsSLYkWAw7UE1EeKQdH I4RW9BPnlYREiTeAcWT3YeOlfQh9EzHqk1uXnuftQxPCbewMDyEcqAzM6O-6r7R7sYuIx I6xPdCoei7JH2Bkpsljdp-/http%3A%2F%2Fshapeblue.com%2Fcloudstack-traini ng%2F This email and any attachments to it may be confidential and are intended solely for the use of the individual to whom it is addressed. Any views or opinions expressed are solely those of the author and do not necessarily represent those of Shape Blue Ltd or related companies. If you are not the intended recipient of this email, you must neither take any action based upon its contents, nor copy or show it to anyone. Please contact the sender if you
AW: cpu overprovisioning
This is because the factor of overprovisioning is attached to the instance too! And this factor is only changing after rebooting the instance. So after a change of cpu.overprovisioning.factor you need to reboot all instances on this cluster which were running before this change was made. Mit freundlichen Grüßen / With kind regards, Swen Brüseke -Ursprüngliche Nachricht- Von: Ugo Vasi [mailto:ugo.v...@procne.it] Gesendet: Dienstag, 21. April 2015 16:06 An: users@cloudstack.apache.org Betreff: Re: cpu overprovisioning If I change the over-provisioning ratio in cluster-relative settings (infrastructure-cluser-cluster-name-settings) the dashboard show the sum of real GHz the overprovisioned amount of GHz (324GHz) as aspected, but after a while also the sum of Ghz is multiplied by the same factor making it unnecessary... Il 21/04/2015 15:26, Bharat Kumar ha scritto: In case of cloudstack, cpu capacity for host is total of cpus * no of Ghz * overporvisoning. total capacity = sum of capacities of individual hosts. Thanks, Bharat. On 21-Apr-2015, at 6:49 pm, Abhinandan Prateek abhinandan.prat...@shapeblue.com wrote: Available CPU will be 3 times the actual CPU when over provisioned by 3. The UI not showing the over provisioned value seems like a bug. -abhi On 21-Apr-2015, at 6:34 pm, Ugo Vasi ugo.v...@procne.it wrote: Hi all, we have a cluster of three machines with 16 CPU at 2.2GHz each and we have set a cpu-overprovizioning to 3. I would expect that the CPU system capacity of the dashboard appear with the sum of megahertz CPUs multiplied by three instead I get the real sum (108MHz). I do not understand if this overprovisioning allows me to allocate more MHz of real ones asthe documentation say since in reality the virtual machines occupy on average only 20% of the computing power. thanks in advance -- U g o V a s iugo.v...@procne.it P r o c n e s.r.l) via Cotonificio 45 33010 Tavagnacco IT phone: +390432486523 fax: +390432486523 Le informazioni contenute in questo messaggio sono riservate e confidenziali ed è vietata la diffusione in qualunque modo eseguita. Qualora Lei non fosse la persona a cui il presente messaggio è destinato, La invitiamo ad eliminarlo e a non leggerlo, dandocene gentilmente comunicazione. Per qualsiasi informazione si prega di contattare supp...@procne.it . Rif. D.L. 196/2003 Find out more about ShapeBlue and our range of CloudStack related services IaaS Cloud Design Buildhttp://secure-web.cisco.com/1Yol7cn0c4CnDObcpSirV3DCPZ0WVdvOa3L hGNjqR1LC8fdUx8eCLTnMMSoshd9HpKAnV6UPQ_yMd3M-1eZw2Ta-m7j5KgANh1cCgIkU g7gUvZUUMIkYZDZDpYP9IDOTuw6o3kuFAtJGiF0j7g8WWr6r9HIr7CqwJi047V_38MGrr r_r5JkLvVUoDdjYuhuBW/http%3A%2F%2Fshapeblue.com%2Fiaas-cloud-design-a nd-build%2F%2F CSForge - rapid IaaS deployment frameworkhttp://secure-web.cisco.com/1QG_8HfqAJxyrN85oTEHIYNcbRgpmjr Akp0COA-UIvjKFK3VDTqCkj9wp1e8W2JML6G56lRvuJpQMr5faxHOlQGVsy3eWivku7VX STR7Z_reGWbZS3mVJGbFxehTWTUAsA_HOfZ_i-dHdhIuYwCSXyx0PRQcIdyEE51ZlHghI wpl_CcVK4rj2EVlq5FWSNjbo/http%3A%2F%2Fshapeblue.com%2Fcsforge%2F CloudStack Consultinghttp://secure-web.cisco.com/1Jd9xC30lbTOK4Yz24hsK-SYyFxcaJ 15JHz5Aat3Lyd0qe4l_RGA3YuQAxdRlfgsKaT6hI61qwykCBNqiJRWwlaPIeK_FNJxaJt TYZ9o6c9gUZUI1GDDw2fGIesLOAjS5FnkfMjK4oqpmjkwKOCLxeXnBDDSoZhjQjyBB65K 27drcx_ll0lovUbqvBoz1HRfM/http%3A%2F%2Fshapeblue.com%2Fcloudstack-con sultancy%2F CloudStack Software Engineeringhttp://secure-web.cisco.com/10UUubQoT9nA8gFa_q8Qn0och7aMN dFTHV-Yar0Ga9h9N4I3YNAockHpCCMMiqhnaECX7ZcolpDZ0IWds3ca9SDAQ_9hoGadj_ YhjpPvW95NwJlv15UDNFNs8r99wke8pQl6BKjgzv94SQuWHueziP1J7X8G7uzAbyj7qqQ IjwV8qqxyV81xYENQyXC13qHt9/http%3A%2F%2Fshapeblue.com%2Fcloudstack-so ftware-engineering%2F CloudStack Infrastructure Supporthttp://secure-web.cisco.com/1tHfpu6yxqCTFv4ED5hd1IzUqlDUAasw9 gn30YT3ucOvb0PNffUKzHjrKXCpTie0_dZ2a1Veui99C8Qp-p9CiKkobjVQ7pQow2X2A6 AYXKH5HwcPQ4zvZuLr30h5QBdE3MjtkFm_PM2JKk7WRAhtnukS0nvUJnIY1CzNyvezE5Y Vmd8PpcV-eZRBptj4Mv_5i/http%3A%2F%2Fshapeblue.com%2Fcloudstack-infras tructure-support%2F CloudStack Bootcamp Training Courseshttp://secure-web.cisco.com/1x7d61M2SDzx2SvrIj9y8lD6Eepy3dddj EIFHasGDV_PPBn4EwtHVaqqdWSD1VShX_OR-DKgxqKGgB-dO7jrsSLYkWAw7UE1EeKQdH I4RW9BPnlYREiTeAcWT3YeOlfQh9EzHqk1uXnuftQxPCbewMDyEcqAzM6O-6r7R7sYuIx I6xPdCoei7JH2Bkpsljdp-/http%3A%2F%2Fshapeblue.com%2Fcloudstack-traini ng%2F This email and any attachments to it may be confidential and are intended solely for the use of the individual to whom it is addressed. Any views or opinions expressed are solely those of the author and do not necessarily represent those of Shape Blue Ltd or related companies. If you are not the intended recipient of this email, you must neither take any action based upon its contents, nor copy or show it to anyone. Please contact the sender if you believe you have received this email in error. Shape Blue Ltd is a company incorporated in England Wales
Re: cpu overprovisioning
When you say instance, did you mean CS web application instance? On Tue, Apr 21, 2015 at 11:16 AM, S. Brüseke - proIO GmbH s.brues...@proio.com wrote: This is because the factor of overprovisioning is attached to the instance too! And this factor is only changing after rebooting the instance. So after a change of cpu.overprovisioning.factor you need to reboot all instances on this cluster which were running before this change was made. Mit freundlichen Grüßen / With kind regards, Swen Brüseke -Ursprüngliche Nachricht- Von: Ugo Vasi [mailto:ugo.v...@procne.it] Gesendet: Dienstag, 21. April 2015 16:06 An: users@cloudstack.apache.org Betreff: Re: cpu overprovisioning If I change the over-provisioning ratio in cluster-relative settings (infrastructure-cluser-cluster-name-settings) the dashboard show the sum of real GHz the overprovisioned amount of GHz (324GHz) as aspected, but after a while also the sum of Ghz is multiplied by the same factor making it unnecessary... Il 21/04/2015 15:26, Bharat Kumar ha scritto: In case of cloudstack, cpu capacity for host is total of cpus * no of Ghz * overporvisoning. total capacity = sum of capacities of individual hosts. Thanks, Bharat. On 21-Apr-2015, at 6:49 pm, Abhinandan Prateek abhinandan.prat...@shapeblue.com wrote: Available CPU will be 3 times the actual CPU when over provisioned by 3. The UI not showing the over provisioned value seems like a bug. -abhi On 21-Apr-2015, at 6:34 pm, Ugo Vasi ugo.v...@procne.it wrote: Hi all, we have a cluster of three machines with 16 CPU at 2.2GHz each and we have set a cpu-overprovizioning to 3. I would expect that the CPU system capacity of the dashboard appear with the sum of megahertz CPUs multiplied by three instead I get the real sum (108MHz). I do not understand if this overprovisioning allows me to allocate more MHz of real ones asthe documentation say since in reality the virtual machines occupy on average only 20% of the computing power. thanks in advance -- U g o V a s iugo.v...@procne.it P r o c n e s.r.l) via Cotonificio 45 33010 Tavagnacco IT phone: +390432486523 fax: +390432486523 Le informazioni contenute in questo messaggio sono riservate e confidenziali ed è vietata la diffusione in qualunque modo eseguita. Qualora Lei non fosse la persona a cui il presente messaggio è destinato, La invitiamo ad eliminarlo e a non leggerlo, dandocene gentilmente comunicazione. Per qualsiasi informazione si prega di contattare supp...@procne.it . Rif. D.L. 196/2003 Find out more about ShapeBlue and our range of CloudStack related services IaaS Cloud Design Buildhttp://secure-web.cisco.com/1Yol7cn0c4CnDObcpSirV3DCPZ0WVdvOa3L hGNjqR1LC8fdUx8eCLTnMMSoshd9HpKAnV6UPQ_yMd3M-1eZw2Ta-m7j5KgANh1cCgIkU g7gUvZUUMIkYZDZDpYP9IDOTuw6o3kuFAtJGiF0j7g8WWr6r9HIr7CqwJi047V_38MGrr r_r5JkLvVUoDdjYuhuBW/http%3A%2F%2Fshapeblue.com%2Fiaas-cloud-design-a nd-build%2F%2F CSForge - rapid IaaS deployment frameworkhttp://secure-web.cisco.com/1QG_8HfqAJxyrN85oTEHIYNcbRgpmjr Akp0COA-UIvjKFK3VDTqCkj9wp1e8W2JML6G56lRvuJpQMr5faxHOlQGVsy3eWivku7VX STR7Z_reGWbZS3mVJGbFxehTWTUAsA_HOfZ_i-dHdhIuYwCSXyx0PRQcIdyEE51ZlHghI wpl_CcVK4rj2EVlq5FWSNjbo/http%3A%2F%2Fshapeblue.com%2Fcsforge%2F CloudStack Consultinghttp://secure-web.cisco.com/1Jd9xC30lbTOK4Yz24hsK-SYyFxcaJ 15JHz5Aat3Lyd0qe4l_RGA3YuQAxdRlfgsKaT6hI61qwykCBNqiJRWwlaPIeK_FNJxaJt TYZ9o6c9gUZUI1GDDw2fGIesLOAjS5FnkfMjK4oqpmjkwKOCLxeXnBDDSoZhjQjyBB65K 27drcx_ll0lovUbqvBoz1HRfM/http%3A%2F%2Fshapeblue.com%2Fcloudstack-con sultancy%2F CloudStack Software Engineeringhttp://secure-web.cisco.com/10UUubQoT9nA8gFa_q8Qn0och7aMN dFTHV-Yar0Ga9h9N4I3YNAockHpCCMMiqhnaECX7ZcolpDZ0IWds3ca9SDAQ_9hoGadj_ YhjpPvW95NwJlv15UDNFNs8r99wke8pQl6BKjgzv94SQuWHueziP1J7X8G7uzAbyj7qqQ IjwV8qqxyV81xYENQyXC13qHt9/http%3A%2F%2Fshapeblue.com%2Fcloudstack-so ftware-engineering%2F CloudStack Infrastructure Supporthttp://secure-web.cisco.com/1tHfpu6yxqCTFv4ED5hd1IzUqlDUAasw9 gn30YT3ucOvb0PNffUKzHjrKXCpTie0_dZ2a1Veui99C8Qp-p9CiKkobjVQ7pQow2X2A6 AYXKH5HwcPQ4zvZuLr30h5QBdE3MjtkFm_PM2JKk7WRAhtnukS0nvUJnIY1CzNyvezE5Y Vmd8PpcV-eZRBptj4Mv_5i/http%3A%2F%2Fshapeblue.com%2Fcloudstack-infras tructure-support%2F CloudStack Bootcamp Training Courseshttp://secure-web.cisco.com/1x7d61M2SDzx2SvrIj9y8lD6Eepy3dddj EIFHasGDV_PPBn4EwtHVaqqdWSD1VShX_OR-DKgxqKGgB-dO7jrsSLYkWAw7UE1EeKQdH I4RW9BPnlYREiTeAcWT3YeOlfQh9EzHqk1uXnuftQxPCbewMDyEcqAzM6O-6r7R7sYuIx I6xPdCoei7JH2Bkpsljdp-/http%3A%2F%2Fshapeblue.com%2Fcloudstack-traini ng%2F This email and any attachments to it may be confidential and are intended solely for the use of the individual to whom it is addressed. Any views or opinions expressed are solely those of the author and do not necessarily represent those of Shape Blue Ltd or related companies. If you are not the intended recipient of this email, you must
Re: cpu overprovisioning
If I change the over-provisioning ratio in cluster-relative settings (infrastructure-cluser-cluster-name-settings) the dashboard show the sum of real GHz the overprovisioned amount of GHz (324GHz) as aspected, but after a while also the sum of Ghz is multiplied by the same factor making it unnecessary... Il 21/04/2015 15:26, Bharat Kumar ha scritto: In case of cloudstack, cpu capacity for host is total of cpus * no of Ghz * overporvisoning. total capacity = sum of capacities of individual hosts. Thanks, Bharat. On 21-Apr-2015, at 6:49 pm, Abhinandan Prateek abhinandan.prat...@shapeblue.com wrote: Available CPU will be 3 times the actual CPU when over provisioned by 3. The UI not showing the over provisioned value seems like a bug. -abhi On 21-Apr-2015, at 6:34 pm, Ugo Vasi ugo.v...@procne.it wrote: Hi all, we have a cluster of three machines with 16 CPU at 2.2GHz each and we have set a cpu-overprovizioning to 3. I would expect that the CPU system capacity of the dashboard appear with the sum of megahertz CPUs multiplied by three instead I get the real sum (108MHz). I do not understand if this overprovisioning allows me to allocate more MHz of real ones asthe documentation say since in reality the virtual machines occupy on average only 20% of the computing power. thanks in advance -- U g o V a s iugo.v...@procne.it P r o c n e s.r.l) via Cotonificio 45 33010 Tavagnacco IT phone: +390432486523 fax: +390432486523 Le informazioni contenute in questo messaggio sono riservate e confidenziali ed è vietata la diffusione in qualunque modo eseguita. Qualora Lei non fosse la persona a cui il presente messaggio è destinato, La invitiamo ad eliminarlo e a non leggerlo, dandocene gentilmente comunicazione. Per qualsiasi informazione si prega di contattare supp...@procne.it . Rif. D.L. 196/2003 Find out more about ShapeBlue and our range of CloudStack related services IaaS Cloud Design Buildhttp://secure-web.cisco.com/1Yol7cn0c4CnDObcpSirV3DCPZ0WVdvOa3LhGNjqR1LC8fdUx8eCLTnMMSoshd9HpKAnV6UPQ_yMd3M-1eZw2Ta-m7j5KgANh1cCgIkUg7gUvZUUMIkYZDZDpYP9IDOTuw6o3kuFAtJGiF0j7g8WWr6r9HIr7CqwJi047V_38MGrrr_r5JkLvVUoDdjYuhuBW/http%3A%2F%2Fshapeblue.com%2Fiaas-cloud-design-and-build%2F%2F CSForge – rapid IaaS deployment frameworkhttp://secure-web.cisco.com/1QG_8HfqAJxyrN85oTEHIYNcbRgpmjrAkp0COA-UIvjKFK3VDTqCkj9wp1e8W2JML6G56lRvuJpQMr5faxHOlQGVsy3eWivku7VXSTR7Z_reGWbZS3mVJGbFxehTWTUAsA_HOfZ_i-dHdhIuYwCSXyx0PRQcIdyEE51ZlHghIwpl_CcVK4rj2EVlq5FWSNjbo/http%3A%2F%2Fshapeblue.com%2Fcsforge%2F CloudStack Consultinghttp://secure-web.cisco.com/1Jd9xC30lbTOK4Yz24hsK-SYyFxcaJ15JHz5Aat3Lyd0qe4l_RGA3YuQAxdRlfgsKaT6hI61qwykCBNqiJRWwlaPIeK_FNJxaJtTYZ9o6c9gUZUI1GDDw2fGIesLOAjS5FnkfMjK4oqpmjkwKOCLxeXnBDDSoZhjQjyBB65K27drcx_ll0lovUbqvBoz1HRfM/http%3A%2F%2Fshapeblue.com%2Fcloudstack-consultancy%2F CloudStack Software Engineeringhttp://secure-web.cisco.com/10UUubQoT9nA8gFa_q8Qn0och7aMNdFTHV-Yar0Ga9h9N4I3YNAockHpCCMMiqhnaECX7ZcolpDZ0IWds3ca9SDAQ_9hoGadj_YhjpPvW95NwJlv15UDNFNs8r99wke8pQl6BKjgzv94SQuWHueziP1J7X8G7uzAbyj7qqQIjwV8qqxyV81xYENQyXC13qHt9/http%3A%2F%2Fshapeblue.com%2Fcloudstack-software-engineering%2F CloudStack Infrastructure Supporthttp://secure-web.cisco.com/1tHfpu6yxqCTFv4ED5hd1IzUqlDUAasw9gn30YT3ucOvb0PNffUKzHjrKXCpTie0_dZ2a1Veui99C8Qp-p9CiKkobjVQ7pQow2X2A6AYXKH5HwcPQ4zvZuLr30h5QBdE3MjtkFm_PM2JKk7WRAhtnukS0nvUJnIY1CzNyvezE5YVmd8PpcV-eZRBptj4Mv_5i/http%3A%2F%2Fshapeblue.com%2Fcloudstack-infrastructure-support%2F CloudStack Bootcamp Training Courseshttp://secure-web.cisco.com/1x7d61M2SDzx2SvrIj9y8lD6Eepy3dddjEIFHasGDV_PPBn4EwtHVaqqdWSD1VShX_OR-DKgxqKGgB-dO7jrsSLYkWAw7UE1EeKQdHI4RW9BPnlYREiTeAcWT3YeOlfQh9EzHqk1uXnuftQxPCbewMDyEcqAzM6O-6r7R7sYuIxI6xPdCoei7JH2Bkpsljdp-/http%3A%2F%2Fshapeblue.com%2Fcloudstack-training%2F This email and any attachments to it may be confidential and are intended solely for the use of the individual to whom it is addressed. Any views or opinions expressed are solely those of the author and do not necessarily represent those of Shape Blue Ltd or related companies. If you are not the intended recipient of this email, you must neither take any action based upon its contents, nor copy or show it to anyone. Please contact the sender if you believe you have received this email in error. Shape Blue Ltd is a company incorporated in England Wales. ShapeBlue Services India LLP is a company incorporated in India and is operated under license from Shape Blue Ltd. Shape Blue Brasil Consultoria Ltda is a company incorporated in Brasil and is operated under license from Shape Blue Ltd. ShapeBlue SA Pty Ltd is a company registered by The Republic of South Africa and is traded under license from Shape Blue Ltd. ShapeBlue is a registered trademark. -- U g o V a s iugo.v...@procne.it P r o c n e s.r.l) via Cotonificio 45 33010 Tavagnacco IT phone: +390432486523 fax: +390432486523 Le informazioni contenute in questo messaggio sono riservate e
AW: AW: cpu overprovisioning
Please try to stop and start the vm. Maybe reboot is not working here. You should start to see more free CPU after the first vm. Mit freundlichen Grüßen / With kind regards, Swen Brüseke -Ursprüngliche Nachricht- Von: Ugo Vasi [mailto:ugo.v...@procne.it] Gesendet: Dienstag, 21. April 2015 16:40 An: users@cloudstack.apache.org Betreff: Re: AW: cpu overprovisioning Hi Swen, I try rebboting 2 vm but the amount of cpu MHz is not changed. Do I have to restart all vm before you see a change? Il 21/04/2015 16:16, S. Brüseke - proIO GmbH ha scritto: This is because the factor of overprovisioning is attached to the instance too! And this factor is only changing after rebooting the instance. So after a change of cpu.overprovisioning.factor you need to reboot all instances on this cluster which were running before this change was made. Mit freundlichen Grüßen / With kind regards, Swen Brüseke -Ursprüngliche Nachricht- Von: Ugo Vasi [mailto:ugo.v...@procne.it] Gesendet: Dienstag, 21. April 2015 16:06 An: users@cloudstack.apache.org Betreff: Re: cpu overprovisioning If I change the over-provisioning ratio in cluster-relative settings (infrastructure-cluser-cluster-name-settings) the dashboard show the sum of real GHz the overprovisioned amount of GHz (324GHz) as aspected, but after a while also the sum of Ghz is multiplied by the same factor making it unnecessary... Il 21/04/2015 15:26, Bharat Kumar ha scritto: In case of cloudstack, cpu capacity for host is total of cpus * no of Ghz * overporvisoning. total capacity = sum of capacities of individual hosts. Thanks, Bharat. On 21-Apr-2015, at 6:49 pm, Abhinandan Prateek abhinandan.prat...@shapeblue.com wrote: Available CPU will be 3 times the actual CPU when over provisioned by 3. The UI not showing the over provisioned value seems like a bug. -abhi On 21-Apr-2015, at 6:34 pm, Ugo Vasi ugo.v...@procne.it wrote: Hi all, we have a cluster of three machines with 16 CPU at 2.2GHz each and we have set a cpu-overprovizioning to 3. I would expect that the CPU system capacity of the dashboard appear with the sum of megahertz CPUs multiplied by three instead I get the real sum (108MHz). I do not understand if this overprovisioning allows me to allocate more MHz of real ones asthe documentation say since in reality the virtual machines occupy on average only 20% of the computing power. thanks in advance -- U g o V a s iugo.v...@procne.it P r o c n e s.r.l) via Cotonificio 45 33010 Tavagnacco IT phone: +390432486523 fax: +390432486523 Le informazioni contenute in questo messaggio sono riservate e confidenziali ed è vietata la diffusione in qualunque modo eseguita. Qualora Lei non fosse la persona a cui il presente messaggio è destinato, La invitiamo ad eliminarlo e a non leggerlo, dandocene gentilmente comunicazione. Per qualsiasi informazione si prega di contattare supp...@procne.it . Rif. D.L. 196/2003 Find out more about ShapeBlue and our range of CloudStack related services IaaS Cloud Design Buildhttp://secure-web.cisco.com/1Yol7cn0c4CnDObcpSirV3DCPZ0WVdvOa3L hGNjqR1LC8fdUx8eCLTnMMSoshd9HpKAnV6UPQ_yMd3M-1eZw2Ta-m7j5KgANh1cCgIkU g7gUvZUUMIkYZDZDpYP9IDOTuw6o3kuFAtJGiF0j7g8WWr6r9HIr7CqwJi047V_38MGrr r_r5JkLvVUoDdjYuhuBW/http%3A%2F%2Fshapeblue.com%2Fiaas-cloud-design-a nd-build%2F%2F CSForge - rapid IaaS deployment frameworkhttp://secure-web.cisco.com/1QG_8HfqAJxyrN85oTEHIYNcbRgpmjr Akp0COA-UIvjKFK3VDTqCkj9wp1e8W2JML6G56lRvuJpQMr5faxHOlQGVsy3eWivku7VX STR7Z_reGWbZS3mVJGbFxehTWTUAsA_HOfZ_i-dHdhIuYwCSXyx0PRQcIdyEE51ZlHghI wpl_CcVK4rj2EVlq5FWSNjbo/http%3A%2F%2Fshapeblue.com%2Fcsforge%2F CloudStack Consultinghttp://secure-web.cisco.com/1Jd9xC30lbTOK4Yz24hsK-SYyFxcaJ 15JHz5Aat3Lyd0qe4l_RGA3YuQAxdRlfgsKaT6hI61qwykCBNqiJRWwlaPIeK_FNJxaJt TYZ9o6c9gUZUI1GDDw2fGIesLOAjS5FnkfMjK4oqpmjkwKOCLxeXnBDDSoZhjQjyBB65K 27drcx_ll0lovUbqvBoz1HRfM/http%3A%2F%2Fshapeblue.com%2Fcloudstack-con sultancy%2F CloudStack Software Engineeringhttp://secure-web.cisco.com/10UUubQoT9nA8gFa_q8Qn0och7aMN dFTHV-Yar0Ga9h9N4I3YNAockHpCCMMiqhnaECX7ZcolpDZ0IWds3ca9SDAQ_9hoGadj_ YhjpPvW95NwJlv15UDNFNs8r99wke8pQl6BKjgzv94SQuWHueziP1J7X8G7uzAbyj7qqQ IjwV8qqxyV81xYENQyXC13qHt9/http%3A%2F%2Fshapeblue.com%2Fcloudstack-so ftware-engineering%2F CloudStack Infrastructure Supporthttp://secure-web.cisco.com/1tHfpu6yxqCTFv4ED5hd1IzUqlDUAasw9 gn30YT3ucOvb0PNffUKzHjrKXCpTie0_dZ2a1Veui99C8Qp-p9CiKkobjVQ7pQow2X2A6 AYXKH5HwcPQ4zvZuLr30h5QBdE3MjtkFm_PM2JKk7WRAhtnukS0nvUJnIY1CzNyvezE5Y Vmd8PpcV-eZRBptj4Mv_5i/http%3A%2F%2Fshapeblue.com%2Fcloudstack-infras tructure-support%2F CloudStack Bootcamp Training Courseshttp://secure-web.cisco.com/1x7d61M2SDzx2SvrIj9y8lD6Eepy3dddj EIFHasGDV_PPBn4EwtHVaqqdWSD1VShX_OR-DKgxqKGgB-dO7jrsSLYkWAw7UE1EeKQdH I4RW9BPnlYREiTeAcWT3YeOlfQh9EzHqk1uXnuftQxPCbewMDyEcqAzM6O-6r7R7sYuIx I6xPdCoei7JH2Bkpsljdp-/http%3A%2F%2Fshapeblue.com%2Fcloudstack-traini ng%2F
AW: cpu overprovisioning
By instance I mean VM. Mit freundlichen Grüßen / With kind regards, Swen Brüseke -Ursprüngliche Nachricht- Von: Rafael Weingartner [mailto:rafaelweingart...@gmail.com] Gesendet: Dienstag, 21. April 2015 16:28 An: users@cloudstack.apache.org Betreff: Re: cpu overprovisioning When you say instance, did you mean CS web application instance? On Tue, Apr 21, 2015 at 11:16 AM, S. Brüseke - proIO GmbH s.brues...@proio.com wrote: This is because the factor of overprovisioning is attached to the instance too! And this factor is only changing after rebooting the instance. So after a change of cpu.overprovisioning.factor you need to reboot all instances on this cluster which were running before this change was made. Mit freundlichen Grüßen / With kind regards, Swen Brüseke -Ursprüngliche Nachricht- Von: Ugo Vasi [mailto:ugo.v...@procne.it] Gesendet: Dienstag, 21. April 2015 16:06 An: users@cloudstack.apache.org Betreff: Re: cpu overprovisioning If I change the over-provisioning ratio in cluster-relative settings (infrastructure-cluser-cluster-name-settings) the dashboard show the sum of real GHz the overprovisioned amount of GHz (324GHz) as aspected, but after a while also the sum of Ghz is multiplied by the same factor making it unnecessary... Il 21/04/2015 15:26, Bharat Kumar ha scritto: In case of cloudstack, cpu capacity for host is total of cpus * no of Ghz * overporvisoning. total capacity = sum of capacities of individual hosts. Thanks, Bharat. On 21-Apr-2015, at 6:49 pm, Abhinandan Prateek abhinandan.prat...@shapeblue.com wrote: Available CPU will be 3 times the actual CPU when over provisioned by 3. The UI not showing the over provisioned value seems like a bug. -abhi On 21-Apr-2015, at 6:34 pm, Ugo Vasi ugo.v...@procne.it wrote: Hi all, we have a cluster of three machines with 16 CPU at 2.2GHz each and we have set a cpu-overprovizioning to 3. I would expect that the CPU system capacity of the dashboard appear with the sum of megahertz CPUs multiplied by three instead I get the real sum (108MHz). I do not understand if this overprovisioning allows me to allocate more MHz of real ones asthe documentation say since in reality the virtual machines occupy on average only 20% of the computing power. thanks in advance -- U g o V a s iugo.v...@procne.it P r o c n e s.r.l) via Cotonificio 45 33010 Tavagnacco IT phone: +390432486523 fax: +390432486523 Le informazioni contenute in questo messaggio sono riservate e confidenziali ed è vietata la diffusione in qualunque modo eseguita. Qualora Lei non fosse la persona a cui il presente messaggio è destinato, La invitiamo ad eliminarlo e a non leggerlo, dandocene gentilmente comunicazione. Per qualsiasi informazione si prega di contattare supp...@procne.it . Rif. D.L. 196/2003 Find out more about ShapeBlue and our range of CloudStack related services IaaS Cloud Design Buildhttp://secure-web.cisco.com/1Yol7cn0c4CnDObcpSirV3DCPZ0WVdvOa 3L hGNjqR1LC8fdUx8eCLTnMMSoshd9HpKAnV6UPQ_yMd3M-1eZw2Ta-m7j5KgANh1cCgI kU g7gUvZUUMIkYZDZDpYP9IDOTuw6o3kuFAtJGiF0j7g8WWr6r9HIr7CqwJi047V_38MG rr r_r5JkLvVUoDdjYuhuBW/http%3A%2F%2Fshapeblue.com%2Fiaas-cloud-design -a nd-build%2F%2F CSForge - rapid IaaS deployment frameworkhttp://secure-web.cisco.com/1QG_8HfqAJxyrN85oTEHIYNcbRgpm jr Akp0COA-UIvjKFK3VDTqCkj9wp1e8W2JML6G56lRvuJpQMr5faxHOlQGVsy3eWivku7 VX STR7Z_reGWbZS3mVJGbFxehTWTUAsA_HOfZ_i-dHdhIuYwCSXyx0PRQcIdyEE51ZlHg hI wpl_CcVK4rj2EVlq5FWSNjbo/http%3A%2F%2Fshapeblue.com%2Fcsforge%2F CloudStack Consultinghttp://secure-web.cisco.com/1Jd9xC30lbTOK4Yz24hsK-SYyFxc aJ 15JHz5Aat3Lyd0qe4l_RGA3YuQAxdRlfgsKaT6hI61qwykCBNqiJRWwlaPIeK_FNJxa Jt TYZ9o6c9gUZUI1GDDw2fGIesLOAjS5FnkfMjK4oqpmjkwKOCLxeXnBDDSoZhjQjyBB6 5K 27drcx_ll0lovUbqvBoz1HRfM/http%3A%2F%2Fshapeblue.com%2Fcloudstack-c on sultancy%2F CloudStack Software Engineeringhttp://secure-web.cisco.com/10UUubQoT9nA8gFa_q8Qn0och7a MN dFTHV-Yar0Ga9h9N4I3YNAockHpCCMMiqhnaECX7ZcolpDZ0IWds3ca9SDAQ_9hoGad j_ YhjpPvW95NwJlv15UDNFNs8r99wke8pQl6BKjgzv94SQuWHueziP1J7X8G7uzAbyj7q qQ IjwV8qqxyV81xYENQyXC13qHt9/http%3A%2F%2Fshapeblue.com%2Fcloudstack- so ftware-engineering%2F CloudStack Infrastructure Supporthttp://secure-web.cisco.com/1tHfpu6yxqCTFv4ED5hd1IzUqlDUAas w9 gn30YT3ucOvb0PNffUKzHjrKXCpTie0_dZ2a1Veui99C8Qp-p9CiKkobjVQ7pQow2X2 A6 AYXKH5HwcPQ4zvZuLr30h5QBdE3MjtkFm_PM2JKk7WRAhtnukS0nvUJnIY1CzNyvezE 5Y Vmd8PpcV-eZRBptj4Mv_5i/http%3A%2F%2Fshapeblue.com%2Fcloudstack-infr as tructure-support%2F CloudStack Bootcamp Training Courseshttp://secure-web.cisco.com/1x7d61M2SDzx2SvrIj9y8lD6Eepy3dd dj EIFHasGDV_PPBn4EwtHVaqqdWSD1VShX_OR-DKgxqKGgB-dO7jrsSLYkWAw7UE1EeKQ dH I4RW9BPnlYREiTeAcWT3YeOlfQh9EzHqk1uXnuftQxPCbewMDyEcqAzM6O-6r7R7sYu Ix I6xPdCoei7JH2Bkpsljdp-/http%3A%2F
Re: cpu overprovisioning
Hi, The change in cpu overcommit factor will not change the amount of resource that are available to you. It will change the way you want to use the free resource available at that time. It won’t change what was already allocated. for example if you have deployed the VMs with overcommit say 2 and after a while you change the overcommit to 3, the used resource will be scaled based on the change. changing the overcommit cannot create resource. It can only change the way you want to use the free resource. So now after the change in overcommit you can deploy 3 times more VMs (of a given service offering) than usual using the the resource that is free at the time of changing the overcommit value. The perviously allocated resource cannot be freed until you restart the VMs. This link will tell you how resource allocation calculations are made. https://cwiki.apache.org/confluence/display/CLOUDSTACK/CPU+and+RAM+Overcommit Thanks, Bharat. On 21-Apr-2015, at 11:20 pm, Rafael Weingärtner rafaelweingart...@gmail.commailto:rafaelweingart...@gmail.com wrote: I have not looked at the code, but that seems odd. Restarting VMs instances to update the resource usage/resource availability when changing the overprovisioning factor. On Tue, Apr 21, 2015 at 12:51 PM, S. Brüseke - proIO GmbH s.brues...@proio.commailto:s.brues...@proio.com wrote: Please try to stop and start the vm. Maybe reboot is not working here. You should start to see more free CPU after the first vm. Mit freundlichen Grüßen / With kind regards, Swen Brüseke -Ursprüngliche Nachricht- Von: Ugo Vasi [mailto:ugo.v...@procne.it] Gesendet: Dienstag, 21. April 2015 16:40 An: users@cloudstack.apache.orgmailto:users@cloudstack.apache.org Betreff: Re: AW: cpu overprovisioning Hi Swen, I try rebboting 2 vm but the amount of cpu MHz is not changed. Do I have to restart all vm before you see a change? Il 21/04/2015 16:16, S. Brüseke - proIO GmbH ha scritto: This is because the factor of overprovisioning is attached to the instance too! And this factor is only changing after rebooting the instance. So after a change of cpu.overprovisioning.factor you need to reboot all instances on this cluster which were running before this change was made. Mit freundlichen Grüßen / With kind regards, Swen Brüseke -Ursprüngliche Nachricht- Von: Ugo Vasi [mailto:ugo.v...@procne.it] Gesendet: Dienstag, 21. April 2015 16:06 An: users@cloudstack.apache.orgmailto:users@cloudstack.apache.org Betreff: Re: cpu overprovisioning If I change the over-provisioning ratio in cluster-relative settings (infrastructure-cluser-cluster-name-settings) the dashboard show the sum of real GHz the overprovisioned amount of GHz (324GHz) as aspected, but after a while also the sum of Ghz is multiplied by the same factor making it unnecessary... Il 21/04/2015 15:26, Bharat Kumar ha scritto: In case of cloudstack, cpu capacity for host is total of cpus * no of Ghz * overporvisoning. total capacity = sum of capacities of individual hosts. Thanks, Bharat. On 21-Apr-2015, at 6:49 pm, Abhinandan Prateek abhinandan.prat...@shapeblue.commailto:abhinandan.prat...@shapeblue.com wrote: Available CPU will be 3 times the actual CPU when over provisioned by 3. The UI not showing the over provisioned value seems like a bug. -abhi On 21-Apr-2015, at 6:34 pm, Ugo Vasi ugo.v...@procne.itmailto:ugo.v...@procne.it wrote: Hi all, we have a cluster of three machines with 16 CPU at 2.2GHz each and we have set a cpu-overprovizioning to 3. I would expect that the CPU system capacity of the dashboard appear with the sum of megahertz CPUs multiplied by three instead I get the real sum (108MHz). I do not understand if this overprovisioning allows me to allocate more MHz of real ones asthe documentation say since in reality the virtual machines occupy on average only 20% of the computing power. thanks in advance -- U g o V a s iugo.v...@procne.itmailto:ugo.v...@procne.it P r o c n e s.r.l) via Cotonificio 45 33010 Tavagnacco IT phone: +390432486523 fax: +390432486523 Le informazioni contenute in questo messaggio sono riservate e confidenziali ed è vietata la diffusione in qualunque modo eseguita. Qualora Lei non fosse la persona a cui il presente messaggio è destinato, La invitiamo ad eliminarlo e a non leggerlo, dandocene gentilmente comunicazione. Per qualsiasi informazione si prega di contattare supp...@procne.itmailto:supp...@procne.it . Rif. D.L. 196/2003 Find out more about ShapeBlue and our range of CloudStack related services IaaS Cloud Design Buildhttp://secure-web.cisco.com/1Yol7cn0c4CnDObcpSirV3DCPZ0WVdvOa3L hGNjqR1LC8fdUx8eCLTnMMSoshd9HpKAnV6UPQ_yMd3M-1eZw2Ta-m7j5KgANh1cCgIkU g7gUvZUUMIkYZDZDpYP9IDOTuw6o3kuFAtJGiF0j7g8WWr6r9HIr7CqwJi047V_38MGrr r_r5JkLvVUoDdjYuhuBW/http%3A%2F%2Fshapeblue.comhttp://2Fshapeblue.com%2Fiaas-cloud-design-a nd-build%2F%2F CSForge - rapid IaaS deployment frameworkhttp://secure-web.cisco.com/1QG_8HfqAJxyrN85oTEHIYNcbRgpmjr
Re: cpu overprovisioning
Can we fix the dashboard to reflect the available capacity given an over commit ? On 22-Apr-2015, at 9:56 am, Bharat Kumar bharat.ku...@citrix.com wrote: Also In case of change in the overcommit value the total capacity will change instantaneously, but the used resource and the total available will change when the capacity checker thread runs. The interval at which this will run can be changed from the global settings. Thanks, Bharat. On 22-Apr-2015, at 9:50 am, Bharat Kumar bharat.ku...@citrix.com wrote: Hi, The change in cpu overcommit factor will not change the amount of resource that are available to you. It will change the way you want to use the free resource available at that time. It won’t change what was already allocated. for example if you have deployed the VMs with overcommit say 2 and after a while you change the overcommit to 3, the used resource will be scaled based on the change. changing the overcommit cannot create resource. It can only change the way you want to use the free resource. So now after the change in overcommit you can deploy 3 times more VMs (of a given service offering) than usual using the the resource that is free at the time of changing the overcommit value. The perviously allocated resource cannot be freed until you restart the VMs. This link will tell you how resource allocation calculations are made. https://cwiki.apache.org/confluence/display/CLOUDSTACK/CPU+and+RAM+Overcommit Thanks, Bharat. On 21-Apr-2015, at 11:20 pm, Rafael Weingärtner rafaelweingart...@gmail.commailto:rafaelweingart...@gmail.com wrote: I have not looked at the code, but that seems odd. Restarting VMs instances to update the resource usage/resource availability when changing the overprovisioning factor. On Tue, Apr 21, 2015 at 12:51 PM, S. Brüseke - proIO GmbH s.brues...@proio.commailto:s.brues...@proio.com wrote: Please try to stop and start the vm. Maybe reboot is not working here. You should start to see more free CPU after the first vm. Mit freundlichen Grüßen / With kind regards, Swen Brüseke -Ursprüngliche Nachricht- Von: Ugo Vasi [mailto:ugo.v...@procne.it] Gesendet: Dienstag, 21. April 2015 16:40 An: users@cloudstack.apache.orgmailto:users@cloudstack.apache.org Betreff: Re: AW: cpu overprovisioning Hi Swen, I try rebboting 2 vm but the amount of cpu MHz is not changed. Do I have to restart all vm before you see a change? Il 21/04/2015 16:16, S. Brüseke - proIO GmbH ha scritto: This is because the factor of overprovisioning is attached to the instance too! And this factor is only changing after rebooting the instance. So after a change of cpu.overprovisioning.factor you need to reboot all instances on this cluster which were running before this change was made. Mit freundlichen Grüßen / With kind regards, Swen Brüseke -Ursprüngliche Nachricht- Von: Ugo Vasi [mailto:ugo.v...@procne.it] Gesendet: Dienstag, 21. April 2015 16:06 An: users@cloudstack.apache.orgmailto:users@cloudstack.apache.org Betreff: Re: cpu overprovisioning If I change the over-provisioning ratio in cluster-relative settings (infrastructure-cluser-cluster-name-settings) the dashboard show the sum of real GHz the overprovisioned amount of GHz (324GHz) as aspected, but after a while also the sum of Ghz is multiplied by the same factor making it unnecessary... Il 21/04/2015 15:26, Bharat Kumar ha scritto: In case of cloudstack, cpu capacity for host is total of cpus * no of Ghz * overporvisoning. total capacity = sum of capacities of individual hosts. Thanks, Bharat. On 21-Apr-2015, at 6:49 pm, Abhinandan Prateek abhinandan.prat...@shapeblue.commailto:abhinandan.prat...@shapeblue.com wrote: Available CPU will be 3 times the actual CPU when over provisioned by 3. The UI not showing the over provisioned value seems like a bug. -abhi On 21-Apr-2015, at 6:34 pm, Ugo Vasi ugo.v...@procne.itmailto:ugo.v...@procne.it wrote: Hi all, we have a cluster of three machines with 16 CPU at 2.2GHz each and we have set a cpu-overprovizioning to 3. I would expect that the CPU system capacity of the dashboard appear with the sum of megahertz CPUs multiplied by three instead I get the real sum (108MHz). I do not understand if this overprovisioning allows me to allocate more MHz of real ones asthe documentation say since in reality the virtual machines occupy on average only 20% of the computing power. thanks in advance -- U g o V a s iugo.v...@procne.itmailto:ugo.v...@procne.it P r o c n e s.r.l) via Cotonificio 45 33010 Tavagnacco IT phone: +390432486523 fax: +390432486523 Le informazioni contenute in questo messaggio sono riservate e confidenziali ed è vietata la diffusione in qualunque modo eseguita. Qualora Lei non fosse la persona a cui il presente messaggio è destinato, La invitiamo ad eliminarlo e a non leggerlo, dandocene gentilmente comunicazione. Per
Re: cpu overprovisioning
Also In case of change in the overcommit value the total capacity will change instantaneously, but the used resource and the total available will change when the capacity checker thread runs. The interval at which this will run can be changed from the global settings. Thanks, Bharat. On 22-Apr-2015, at 9:50 am, Bharat Kumar bharat.ku...@citrix.com wrote: Hi, The change in cpu overcommit factor will not change the amount of resource that are available to you. It will change the way you want to use the free resource available at that time. It won’t change what was already allocated. for example if you have deployed the VMs with overcommit say 2 and after a while you change the overcommit to 3, the used resource will be scaled based on the change. changing the overcommit cannot create resource. It can only change the way you want to use the free resource. So now after the change in overcommit you can deploy 3 times more VMs (of a given service offering) than usual using the the resource that is free at the time of changing the overcommit value. The perviously allocated resource cannot be freed until you restart the VMs. This link will tell you how resource allocation calculations are made. https://cwiki.apache.org/confluence/display/CLOUDSTACK/CPU+and+RAM+Overcommit Thanks, Bharat. On 21-Apr-2015, at 11:20 pm, Rafael Weingärtner rafaelweingart...@gmail.commailto:rafaelweingart...@gmail.com wrote: I have not looked at the code, but that seems odd. Restarting VMs instances to update the resource usage/resource availability when changing the overprovisioning factor. On Tue, Apr 21, 2015 at 12:51 PM, S. Brüseke - proIO GmbH s.brues...@proio.commailto:s.brues...@proio.com wrote: Please try to stop and start the vm. Maybe reboot is not working here. You should start to see more free CPU after the first vm. Mit freundlichen Grüßen / With kind regards, Swen Brüseke -Ursprüngliche Nachricht- Von: Ugo Vasi [mailto:ugo.v...@procne.it] Gesendet: Dienstag, 21. April 2015 16:40 An: users@cloudstack.apache.orgmailto:users@cloudstack.apache.org Betreff: Re: AW: cpu overprovisioning Hi Swen, I try rebboting 2 vm but the amount of cpu MHz is not changed. Do I have to restart all vm before you see a change? Il 21/04/2015 16:16, S. Brüseke - proIO GmbH ha scritto: This is because the factor of overprovisioning is attached to the instance too! And this factor is only changing after rebooting the instance. So after a change of cpu.overprovisioning.factor you need to reboot all instances on this cluster which were running before this change was made. Mit freundlichen Grüßen / With kind regards, Swen Brüseke -Ursprüngliche Nachricht- Von: Ugo Vasi [mailto:ugo.v...@procne.it] Gesendet: Dienstag, 21. April 2015 16:06 An: users@cloudstack.apache.orgmailto:users@cloudstack.apache.org Betreff: Re: cpu overprovisioning If I change the over-provisioning ratio in cluster-relative settings (infrastructure-cluser-cluster-name-settings) the dashboard show the sum of real GHz the overprovisioned amount of GHz (324GHz) as aspected, but after a while also the sum of Ghz is multiplied by the same factor making it unnecessary... Il 21/04/2015 15:26, Bharat Kumar ha scritto: In case of cloudstack, cpu capacity for host is total of cpus * no of Ghz * overporvisoning. total capacity = sum of capacities of individual hosts. Thanks, Bharat. On 21-Apr-2015, at 6:49 pm, Abhinandan Prateek abhinandan.prat...@shapeblue.commailto:abhinandan.prat...@shapeblue.com wrote: Available CPU will be 3 times the actual CPU when over provisioned by 3. The UI not showing the over provisioned value seems like a bug. -abhi On 21-Apr-2015, at 6:34 pm, Ugo Vasi ugo.v...@procne.itmailto:ugo.v...@procne.it wrote: Hi all, we have a cluster of three machines with 16 CPU at 2.2GHz each and we have set a cpu-overprovizioning to 3. I would expect that the CPU system capacity of the dashboard appear with the sum of megahertz CPUs multiplied by three instead I get the real sum (108MHz). I do not understand if this overprovisioning allows me to allocate more MHz of real ones asthe documentation say since in reality the virtual machines occupy on average only 20% of the computing power. thanks in advance -- U g o V a s iugo.v...@procne.itmailto:ugo.v...@procne.it P r o c n e s.r.l) via Cotonificio 45 33010 Tavagnacco IT phone: +390432486523 fax: +390432486523 Le informazioni contenute in questo messaggio sono riservate e confidenziali ed è vietata la diffusione in qualunque modo eseguita. Qualora Lei non fosse la persona a cui il presente messaggio è destinato, La invitiamo ad eliminarlo e a non leggerlo, dandocene gentilmente comunicazione. Per qualsiasi informazione si prega di contattare supp...@procne.itmailto:supp...@procne.it . Rif. D.L. 196/2003 Find out more about
KVM CPU Overprovisioning issues.
I'm trying to figure out how CPU over-provisioning works in cloudstack. It seems that no matter how much I change the over-provisioning factor value in global settings, I cannot over-provision CPU allocation on the hosts. I suspect that I'm just having a lack of understanding on my part, but it seems like I should be able to increase the number of VMs I can deploy by increasing the CPU over-provisioning value (given that I'm not close to any other resource limits). But this doesn't seem to be the case in practice. https://screencloud.net/v/l1X7 https://screencloud.net/v/9ifx Error message when trying to create additional machine via API. grayson@gworkstation:~$ cloudmonkey deploy virtualmachine zoneid=a4c20770-f17e-425e-bb21-413dd610b975 serviceofferingid=4b391121-49c7-4434-883d-ffe569f63a3b templateid=e5701f73-b0c3-4dd7-8b2d-b8bf78875a85 keypair=key1 networkids=86e6ded0-6155-449b-a4bd-03411bf0a9cd name=tvmsman1 displayname [1] 3907 Async job 09148c21-3c42-4334-93b2-428b48fb1fa2 failed Error 533, Unable to create a deployment for VM[User|i-15-1151-VM] accountid = a4e6eaed-9b06-4806-98f9-4fcc781b773f cmd = org.apache.cloudstack.api.command.user.vm.DeployVMCmd created = 2015-04-17T13:46:22-0700 jobid = 09148c21-3c42-4334-93b2-428b48fb1fa2 jobprocstatus = 0 jobresult: errorcode = 533 errortext = Unable to create a deployment for VM[User|i-15-1151-VM] jobresultcode = 530 jobresulttype = object jobstatus = 2 userid = c7a0889e-fcec-4095-9d07-d29ea3c1e5d9 (local) mycloudmonkey list hosts filter=name,clustername,cpuallocated,cpunumber,cpusockets,cpuspeed,cpuused,cpuwithoverprovisioning, name = v-78-VM name = s-871-VM name = cl2hyper2 clustername = CL2 cpuallocated = 100.3% cpunumber = 8 cpusockets = 2 cpuspeed = 1994 cpuused = 1.2% cpuwithoverprovisioning = 63808.0 name = v-1-VM name = cl2hyper1 clustername = CL2 cpuallocated = 81.45% cpunumber = 8 cpusockets = 2 cpuspeed = 1995 cpuused = 0.6% cpuwithoverprovisioning = 63840.0 2015-04-17 13:46:22,517 DEBUG [o.a.c.f.j.i.AsyncJobManagerImpl] (catalina-exec-25:ctx-7b0eb43a ctx-751b2eca ctx-5c8a75fc) submit async job-7312, details: AsyncJobVO {id:7312, userId: 15, accountId: 15, instanceType: VirtualMachine, instanceId: 1151, cmd: org.apache.cloudstack.api.command.user.vm.DeployVMCmd, cmdInfo: {serviceofferingid:4b391121-49c7-4434-883d-ffe569f63a3b,cmdEventType:VM.CREATE,ctxUserId:15,zoneid:a4c20770-f17e-425e-bb21-413dd610b975,signatureversion:3,httpmethod:GET,templateid:e5701f73-b0c3-4dd7-8b2d-b8bf78875a85,networkids:86e6ded0-6155-449b-a4bd-03411bf0a9cd,apiKey:wrxDdS8yi2kJPe8UrNdOdLtp55mCSKskk3MyTJ1ucIApdMoYnOWsd-dmigPywD1KC-6BVfVmKiJVenEM_kovpw,id:1151,response:json,ctxDetails:{\com.cloud.template.VirtualMachineTemplate\:\e5701f73-b0c3-4dd7-8b2d-b8bf78875a85\,\com.cloud.vm.VirtualMachine\:\6b3ace85-8e4c-4467-afdf-b511136ca6b1\,\com.cloud.network.Network\:\86e6ded0-6155-449b-a4bd-03411bf0a9cd\,\com.cloud.dc.DataCenter\:\a4c20770-f17e-425e-bb21-413dd610b975\,\com.cloud.offering.ServiceOffering\:\4b391121-49c7-4434-883d-ffe569f63a3b\},expires:2015-04-17T20:56:22+,keypair:key1,name:tvmsman1,uuid:6b3ace85-8e4c-4467-afdf-b511136ca6b1,ctxAccountId:15,ctxStartEventId:11922,signature:8Ebg1+qjfnk5nv7xz1GtdSju2ws\u003d}, cmdVersion: 0, status: IN_PROGRESS, processStatus: 0, resultCode: 0, result: null, initMsid: 345050015385, completeMsid: null, lastUpdated: null, lastPolled: null, created: null} 2015-04-17 13:46:22,518 INFO [o.a.c.f.j.i.AsyncJobMonitor] (API-Job-Executor-16:ctx-e039eccb job-7312) Add job-7312 into job monitoring 2015-04-17 13:46:22,518 DEBUG [o.a.c.f.j.i.AsyncJobManagerImpl] (API-Job-Executor-16:ctx-e039eccb job-7312) Executing AsyncJobVO {id:7312, userId: 15, accountId: 15, instanceType: VirtualMachine, instanceId: 1151, cmd: org.apache.cloudstack.api.command.user.vm.DeployVMCmd, cmdInfo:
Re: KVM CPU Overprovisioning issues.
If not mistaken, there is global overprovisioning factor, and there is cluster level overprovisioning - the last one takes presedence I think... On 17 April 2015 at 23:01, Grayson Head gray...@graysonhead.net wrote: I'm trying to figure out how CPU over-provisioning works in cloudstack. It seems that no matter how much I change the over-provisioning factor value in global settings, I cannot over-provision CPU allocation on the hosts. I suspect that I'm just having a lack of understanding on my part, but it seems like I should be able to increase the number of VMs I can deploy by increasing the CPU over-provisioning value (given that I'm not close to any other resource limits). But this doesn't seem to be the case in practice. https://screencloud.net/v/l1X7 https://screencloud.net/v/9ifx Error message when trying to create additional machine via API. grayson@gworkstation:~$ cloudmonkey deploy virtualmachine zoneid=a4c20770-f17e-425e-bb21-413dd610b975 serviceofferingid=4b391121-49c7-4434-883d-ffe569f63a3b templateid=e5701f73-b0c3-4dd7-8b2d-b8bf78875a85 keypair=key1 networkids=86e6ded0-6155-449b-a4bd-03411bf0a9cd name=tvmsman1 displayname [1] 3907 Async job 09148c21-3c42-4334-93b2-428b48fb1fa2 failed Error 533, Unable to create a deployment for VM[User|i-15-1151-VM] accountid = a4e6eaed-9b06-4806-98f9-4fcc781b773f cmd = org.apache.cloudstack.api.command.user.vm.DeployVMCmd created = 2015-04-17T13:46:22-0700 jobid = 09148c21-3c42-4334-93b2-428b48fb1fa2 jobprocstatus = 0 jobresult: errorcode = 533 errortext = Unable to create a deployment for VM[User|i-15-1151-VM] jobresultcode = 530 jobresulttype = object jobstatus = 2 userid = c7a0889e-fcec-4095-9d07-d29ea3c1e5d9 (local) mycloudmonkey list hosts filter=name,clustername,cpuallocated,cpunumber,cpusockets,cpuspeed,cpuused,cpuwithoverprovisioning, name = v-78-VM name = s-871-VM name = cl2hyper2 clustername = CL2 cpuallocated = 100.3% cpunumber = 8 cpusockets = 2 cpuspeed = 1994 cpuused = 1.2% cpuwithoverprovisioning = 63808.0 name = v-1-VM name = cl2hyper1 clustername = CL2 cpuallocated = 81.45% cpunumber = 8 cpusockets = 2 cpuspeed = 1995 cpuused = 0.6% cpuwithoverprovisioning = 63840.0 2015-04-17 13:46:22,517 DEBUG [o.a.c.f.j.i.AsyncJobManagerImpl] (catalina-exec-25:ctx-7b0eb43a ctx-751b2eca ctx-5c8a75fc) submit async job-7312, details: AsyncJobVO {id:7312, userId: 15, accountId: 15, instanceType: VirtualMachine, instanceId: 1151, cmd: org.apache.cloudstack.api.command.user.vm.DeployVMCmd, cmdInfo: {serviceofferingid:4b391121-49c7-4434-883d-ffe569f63a3b,cmdEventType:VM.CREATE,ctxUserId:15,zoneid:a4c20770-f17e-425e-bb21-413dd610b975,signatureversion:3,httpmethod:GET,templateid:e5701f73-b0c3-4dd7-8b2d-b8bf78875a85,networkids:86e6ded0-6155-449b-a4bd-03411bf0a9cd,apiKey:wrxDdS8yi2kJPe8UrNdOdLtp55mCSKskk3MyTJ1ucIApdMoYnOWsd-dmigPywD1KC-6BVfVmKiJVenEM_kovpw,id:1151,response:json,ctxDetails:{\com.cloud.template.VirtualMachineTemplate\:\e5701f73-b0c3-4dd7-8b2d-b8bf78875a85\,\com.cloud.vm.VirtualMachine\:\6b3ace85-8e4c-4467-afdf-b511136ca6b1\,\com.cloud.network.Network\:\86e6ded0-6155-449b-a4bd-03411bf0a9cd\,\com.cloud.dc.DataCenter\:\a4c20770-f17e-425e-bb21-413dd610b975\,\com.cloud.offering.ServiceOffering\:\4b391121-49c7-4434-883d-ffe569f63a3b\},expires:2015-04-17T20:56:22+,keypair:key1,name:tvmsman1,uuid:6b3ace85-8e4c-4467-afdf-b511136ca6b1,ctxAccountId:15,ctxStartEventId:11922,signature:8Ebg1+qjfnk5nv7xz1GtdSju2ws\u003d}, cmdVersion: 0, status: IN_PROGRESS, processStatus: 0, resultCode: 0, result: null, initMsid: 345050015385, completeMsid: null, lastUpdated: null, lastPolled: null, created: null} 2015-04-17 13:46:22,518 INFO [o.a.c.f.j.i.AsyncJobMonitor] (API-Job-Executor-16:ctx-e039eccb job-7312) Add job-7312 into job monitoring 2015-04-17 13:46:22,518 DEBUG [o.a.c.f.j.i.AsyncJobManagerImpl] (API-Job-Executor-16:ctx-e039eccb job-7312) Executing AsyncJobVO {id:7312, userId: 15, accountId: 15, instanceType: VirtualMachine, instanceId: 1151, cmd: org.apache.cloudstack.api.command.user.vm.DeployVMCmd, cmdInfo:
Re: KVM CPU Overprovisioning issues.
When the deployment goes through, the allocation placement algorithm will tell you if cpu over provisioning worked. You can see it in management-server.log file.. Here is an easy way to extract useful info for failed vm deployment. After deployment failed, grep for cloudstack internal name of the VM and note the job id (i see in your log it was job-7312) in management-server.log . Once you have the job id, grep 'job-' management-server.log. Post the content here... I do see you post it the log below, it appears we are missing some info. You can override CPU overprovisioning values in global settings as well as cluster settings. If you are enable CPU reservations, than it probably wont work, because you trying to reserve more than whats available. What version of ACS you have and what hypervisor? On 4/17/15 2:01 PM, Grayson Head wrote: I'm trying to figure out how CPU over-provisioning works in cloudstack. It seems that no matter how much I change the over-provisioning factor value in global settings, I cannot over-provision CPU allocation on the hosts. I suspect that I'm just having a lack of understanding on my part, but it seems like I should be able to increase the number of VMs I can deploy by increasing the CPU over-provisioning value (given that I'm not close to any other resource limits). But this doesn't seem to be the case in practice. https://screencloud.net/v/l1X7 https://screencloud.net/v/9ifx Error message when trying to create additional machine via API. grayson@gworkstation:~$ cloudmonkey deploy virtualmachine zoneid=a4c20770-f17e-425e-bb21-413dd610b975 serviceofferingid=4b391121-49c7-4434-883d-ffe569f63a3b templateid=e5701f73-b0c3-4dd7-8b2d-b8bf78875a85 keypair=key1 networkids=86e6ded0-6155-449b-a4bd-03411bf0a9cd name=tvmsman1 displayname [1] 3907 Async job 09148c21-3c42-4334-93b2-428b48fb1fa2 failed Error 533, Unable to create a deployment for VM[User|i-15-1151-VM] accountid = a4e6eaed-9b06-4806-98f9-4fcc781b773f cmd = org.apache.cloudstack.api.command.user.vm.DeployVMCmd created = 2015-04-17T13:46:22-0700 jobid = 09148c21-3c42-4334-93b2-428b48fb1fa2 jobprocstatus = 0 jobresult: errorcode = 533 errortext = Unable to create a deployment for VM[User|i-15-1151-VM] jobresultcode = 530 jobresulttype = object jobstatus = 2 userid = c7a0889e-fcec-4095-9d07-d29ea3c1e5d9 (local) mycloudmonkey list hosts filter=name,clustername,cpuallocated,cpunumber,cpusockets,cpuspeed,cpuused,cpuwithoverprovisioning, name = v-78-VM name = s-871-VM name = cl2hyper2 clustername = CL2 cpuallocated = 100.3% cpunumber = 8 cpusockets = 2 cpuspeed = 1994 cpuused = 1.2% cpuwithoverprovisioning = 63808.0 name = v-1-VM name = cl2hyper1 clustername = CL2 cpuallocated = 81.45% cpunumber = 8 cpusockets = 2 cpuspeed = 1995 cpuused = 0.6% cpuwithoverprovisioning = 63840.0 2015-04-17 13:46:22,517 DEBUG [o.a.c.f.j.i.AsyncJobManagerImpl] (catalina-exec-25:ctx-7b0eb43a ctx-751b2eca ctx-5c8a75fc) submit async job-7312, details: AsyncJobVO {id:7312, userId: 15, accountId: 15, instanceType: VirtualMachine, instanceId: 1151, cmd: org.apache.cloudstack.api.command.user.vm.DeployVMCmd, cmdInfo: {serviceofferingid:4b391121-49c7-4434-883d-ffe569f63a3b,cmdEventType:VM.CREATE,ctxUserId:15,zoneid:a4c20770-f17e-425e-bb21-413dd610b975,signatureversion:3,httpmethod:GET,templateid:e5701f73-b0c3-4dd7-8b2d-b8bf78875a85,networkids:86e6ded0-6155-449b-a4bd-03411bf0a9cd,apiKey:wrxDdS8yi2kJPe8UrNdOdLtp55mCSKskk3MyTJ1ucIApdMoYnOWsd-dmigPywD1KC-6BVfVmKiJVenEM_kovpw,id:1151,response:json,ctxDetails:{\com.cloud.template.VirtualMachineTemplate\:\e5701f73-b0c3-4dd7-8b2d-b8bf78875a85\,\com.cloud.vm.VirtualMachine\:\6b3ace85-8e4c-4467-afdf-b511136ca6b1\,\com.cloud.network.Network\:\86e6ded0-6155-449b-a4bd-03411bf0a9cd\,\com.cloud.dc.DataCenter\:\a4c20770-f17e-425e-bb21-413dd610b975\,\com.cloud.offering.ServiceOffering\:\4b391121-49c7-4434-883d-ffe569f63a3b\},expires:2015-04-17T20:56:22+,keypair:key1,name:tvmsman1,uuid:6b3ace85-8e4c-4467-afdf-b511136ca6b1,ctxAccountId:15,ctxStartEventId:11922,signature:8Ebg1+qjfnk5nv7xz1GtdSju2ws\u003d}, cmdVersion: 0, status: IN_PROGRESS, processStatus: 0, resultCode: 0, result: null, initMsid: 345050015385, completeMsid: null, lastUpdated: null, lastPolled: null, created: null} 2015-04-17 13:46:22,518 INFO [o.a.c.f.j.i.AsyncJobMonitor] (API-Job-Executor-16:ctx-e039eccb job-7312) Add job-7312 into job monitoring 2015-04-17 13:46:22,518 DEBUG [o.a.c.f.j.i.AsyncJobManagerImpl] (API-Job-Executor-16:ctx-e039eccb job-7312) Executing AsyncJobVO {id:7312, userId: 15, accountId: 15, instanceType
Re: Cloudstack 4.3 KVM CPU overprovisioning
More information from my previous post, On this particular blade I only have 9 vm's running Total CPU24 x 2.79 GHzCPU Utilized3.9%CPU Allocated for VMs 97%Memory Total126.02 GBMemory Allocated53.50 GB Memory Used36.74 MBNetwork Read35.99 GBNetwork Write [root@cs2-chas1-bl03 ~]# virsh list IdName State 9 i-8-70-VM running 11i-8-75-VM running 14r-93-VMrunning 15i-8-72-VM running 16r-95-VMrunning 17i-3-84-VM running 18i-3-73-VM running 19i-3-91-VM running 28i-4-110-VM running 29i-9-112-VM running 30i-3-128-VM running My service offering is # of CPU Cores4CPU (in MHz)2.00 GHz Where the number of CPU cores varies, I'm wondering if my service offering is incorrect because on the # of cores in my understanding is the number of vcpu's and the speed is lower than the real speed 2,000 Mhz Any ideas will be really appreciate it Below is the virs vcpuinfo VCPU: 0 CPU:12 State: running CPU time: 11802.8s CPU Affinity: VCPU: 1 CPU:12 State: running CPU time: 11317.7s CPU Affinity: VCPU: 0 CPU:2 State: running CPU time: 115618.7s CPU Affinity: VCPU: 1 CPU:2 State: running CPU time: 113330.9s CPU Affinity: VCPU: 0 CPU:4 State: running CPU time: 3928.5s CPU Affinity: VCPU: 1 CPU:0 State: running CPU time: 3459.6s CPU Affinity: VCPU: 2 CPU:14 State: running CPU time: 3429.3s CPU Affinity: VCPU: 3 CPU:12 State: running CPU time: 3808.8s CPU Affinity: VCPU: 4 CPU:0 State: running CPU time: 3506.9s CPU Affinity: VCPU: 5 CPU:2 State: running CPU time: 3695.5s CPU Affinity: VCPU: 6 CPU:21 State: running CPU time: 4199.5s CPU Affinity: VCPU: 7 CPU:0 State: running CPU time: 3633.2s CPU Affinity: VCPU: 0 CPU:2 State: running CPU time: 650355.2s CPU Affinity: VCPU: 1 CPU:14 State: running CPU time: 652099.4s CPU Affinity: VCPU: 2 CPU:6 State: running CPU time: 644120.8s CPU Affinity: VCPU: 3 CPU:1 State: running CPU time: 648950.4s CPU Affinity: VCPU: 0 CPU:12 State: running CPU time: 10297.6s CPU Affinity: VCPU: 1 CPU:0 State: running CPU time: 10297.3s CPU Affinity: VCPU: 0 CPU:1 State: running CPU time: 1815.1s CPU Affinity: VCPU: 1 CPU:1 State: running CPU time: 3389.8s CPU Affinity: VCPU: 0 CPU:1 State: running CPU time: 409.7s CPU Affinity: VCPU: 1 CPU:2 State: running CPU time: 463.9s CPU Affinity: VCPU: 2 CPU:14 State: running CPU time: 602.6s CPU Affinity: VCPU: 3 CPU:14 State: running CPU time: 429.9s CPU Affinity: VCPU: 0 CPU:4 State: running CPU time: 10406.0s CPU Affinity: VCPU: 1 CPU:2 State: running CPU time: 8263.1s CPU Affinity: VCPU: 2 CPU:0 State: running CPU time: 8247.2s CPU Affinity: VCPU: 3 CPU:0 State: running CPU time: 6616.0s CPU Affinity: VCPU: 0 CPU:0 State: running CPU time: 33693.2s CPU Affinity: VCPU: 1 CPU:16 State: running CPU time:
RE: Cloudstack 4.3 KVM CPU overprovisioning
I am giving an example based on my understanding. Data -- Host= 2 cpu ,2.3GHZ Total capacity =2*2.3 GHZ Total allocated: Total capacity assign to vms 1-Without over provisioning you can have total cpu allocated not more than total capacity . 2-With overprovisioning x you can have total allocated x*total capacity , 3-From the Cloudstack point of view If you are able to use total capacity which is more than physical, it is over provisioned. 4-From the kvm Point of view : I guess you are interested in Cloudstack point of view so leaving it Thanks Prashant -Original Message- From: Ivan Rodriguez [mailto:ivan...@gmail.com] Sent: Tuesday, June 17, 2014 11:55 AM To: cloudstack-us...@incubator.apache.org Subject: Re: Cloudstack 4.3 KVM CPU overprovisioning More information from my previous post, On this particular blade I only have 9 vm's running Total CPU24 x 2.79 GHzCPU Utilized3.9%CPU Allocated for VMs 97%Memory Total126.02 GBMemory Allocated53.50 GB Memory Used36.74 MBNetwork Read35.99 GBNetwork Write [root@cs2-chas1-bl03 ~]# virsh list IdName State 9 i-8-70-VM running 11i-8-75-VM running 14r-93-VMrunning 15i-8-72-VM running 16r-95-VMrunning 17i-3-84-VM running 18i-3-73-VM running 19i-3-91-VM running 28i-4-110-VM running 29i-9-112-VM running 30i-3-128-VM running My service offering is # of CPU Cores4CPU (in MHz)2.00 GHz Where the number of CPU cores varies, I'm wondering if my service offering is incorrect because on the # of cores in my understanding is the number of vcpu's and the speed is lower than the real speed 2,000 Mhz Any ideas will be really appreciate it Below is the virs vcpuinfo VCPU: 0 CPU:12 State: running CPU time: 11802.8s CPU Affinity: VCPU: 1 CPU:12 State: running CPU time: 11317.7s CPU Affinity: VCPU: 0 CPU:2 State: running CPU time: 115618.7s CPU Affinity: VCPU: 1 CPU:2 State: running CPU time: 113330.9s CPU Affinity: VCPU: 0 CPU:4 State: running CPU time: 3928.5s CPU Affinity: VCPU: 1 CPU:0 State: running CPU time: 3459.6s CPU Affinity: VCPU: 2 CPU:14 State: running CPU time: 3429.3s CPU Affinity: VCPU: 3 CPU:12 State: running CPU time: 3808.8s CPU Affinity: VCPU: 4 CPU:0 State: running CPU time: 3506.9s CPU Affinity: VCPU: 5 CPU:2 State: running CPU time: 3695.5s CPU Affinity: VCPU: 6 CPU:21 State: running CPU time: 4199.5s CPU Affinity: VCPU: 7 CPU:0 State: running CPU time: 3633.2s CPU Affinity: VCPU: 0 CPU:2 State: running CPU time: 650355.2s CPU Affinity: VCPU: 1 CPU:14 State: running CPU time: 652099.4s CPU Affinity: VCPU: 2 CPU:6 State: running CPU time: 644120.8s CPU Affinity: VCPU: 3 CPU:1 State: running CPU time: 648950.4s CPU Affinity: VCPU: 0 CPU:12 State: running CPU time: 10297.6s CPU Affinity: VCPU: 1 CPU:0 State: running CPU time: 10297.3s CPU Affinity: VCPU: 0 CPU:1 State: running CPU time: 1815.1s CPU Affinity: VCPU: 1 CPU:1 State: running CPU time: 3389.8s CPU Affinity: VCPU: 0 CPU:1 State: running CPU time: 409.7s CPU Affinity: VCPU: 1 CPU:2 State: running CPU time: 463.9s CPU Affinity: VCPU: 2 CPU:14 State: running CPU time: 602.6s CPU Affinity: VCPU: 3 CPU:14 State
Re: Cloudstack 4.3 KVM CPU overprovisioning
I've found more information on the host I have 2 sockets Processor Information Socket Designation: CPU1 Type: Central Processor Family: Xeon Manufacturer: Intel Processor Information Socket Designation: CPU2 Type: Central Processor Family: Xeon According to /proc/cpuinfo I have 24 cpu's processor : 23 vendor_id : GenuineIntel cpu family : 6 model : 44 model name : Intel(R) Xeon(R) CPU X5660 @ 2.80GHz According to Cloudstack cpu count matches *Total CPU24 x 2.79 GHz**CPU Allocated for VMs97%* But *The Number of CPU Sockets1* On KVM counting vcpus and matching that one to the real CPU;s #of VCPUS living in - Physical CPU Number 4 - 0 1 - 1 2 - 2 2 - 3 1 - 4 6 - 5 2 - 6 1 - 10 6 - 12 5 - 14 1 - 17 1 - 22 For example 4 vcpus are living in CPU 0 so overprovisioning is working, now why is it that cloudstack sees this host as 97 % full when I'm using only *12 CPU's* Where are the rest of my CPU's Any help would be really appreciate it Cheers On Tue, Jun 17, 2014 at 5:11 PM, Prashant Kumar Mishra prashantkumar.mis...@citrix.com wrote: I am giving an example based on my understanding. Data -- Host= 2 cpu ,2.3GHZ Total capacity =2*2.3 GHZ Total allocated: Total capacity assign to vms 1-Without over provisioning you can have total cpu allocated not more than total capacity . 2-With overprovisioning x you can have total allocated x*total capacity , 3-From the Cloudstack point of view If you are able to use total capacity which is more than physical, it is over provisioned. 4-From the kvm Point of view : I guess you are interested in Cloudstack point of view so leaving it Thanks Prashant -Original Message- From: Ivan Rodriguez [mailto:ivan...@gmail.com] Sent: Tuesday, June 17, 2014 11:55 AM To: cloudstack-us...@incubator.apache.org Subject: Re: Cloudstack 4.3 KVM CPU overprovisioning More information from my previous post, On this particular blade I only have 9 vm's running Total CPU24 x 2.79 GHzCPU Utilized3.9%CPU Allocated for VMs 97%Memory Total126.02 GBMemory Allocated53.50 GB Memory Used36.74 MBNetwork Read35.99 GBNetwork Write [root@cs2-chas1-bl03 ~]# virsh list IdName State 9 i-8-70-VM running 11i-8-75-VM running 14r-93-VMrunning 15i-8-72-VM running 16r-95-VMrunning 17i-3-84-VM running 18i-3-73-VM running 19i-3-91-VM running 28i-4-110-VM running 29i-9-112-VM running 30i-3-128-VM running My service offering is # of CPU Cores4CPU (in MHz)2.00 GHz Where the number of CPU cores varies, I'm wondering if my service offering is incorrect because on the # of cores in my understanding is the number of vcpu's and the speed is lower than the real speed 2,000 Mhz Any ideas will be really appreciate it Below is the virs vcpuinfo VCPU: 0 CPU:12 State: running CPU time: 11802.8s CPU Affinity: VCPU: 1 CPU:12 State: running CPU time: 11317.7s CPU Affinity: VCPU: 0 CPU:2 State: running CPU time: 115618.7s CPU Affinity: VCPU: 1 CPU:2 State: running CPU time: 113330.9s CPU Affinity: VCPU: 0 CPU:4 State: running CPU time: 3928.5s CPU Affinity: VCPU: 1 CPU:0 State: running CPU time: 3459.6s CPU Affinity: VCPU: 2 CPU:14 State: running CPU time: 3429.3s CPU Affinity: VCPU: 3 CPU:12 State: running CPU time: 3808.8s CPU Affinity: VCPU: 4 CPU:0 State: running CPU time: 3506.9s CPU Affinity: VCPU: 5 CPU:2 State: running CPU time: 3695.5s CPU Affinity: VCPU: 6 CPU:21 State: running CPU time: 4199.5s CPU Affinity: VCPU: 7 CPU:0 State: running CPU time: 3633.2s CPU Affinity: VCPU: 0 CPU:2 State: running CPU time: 650355.2s
Cloudstack 4.3 KVM CPU overprovisioning
Dear Cloudstack users, Our current setup is using dell blades with 24 cpus on KVM, currently we have 5 servers like that(120 cpus) , and 28 Vm's currently running all of them linux centos with virtio modules the majority of the vm's have 2 vcpus per VM so that would be around 56 vcpus According to my Cloudstach Dashboard I'm already in 56 % usage of CPU's, it seems that CPU overprovision is not working on KVM, I've setup cloudstack in global preferences to have a 100 guests per hosts as the limit if I my understanding is correct then I should be able to provision around 500 vms on those 120 cpu's if I wanted to using cpu overprovision. How can I confirm if CPU overprovision is working as far as I can see cloudstack is detecting the right numper of cpu's per physical host Total CPU24 x 2.79 GHzCPU Utilized3.9%CPU Allocated for VMs97%Memory Total126.02 GBMemory Allocated53.50 GBMemory Used36.74 MBNetwork Read35.99 GBNetwork Write Any help would be really appreciate it thanks
CPU overprovisioning.
Hi all, I configured CPU over provisioning factor 2.0 but cloudstack (4.2) shows no changes on the dashboard. computational nodes are XenServer 6.2, 2x4cores. Any hints are more then welcome. Dan. This message was sent using IMP, the Internet Messaging Program.
Re: CPU overprovisioning.
Did you restart the management service after making the change? Regards, Kirk Jantzer http://about.me/kirkjantzer On Wed, Nov 27, 2013 at 3:26 PM, d...@soleks.com wrote: Hi all, I configured CPU over provisioning factor 2.0 but cloudstack (4.2) shows no changes on the dashboard. computational nodes are XenServer 6.2, 2x4cores. Any hints are more then welcome. Dan. This message was sent using IMP, the Internet Messaging Program.
Re: CPU overprovisioning.
Did you change the global setting or the cluster setting ? In 4.2 changing global setting only affects the newly created clusters factor not the existing ones. On 27/11/13 12:26 PM, d...@soleks.com d...@soleks.com wrote: Hi all, I configured CPU over provisioning factor 2.0 but cloudstack (4.2) shows no changes on the dashboard. computational nodes are XenServer 6.2, 2x4cores. Any hints are more then welcome. Dan. This message was sent using IMP, the Internet Messaging Program.
Re: CPU overprovisioning.
That is what i didn't know about. Is it possible to update that settings for existing cluster ? Did you change the global setting or the cluster setting ? In 4.2 changing global setting only affects the newly created clusters factor not the existing ones. On 27/11/13 12:26 PM, d...@soleks.com d...@soleks.com wrote: Hi all, I configured CPU over provisioning factor 2.0 but cloudstack (4.2) shows no changes on the dashboard. computational nodes are XenServer 6.2, 2x4cores. Any hints are more then welcome. Dan. This message was sent using IMP, the Internet Messaging Program. This message was sent using IMP, the Internet Messaging Program.
Re: CPU overprovisioning.
Super !!! Fixed. Thanks for heads-up. That is what i didn't know about. Is it possible to update that settings for existing cluster ? Did you change the global setting or the cluster setting ? In 4.2 changing global setting only affects the newly created clusters factor not the existing ones. On 27/11/13 12:26 PM, d...@soleks.com d...@soleks.com wrote: Hi all, I configured CPU over provisioning factor 2.0 but cloudstack (4.2) shows no changes on the dashboard. computational nodes are XenServer 6.2, 2x4cores. Any hints are more then welcome. Dan. This message was sent using IMP, the Internet Messaging Program. This message was sent using IMP, the Internet Messaging Program. This message was sent using IMP, the Internet Messaging Program.