Re: [smartos-discuss] New host and CPU question

2016-12-02 Thread Len Weincier
Just to note I see that in triton the cpu_cap is set as well as cpu_shares == max_physical_memory I am struggling to understand how this works. I am guessing that if the ratio of cpu_cap to cores is low then its not that noticeable to the guests, the threads get through in a reasonable amount of

Re: [smartos-discuss] New host and CPU question

2016-12-02 Thread Nahum Shalman
I like to think about CPU as a resource either under contention (more processes need CPU time than CPU cores to go around) or not: CPU caps limit how much you can use when there's no contention. In the Joyent Could it ensures people don't get more CPU time than they pay for. (example 1 below)

Re: [smartos-discuss] New host and CPU question

2016-12-02 Thread Robert Mustacchi
On 12/2/16 8:17 , Len Weincier wrote: > On 2 December 2016 at 18:04, Robert Mustacchi wrote: > >> On 12/1/16 23:44 , Len Weincier wrote: This is the classic symptom of a machine with a cpu_cap less than its >> CPU (core) count. >>> >>> So the vm sees all the

Re: [smartos-discuss] New host and CPU question

2016-12-02 Thread Len Weincier
On 2 December 2016 at 16:43, Nahum Shalman wrote: > I like to think about CPU as a resource either under contention (more > processes need CPU time than CPU cores to go around) or not: > > CPU caps limit how much you can use when there's no contention. In the > Joyent Could

Re: [smartos-discuss] New host and CPU question

2016-12-02 Thread Len Weincier
On 2 December 2016 at 18:30, Robert Mustacchi wrote: > On 12/2/16 8:17 , Len Weincier wrote: > > On 2 December 2016 at 18:04, Robert Mustacchi wrote: > > > >> On 12/1/16 23:44 , Len Weincier wrote: > > This is the classic symptom of a machine with a

Re: [smartos-discuss] New host and CPU question

2016-12-02 Thread Len Weincier
On 2 December 2016 at 18:04, Robert Mustacchi wrote: > On 12/1/16 23:44 , Len Weincier wrote: > >> > >> This is the classic symptom of a machine with a cpu_cap less than its > CPU > >> (core) count. > >> > > > > So the vm sees all the cores and dispatches threads / processes for

[smartos-discuss] VRRP hangs in INIT mode.

2016-12-02 Thread Jasper Siepkes
Hi all, I tried setting up a VRRP interface with help of the wiki ( https://wiki.smartos.org/display/DOC/Managing+NICs#ManagingNICs-AddingVRRPnicstoVMs ). I used the following configuration to add an interface for use with VRRP (changed IP's and MAC's): -8<- { "add_nics":

Re: [smartos-discuss] New host and CPU question

2016-12-02 Thread Robert Mustacchi
On 12/1/16 23:44 , Len Weincier wrote: >> >> This is the classic symptom of a machine with a cpu_cap less than its CPU >> (core) count. >> > > So the vm sees all the cores and dispatches threads / processes for that > many cores but the actual uasage is limited by the cpu_cap so the threads > are

Re: [smartos-discuss] Problem to set maxbw of vnic dynamic

2016-12-02 Thread Robert Mustacchi
On 11/28/16 22:32 , 郑圆杰 wrote: > Hi, > > I got some problems using dladm to limit bandwith of vnic in smartos(20160921) > > > 1) I enforce a bandwith limit to 1G using dladm set-linkprop –z -t > –p maxbw=1G eth0. > > I can ping the ip and wget file for the ip. > > It work fine and the

[smartos-discuss] the difference between reboot and halt / boot sequence about zoneadm

2016-12-02 Thread 杨武
hi,all Purpose: I want to change dedicated-cpu as cpu-share for vm by zonecfg. Program 1: When the modifiy is completed, I only type the cmd: $ zoneadm -z 2b1e7695-c7c6-4752-9990-ee83f5756664 reboot And finally use the "poolstat" to view the result，such as: [root@smartos-pxe ~]# poolstat

Re: [smartos-discuss] New host and CPU question

2016-12-02 Thread Ian Collins
On 12/ 3/16 03:43 AM, Nahum Shalman wrote: I like to think about CPU as a resource either under contention (more processes need CPU time than CPU cores to go around) or not: CPU caps limit how much you can use when there's no contention. In the Joyent Could it ensures people don't get more