8
edits
Changes
Created page with 'There are several parameters tuning which the OpenVZ administrator can change the CPU usage of a VE. Usually one sets these parameters with the aid of the <code>vzctl</code> util…'
There are several parameters tuning which the OpenVZ administrator can change the CPU usage of a VE. Usually one sets these parameters with the aid of the <code>vzctl</code> utility. But sometimes it can be useful to modify these parameters directly, without using <code>vzctl</code>. For example, it can be required by developers who want to implement an in-place solution to control a particular virtualization system based on OpenVZ. That is why the Fairsched API is introduced.
The '''Fairsched API''' is the set of system calls that can be used (and that are, in fact, used in the <code>vzctl</code> utility) for altering various parameters of the [[CPU Fair scheduler]], such as <code>cpuunits</code>, <code>cpulimit</code>, <code>cpus</code>, and <code>cpumask</code>. The article is targeted to describe the API.
== CPU weight ==
'''Synopsis:'''
<source lang="c">
int fairsched_chwt(unsigned int id, unsigned int wght);
</source>
'''Description:'''
The CPU weight defines how much CPU time a VE gets. The smaller the weight is, the more CPU time the container gets. The CPU weight is a relative parameter. That means that multiplying the weight of all running VEs by the same value does not change the CPU time distribution. The minimal value of the weight is 1, and the maximal value is <code>FSCHWEIGHT_MAX</code> (65535). The weight of a newly created VE is set to 500 by default.
The <code>fairsched_chwt()</code> system call sets the CPU weight of a VE. <code>id</code> is the id of the VE. <code>wght</code> is the desired weight.
'''Return value:'''
On success, <code>fairsched_chwt()</code> returns 0. On error, -1 is returned, and <code>errno</code> is set appropriately.
'''Errors:'''
* <code>EINVAL</code>: <code>id</code>=0.
* <code>EINVAL</code>: the value of <code>wght</code> is out of the allowed range.
* <code>ENOENT</code>: the VE does not exist.
* <code>EPERM</code>: the caller does not have permissions to modify the CPU parameters of the VE.
'''Notes:'''
It is possible to change the CPU weight of the host system. The host system's id equals <code>INT_MAX</code> (2147483647).
The <code>cpuunits</code> option of the <code>vzctl</code> utility is not the same thing as the CPU weight described above, but they are closely connected by the simple equation:
''cpuweight = 500000 / cpuunits''
== CPU limit ==
'''Synopsis:'''
<source lang="c">
int fairsched_rate(unsigned int id, int op, unsigned int rate);
</source>
'''Description:'''
The CPU limit is the upper bound to the CPU usage for a VE. The limit is set for all CPUs the VE can execute on. That means the maximal value of the CPU limit (i.e. no limit) is the maximal limit on 1 CPU, which equals 1024, multiplied by the number of CPUs this VM can execute on. The minimal value is 1. The CPU limit is an absolute parameter in the sense that altering the limit of one VE does not affect the limits of other VEs.
The <code>fairsched_rate()</code> system call is used to set, get, or drop (i.e. set to the maximum) CPU limit of a VE. <code>id</code> is the id of the VE. <code>op</code> can be one of the following:
* <code>FAIRSCHED_SET_RATE</code> to set the limit; in this case <code>rate</code> is the limit value to set.
* <code>FAIRSCHED_DROP_RATE</code> to drop the limit; <code>rate</code> is not used.
* <code>FAIRSCHED_GET_RATE</code> to get the current value of the limit; the function returns the limit value, <code>rate</code> is not used.
'''Return value:'''
On success, <code>fairsched_rate()</code> returns the current value of the CPU limit if <code>op</code> is <code>FAIRSCHED_SET_RATE</code> or <code>FAIRSCHED_GET_RATE</code>, or 0 if <code>op</code> is <code>FAIRSCHED_DROP_RATE</code>. On error, -1 is returned, and <code>errno</code> is set appropriately.
'''Errors:'''
* <code>EINVAL</code>: <code>id</code>=0.
* <code>EINVAL</code>: <code>op</code> is invalid.
* <code>EINVAL</code>: <code>op</code>=<code>FAIRSCHED_SET_RATE</code>, and the value of <code>rate</code> is out of the allowed range.
* <code>ENOENT</code>: the VE does not exist.
* <code>ENODATA</code>: <code>op</code>=<code>FAIRSCHED_SET_RATE</code>, and the limit is not set (or was dropped).
* <code>EPERM</code>: the caller does not have permissions to modify the CPU parameters of the VE.
'''Notes:'''
It is possible to limit the CPU usage of the host system. The host system's id equals <code>INT_MAX</code> (2147483647).
CPU limits are available only in rhel5-based and rhel6-based kernels, and they behave a bit differently in them in respect of distributing the CPU time among CPUs the VE can execute on.
In the rhel5 kernel the limit has a container-wide meaning. For example, if there are 2 CPUs available for a container, and the limit is set to 1024 (of 2048), the container's CPU usage can be 100/0%, or 50/50%, or any other values whose sum does not exceed 100%.
In the rhel6 kernel the limit is divided between the CPUs proportionally, and a busy CPU cannot borrow time from an idle one, i.e. with a 2 CPUs container and 1024 (of 2048) limit set the usage of each CPU cannot exceed 50% in any case.
== Number of CPUs ==
'''Synopsis:'''
<source lang="c">
int fairsched_vcpus(unsigned int id, unsigned int vcpus);
</source>
'''Description:'''
The <code>fairsched_vcpus()</code> system call sets the number of virtual CPUs available in a VE. <code>id</code> is the id of the VE. <code>vcpus</code> is the number of virtual CPUs to set for the VE. If <code>vcpus</code>=0, the call attempts to set the number of CPUs in the VE to the number of online CPUs.
'''Return value:'''
On success, <code>fairsched_vcpus()</code> returns 0. On error, -1 is returned, and <code>errno</code> is set appropriately.
'''Errors:'''
* <code>EINVAL</code>: <code>id</code>=0.
* <code>ENOENT</code>: the VE does not exist.
* <code>EPERM</code>: the caller does not have permissions to modify the CPU parameters of the VE.
'''Notes:'''
The parameter have not been implemented in the rhel6 kernel yet.
== CPU affinity mask ==
'''Synopsis:'''
<source lang="c">
int fairsched_cpumask(unsigned int id, unsigned int len, unsigned long *mask)
</source>
'''Description:'''
A VE's CPU affinity mask determines the set of CPUs on which it is eligible to run. A CPU affinity mask is represented by an array of <code>long</code>'s so that a VE is allowed to execute on the n-th CPU if and only if the (<code>n%sizeof(long)</code>)-th bit of the (<code>n/sizeof(long)</code>)-th element of the array is set.
The <code>fairsched_cpumask()</code> system call sets the CPU affinity mask for a VE. <code>id</code> is the id of the VE. <code>mask</code> is the mask, and <code>len</code> is the size of the mask, in bytes.
'''Return value:'''
On success, <code>fairsched_cpumask()</code> returns 0. On error, -1 is returned, and <code>errno</code> is set appropriately.
'''Errors:'''
* <code>EBUSY</code>: the VE has a child cpuset which is not a subset of the mask.
* <code>EINVAL</code>: <code>id</code>=0.
* <code>EINVAL</code>: the mask intersects with a cpuset, and either that cpuset or the VE's cpuset is marked exclusive.
* <code>ENOENT</code>: the VE does not exist.
* <code>ENOMEM</code>: there is no memory to copy the mask.
* <code>ENOSPC</code>: the mask has no active CPUs set.
* <code>EPERM</code>: the caller does not have permissions to modify the CPU parameters of the VE.
'''Notes:'''
The parameter is available since the rhel6 kernel.
The '''Fairsched API''' is the set of system calls that can be used (and that are, in fact, used in the <code>vzctl</code> utility) for altering various parameters of the [[CPU Fair scheduler]], such as <code>cpuunits</code>, <code>cpulimit</code>, <code>cpus</code>, and <code>cpumask</code>. The article is targeted to describe the API.
== CPU weight ==
'''Synopsis:'''
<source lang="c">
int fairsched_chwt(unsigned int id, unsigned int wght);
</source>
'''Description:'''
The CPU weight defines how much CPU time a VE gets. The smaller the weight is, the more CPU time the container gets. The CPU weight is a relative parameter. That means that multiplying the weight of all running VEs by the same value does not change the CPU time distribution. The minimal value of the weight is 1, and the maximal value is <code>FSCHWEIGHT_MAX</code> (65535). The weight of a newly created VE is set to 500 by default.
The <code>fairsched_chwt()</code> system call sets the CPU weight of a VE. <code>id</code> is the id of the VE. <code>wght</code> is the desired weight.
'''Return value:'''
On success, <code>fairsched_chwt()</code> returns 0. On error, -1 is returned, and <code>errno</code> is set appropriately.
'''Errors:'''
* <code>EINVAL</code>: <code>id</code>=0.
* <code>EINVAL</code>: the value of <code>wght</code> is out of the allowed range.
* <code>ENOENT</code>: the VE does not exist.
* <code>EPERM</code>: the caller does not have permissions to modify the CPU parameters of the VE.
'''Notes:'''
It is possible to change the CPU weight of the host system. The host system's id equals <code>INT_MAX</code> (2147483647).
The <code>cpuunits</code> option of the <code>vzctl</code> utility is not the same thing as the CPU weight described above, but they are closely connected by the simple equation:
''cpuweight = 500000 / cpuunits''
== CPU limit ==
'''Synopsis:'''
<source lang="c">
int fairsched_rate(unsigned int id, int op, unsigned int rate);
</source>
'''Description:'''
The CPU limit is the upper bound to the CPU usage for a VE. The limit is set for all CPUs the VE can execute on. That means the maximal value of the CPU limit (i.e. no limit) is the maximal limit on 1 CPU, which equals 1024, multiplied by the number of CPUs this VM can execute on. The minimal value is 1. The CPU limit is an absolute parameter in the sense that altering the limit of one VE does not affect the limits of other VEs.
The <code>fairsched_rate()</code> system call is used to set, get, or drop (i.e. set to the maximum) CPU limit of a VE. <code>id</code> is the id of the VE. <code>op</code> can be one of the following:
* <code>FAIRSCHED_SET_RATE</code> to set the limit; in this case <code>rate</code> is the limit value to set.
* <code>FAIRSCHED_DROP_RATE</code> to drop the limit; <code>rate</code> is not used.
* <code>FAIRSCHED_GET_RATE</code> to get the current value of the limit; the function returns the limit value, <code>rate</code> is not used.
'''Return value:'''
On success, <code>fairsched_rate()</code> returns the current value of the CPU limit if <code>op</code> is <code>FAIRSCHED_SET_RATE</code> or <code>FAIRSCHED_GET_RATE</code>, or 0 if <code>op</code> is <code>FAIRSCHED_DROP_RATE</code>. On error, -1 is returned, and <code>errno</code> is set appropriately.
'''Errors:'''
* <code>EINVAL</code>: <code>id</code>=0.
* <code>EINVAL</code>: <code>op</code> is invalid.
* <code>EINVAL</code>: <code>op</code>=<code>FAIRSCHED_SET_RATE</code>, and the value of <code>rate</code> is out of the allowed range.
* <code>ENOENT</code>: the VE does not exist.
* <code>ENODATA</code>: <code>op</code>=<code>FAIRSCHED_SET_RATE</code>, and the limit is not set (or was dropped).
* <code>EPERM</code>: the caller does not have permissions to modify the CPU parameters of the VE.
'''Notes:'''
It is possible to limit the CPU usage of the host system. The host system's id equals <code>INT_MAX</code> (2147483647).
CPU limits are available only in rhel5-based and rhel6-based kernels, and they behave a bit differently in them in respect of distributing the CPU time among CPUs the VE can execute on.
In the rhel5 kernel the limit has a container-wide meaning. For example, if there are 2 CPUs available for a container, and the limit is set to 1024 (of 2048), the container's CPU usage can be 100/0%, or 50/50%, or any other values whose sum does not exceed 100%.
In the rhel6 kernel the limit is divided between the CPUs proportionally, and a busy CPU cannot borrow time from an idle one, i.e. with a 2 CPUs container and 1024 (of 2048) limit set the usage of each CPU cannot exceed 50% in any case.
== Number of CPUs ==
'''Synopsis:'''
<source lang="c">
int fairsched_vcpus(unsigned int id, unsigned int vcpus);
</source>
'''Description:'''
The <code>fairsched_vcpus()</code> system call sets the number of virtual CPUs available in a VE. <code>id</code> is the id of the VE. <code>vcpus</code> is the number of virtual CPUs to set for the VE. If <code>vcpus</code>=0, the call attempts to set the number of CPUs in the VE to the number of online CPUs.
'''Return value:'''
On success, <code>fairsched_vcpus()</code> returns 0. On error, -1 is returned, and <code>errno</code> is set appropriately.
'''Errors:'''
* <code>EINVAL</code>: <code>id</code>=0.
* <code>ENOENT</code>: the VE does not exist.
* <code>EPERM</code>: the caller does not have permissions to modify the CPU parameters of the VE.
'''Notes:'''
The parameter have not been implemented in the rhel6 kernel yet.
== CPU affinity mask ==
'''Synopsis:'''
<source lang="c">
int fairsched_cpumask(unsigned int id, unsigned int len, unsigned long *mask)
</source>
'''Description:'''
A VE's CPU affinity mask determines the set of CPUs on which it is eligible to run. A CPU affinity mask is represented by an array of <code>long</code>'s so that a VE is allowed to execute on the n-th CPU if and only if the (<code>n%sizeof(long)</code>)-th bit of the (<code>n/sizeof(long)</code>)-th element of the array is set.
The <code>fairsched_cpumask()</code> system call sets the CPU affinity mask for a VE. <code>id</code> is the id of the VE. <code>mask</code> is the mask, and <code>len</code> is the size of the mask, in bytes.
'''Return value:'''
On success, <code>fairsched_cpumask()</code> returns 0. On error, -1 is returned, and <code>errno</code> is set appropriately.
'''Errors:'''
* <code>EBUSY</code>: the VE has a child cpuset which is not a subset of the mask.
* <code>EINVAL</code>: <code>id</code>=0.
* <code>EINVAL</code>: the mask intersects with a cpuset, and either that cpuset or the VE's cpuset is marked exclusive.
* <code>ENOENT</code>: the VE does not exist.
* <code>ENOMEM</code>: there is no memory to copy the mask.
* <code>ENOSPC</code>: the mask has no active CPUs set.
* <code>EPERM</code>: the caller does not have permissions to modify the CPU parameters of the VE.
'''Notes:'''
The parameter is available since the rhel6 kernel.
