| Message ID | 20210423181727.596466-4-jingzhangos@google.com (mailing list archive) |
|---|---|
| State | New |
| Headers | show |
| Series | KVM statistics data fd-based binary interface | expand |
On Fri, Apr 23, 2021 at 1:17 PM Jing Zhang <jingzhangos@google.com> wrote: > > Signed-off-by: Jing Zhang <jingzhangos@google.com> > --- > Documentation/virt/kvm/api.rst | 171 +++++++++++++++++++++++++++++++++ > 1 file changed, 171 insertions(+) > > diff --git a/Documentation/virt/kvm/api.rst b/Documentation/virt/kvm/api.rst > index 8d614a577e43..faceadc2bd66 100644 > --- a/Documentation/virt/kvm/api.rst > +++ b/Documentation/virt/kvm/api.rst > @@ -5021,6 +5021,169 @@ see KVM_XEN_VCPU_SET_ATTR above. > The KVM_XEN_VCPU_ATTR_TYPE_RUNSTATE_ADJUST type may not be used > with the KVM_XEN_VCPU_GET_ATTR ioctl. > > +4.130 KVM_STATS_GETFD > +--------------------- > + > +:Capability: KVM_CAP_STATS_BINARY_FD > +:Architectures: all > +:Type: vm ioctl, vcpu ioctl > +:Parameters: none > +:Returns: statistics file descriptor on success, < 0 on error > + > +Errors: > + > + ====== ====================================================== > + ENOMEM if the fd could not be created due to lack of memory > + EMFILE if the number of opened files exceeds the limit > + ====== ====================================================== > + > +The file descriptor can be used to read VM/vCPU statistics data in binary > +format. The file data is organized into three blocks as below: > ++-------------+ > +| Header | > ++-------------+ > +| Descriptors | > ++-------------+ > +| Stats Data | > ++-------------+ > + > +The Header block is always at the start of the file. It is only needed to be > +read one time after a system boot. > +It is in the form of ``struct kvm_stats_header`` as below:: > + > + #define KVM_STATS_ID_MAXLEN 64 > + > + struct kvm_stats_header { > + char id[KVM_STATS_ID_MAXLEN]; > + __u32 name_size; > + __u32 count; > + __u32 desc_offset; > + __u32 data_offset; > + }; > + > +The ``id`` field is identification for the corresponding KVM statistics. For > +KVM statistics, it is in the form of "kvm-{kvm pid}", like "kvm-12345". For > +VCPU statistics, it is in the form of "kvm-{kvm pid}/vcpu-{vcpu id}", like > +"kvm-12345/vcpu-12". > + > +The ``name_size`` field is the size (byte) of the statistics name string > +(including trailing '\0') appended to the end of every statistics descriptor. > + > +The ``count`` field is the number of statistics. > + > +The ``desc_offset`` field is the offset of the Descriptors block from the start > +of the file indicated by the file descriptor. > + > +The ``data_offset`` field is the offset of the Stats Data block from the start > +of the file indicated by the file descriptor. > + > +The Descriptors block is only needed to be read once after a system boot. It is > +an array of ``struct kvm_stats_desc`` as below:: > + > + #define KVM_STATS_TYPE_SHIFT 0 > + #define KVM_STATS_TYPE_MASK (0xF << KVM_STATS_TYPE_SHIFT) > + #define KVM_STATS_TYPE_CUMULATIVE (0x0 << KVM_STATS_TYPE_SHIFT) > + #define KVM_STATS_TYPE_INSTANT (0x1 << KVM_STATS_TYPE_SHIFT) > + #define KVM_STATS_TYPE_MAX KVM_STATS_TYPE_INSTANT > + > + #define KVM_STATS_UNIT_SHIFT 4 > + #define KVM_STATS_UNIT_MASK (0xF << KVM_STATS_UNIT_SHIFT) > + #define KVM_STATS_UNIT_NONE (0x0 << KVM_STATS_UNIT_SHIFT) > + #define KVM_STATS_UNIT_BYTES (0x1 << KVM_STATS_UNIT_SHIFT) > + #define KVM_STATS_UNIT_SECONDS (0x2 << KVM_STATS_UNIT_SHIFT) > + #define KVM_STATS_UNIT_CYCLES (0x3 << KVM_STATS_UNIT_SHIFT) > + #define KVM_STATS_UNIT_MAX KVM_STATS_UNIT_CYCLES > + > + #define KVM_STATS_SCALE_SHIFT 8 > + #define KVM_STATS_SCALE_MASK (0xF << KVM_STATS_SCALE_SHIFT) > + #define KVM_STATS_SCALE_POW10 (0x0 << KVM_STATS_SCALE_SHIFT) > + #define KVM_STATS_SCALE_POW2 (0x1 << KVM_STATS_SCALE_SHIFT) > + #define KVM_STATS_SCALE_MAX KVM_STATS_SCALE_POW2 > + > + struct kvm_stats_desc { > + __u32 flags; > + __s16 exponent; > + __u16 size; > + __u32 unused1; > + __u32 unused2; > + __u8 name[0]; Should be "char name[0]" as defined in include/uapi/linux/kvm.h. > + }; > + > +The ``flags`` field contains the type and unit of the statistics data described > +by this descriptor. The following flags are supported: > + * ``KVM_STATS_TYPE_CUMULATIVE`` > + The statistics data is cumulative. The value of data can only be increased. > + Most of the counters used in KVM are of this type. > + The corresponding ``count`` filed for this type is always 1. > + * ``KVM_STATS_TYPE_INSTANT`` > + The statistics data is instantaneous. Its value can be increased or > + decreased. This type is usually used as a measurement of some resources, > + like the number of dirty pages, the number of large pages, etc. > + The corresponding ``count`` field for this type is always 1. > + * ``KVM_STATS_UNIT_NONE`` > + There is no unit for the value of statistics data. This usually means that > + the value is a simple counter of an event. > + * ``KVM_STATS_UNIT_BYTES`` > + It indicates that the statistics data is used to measure memory size, in the > + unit of Byte, KiByte, MiByte, GiByte, etc. The unit of the data is > + determined by the ``exponent`` field in the descriptor. The > + ``KVM_STATS_SCALE_POW2`` flag is valid in this case. The unit of the data is > + determined by ``pow(2, exponent)``. For example, if value is 10, > + ``exponent`` is 20, which means the unit of statistics data is MiByte, we > + can get the statistics data in the unit of Byte by > + ``value * pow(2, exponent) = 10 * pow(2, 20) = 10 MiByte`` which is > + 10 * 1024 * 1024 Bytes. > + * ``KVM_STATS_UNIT_SECONDS`` > + It indicates that the statistics data is used to measure time/latency, in > + the unit of nanosecond, microsecond, millisecond and second. The unit of the > + data is determined by the ``exponent`` field in the descriptor. The > + ``KVM_STATS_SCALE_POW10`` flag is valid in this case. The unit of the data > + is determined by ``pow(10, exponent)``. For example, if value is 2000000, > + ``exponent`` is -6, which means the unit of statistics data is microsecond, > + we can get the statistics data in the unit of second by > + ``value * pow(10, exponent) = 2000000 * pow(10, -6) = 2 seconds``. > + * ``KVM_STATS_UNIT_CYCLES`` > + It indicates that the statistics data is used to measure CPU clock cycles. > + The ``KVM_STATS_SCALE_POW10`` flag is valid in this case. For example, if > + value is 200, ``exponent`` is 4, we can get the number of CPU clock cycles > + by ``value * pow(10, exponent) = 200 * pow(10, 4) = 2000000``. > + > +The ``exponent`` field is the scale of corresponding statistics data. It has two > +values as follows: > + * ``KVM_STATS_SCALE_POW10`` > + The scale is based on power of 10. It is used for measurement of time and > + CPU clock cycles. > + * ``KVM_STATS_SCALE_POW2`` > + The scale is based on power of 2. It is used for measurement of memory size. > + > +The ``size`` field is the number of values of this statistics data. It is in the > +unit of ``unsigned long`` for VCPU or ``__u64`` for VM. > + > +The ``unused1`` and ``unused2`` fields are reserved for future > +support for other types of statistics data, like log/linear histogram. > + > +The ``name`` field points to the name string of the statistics data. The name > +string starts at the end of ``struct kvm_stats_desc``. > +The maximum length (including trailing '\0') is indicated by ``name_size`` > +in ``struct kvm_stats_header``. > + > +The Stats Data block contains an array of data values of type ``struct > +kvm_vm_stats_data`` or ``struct kvm_vcpu_stats_data``. It would be read by > +user space periodically to pull statistics data. > +The order of data value in Stats Data block is the same as the order of > +descriptors in Descriptors block. > + * Statistics data for VM:: > + > + struct kvm_vm_stats_data { > + unsigned long value[0]; > + }; > + > + * Statistics data for VCPU:: > + > + struct kvm_vcpu_stats_data { > + __u64 value[0]; > + }; > + > 5. The kvm_run structure > ======================== > > @@ -6888,3 +7051,11 @@ depends on the individual hypercall. > Right now, the only bit that can be set is bit 12, corresponding to > KVM_HC_PAGE_ENC_STATUS. The hypercall returns ENOSYS if bit 12 is not > set or KVM_CAP_EXIT_HYPERCALL is not enabled. > + > +8.33 KVM_CAP_STATS_BINARY_FD > +---------------------------- > + > +:Architectures: all > + > +This capability indicates the feature that user space can create get a file > +descriptor for every VM and VCPU to read statistics data in binary format. > -- > 2.31.1.498.g6c1eba8ee3d-goog >
diff --git a/Documentation/virt/kvm/api.rst b/Documentation/virt/kvm/api.rst index 8d614a577e43..faceadc2bd66 100644 --- a/Documentation/virt/kvm/api.rst +++ b/Documentation/virt/kvm/api.rst @@ -5021,6 +5021,169 @@ see KVM_XEN_VCPU_SET_ATTR above. The KVM_XEN_VCPU_ATTR_TYPE_RUNSTATE_ADJUST type may not be used with the KVM_XEN_VCPU_GET_ATTR ioctl. +4.130 KVM_STATS_GETFD +--------------------- + +:Capability: KVM_CAP_STATS_BINARY_FD +:Architectures: all +:Type: vm ioctl, vcpu ioctl +:Parameters: none +:Returns: statistics file descriptor on success, < 0 on error + +Errors: + + ====== ====================================================== + ENOMEM if the fd could not be created due to lack of memory + EMFILE if the number of opened files exceeds the limit + ====== ====================================================== + +The file descriptor can be used to read VM/vCPU statistics data in binary +format. The file data is organized into three blocks as below: ++-------------+ +| Header | ++-------------+ +| Descriptors | ++-------------+ +| Stats Data | ++-------------+ + +The Header block is always at the start of the file. It is only needed to be +read one time after a system boot. +It is in the form of ``struct kvm_stats_header`` as below:: + + #define KVM_STATS_ID_MAXLEN 64 + + struct kvm_stats_header { + char id[KVM_STATS_ID_MAXLEN]; + __u32 name_size; + __u32 count; + __u32 desc_offset; + __u32 data_offset; + }; + +The ``id`` field is identification for the corresponding KVM statistics. For +KVM statistics, it is in the form of "kvm-{kvm pid}", like "kvm-12345". For +VCPU statistics, it is in the form of "kvm-{kvm pid}/vcpu-{vcpu id}", like +"kvm-12345/vcpu-12". + +The ``name_size`` field is the size (byte) of the statistics name string +(including trailing '\0') appended to the end of every statistics descriptor. + +The ``count`` field is the number of statistics. + +The ``desc_offset`` field is the offset of the Descriptors block from the start +of the file indicated by the file descriptor. + +The ``data_offset`` field is the offset of the Stats Data block from the start +of the file indicated by the file descriptor. + +The Descriptors block is only needed to be read once after a system boot. It is +an array of ``struct kvm_stats_desc`` as below:: + + #define KVM_STATS_TYPE_SHIFT 0 + #define KVM_STATS_TYPE_MASK (0xF << KVM_STATS_TYPE_SHIFT) + #define KVM_STATS_TYPE_CUMULATIVE (0x0 << KVM_STATS_TYPE_SHIFT) + #define KVM_STATS_TYPE_INSTANT (0x1 << KVM_STATS_TYPE_SHIFT) + #define KVM_STATS_TYPE_MAX KVM_STATS_TYPE_INSTANT + + #define KVM_STATS_UNIT_SHIFT 4 + #define KVM_STATS_UNIT_MASK (0xF << KVM_STATS_UNIT_SHIFT) + #define KVM_STATS_UNIT_NONE (0x0 << KVM_STATS_UNIT_SHIFT) + #define KVM_STATS_UNIT_BYTES (0x1 << KVM_STATS_UNIT_SHIFT) + #define KVM_STATS_UNIT_SECONDS (0x2 << KVM_STATS_UNIT_SHIFT) + #define KVM_STATS_UNIT_CYCLES (0x3 << KVM_STATS_UNIT_SHIFT) + #define KVM_STATS_UNIT_MAX KVM_STATS_UNIT_CYCLES + + #define KVM_STATS_SCALE_SHIFT 8 + #define KVM_STATS_SCALE_MASK (0xF << KVM_STATS_SCALE_SHIFT) + #define KVM_STATS_SCALE_POW10 (0x0 << KVM_STATS_SCALE_SHIFT) + #define KVM_STATS_SCALE_POW2 (0x1 << KVM_STATS_SCALE_SHIFT) + #define KVM_STATS_SCALE_MAX KVM_STATS_SCALE_POW2 + + struct kvm_stats_desc { + __u32 flags; + __s16 exponent; + __u16 size; + __u32 unused1; + __u32 unused2; + __u8 name[0]; + }; + +The ``flags`` field contains the type and unit of the statistics data described +by this descriptor. The following flags are supported: + * ``KVM_STATS_TYPE_CUMULATIVE`` + The statistics data is cumulative. The value of data can only be increased. + Most of the counters used in KVM are of this type. + The corresponding ``count`` filed for this type is always 1. + * ``KVM_STATS_TYPE_INSTANT`` + The statistics data is instantaneous. Its value can be increased or + decreased. This type is usually used as a measurement of some resources, + like the number of dirty pages, the number of large pages, etc. + The corresponding ``count`` field for this type is always 1. + * ``KVM_STATS_UNIT_NONE`` + There is no unit for the value of statistics data. This usually means that + the value is a simple counter of an event. + * ``KVM_STATS_UNIT_BYTES`` + It indicates that the statistics data is used to measure memory size, in the + unit of Byte, KiByte, MiByte, GiByte, etc. The unit of the data is + determined by the ``exponent`` field in the descriptor. The + ``KVM_STATS_SCALE_POW2`` flag is valid in this case. The unit of the data is + determined by ``pow(2, exponent)``. For example, if value is 10, + ``exponent`` is 20, which means the unit of statistics data is MiByte, we + can get the statistics data in the unit of Byte by + ``value * pow(2, exponent) = 10 * pow(2, 20) = 10 MiByte`` which is + 10 * 1024 * 1024 Bytes. + * ``KVM_STATS_UNIT_SECONDS`` + It indicates that the statistics data is used to measure time/latency, in + the unit of nanosecond, microsecond, millisecond and second. The unit of the + data is determined by the ``exponent`` field in the descriptor. The + ``KVM_STATS_SCALE_POW10`` flag is valid in this case. The unit of the data + is determined by ``pow(10, exponent)``. For example, if value is 2000000, + ``exponent`` is -6, which means the unit of statistics data is microsecond, + we can get the statistics data in the unit of second by + ``value * pow(10, exponent) = 2000000 * pow(10, -6) = 2 seconds``. + * ``KVM_STATS_UNIT_CYCLES`` + It indicates that the statistics data is used to measure CPU clock cycles. + The ``KVM_STATS_SCALE_POW10`` flag is valid in this case. For example, if + value is 200, ``exponent`` is 4, we can get the number of CPU clock cycles + by ``value * pow(10, exponent) = 200 * pow(10, 4) = 2000000``. + +The ``exponent`` field is the scale of corresponding statistics data. It has two +values as follows: + * ``KVM_STATS_SCALE_POW10`` + The scale is based on power of 10. It is used for measurement of time and + CPU clock cycles. + * ``KVM_STATS_SCALE_POW2`` + The scale is based on power of 2. It is used for measurement of memory size. + +The ``size`` field is the number of values of this statistics data. It is in the +unit of ``unsigned long`` for VCPU or ``__u64`` for VM. + +The ``unused1`` and ``unused2`` fields are reserved for future +support for other types of statistics data, like log/linear histogram. + +The ``name`` field points to the name string of the statistics data. The name +string starts at the end of ``struct kvm_stats_desc``. +The maximum length (including trailing '\0') is indicated by ``name_size`` +in ``struct kvm_stats_header``. + +The Stats Data block contains an array of data values of type ``struct +kvm_vm_stats_data`` or ``struct kvm_vcpu_stats_data``. It would be read by +user space periodically to pull statistics data. +The order of data value in Stats Data block is the same as the order of +descriptors in Descriptors block. + * Statistics data for VM:: + + struct kvm_vm_stats_data { + unsigned long value[0]; + }; + + * Statistics data for VCPU:: + + struct kvm_vcpu_stats_data { + __u64 value[0]; + }; + 5. The kvm_run structure ======================== @@ -6888,3 +7051,11 @@ depends on the individual hypercall. Right now, the only bit that can be set is bit 12, corresponding to KVM_HC_PAGE_ENC_STATUS. The hypercall returns ENOSYS if bit 12 is not set or KVM_CAP_EXIT_HYPERCALL is not enabled. + +8.33 KVM_CAP_STATS_BINARY_FD +---------------------------- + +:Architectures: all + +This capability indicates the feature that user space can create get a file +descriptor for every VM and VCPU to read statistics data in binary format.
Signed-off-by: Jing Zhang <jingzhangos@google.com> --- Documentation/virt/kvm/api.rst | 171 +++++++++++++++++++++++++++++++++ 1 file changed, 171 insertions(+)