diff mbox series

[v3,3/4] KVM: stats: Add documentation for statistics data binary interface

Message ID 20210423181727.596466-4-jingzhangos@google.com
State Superseded
Headers show
Series KVM statistics data fd-based binary interface | expand

Commit Message

Jing Zhang April 23, 2021, 6:17 p.m. UTC
Signed-off-by: Jing Zhang <jingzhangos@google.com>
---
 Documentation/virt/kvm/api.rst | 171 +++++++++++++++++++++++++++++++++
 1 file changed, 171 insertions(+)

Comments

Jing Zhang May 13, 2021, 8:54 p.m. UTC | #1
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 mbox series

Patch

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.