[linux-2.6-block.git] / Documentation / accounting / taskstats-struct.rst

====================
The struct taskstats
====================

This document contains an explanation of the struct taskstats fields.

There are three different groups of fields in the struct taskstats:

1) Common and basic accounting fields
    If CONFIG_TASKSTATS is set, the taskstats interface is enabled and
    the common fields and basic accounting fields are collected for
    delivery at do_exit() of a task.
2) Delay accounting fields
    These fields are placed between::

	/* Delay accounting fields start */

    and::

	/* Delay accounting fields end */

    Their values are collected if CONFIG_TASK_DELAY_ACCT is set.
3) Extended accounting fields
    These fields are placed between::

	/* Extended accounting fields start */

    and::

	/* Extended accounting fields end */

    Their values are collected if CONFIG_TASK_XACCT is set.

4) Per-task and per-thread context switch count statistics

5) Time accounting for SMT machines

6) Extended delay accounting fields for memory reclaim

Future extension should add fields to the end of the taskstats struct, and
should not change the relative position of each field within the struct.

::

  struct taskstats {

1) Common and basic accounting fields::

	/* The version number of this struct. This field is always set to
	 * TAKSTATS_VERSION, which is defined in <linux/taskstats.h>.
	 * Each time the struct is changed, the value should be incremented.
	 */
	__u16	version;

	/* The exit code of a task. */
	__u32	ac_exitcode;		/* Exit status */

	/* The accounting flags of a task as defined in <linux/acct.h>
	 * Defined values are AFORK, ASU, ACOMPAT, ACORE, and AXSIG.
	 */
	__u8	ac_flag;		/* Record flags */

	/* The value of task_nice() of a task. */
	__u8	ac_nice;		/* task_nice */

	/* The name of the command that started this task. */
	char	ac_comm[TS_COMM_LEN];	/* Command name */

	/* The scheduling discipline as set in task->policy field. */
	__u8	ac_sched;		/* Scheduling discipline */

	__u8	ac_pad[3];
	__u32	ac_uid;			/* User ID */
	__u32	ac_gid;			/* Group ID */
	__u32	ac_pid;			/* Process ID */
	__u32	ac_ppid;		/* Parent process ID */

	/* The time when a task begins, in [secs] since 1970. */
	__u32	ac_btime;		/* Begin time [sec since 1970] */

	/* The elapsed time of a task, in [usec]. */
	__u64	ac_etime;		/* Elapsed time [usec] */

	/* The user CPU time of a task, in [usec]. */
	__u64	ac_utime;		/* User CPU time [usec] */

	/* The system CPU time of a task, in [usec]. */
	__u64	ac_stime;		/* System CPU time [usec] */

	/* The minor page fault count of a task, as set in task->min_flt. */
	__u64	ac_minflt;		/* Minor Page Fault Count */

	/* The major page fault count of a task, as set in task->maj_flt. */
	__u64	ac_majflt;		/* Major Page Fault Count */


2) Delay accounting fields::

	/* Delay accounting fields start
	 *
	 * All values, until the comment "Delay accounting fields end" are
	 * available only if delay accounting is enabled, even though the last
	 * few fields are not delays
	 *
	 * xxx_count is the number of delay values recorded
	 * xxx_delay_total is the corresponding cumulative delay in nanoseconds
	 *
	 * xxx_delay_total wraps around to zero on overflow
	 * xxx_count incremented regardless of overflow
	 */

	/* Delay waiting for cpu, while runnable
	 * count, delay_total NOT updated atomically
	 */
	__u64	cpu_count;
	__u64	cpu_delay_total;

	/* Following four fields atomically updated using task->delays->lock */

	/* Delay waiting for synchronous block I/O to complete
	 * does not account for delays in I/O submission
	 */
	__u64	blkio_count;
	__u64	blkio_delay_total;

	/* Delay waiting for page fault I/O (swap in only) */
	__u64	swapin_count;
	__u64	swapin_delay_total;

	/* cpu "wall-clock" running time
	 * On some architectures, value will adjust for cpu time stolen
	 * from the kernel in involuntary waits due to virtualization.
	 * Value is cumulative, in nanoseconds, without a corresponding count
	 * and wraps around to zero silently on overflow
	 */
	__u64	cpu_run_real_total;

	/* cpu "virtual" running time
	 * Uses time intervals seen by the kernel i.e. no adjustment
	 * for kernel's involuntary waits due to virtualization.
	 * Value is cumulative, in nanoseconds, without a corresponding count
	 * and wraps around to zero silently on overflow
	 */
	__u64	cpu_run_virtual_total;
	/* Delay accounting fields end */
	/* version 1 ends here */


3) Extended accounting fields::

	/* Extended accounting fields start */

	/* Accumulated RSS usage in duration of a task, in MBytes-usecs.
	 * The current rss usage is added to this counter every time
	 * a tick is charged to a task's system time. So, at the end we
	 * will have memory usage multiplied by system time. Thus an
	 * average usage per system time unit can be calculated.
	 */
	__u64	coremem;		/* accumulated RSS usage in MB-usec */

	/* Accumulated virtual memory usage in duration of a task.
	 * Same as acct_rss_mem1 above except that we keep track of VM usage.
	 */
	__u64	virtmem;		/* accumulated VM usage in MB-usec */

	/* High watermark of RSS usage in duration of a task, in KBytes. */
	__u64	hiwater_rss;		/* High-watermark of RSS usage */

	/* High watermark of VM  usage in duration of a task, in KBytes. */
	__u64	hiwater_vm;		/* High-water virtual memory usage */

	/* The following four fields are I/O statistics of a task. */
	__u64	read_char;		/* bytes read */
	__u64	write_char;		/* bytes written */
	__u64	read_syscalls;		/* read syscalls */
	__u64	write_syscalls;		/* write syscalls */

	/* Extended accounting fields end */

4) Per-task and per-thread statistics::

	__u64	nvcsw;			/* Context voluntary switch counter */
	__u64	nivcsw;			/* Context involuntary switch counter */

5) Time accounting for SMT machines::

	__u64	ac_utimescaled;		/* utime scaled on frequency etc */
	__u64	ac_stimescaled;		/* stime scaled on frequency etc */
	__u64	cpu_scaled_run_real_total; /* scaled cpu_run_real_total */

6) Extended delay accounting fields for memory reclaim::

	/* Delay waiting for memory reclaim */
	__u64	freepages_count;
	__u64	freepages_delay_total;

::

  }
Commit	Line	Data
c3123552	1	====================
db5fed26	2	The struct taskstats
c3123552	3	====================
db5fed26 JL	4
	5	This document contains an explanation of the struct taskstats fields.
	6
	7	There are three different groups of fields in the struct taskstats:
	8
	9	1) Common and basic accounting fields
d9195881	10	If CONFIG_TASKSTATS is set, the taskstats interface is enabled and
db5fed26 JL	11	the common fields and basic accounting fields are collected for
	12	delivery at do_exit() of a task.
	13	2) Delay accounting fields
c3123552 MCC	14	These fields are placed between::
	15
	16	/* Delay accounting fields start */
	17
	18	and::
	19
	20	/* Delay accounting fields end */
	21
db5fed26 JL	22	Their values are collected if CONFIG_TASK_DELAY_ACCT is set.
db5fed26 JL	23	3) Extended accounting fields
c3123552 MCC	24	These fields are placed between::
	25
	26	/* Extended accounting fields start */
	27
	28	and::
	29
	30	/* Extended accounting fields end */
	31
db5fed26 JL	32	Their values are collected if CONFIG_TASK_XACCT is set.
db5fed26 JL	33
b663a79c MU	34	4) Per-task and per-thread context switch count statistics
b663a79c MU	35
f93f18cd HS	36	5) Time accounting for SMT machines
f93f18cd HS	37
016ae219 KK	38	6) Extended delay accounting fields for memory reclaim
016ae219 KK	39
db5fed26 JL	40	Future extension should add fields to the end of the taskstats struct, and
	41	should not change the relative position of each field within the struct.
	42
c3123552	43	::
db5fed26	44
c3123552 MCC	45	struct taskstats {
	46
	47	1) Common and basic accounting fields::
db5fed26	48
db5fed26 JL	49	/* The version number of this struct. This field is always set to
	50	* TAKSTATS_VERSION, which is defined in <linux/taskstats.h>.
	51	* Each time the struct is changed, the value should be incremented.
	52	*/
	53	__u16 version;
	54
c3123552	55	/* The exit code of a task. */
db5fed26 JL	56	__u32 ac_exitcode; /* Exit status */
db5fed26 JL	57
c3123552	58	/* The accounting flags of a task as defined in <linux/acct.h>
db5fed26 JL	59	* Defined values are AFORK, ASU, ACOMPAT, ACORE, and AXSIG.
	60	*/
	61	__u8 ac_flag; /* Record flags */
	62
c3123552	63	/* The value of task_nice() of a task. */
db5fed26 JL	64	__u8 ac_nice; /* task_nice */
db5fed26 JL	65
c3123552	66	/* The name of the command that started this task. */
db5fed26 JL	67	char ac_comm[TS_COMM_LEN]; /* Command name */
db5fed26 JL	68
c3123552	69	/* The scheduling discipline as set in task->policy field. */
db5fed26 JL	70	__u8 ac_sched; /* Scheduling discipline */
	71
	72	__u8 ac_pad[3];
	73	__u32 ac_uid; /* User ID */
	74	__u32 ac_gid; /* Group ID */
	75	__u32 ac_pid; /* Process ID */
	76	__u32 ac_ppid; /* Parent process ID */
	77
c3123552	78	/* The time when a task begins, in [secs] since 1970. */
db5fed26 JL	79	__u32 ac_btime; /* Begin time [sec since 1970] */
db5fed26 JL	80
c3123552	81	/* The elapsed time of a task, in [usec]. */
db5fed26 JL	82	__u64 ac_etime; /* Elapsed time [usec] */
db5fed26 JL	83
c3123552	84	/* The user CPU time of a task, in [usec]. */
db5fed26 JL	85	__u64 ac_utime; /* User CPU time [usec] */
db5fed26 JL	86
c3123552	87	/* The system CPU time of a task, in [usec]. */
db5fed26 JL	88	__u64 ac_stime; /* System CPU time [usec] */
db5fed26 JL	89
c3123552	90	/* The minor page fault count of a task, as set in task->min_flt. */
db5fed26 JL	91	__u64 ac_minflt; /* Minor Page Fault Count */
	92
	93	/* The major page fault count of a task, as set in task->maj_flt. */
	94	__u64 ac_majflt; /* Major Page Fault Count */
	95
	96
c3123552 MCC	97	2) Delay accounting fields::
c3123552 MCC	98
db5fed26 JL	99	/* Delay accounting fields start
	100	*
	101	* All values, until the comment "Delay accounting fields end" are
	102	* available only if delay accounting is enabled, even though the last
	103	* few fields are not delays
	104	*
	105	* xxx_count is the number of delay values recorded
	106	* xxx_delay_total is the corresponding cumulative delay in nanoseconds
	107	*
	108	* xxx_delay_total wraps around to zero on overflow
	109	* xxx_count incremented regardless of overflow
	110	*/
	111
	112	/* Delay waiting for cpu, while runnable
	113	* count, delay_total NOT updated atomically
	114	*/
	115	__u64 cpu_count;
	116	__u64 cpu_delay_total;
	117
	118	/* Following four fields atomically updated using task->delays->lock */
	119
	120	/* Delay waiting for synchronous block I/O to complete
	121	* does not account for delays in I/O submission
	122	*/
	123	__u64 blkio_count;
	124	__u64 blkio_delay_total;
	125
	126	/* Delay waiting for page fault I/O (swap in only) */
	127	__u64 swapin_count;
	128	__u64 swapin_delay_total;
	129
	130	/* cpu "wall-clock" running time
	131	* On some architectures, value will adjust for cpu time stolen
	132	* from the kernel in involuntary waits due to virtualization.
	133	* Value is cumulative, in nanoseconds, without a corresponding count
	134	* and wraps around to zero silently on overflow
	135	*/
	136	__u64 cpu_run_real_total;
	137
	138	/* cpu "virtual" running time
	139	* Uses time intervals seen by the kernel i.e. no adjustment
	140	* for kernel's involuntary waits due to virtualization.
	141	* Value is cumulative, in nanoseconds, without a corresponding count
	142	* and wraps around to zero silently on overflow
	143	*/
	144	__u64 cpu_run_virtual_total;
	145	/* Delay accounting fields end */
	146	/* version 1 ends here */
	147
	148
c3123552 MCC	149	3) Extended accounting fields::
c3123552 MCC	150
db5fed26 JL	151	/* Extended accounting fields start */
	152
	153	/* Accumulated RSS usage in duration of a task, in MBytes-usecs.
	154	* The current rss usage is added to this counter every time
	155	* a tick is charged to a task's system time. So, at the end we
	156	* will have memory usage multiplied by system time. Thus an
	157	* average usage per system time unit can be calculated.
	158	*/
	159	__u64 coremem; /* accumulated RSS usage in MB-usec */
	160
c3123552	161	/* Accumulated virtual memory usage in duration of a task.
db5fed26 JL	162	* Same as acct_rss_mem1 above except that we keep track of VM usage.
	163	*/
	164	__u64 virtmem; /* accumulated VM usage in MB-usec */
	165
c3123552	166	/* High watermark of RSS usage in duration of a task, in KBytes. */
db5fed26 JL	167	__u64 hiwater_rss; /* High-watermark of RSS usage */
db5fed26 JL	168
c3123552	169	/* High watermark of VM usage in duration of a task, in KBytes. */
db5fed26 JL	170	__u64 hiwater_vm; /* High-water virtual memory usage */
	171
	172	/* The following four fields are I/O statistics of a task. */
	173	__u64 read_char; /* bytes read */
	174	__u64 write_char; /* bytes written */
	175	__u64 read_syscalls; /* read syscalls */
	176	__u64 write_syscalls; /* write syscalls */
	177
	178	/* Extended accounting fields end */
	179
c3123552 MCC	180	4) Per-task and per-thread statistics::
c3123552 MCC	181
b663a79c MU	182	__u64 nvcsw; /* Context voluntary switch counter */
	183	__u64 nivcsw; /* Context involuntary switch counter */
	184
c3123552 MCC	185	5) Time accounting for SMT machines::
c3123552 MCC	186
f93f18cd HS	187	__u64 ac_utimescaled; /* utime scaled on frequency etc */
	188	__u64 ac_stimescaled; /* stime scaled on frequency etc */
	189	__u64 cpu_scaled_run_real_total; /* scaled cpu_run_real_total */
016ae219	190
c3123552 MCC	191	6) Extended delay accounting fields for memory reclaim::
c3123552 MCC	192
016ae219 KK	193	/* Delay waiting for memory reclaim */
	194	__u64 freepages_count;
	195	__u64 freepages_delay_total;
c3123552 MCC	196
	197	::
	198
	199	}