aboutsummaryrefslogtreecommitdiff
path: root/Documentation/accounting
diff options
context:
space:
mode:
Diffstat (limited to 'Documentation/accounting')
-rw-r--r--Documentation/accounting/.gitignore1
-rw-r--r--Documentation/accounting/Makefile10
-rw-r--r--Documentation/accounting/cgroupstats.txt27
-rw-r--r--Documentation/accounting/delay-accounting.txt11
-rw-r--r--Documentation/accounting/getdelays.c189
-rw-r--r--Documentation/accounting/taskstats-struct.txt21
6 files changed, 221 insertions, 38 deletions
diff --git a/Documentation/accounting/.gitignore b/Documentation/accounting/.gitignore
new file mode 100644
index 00000000000..86485203c4a
--- /dev/null
+++ b/Documentation/accounting/.gitignore
@@ -0,0 +1 @@
+getdelays
diff --git a/Documentation/accounting/Makefile b/Documentation/accounting/Makefile
new file mode 100644
index 00000000000..31929eb875b
--- /dev/null
+++ b/Documentation/accounting/Makefile
@@ -0,0 +1,10 @@
+# kbuild trick to avoid linker error. Can be omitted if a module is built.
+obj- := dummy.o
+
+# List of programs to build
+hostprogs-y := getdelays
+
+# Tell kbuild to always build the programs
+always := $(hostprogs-y)
+
+HOSTCFLAGS_getdelays.o += -I$(objtree)/usr/include
diff --git a/Documentation/accounting/cgroupstats.txt b/Documentation/accounting/cgroupstats.txt
new file mode 100644
index 00000000000..d16a9849e60
--- /dev/null
+++ b/Documentation/accounting/cgroupstats.txt
@@ -0,0 +1,27 @@
+Control Groupstats is inspired by the discussion at
+http://lkml.org/lkml/2007/4/11/187 and implements per cgroup statistics as
+suggested by Andrew Morton in http://lkml.org/lkml/2007/4/11/263.
+
+Per cgroup statistics infrastructure re-uses code from the taskstats
+interface. A new set of cgroup operations are registered with commands
+and attributes specific to cgroups. It should be very easy to
+extend per cgroup statistics, by adding members to the cgroupstats
+structure.
+
+The current model for cgroupstats is a pull, a push model (to post
+statistics on interesting events), should be very easy to add. Currently
+user space requests for statistics by passing the cgroup path.
+Statistics about the state of all the tasks in the cgroup is returned to
+user space.
+
+NOTE: We currently rely on delay accounting for extracting information
+about tasks blocked on I/O. If CONFIG_TASK_DELAY_ACCT is disabled, this
+information will not be available.
+
+To extract cgroup statistics a utility very similar to getdelays.c
+has been developed, the sample output of the utility is shown below
+
+~/balbir/cgroupstats # ./getdelays -C "/sys/fs/cgroup/a"
+sleeping 1, blocked 0, running 1, stopped 0, uninterruptible 0
+~/balbir/cgroupstats # ./getdelays -C "/sys/fs/cgroup"
+sleeping 155, blocked 0, running 1, stopped 0, uninterruptible 2
diff --git a/Documentation/accounting/delay-accounting.txt b/Documentation/accounting/delay-accounting.txt
index 1443cd71d26..8a12f0730c9 100644
--- a/Documentation/accounting/delay-accounting.txt
+++ b/Documentation/accounting/delay-accounting.txt
@@ -11,6 +11,7 @@ the delays experienced by a task while
a) waiting for a CPU (while being runnable)
b) completion of synchronous block I/O initiated by the task
c) swapping in pages
+d) memory reclaim
and makes these statistics available to userspace through
the taskstats interface.
@@ -41,7 +42,7 @@ this structure. See
include/linux/taskstats.h
for a description of the fields pertaining to delay accounting.
It will generally be in the form of counters returning the cumulative
-delay seen for cpu, sync block I/O, swapin etc.
+delay seen for cpu, sync block I/O, swapin, memory reclaim etc.
Taking the difference of two successive readings of a given
counter (say cpu_delay_total) for a task will give the delay
@@ -94,7 +95,9 @@ CPU count real total virtual total delay total
7876 92005750 100000000 24001500
IO count delay total
0 0
-MEM count delay total
+SWAP count delay total
+ 0 0
+RECLAIM count delay total
0 0
Get delays seen in executing a given simple command
@@ -108,5 +111,7 @@ CPU count real total virtual total delay total
6 4000250 4000000 0
IO count delay total
0 0
-MEM count delay total
+SWAP count delay total
+ 0 0
+RECLAIM count delay total
0 0
diff --git a/Documentation/accounting/getdelays.c b/Documentation/accounting/getdelays.c
index e9126e794ed..f40578026a0 100644
--- a/Documentation/accounting/getdelays.c
+++ b/Documentation/accounting/getdelays.c
@@ -21,11 +21,12 @@
#include <sys/types.h>
#include <sys/stat.h>
#include <sys/socket.h>
-#include <sys/types.h>
+#include <sys/wait.h>
#include <signal.h>
#include <linux/genetlink.h>
#include <linux/taskstats.h>
+#include <linux/cgroupstats.h>
/*
* Generic macros for dealing with netlink sockets. Might be duplicated
@@ -49,7 +50,7 @@ char name[100];
int dbg;
int print_delays;
int print_io_accounting;
-__u64 stime, utime;
+int print_task_context_switch_counts;
#define PRINTF(fmt, arg...) { \
if (dbg) { \
@@ -61,8 +62,6 @@ __u64 stime, utime;
#define MAX_MSG_SIZE 1024
/* Maximum number of cpus expected to be specified in a cpumask */
#define MAX_CPUS 32
-/* Maximum length of pathname to log file */
-#define MAX_FILENAME 256
struct msgtemplate {
struct nlmsghdr n;
@@ -72,6 +71,17 @@ struct msgtemplate {
char cpumask[100+6*MAX_CPUS];
+static void usage(void)
+{
+ fprintf(stderr, "getdelays [-dilv] [-w logfile] [-r bufsize] "
+ "[-m cpumask] [-t tgid] [-p pid]\n");
+ fprintf(stderr, " -d: print delayacct stats\n");
+ fprintf(stderr, " -i: print IO accounting (works only with -p)\n");
+ fprintf(stderr, " -l: listen forever\n");
+ fprintf(stderr, " -v: debug on\n");
+ fprintf(stderr, " -C: container path\n");
+}
+
/*
* Create a raw netlink socket and bind
*/
@@ -87,10 +97,9 @@ static int create_nl_socket(int protocol)
if (rcvbufsz)
if (setsockopt(fd, SOL_SOCKET, SO_RCVBUF,
&rcvbufsz, sizeof(rcvbufsz)) < 0) {
- fprintf(stderr, "Unable to set socket rcv buf size "
- "to %d\n",
+ fprintf(stderr, "Unable to set socket rcv buf size to %d\n",
rcvbufsz);
- return -1;
+ goto error;
}
memset(&local, 0, sizeof(local));
@@ -106,7 +115,7 @@ error:
}
-int send_cmd(int sd, __u16 nlmsg_type, __u32 nlmsg_pid,
+static int send_cmd(int sd, __u16 nlmsg_type, __u32 nlmsg_pid,
__u8 genl_cmd, __u16 nla_type,
void *nla_data, int nla_len)
{
@@ -150,7 +159,7 @@ int send_cmd(int sd, __u16 nlmsg_type, __u32 nlmsg_pid,
* Probe the controller in genetlink to find the family id
* for the TASKSTATS family
*/
-int get_family_id(int sd)
+static int get_family_id(int sd)
{
struct {
struct nlmsghdr n;
@@ -158,7 +167,7 @@ int get_family_id(int sd)
char buf[256];
} ans;
- int id, rc;
+ int id = 0, rc;
struct nlattr *na;
int rep_len;
@@ -166,6 +175,8 @@ int get_family_id(int sd)
rc = send_cmd(sd, GENL_ID_CTRL, getpid(), CTRL_CMD_GETFAMILY,
CTRL_ATTR_FAMILY_NAME, (void *)name,
strlen(TASKSTATS_GENL_NAME)+1);
+ if (rc < 0)
+ return 0; /* sendto() failure? */
rep_len = recv(sd, &ans, sizeof(ans), 0);
if (ans.n.nlmsg_type == NLMSG_ERROR ||
@@ -180,23 +191,59 @@ int get_family_id(int sd)
return id;
}
-void print_delayacct(struct taskstats *t)
+#define average_ms(t, c) (t / 1000000ULL / (c ? c : 1))
+
+static void print_delayacct(struct taskstats *t)
+{
+ printf("\n\nCPU %15s%15s%15s%15s%15s\n"
+ " %15llu%15llu%15llu%15llu%15.3fms\n"
+ "IO %15s%15s%15s\n"
+ " %15llu%15llu%15llums\n"
+ "SWAP %15s%15s%15s\n"
+ " %15llu%15llu%15llums\n"
+ "RECLAIM %12s%15s%15s\n"
+ " %15llu%15llu%15llums\n",
+ "count", "real total", "virtual total",
+ "delay total", "delay average",
+ (unsigned long long)t->cpu_count,
+ (unsigned long long)t->cpu_run_real_total,
+ (unsigned long long)t->cpu_run_virtual_total,
+ (unsigned long long)t->cpu_delay_total,
+ average_ms((double)t->cpu_delay_total, t->cpu_count),
+ "count", "delay total", "delay average",
+ (unsigned long long)t->blkio_count,
+ (unsigned long long)t->blkio_delay_total,
+ average_ms(t->blkio_delay_total, t->blkio_count),
+ "count", "delay total", "delay average",
+ (unsigned long long)t->swapin_count,
+ (unsigned long long)t->swapin_delay_total,
+ average_ms(t->swapin_delay_total, t->swapin_count),
+ "count", "delay total", "delay average",
+ (unsigned long long)t->freepages_count,
+ (unsigned long long)t->freepages_delay_total,
+ average_ms(t->freepages_delay_total, t->freepages_count));
+}
+
+static void task_context_switch_counts(struct taskstats *t)
{
- printf("\n\nCPU %15s%15s%15s%15s\n"
- " %15llu%15llu%15llu%15llu\n"
- "IO %15s%15s\n"
- " %15llu%15llu\n"
- "MEM %15s%15s\n"
- " %15llu%15llu\n\n",
- "count", "real total", "virtual total", "delay total",
- t->cpu_count, t->cpu_run_real_total, t->cpu_run_virtual_total,
- t->cpu_delay_total,
- "count", "delay total",
- t->blkio_count, t->blkio_delay_total,
- "count", "delay total", t->swapin_count, t->swapin_delay_total);
+ printf("\n\nTask %15s%15s\n"
+ " %15llu%15llu\n",
+ "voluntary", "nonvoluntary",
+ (unsigned long long)t->nvcsw, (unsigned long long)t->nivcsw);
}
-void print_ioacct(struct taskstats *t)
+static void print_cgroupstats(struct cgroupstats *c)
+{
+ printf("sleeping %llu, blocked %llu, running %llu, stopped %llu, "
+ "uninterruptible %llu\n", (unsigned long long)c->nr_sleeping,
+ (unsigned long long)c->nr_io_wait,
+ (unsigned long long)c->nr_running,
+ (unsigned long long)c->nr_stopped,
+ (unsigned long long)c->nr_uninterruptible);
+}
+
+
+static void print_ioacct(struct taskstats *t)
{
printf("%s: read=%llu, write=%llu, cancelled_write=%llu\n",
t->ac_comm,
@@ -207,7 +254,8 @@ void print_ioacct(struct taskstats *t)
int main(int argc, char *argv[])
{
- int c, rc, rep_len, aggr_len, len2, cmd_type;
+ int c, rc, rep_len, aggr_len, len2;
+ int cmd_type = TASKSTATS_CMD_ATTR_UNSPEC;
__u16 id;
__u32 mypid;
@@ -221,13 +269,18 @@ int main(int argc, char *argv[])
int count = 0;
int write_file = 0;
int maskset = 0;
- char logfile[128];
+ char *logfile = NULL;
int loop = 0;
+ int containerset = 0;
+ char *containerpath = NULL;
+ int cfd = 0;
+ int forking = 0;
+ sigset_t sigset;
struct msgtemplate msg;
- while (1) {
- c = getopt(argc, argv, "diw:r:m:t:p:v:l");
+ while (!forking) {
+ c = getopt(argc, argv, "qdiw:r:m:t:p:vlC:c:");
if (c < 0)
break;
@@ -240,8 +293,16 @@ int main(int argc, char *argv[])
printf("printing IO accounting\n");
print_io_accounting = 1;
break;
+ case 'q':
+ printf("printing task/process context switch rates\n");
+ print_task_context_switch_counts = 1;
+ break;
+ case 'C':
+ containerset = 1;
+ containerpath = optarg;
+ break;
case 'w':
- strncpy(logfile, optarg, MAX_FILENAME);
+ logfile = strdup(optarg);
printf("write to file %s\n", logfile);
write_file = 1;
break;
@@ -253,6 +314,7 @@ int main(int argc, char *argv[])
break;
case 'm':
strncpy(cpumask, optarg, sizeof(cpumask));
+ cpumask[sizeof(cpumask) - 1] = '\0';
maskset = 1;
printf("cpumask %s maskset %d\n", cpumask, maskset);
break;
@@ -268,6 +330,28 @@ int main(int argc, char *argv[])
err(1, "Invalid pid\n");
cmd_type = TASKSTATS_CMD_ATTR_PID;
break;
+ case 'c':
+
+ /* Block SIGCHLD for sigwait() later */
+ if (sigemptyset(&sigset) == -1)
+ err(1, "Failed to empty sigset");
+ if (sigaddset(&sigset, SIGCHLD))
+ err(1, "Failed to set sigchld in sigset");
+ sigprocmask(SIG_BLOCK, &sigset, NULL);
+
+ /* fork/exec a child */
+ tid = fork();
+ if (tid < 0)
+ err(1, "Fork failed\n");
+ if (tid == 0)
+ if (execvp(argv[optind - 1],
+ &argv[optind - 1]) < 0)
+ exit(-1);
+
+ /* Set the command type and avoid further processing */
+ cmd_type = TASKSTATS_CMD_ATTR_PID;
+ forking = 1;
+ break;
case 'v':
printf("debug on\n");
dbg = 1;
@@ -277,7 +361,7 @@ int main(int argc, char *argv[])
loop = 1;
break;
default:
- printf("Unknown option %d\n", c);
+ usage();
exit(-1);
}
}
@@ -314,6 +398,20 @@ int main(int argc, char *argv[])
}
}
+ if (tid && containerset) {
+ fprintf(stderr, "Select either -t or -C, not both\n");
+ goto err;
+ }
+
+ /*
+ * If we forked a child, wait for it to exit. Cannot use waitpid()
+ * as all the delicious data would be reaped as part of the wait
+ */
+ if (tid && forking) {
+ int sig_received;
+ sigwait(&sigset, &sig_received);
+ }
+
if (tid) {
rc = send_cmd(nl_sd, id, mypid, TASKSTATS_CMD_GET,
cmd_type, &tid, sizeof(__u32));
@@ -324,9 +422,25 @@ int main(int argc, char *argv[])
}
}
- do {
- int i;
+ if (containerset) {
+ cfd = open(containerpath, O_RDONLY);
+ if (cfd < 0) {
+ perror("error opening container file");
+ goto err;
+ }
+ rc = send_cmd(nl_sd, id, mypid, CGROUPSTATS_CMD_GET,
+ CGROUPSTATS_CMD_ATTR_FD, &cfd, sizeof(__u32));
+ if (rc < 0) {
+ perror("error sending cgroupstats command");
+ goto err;
+ }
+ }
+ if (!maskset && !tid && !containerset) {
+ usage();
+ goto err;
+ }
+ do {
rep_len = recv(nl_sd, &msg, sizeof(msg), 0);
PRINTF("received %d bytes\n", rep_len);
@@ -343,7 +457,7 @@ int main(int argc, char *argv[])
goto done;
}
- PRINTF("nlmsghdr size=%d, nlmsg_len=%d, rep_len=%d\n",
+ PRINTF("nlmsghdr size=%zu, nlmsg_len=%d, rep_len=%d\n",
sizeof(struct nlmsghdr), msg.n.nlmsg_len, rep_len);
@@ -351,7 +465,6 @@ int main(int argc, char *argv[])
na = (struct nlattr *) GENLMSG_DATA(&msg);
len = 0;
- i = 0;
while (len < rep_len) {
len += NLA_ALIGN(na->nla_len);
switch (na->nla_type) {
@@ -381,6 +494,8 @@ int main(int argc, char *argv[])
print_delayacct((struct taskstats *) NLA_DATA(na));
if (print_io_accounting)
print_ioacct((struct taskstats *) NLA_DATA(na));
+ if (print_task_context_switch_counts)
+ task_context_switch_counts((struct taskstats *) NLA_DATA(na));
if (fd) {
if (write(fd, NLA_DATA(na), na->nla_len) < 0) {
err(1,"write error\n");
@@ -400,9 +515,13 @@ int main(int argc, char *argv[])
}
break;
+ case CGROUPSTATS_TYPE_CGROUP_STATS:
+ print_cgroupstats(NLA_DATA(na));
+ break;
default:
fprintf(stderr, "Unknown nla_type %d\n",
na->nla_type);
+ case TASKSTATS_TYPE_NULL:
break;
}
na = (struct nlattr *) (GENLMSG_DATA(&msg) + len);
@@ -421,5 +540,7 @@ err:
close(nl_sd);
if (fd)
close(fd);
+ if (cfd)
+ close(cfd);
return 0;
}
diff --git a/Documentation/accounting/taskstats-struct.txt b/Documentation/accounting/taskstats-struct.txt
index 661c797eaf7..e7512c061c1 100644
--- a/Documentation/accounting/taskstats-struct.txt
+++ b/Documentation/accounting/taskstats-struct.txt
@@ -6,7 +6,7 @@ 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 inteface is enabled and
+ 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
@@ -22,6 +22,12 @@ There are three different groups of fields in the struct taskstats:
/* 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.
@@ -158,4 +164,17 @@ struct taskstats {
/* 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;
}
generated by cgit v1.2.3-70-g09d2 (git 2.46.0) at 2025-12-15 19:58:40 +0000