aboutsummaryrefslogtreecommitdiff
path: root/tools
diff options
context:
space:
mode:
Diffstat (limited to 'tools')
-rw-r--r--tools/hv/hv_kvp_daemon.c10
-rw-r--r--tools/perf/builtin-stat.c8
-rw-r--r--tools/perf/util/header.c48
-rw-r--r--tools/perf/util/include/linux/bitops.h2
-rw-r--r--tools/perf/util/map.c29
-rw-r--r--tools/perf/util/session.c12
-rw-r--r--tools/perf/util/session.h1
-rw-r--r--tools/perf/util/trace-event-parse.c3
-rw-r--r--tools/power/x86/turbostat/Makefile1
-rw-r--r--tools/power/x86/turbostat/turbostat.877
-rw-r--r--tools/power/x86/turbostat/turbostat.c1333
11 files changed, 957 insertions, 567 deletions
diff --git a/tools/hv/hv_kvp_daemon.c b/tools/hv/hv_kvp_daemon.c
index 146fd6147e8..d9834b36294 100644
--- a/tools/hv/hv_kvp_daemon.c
+++ b/tools/hv/hv_kvp_daemon.c
@@ -701,14 +701,18 @@ int main(void)
pfd.fd = fd;
while (1) {
+ struct sockaddr *addr_p = (struct sockaddr *) &addr;
+ socklen_t addr_l = sizeof(addr);
pfd.events = POLLIN;
pfd.revents = 0;
poll(&pfd, 1, -1);
- len = recv(fd, kvp_recv_buffer, sizeof(kvp_recv_buffer), 0);
+ len = recvfrom(fd, kvp_recv_buffer, sizeof(kvp_recv_buffer), 0,
+ addr_p, &addr_l);
- if (len < 0) {
- syslog(LOG_ERR, "recv failed; error:%d", len);
+ if (len < 0 || addr.nl_pid) {
+ syslog(LOG_ERR, "recvfrom failed; pid:%u error:%d %s",
+ addr.nl_pid, errno, strerror(errno));
close(fd);
return -1;
}
diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index 262589991ea..07b5c7703dd 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -1179,6 +1179,12 @@ int cmd_stat(int argc, const char **argv, const char *prefix __used)
fprintf(stderr, "cannot use both --output and --log-fd\n");
usage_with_options(stat_usage, options);
}
+
+ if (output_fd < 0) {
+ fprintf(stderr, "argument to --log-fd must be a > 0\n");
+ usage_with_options(stat_usage, options);
+ }
+
if (!output) {
struct timespec tm;
mode = append_file ? "a" : "w";
@@ -1190,7 +1196,7 @@ int cmd_stat(int argc, const char **argv, const char *prefix __used)
}
clock_gettime(CLOCK_REALTIME, &tm);
fprintf(output, "# started on %s\n", ctime(&tm.tv_sec));
- } else if (output_fd != 2) {
+ } else if (output_fd > 0) {
mode = append_file ? "a" : "w";
output = fdopen(output_fd, mode);
if (!output) {
diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c
index 2dd5edf161b..e909d43cf54 100644
--- a/tools/perf/util/header.c
+++ b/tools/perf/util/header.c
@@ -1942,7 +1942,6 @@ int perf_file_header__read(struct perf_file_header *header,
else
return -1;
} else if (ph->needs_swap) {
- unsigned int i;
/*
* feature bitmap is declared as an array of unsigned longs --
* not good since its size can differ between the host that
@@ -1958,14 +1957,17 @@ int perf_file_header__read(struct perf_file_header *header,
* file), punt and fallback to the original behavior --
* clearing all feature bits and setting buildid.
*/
- for (i = 0; i < BITS_TO_LONGS(HEADER_FEAT_BITS); ++i)
- header->adds_features[i] = bswap_64(header->adds_features[i]);
+ mem_bswap_64(&header->adds_features,
+ BITS_TO_U64(HEADER_FEAT_BITS));
if (!test_bit(HEADER_HOSTNAME, header->adds_features)) {
- for (i = 0; i < BITS_TO_LONGS(HEADER_FEAT_BITS); ++i) {
- header->adds_features[i] = bswap_64(header->adds_features[i]);
- header->adds_features[i] = bswap_32(header->adds_features[i]);
- }
+ /* unswap as u64 */
+ mem_bswap_64(&header->adds_features,
+ BITS_TO_U64(HEADER_FEAT_BITS));
+
+ /* unswap as u32 */
+ mem_bswap_32(&header->adds_features,
+ BITS_TO_U32(HEADER_FEAT_BITS));
}
if (!test_bit(HEADER_HOSTNAME, header->adds_features)) {
@@ -2091,6 +2093,35 @@ static int read_attr(int fd, struct perf_header *ph,
return ret <= 0 ? -1 : 0;
}
+static int perf_evsel__set_tracepoint_name(struct perf_evsel *evsel)
+{
+ struct event_format *event = trace_find_event(evsel->attr.config);
+ char bf[128];
+
+ if (event == NULL)
+ return -1;
+
+ snprintf(bf, sizeof(bf), "%s:%s", event->system, event->name);
+ evsel->name = strdup(bf);
+ if (event->name == NULL)
+ return -1;
+
+ return 0;
+}
+
+static int perf_evlist__set_tracepoint_names(struct perf_evlist *evlist)
+{
+ struct perf_evsel *pos;
+
+ list_for_each_entry(pos, &evlist->entries, node) {
+ if (pos->attr.type == PERF_TYPE_TRACEPOINT &&
+ perf_evsel__set_tracepoint_name(pos))
+ return -1;
+ }
+
+ return 0;
+}
+
int perf_session__read_header(struct perf_session *session, int fd)
{
struct perf_header *header = &session->header;
@@ -2172,6 +2203,9 @@ int perf_session__read_header(struct perf_session *session, int fd)
lseek(fd, header->data_offset, SEEK_SET);
+ if (perf_evlist__set_tracepoint_names(session->evlist))
+ goto out_delete_evlist;
+
header->frozen = 1;
return 0;
out_errno:
diff --git a/tools/perf/util/include/linux/bitops.h b/tools/perf/util/include/linux/bitops.h
index f1584833bd2..587a230d207 100644
--- a/tools/perf/util/include/linux/bitops.h
+++ b/tools/perf/util/include/linux/bitops.h
@@ -8,6 +8,8 @@
#define BITS_PER_LONG __WORDSIZE
#define BITS_PER_BYTE 8
#define BITS_TO_LONGS(nr) DIV_ROUND_UP(nr, BITS_PER_BYTE * sizeof(long))
+#define BITS_TO_U64(nr) DIV_ROUND_UP(nr, BITS_PER_BYTE * sizeof(u64))
+#define BITS_TO_U32(nr) DIV_ROUND_UP(nr, BITS_PER_BYTE * sizeof(u32))
#define for_each_set_bit(bit, addr, size) \
for ((bit) = find_first_bit((addr), (size)); \
diff --git a/tools/perf/util/map.c b/tools/perf/util/map.c
index 35ae56864e4..a1f4e366914 100644
--- a/tools/perf/util/map.c
+++ b/tools/perf/util/map.c
@@ -669,25 +669,26 @@ struct machine *machines__find(struct rb_root *self, pid_t pid)
struct machine *machines__findnew(struct rb_root *self, pid_t pid)
{
char path[PATH_MAX];
- const char *root_dir;
+ const char *root_dir = "";
struct machine *machine = machines__find(self, pid);
- if (!machine || machine->pid != pid) {
- if (pid == HOST_KERNEL_ID || pid == DEFAULT_GUEST_KERNEL_ID)
- root_dir = "";
- else {
- if (!symbol_conf.guestmount)
- goto out;
- sprintf(path, "%s/%d", symbol_conf.guestmount, pid);
- if (access(path, R_OK)) {
- pr_err("Can't access file %s\n", path);
- goto out;
- }
- root_dir = path;
+ if (machine && (machine->pid == pid))
+ goto out;
+
+ if ((pid != HOST_KERNEL_ID) &&
+ (pid != DEFAULT_GUEST_KERNEL_ID) &&
+ (symbol_conf.guestmount)) {
+ sprintf(path, "%s/%d", symbol_conf.guestmount, pid);
+ if (access(path, R_OK)) {
+ pr_err("Can't access file %s\n", path);
+ machine = NULL;
+ goto out;
}
- machine = machines__add(self, pid, root_dir);
+ root_dir = path;
}
+ machine = machines__add(self, pid, root_dir);
+
out:
return machine;
}
diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
index 2600916efa8..56142d0fb8d 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -442,6 +442,16 @@ static void perf_tool__fill_defaults(struct perf_tool *tool)
tool->finished_round = process_finished_round_stub;
}
}
+
+void mem_bswap_32(void *src, int byte_size)
+{
+ u32 *m = src;
+ while (byte_size > 0) {
+ *m = bswap_32(*m);
+ byte_size -= sizeof(u32);
+ ++m;
+ }
+}
void mem_bswap_64(void *src, int byte_size)
{
@@ -916,7 +926,7 @@ static struct machine *
else
pid = event->ip.pid;
- return perf_session__find_machine(session, pid);
+ return perf_session__findnew_machine(session, pid);
}
return perf_session__find_host_machine(session);
diff --git a/tools/perf/util/session.h b/tools/perf/util/session.h
index 7a5434c0056..0c702e3f0a3 100644
--- a/tools/perf/util/session.h
+++ b/tools/perf/util/session.h
@@ -80,6 +80,7 @@ struct branch_info *machine__resolve_bstack(struct machine *self,
bool perf_session__has_traces(struct perf_session *self, const char *msg);
void mem_bswap_64(void *src, int byte_size);
+void mem_bswap_32(void *src, int byte_size);
void perf_event__attr_swap(struct perf_event_attr *attr);
int perf_session__create_kernel_maps(struct perf_session *self);
diff --git a/tools/perf/util/trace-event-parse.c b/tools/perf/util/trace-event-parse.c
index df2fddbf0cd..5dd3b5ec841 100644
--- a/tools/perf/util/trace-event-parse.c
+++ b/tools/perf/util/trace-event-parse.c
@@ -198,9 +198,8 @@ void print_trace_event(int cpu, void *data, int size)
record.data = data;
trace_seq_init(&s);
- pevent_print_event(pevent, &s, &record);
+ pevent_event_info(&s, event, &record);
trace_seq_do_printf(&s);
- printf("\n");
}
void print_event(int cpu, void *data, int size, unsigned long long nsecs,
diff --git a/tools/power/x86/turbostat/Makefile b/tools/power/x86/turbostat/Makefile
index fd8e1f1297a..f8564955419 100644
--- a/tools/power/x86/turbostat/Makefile
+++ b/tools/power/x86/turbostat/Makefile
@@ -1,4 +1,5 @@
turbostat : turbostat.c
+CFLAGS += -Wall
clean :
rm -f turbostat
diff --git a/tools/power/x86/turbostat/turbostat.8 b/tools/power/x86/turbostat/turbostat.8
index adf175f6149..74e44507dfe 100644
--- a/tools/power/x86/turbostat/turbostat.8
+++ b/tools/power/x86/turbostat/turbostat.8
@@ -27,7 +27,11 @@ supports an "invariant" TSC, plus the APERF and MPERF MSRs.
on processors that additionally support C-state residency counters.
.SS Options
-The \fB-s\fP option prints only a 1-line summary for each sample interval.
+The \fB-s\fP option limits output to a 1-line system summary for each interval.
+.PP
+The \fB-c\fP option limits output to the 1st thread in each core.
+.PP
+The \fB-p\fP option limits output to the 1st thread in each package.
.PP
The \fB-v\fP option increases verbosity.
.PP
@@ -65,19 +69,19 @@ Subsequent rows show per-CPU statistics.
.nf
[root@x980]# ./turbostat
cor CPU %c0 GHz TSC %c1 %c3 %c6 %pc3 %pc6
- 0.60 1.63 3.38 2.91 0.00 96.49 0.00 76.64
- 0 0 0.59 1.62 3.38 4.51 0.00 94.90 0.00 76.64
- 0 6 1.13 1.64 3.38 3.97 0.00 94.90 0.00 76.64
- 1 2 0.08 1.62 3.38 0.07 0.00 99.85 0.00 76.64
- 1 8 0.03 1.62 3.38 0.12 0.00 99.85 0.00 76.64
- 2 4 0.01 1.62 3.38 0.06 0.00 99.93 0.00 76.64
- 2 10 0.04 1.62 3.38 0.02 0.00 99.93 0.00 76.64
- 8 1 2.85 1.62 3.38 11.71 0.00 85.44 0.00 76.64
- 8 7 1.98 1.62 3.38 12.58 0.00 85.44 0.00 76.64
- 9 3 0.36 1.62 3.38 0.71 0.00 98.93 0.00 76.64
- 9 9 0.09 1.62 3.38 0.98 0.00 98.93 0.00 76.64
- 10 5 0.03 1.62 3.38 0.09 0.00 99.87 0.00 76.64
- 10 11 0.07 1.62 3.38 0.06 0.00 99.87 0.00 76.64
+ 0.09 1.62 3.38 1.83 0.32 97.76 1.26 83.61
+ 0 0 0.15 1.62 3.38 10.23 0.05 89.56 1.26 83.61
+ 0 6 0.05 1.62 3.38 10.34
+ 1 2 0.03 1.62 3.38 0.07 0.05 99.86
+ 1 8 0.03 1.62 3.38 0.06
+ 2 4 0.21 1.62 3.38 0.10 1.49 98.21
+ 2 10 0.02 1.62 3.38 0.29
+ 8 1 0.04 1.62 3.38 0.04 0.08 99.84
+ 8 7 0.01 1.62 3.38 0.06
+ 9 3 0.53 1.62 3.38 0.10 0.20 99.17
+ 9 9 0.02 1.62 3.38 0.60
+ 10 5 0.01 1.62 3.38 0.02 0.04 99.92
+ 10 11 0.02 1.62 3.38 0.02
.fi
.SH SUMMARY EXAMPLE
The "-s" option prints the column headers just once,
@@ -86,9 +90,10 @@ and then the one line system summary for each sample interval.
.nf
[root@x980]# ./turbostat -s
%c0 GHz TSC %c1 %c3 %c6 %pc3 %pc6
- 0.61 1.89 3.38 5.95 0.00 93.44 0.00 66.33
- 0.52 1.62 3.38 6.83 0.00 92.65 0.00 61.11
- 0.62 1.92 3.38 5.47 0.00 93.91 0.00 67.31
+ 0.23 1.67 3.38 2.00 0.30 97.47 1.07 82.12
+ 0.10 1.62 3.38 1.87 2.25 95.77 12.02 72.60
+ 0.20 1.64 3.38 1.98 0.11 97.72 0.30 83.36
+ 0.11 1.70 3.38 1.86 1.81 96.22 9.71 74.90
.fi
.SH VERBOSE EXAMPLE
The "-v" option adds verbosity to the output:
@@ -120,30 +125,28 @@ until ^C while the other CPUs are mostly idle:
[root@x980 lenb]# ./turbostat cat /dev/zero > /dev/null
^C
cor CPU %c0 GHz TSC %c1 %c3 %c6 %pc3 %pc6
- 8.63 3.64 3.38 14.46 0.49 76.42 0.00 0.00
- 0 0 0.34 3.36 3.38 99.66 0.00 0.00 0.00 0.00
- 0 6 99.96 3.64 3.38 0.04 0.00 0.00 0.00 0.00
- 1 2 0.14 3.50 3.38 1.75 2.04 96.07 0.00 0.00
- 1 8 0.38 3.57 3.38 1.51 2.04 96.07 0.00 0.00
- 2 4 0.01 2.65 3.38 0.06 0.00 99.93 0.00 0.00
- 2 10 0.03 2.12 3.38 0.04 0.00 99.93 0.00 0.00
- 8 1 0.91 3.59 3.38 35.27 0.92 62.90 0.00 0.00
- 8 7 1.61 3.63 3.38 34.57 0.92 62.90 0.00 0.00
- 9 3 0.04 3.38 3.38 0.20 0.00 99.76 0.00 0.00
- 9 9 0.04 3.29 3.38 0.20 0.00 99.76 0.00 0.00
- 10 5 0.03 3.08 3.38 0.12 0.00 99.85 0.00 0.00
- 10 11 0.05 3.07 3.38 0.10 0.00 99.85 0.00 0.00
-4.907015 sec
-
+ 8.86 3.61 3.38 15.06 31.19 44.89 0.00 0.00
+ 0 0 1.46 3.22 3.38 16.84 29.48 52.22 0.00 0.00
+ 0 6 0.21 3.06 3.38 18.09
+ 1 2 0.53 3.33 3.38 2.80 46.40 50.27
+ 1 8 0.89 3.47 3.38 2.44
+ 2 4 1.36 3.43 3.38 9.04 23.71 65.89
+ 2 10 0.18 2.86 3.38 10.22
+ 8 1 0.04 2.87 3.38 99.96 0.01 0.00
+ 8 7 99.72 3.63 3.38 0.27
+ 9 3 0.31 3.21 3.38 7.64 56.55 35.50
+ 9 9 0.08 2.95 3.38 7.88
+ 10 5 1.42 3.43 3.38 2.14 30.99 65.44
+ 10 11 0.16 2.88 3.38 3.40
.fi
-Above the cycle soaker drives cpu6 up 3.6 Ghz turbo limit
+Above the cycle soaker drives cpu7 up its 3.6 Ghz turbo limit
while the other processors are generally in various states of idle.
-Note that cpu0 is an HT sibling sharing core0
-with cpu6, and thus it is unable to get to an idle state
-deeper than c1 while cpu6 is busy.
+Note that cpu1 and cpu7 are HT siblings within core8.
+As cpu7 is very busy, it prevents its sibling, cpu1,
+from entering a c-state deeper than c1.
-Note that turbostat reports average GHz of 3.64, while
+Note that turbostat reports average GHz of 3.63, while
the arithmetic average of the GHz column above is lower.
This is a weighted average, where the weight is %c0. ie. it is the total number of
un-halted cycles elapsed per time divided by the number of CPUs.
diff --git a/tools/power/x86/turbostat/turbostat.c b/tools/power/x86/turbostat/turbostat.c
index 16de7ad4850..861d7719020 100644
--- a/tools/power/x86/turbostat/turbostat.c
+++ b/tools/power/x86/turbostat/turbostat.c
@@ -67,92 +67,119 @@ double bclk;
unsigned int show_pkg;
unsigned int show_core;
unsigned int show_cpu;
+unsigned int show_pkg_only;
+unsigned int show_core_only;
+char *output_buffer, *outp;
int aperf_mperf_unstable;
int backwards_count;
char *progname;
-int num_cpus;
-cpu_set_t *cpu_present_set, *cpu_mask;
-size_t cpu_present_setsize, cpu_mask_size;
-
-struct counters {
- unsigned long long tsc; /* per thread */
- unsigned long long aperf; /* per thread */
- unsigned long long mperf; /* per thread */
- unsigned long long c1; /* per thread (calculated) */
- unsigned long long c3; /* per core */
- unsigned long long c6; /* per core */
- unsigned long long c7; /* per core */
- unsigned long long pc2; /* per package */
- unsigned long long pc3; /* per package */
- unsigned long long pc6; /* per package */
- unsigned long long pc7; /* per package */
- unsigned long long extra_msr; /* per thread */
- int pkg;
- int core;
- int cpu;
- struct counters *next;
-};
-
-struct counters *cnt_even;
-struct counters *cnt_odd;
-struct counters *cnt_delta;
-struct counters *cnt_average;
-struct timeval tv_even;
-struct timeval tv_odd;
-struct timeval tv_delta;
-
-int mark_cpu_present(int pkg, int core, int cpu)
+cpu_set_t *cpu_present_set, *cpu_affinity_set;
+size_t cpu_present_setsize, cpu_affinity_setsize;
+
+struct thread_data {
+ unsigned long long tsc;
+ unsigned long long aperf;
+ unsigned long long mperf;
+ unsigned long long c1; /* derived */
+ unsigned long long extra_msr;
+ unsigned int cpu_id;
+ unsigned int flags;
+#define CPU_IS_FIRST_THREAD_IN_CORE 0x2
+#define CPU_IS_FIRST_CORE_IN_PACKAGE 0x4
+} *thread_even, *thread_odd;
+
+struct core_data {
+ unsigned long long c3;
+ unsigned long long c6;
+ unsigned long long c7;
+ unsigned int core_id;
+} *core_even, *core_odd;
+
+struct pkg_data {
+ unsigned long long pc2;
+ unsigned long long pc3;
+ unsigned long long pc6;
+ unsigned long long pc7;
+ unsigned int package_id;
+} *package_even, *package_odd;
+
+#define ODD_COUNTERS thread_odd, core_odd, package_odd
+#define EVEN_COUNTERS thread_even, core_even, package_even
+
+#define GET_THREAD(thread_base, thread_no, core_no, pkg_no) \
+ (thread_base + (pkg_no) * topo.num_cores_per_pkg * \
+ topo.num_threads_per_core + \
+ (core_no) * topo.num_threads_per_core + (thread_no))
+#define GET_CORE(core_base, core_no, pkg_no) \
+ (core_base + (pkg_no) * topo.num_cores_per_pkg + (core_no))
+#define GET_PKG(pkg_base, pkg_no) (pkg_base + pkg_no)
+
+struct system_summary {
+ struct thread_data threads;
+ struct core_data cores;
+ struct pkg_data packages;
+} sum, average;
+
+
+struct topo_params {
+ int num_packages;
+ int num_cpus;
+ int num_cores;
+ int max_cpu_num;
+ int num_cores_per_pkg;
+ int num_threads_per_core;
+} topo;
+
+struct timeval tv_even, tv_odd, tv_delta;
+
+void setup_all_buffers(void);
+
+int cpu_is_not_present(int cpu)
{
- CPU_SET_S(cpu, cpu_present_setsize, cpu_present_set);
- return 0;
+ return !CPU_ISSET_S(cpu, cpu_present_setsize, cpu_present_set);
}
-
/*
- * cpu_mask_init(ncpus)
- *
- * allocate and clear cpu_mask
- * set cpu_mask_size
+ * run func(thread, core, package) in topology order
+ * skip non-present cpus
*/
-void cpu_mask_init(int ncpus)
+
+int for_all_cpus(int (func)(struct thread_data *, struct core_data *, struct pkg_data *),
+ struct thread_data *thread_base, struct core_data *core_base, struct pkg_data *pkg_base)
{
- cpu_mask = CPU_ALLOC(ncpus);
- if (cpu_mask == NULL) {
- perror("CPU_ALLOC");
- exit(3);
- }
- cpu_mask_size = CPU_ALLOC_SIZE(ncpus);
- CPU_ZERO_S(cpu_mask_size, cpu_mask);
+ int retval, pkg_no, core_no, thread_no;
- /*
- * Allocate and initialize cpu_present_set
- */
- cpu_present_set = CPU_ALLOC(ncpus);
- if (cpu_present_set == NULL) {
- perror("CPU_ALLOC");
- exit(3);
- }
- cpu_present_setsize = CPU_ALLOC_SIZE(ncpus);
- CPU_ZERO_S(cpu_present_setsize, cpu_present_set);
- for_all_cpus(mark_cpu_present);
-}
+ for (pkg_no = 0; pkg_no < topo.num_packages; ++pkg_no) {
+ for (core_no = 0; core_no < topo.num_cores_per_pkg; ++core_no) {
+ for (thread_no = 0; thread_no <
+ topo.num_threads_per_core; ++thread_no) {
+ struct thread_data *t;
+ struct core_data *c;
+ struct pkg_data *p;
-void cpu_mask_uninit()
-{
- CPU_FREE(cpu_mask);
- cpu_mask = NULL;
- cpu_mask_size = 0;
- CPU_FREE(cpu_present_set);
- cpu_present_set = NULL;
- cpu_present_setsize = 0;
+ t = GET_THREAD(thread_base, thread_no, core_no, pkg_no);
+
+ if (cpu_is_not_present(t->cpu_id))
+ continue;
+
+ c = GET_CORE(core_base, core_no, pkg_no);
+ p = GET_PKG(pkg_base, pkg_no);
+
+ retval = func(t, c, p);
+ if (retval)
+ return retval;
+ }
+ }
+ }
+ return 0;
}
int cpu_migrate(int cpu)
{
- CPU_ZERO_S(cpu_mask_size, cpu_mask);
- CPU_SET_S(cpu, cpu_mask_size, cpu_mask);
- if (sched_setaffinity(0, cpu_mask_size, cpu_mask) == -1)
+ CPU_ZERO_S(cpu_affinity_setsize, cpu_affinity_set);
+ CPU_SET_S(cpu, cpu_affinity_setsize, cpu_affinity_set);
+ if (sched_setaffinity(0, cpu_affinity_setsize, cpu_affinity_set) == -1)
return -1;
else
return 0;
@@ -181,67 +208,72 @@ int get_msr(int cpu, off_t offset, unsigned long long *msr)
void print_header(void)
{
if (show_pkg)
- fprintf(stderr, "pk");
+ outp += sprintf(outp, "pk");
if (show_pkg)
- fprintf(stderr, " ");
+ outp += sprintf(outp, " ");
if (show_core)
- fprintf(stderr, "cor");
+ outp += sprintf(outp, "cor");
if (show_cpu)
- fprintf(stderr, " CPU");
+ outp += sprintf(outp, " CPU");
if (show_pkg || show_core || show_cpu)
- fprintf(stderr, " ");
+ outp += sprintf(outp, " ");
if (do_nhm_cstates)
- fprintf(stderr, " %%c0");
+ outp += sprintf(outp, " %%c0");
if (has_aperf)
- fprintf(stderr, " GHz");
- fprintf(stderr, " TSC");
+ outp += sprintf(outp, " GHz");
+ outp += sprintf(outp, " TSC");
if (do_nhm_cstates)
- fprintf(stderr, " %%c1");
+ outp += sprintf(outp, " %%c1");
if (do_nhm_cstates)
- fprintf(stderr, " %%c3");
+ outp += sprintf(outp, " %%c3");
if (do_nhm_cstates)
- fprintf(stderr, " %%c6");
+ outp += sprintf(outp, " %%c6");
if (do_snb_cstates)
- fprintf(stderr, " %%c7");
+ outp += sprintf(outp, " %%c7");
if (do_snb_cstates)
- fprintf(stderr, " %%pc2");
+ outp += sprintf(outp, " %%pc2");
if (do_nhm_cstates)
- fprintf(stderr, " %%pc3");
+ outp += sprintf(outp, " %%pc3");
if (do_nhm_cstates)
- fprintf(stderr, " %%pc6");
+ outp += sprintf(outp, " %%pc6");
if (do_snb_cstates)
- fprintf(stderr, " %%pc7");
+ outp += sprintf(outp, " %%pc7");
if (extra_msr_offset)
- fprintf(stderr, " MSR 0x%x ", extra_msr_offset);
+ outp += sprintf(outp, " MSR 0x%x ", extra_msr_offset);
- putc('\n', stderr);
+ outp += sprintf(outp, "\n");
}
-void dump_cnt(struct counters *cnt)
+int dump_counters(struct thread_data *t, struct core_data *c,
+ struct pkg_data *p)
{
- if (!cnt)
- return;
- if (cnt->pkg) fprintf(stderr, "package: %d ", cnt->pkg);
- if (cnt->core) fprintf(stderr, "core:: %d ", cnt->core);
- if (cnt->cpu) fprintf(stderr, "CPU: %d ", cnt->cpu);
- if (cnt->tsc) fprintf(stderr, "TSC: %016llX\n", cnt->tsc);
- if (cnt->c3) fprintf(stderr, "c3: %016llX\n", cnt->c3);
- if (cnt->c6) fprintf(stderr, "c6: %016llX\n", cnt->c6);
- if (cnt->c7) fprintf(stderr, "c7: %016llX\n", cnt->c7);
- if (cnt->aperf) fprintf(stderr, "aperf: %016llX\n", cnt->aperf);
- if (cnt->pc2) fprintf(stderr, "pc2: %016llX\n", cnt->pc2);
- if (cnt->pc3) fprintf(stderr, "pc3: %016llX\n", cnt->pc3);
- if (cnt->pc6) fprintf(stderr, "pc6: %016llX\n", cnt->pc6);
- if (cnt->pc7) fprintf(stderr, "pc7: %016llX\n", cnt->pc7);
- if (cnt->extra_msr) fprintf(stderr, "msr0x%x: %016llX\n", extra_msr_offset, cnt->extra_msr);
-}
+ fprintf(stderr, "t %p, c %p, p %p\n", t, c, p);
+
+ if (t) {
+ fprintf(stderr, "CPU: %d flags 0x%x\n", t->cpu_id, t->flags);
+ fprintf(stderr, "TSC: %016llX\n", t->tsc);
+ fprintf(stderr, "aperf: %016llX\n", t->aperf);
+ fprintf(stderr, "mperf: %016llX\n", t->mperf);
+ fprintf(stderr, "c1: %016llX\n", t->c1);
+ fprintf(stderr, "msr0x%x: %016llX\n",
+ extra_msr_offset, t->extra_msr);
+ }
-void dump_list(struct counters *cnt)
-{
- printf("dump_list 0x%p\n", cnt);
+ if (c) {
+ fprintf(stderr, "core: %d\n", c->core_id);
+ fprintf(stderr, "c3: %016llX\n", c->c3);
+ fprintf(stderr, "c6: %016llX\n", c->c6);
+ fprintf(stderr, "c7: %016llX\n", c->c7);
+ }
- for (; cnt; cnt = cnt->next)
- dump_cnt(cnt);
+ if (p) {
+ fprintf(stderr, "package: %d\n", p->package_id);
+ fprintf(stderr, "pc2: %016llX\n", p->pc2);
+ fprintf(stderr, "pc3: %016llX\n", p->pc3);
+ fprintf(stderr, "pc6: %016llX\n", p->pc6);
+ fprintf(stderr, "pc7: %016llX\n", p->pc7);
+ }
+ return 0;
}
/*
@@ -253,321 +285,389 @@ void dump_list(struct counters *cnt)
* TSC: "TSC" 3 columns %3.2
* percentage " %pc3" %6.2
*/
-void print_cnt(struct counters *p)
+int format_counters(struct thread_data *t, struct core_data *c,
+ struct pkg_data *p)
{
double interval_float;
+ /* if showing only 1st thread in core and this isn't one, bail out */
+ if (show_core_only && !(t->flags & CPU_IS_FIRST_THREAD_IN_CORE))
+ return 0;
+
+ /* if showing only 1st thread in pkg and this isn't one, bail out */
+ if (show_pkg_only && !(t->flags & CPU_IS_FIRST_CORE_IN_PACKAGE))
+ return 0;
+
interval_float = tv_delta.tv_sec + tv_delta.tv_usec/1000000.0;
- /* topology columns, print blanks on 1st (average) line */
- if (p == cnt_average) {
+ /* topo columns, print blanks on 1st (average) line */
+ if (t == &average.threads) {
if (show_pkg)
- fprintf(stderr, " ");
+ outp += sprintf(outp, " ");
if (show_pkg && show_core)
- fprintf(stderr, " ");
+ outp += sprintf(outp, " ");
if (show_core)
- fprintf(stderr, " ");
+ outp += sprintf(outp, " ");
if (show_cpu)
- fprintf(stderr, " " " ");
+ outp += sprintf(outp, " " " ");
} else {
- if (show_pkg)
- fprintf(stderr, "%2d", p->pkg);
+ if (show_pkg) {
+ if (p)
+ outp += sprintf(outp, "%2d", p->package_id);
+ else
+ outp += sprintf(outp, " ");
+ }
if (show_pkg && show_core)
- fprintf(stderr, " ");
- if (show_core)
- fprintf(stderr, "%3d", p->core);
+ outp += sprintf(outp, " ");
+ if (show_core) {
+ if (c)
+ outp += sprintf(outp, "%3d", c->core_id);
+ else
+ outp += sprintf(outp, " ");
+ }
if (show_cpu)
- fprintf(stderr, " %3d", p->cpu);
+ outp += sprintf(outp, " %3d", t->cpu_id);
}
/* %c0 */
if (do_nhm_cstates) {
if (show_pkg || show_core || show_cpu)
- fprintf(stderr, " ");
+ outp += sprintf(outp, " ");
if (!skip_c0)
- fprintf(stderr, "%6.2f", 100.0 * p->mperf/p->tsc);
+ outp += sprintf(outp, "%6.2f", 100.0 * t->mperf/t->tsc);
else
- fprintf(stderr, " ****");
+ outp += sprintf(outp, " ****");
}
/* GHz */
if (has_aperf) {
if (!aperf_mperf_unstable) {
- fprintf(stderr, " %3.2f",
- 1.0 * p->tsc / units * p->aperf /
- p->mperf / interval_float);
+ outp += sprintf(outp, " %3.2f",
+ 1.0 * t->tsc / units * t->aperf /
+ t->mperf / interval_float);
} else {
- if (p->aperf > p->tsc || p->mperf > p->tsc) {
- fprintf(stderr, " ***");
+ if (t->aperf > t->tsc || t->mperf > t->tsc) {
+ outp += sprintf(outp, " ***");
} else {
- fprintf(stderr, "%3.1f*",
- 1.0 * p->tsc /
- units * p->aperf /
- p->mperf / interval_float);
+ outp += sprintf(outp, "%3.1f*",
+ 1.0 * t->tsc /
+ units * t->aperf /
+ t->mperf / interval_float);
}
}
}
/* TSC */
- fprintf(stderr, "%5.2f", 1.0 * p->tsc/units/interval_float);
+ outp += sprintf(outp, "%5.2f", 1.0 * t->tsc/units/interval_float);
if (do_nhm_cstates) {
if (!skip_c1)
- fprintf(stderr, " %6.2f", 100.0 * p->c1/p->tsc);
+ outp += sprintf(outp, " %6.2f", 100.0 * t->c1/t->tsc);
else
- fprintf(stderr, " ****");
+ outp += sprintf(outp, " ****");
}
+
+ /* print per-core data only for 1st thread in core */
+ if (!(t->flags & CPU_IS_FIRST_THREAD_IN_CORE))
+ goto done;
+
if (do_nhm_cstates)
- fprintf(stderr, " %6.2f", 100.0 * p->c3/p->tsc);
+ outp += sprintf(outp, " %6.2f", 100.0 * c->c3/t->tsc);
if (do_nhm_cstates)
- fprintf(stderr, " %6.2f", 100.0 * p->c6/p->tsc);
+ outp += sprintf(outp, " %6.2f", 100.0 * c->c6/t->tsc);
if (do_snb_cstates)
- fprintf(stderr, " %6.2f", 100.0 * p->c7/p->tsc);
+ outp += sprintf(outp, " %6.2f", 100.0 * c->c7/t->tsc);
+
+ /* print per-package data only for 1st core in package */
+ if (!(t->flags & CPU_IS_FIRST_CORE_IN_PACKAGE))
+ goto done;
+
if (do_snb_cstates)
- fprintf(stderr, " %6.2f", 100.0 * p->pc2/p->tsc);
+ outp += sprintf(outp, " %6.2f", 100.0 * p->pc2/t->tsc);
if (do_nhm_cstates)
- fprintf(stderr, " %6.2f", 100.0 * p->pc3/p->tsc);
+ outp += sprintf(outp, " %6.2f", 100.0 * p->pc3/t->tsc);
if (do_nhm_cstates)
- fprintf(stderr, " %6.2f", 100.0 * p->pc6/p->tsc);
+ outp += sprintf(outp, " %6.2f", 100.0 * p->pc6/t->tsc);
if (do_snb_cstates)
- fprintf(stderr, " %6.2f", 100.0 * p->pc7/p->tsc);
+ outp += sprintf(outp, " %6.2f", 100.0 * p->pc7/t->tsc);
+done:
if (extra_msr_offset)
- fprintf(stderr, " 0x%016llx", p->extra_msr);
- putc('\n', stderr);
+ outp += sprintf(outp, " 0x%016llx", t->extra_msr);
+ outp += sprintf(outp, "\n");
+
+ return 0;
}
-void print_counters(struct counters *counters)
+void flush_stdout()
+{
+ fputs(output_buffer, stdout);
+ outp = output_buffer;
+}
+void flush_stderr()
+{
+ fputs(output_buffer, stderr);
+ outp = output_buffer;
+}
+void format_all_counters(struct thread_data *t, struct core_data *c, struct pkg_data *p)
{
- struct counters *cnt;
static int printed;
-
if (!printed || !summary_only)
print_header();
- if (num_cpus > 1)
- print_cnt(cnt_average);
+ if (topo.num_cpus > 1)
+ format_counters(&average.threads, &average.cores,
+ &average.packages);
printed = 1;
if (summary_only)
return;
- for (cnt = counters; cnt != NULL; cnt = cnt->next)
- print_cnt(cnt);
-
+ for_all_cpus(format_counters, t, c, p);
}
-#define SUBTRACT_COUNTER(after, before, delta) (delta = (after - before), (before > after))
+void
+delta_package(struct pkg_data *new, struct pkg_data *old)
+{
+ old->pc2 = new->pc2 - old->pc2;
+ old->pc3 = new->pc3 - old->pc3;
+ old->pc6 = new->pc6 - old->pc6;
+ old->pc7 = new->pc7 - old->pc7;
+}
-int compute_delta(struct counters *after,
- struct counters *before, struct counters *delta)
+void
+delta_core(struct core_data *new, struct core_data *old)
{
- int errors = 0;
- int perf_err = 0;
+ old->c3 = new->c3 - old->c3;
+ old->c6 = new->c6 - old->c6;
+ old->c7 = new->c7 - old->c7;
+}
- skip_c0 = skip_c1 = 0;
+/*
+ * old = new - old
+ */
+void
+delta_thread(struct thread_data *new, struct thread_data *old,
+ struct core_data *core_delta)
+{
+ old->tsc = new->tsc - old->tsc;
+
+ /* check for TSC < 1 Mcycles over interval */
+ if (old->tsc < (1000 * 1000)) {
+ fprintf(stderr, "Insanely slow TSC rate, TSC stops in idle?\n");
+ fprintf(stderr, "You can disable all c-states by booting with \"idle=poll\"\n");
+ fprintf(stderr, "or just the deep ones with \"processor.max_cstate=1\"\n");
+ exit(-3);
+ }
- for ( ; after && before && delta;
- after = after->next, before = before->next, delta = delta->next) {
- if (before->cpu != after->cpu) {
- printf("cpu configuration changed: %d != %d\n",
- before->cpu, after->cpu);
- return -1;
- }
+ old->c1 = new->c1 - old->c1;
- if (SUBTRACT_COUNTER(after->tsc, before->tsc, delta->tsc)) {
- fprintf(stderr, "cpu%d TSC went backwards %llX to %llX\n",
- before->cpu, before->tsc, after->tsc);
- errors++;
- }
- /* check for TSC < 1 Mcycles over interval */
- if (delta->tsc < (1000 * 1000)) {
- fprintf(stderr, "Insanely slow TSC rate,"
- " TSC stops in idle?\n");
- fprintf(stderr, "You can disable all c-states"
- " by booting with \"idle=poll\"\n");
- fprintf(stderr, "or just the deep ones with"
- " \"processor.max_cstate=1\"\n");
- exit(-3);
- }
- if (SUBTRACT_COUNTER(after->c3, before->c3, delta->c3)) {
- fprintf(stderr, "cpu%d c3 counter went backwards %llX to %llX\n",
- before->cpu, before->c3, after->c3);
- errors++;
- }
- if (SUBTRACT_COUNTER(after->c6, before->c6, delta->c6)) {
- fprintf(stderr, "cpu%d c6 counter went backwards %llX to %llX\n",
- before->cpu, before->c6, after->c6);
- errors++;
- }
- if (SUBTRACT_COUNTER(after->c7, before->c7, delta->c7)) {
- fprintf(stderr, "cpu%d c7 counter went backwards %llX to %llX\n",
- before->cpu, before->c7, after->c7);
- errors++;
- }
- if (SUBTRACT_COUNTER(after->pc2, before->pc2, delta->pc2)) {
- fprintf(stderr, "cpu%d pc2 counter went backwards %llX to %llX\n",
- before->cpu, before->pc2, after->pc2);
- errors++;
- }
- if (SUBTRACT_COUNTER(after->pc3, before->pc3, delta->pc3)) {
- fprintf(stderr, "cpu%d pc3 counter went backwards %llX to %llX\n",
- before->cpu, before->pc3, after->pc3);
- errors++;
- }
- if (SUBTRACT_COUNTER(after->pc6, before->pc6, delta->pc6)) {
- fprintf(stderr, "cpu%d pc6 counter went backwards %llX to %llX\n",
- before->cpu, before->pc6, after->pc6);
- errors++;
- }
- if (SUBTRACT_COUNTER(after->pc7, before->pc7, delta->pc7)) {
- fprintf(stderr, "cpu%d pc7 counter went backwards %llX to %llX\n",
- before->cpu, before->pc7, after->pc7);
- errors++;
- }
+ if ((new->aperf > old->aperf) && (new->mperf > old->mperf)) {
+ old->aperf = new->aperf - old->aperf;
+ old->mperf = new->mperf - old->mperf;
+ } else {
- perf_err = SUBTRACT_COUNTER(after->aperf, before->aperf, delta->aperf);
- if (perf_err) {
- fprintf(stderr, "cpu%d aperf counter went backwards %llX to %llX\n",
- before->cpu, before->aperf, after->aperf);
- }
- perf_err |= SUBTRACT_COUNTER(after->mperf, before->mperf, delta->mperf);
- if (perf_