renegade-project/linux-next
2
0
Fork 0
mirror of https://github.com/edk2-porting/linux-next.git synced 2024-12-23 04:34:11 +08:00
Code
4dae560f97
linux-next/kernel/trace/ring_buffer_benchmark.c

420 lines
8.5 KiB
C
Raw Normal View History

ring-buffer: add benchmark and tester This patch adds code that can benchmark the ring buffer as well as test it. This code can be compiled into the kernel (not recommended) or as a module. A separate ring buffer is used to not interfer with other users, like ftrace. It creates a producer and a consumer (option to disable creation of the consumer) and will run for 10 seconds, then sleep for 10 seconds and then repeat. While running, the producer will write 10 byte loads into the ring buffer with just putting in the current CPU number. The reader will continually try to read the buffer. The reader will alternate from reading the buffer via event by event, or by full pages. The output is a pr_info, thus it will fill up the syslogs. Starting ring buffer hammer End ring buffer hammer Time: 9000349 (usecs) Overruns: 12578640 Read: 5358440 (by events) Entries: 0 Total: 17937080 Missed: 0 Hit: 17937080 Entries per millisec: 1993 501 ns per entry Sleeping for 10 secs Starting ring buffer hammer End ring buffer hammer Time: 9936350 (usecs) Overruns: 0 Read: 28146644 (by pages) Entries: 74 Total: 28146718 Missed: 0 Hit: 28146718 Entries per millisec: 2832 353 ns per entry Sleeping for 10 secs Time: is the time the test ran Overruns: the number of events that were overwritten and not read Read: the number of events read (either by pages or events) Entries: the number of entries left in the buffer (the by pages will only read full pages) Total: Entries + Read + Overruns Missed: the number of entries that failed to write Hit: the number of entries that were written The above example shows that it takes ~353 nanosecs per entry when there is a reader, reading by pages (and no overruns) The event by event reader slowed the producer down to 501 nanosecs. [ Impact: see how changes to the ring buffer affect stability and performance ] Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2009-05-06 10:47:18 +08:00
/*
* ring buffer tester and benchmark
*
* Copyright (C) 2009 Steven Rostedt <srostedt@redhat.com>
*/
#include <linux/ring_buffer.h>
#include <linux/completion.h>
#include <linux/kthread.h>
#include <linux/module.h>
#include <linux/time.h>
struct rb_page {
u64 ts;
local_t commit;
char data[4080];
};
/* run time and sleep time in seconds */
#define RUN_TIME 10
#define SLEEP_TIME 10
/* number of events for writer to wake up the reader */
static int wakeup_interval = 100;
static int reader_finish;
static struct completion read_start;
static struct completion read_done;
static struct ring_buffer *buffer;
static struct task_struct *producer;
static struct task_struct *consumer;
static unsigned long read;
static int disable_reader;
module_param(disable_reader, uint, 0644);
MODULE_PARM_DESC(disable_reader, "only run producer");
static int read_events;
static int kill_test;
#define KILL_TEST() \
do { \
if (!kill_test) { \
kill_test = 1; \
WARN_ON(1); \
} \
} while (0)
enum event_status {
EVENT_FOUND,
EVENT_DROPPED,
};
static enum event_status read_event(int cpu)
{
struct ring_buffer_event *event;
int *entry;
u64 ts;
event = ring_buffer_consume(buffer, cpu, &ts);
if (!event)
return EVENT_DROPPED;
entry = ring_buffer_event_data(event);
if (*entry != cpu) {
KILL_TEST();
return EVENT_DROPPED;
}
read++;
return EVENT_FOUND;
}
static enum event_status read_page(int cpu)
{
struct ring_buffer_event *event;
struct rb_page *rpage;
unsigned long commit;
void *bpage;
int *entry;
int ret;
int inc;
int i;
bpage = ring_buffer_alloc_read_page(buffer);
ring-buffer: check for failed allocation in ring buffer benchmark The result of the allocation of the ring buffer read page in the ring buffer bench mark does not check the return to see if a page was actually allocated. This patch fixes that. [ Impact: avoid NULL dereference ] Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2009-05-07 00:40:51 +08:00
if (!bpage)
return EVENT_DROPPED;
ring-buffer: add benchmark and tester This patch adds code that can benchmark the ring buffer as well as test it. This code can be compiled into the kernel (not recommended) or as a module. A separate ring buffer is used to not interfer with other users, like ftrace. It creates a producer and a consumer (option to disable creation of the consumer) and will run for 10 seconds, then sleep for 10 seconds and then repeat. While running, the producer will write 10 byte loads into the ring buffer with just putting in the current CPU number. The reader will continually try to read the buffer. The reader will alternate from reading the buffer via event by event, or by full pages. The output is a pr_info, thus it will fill up the syslogs. Starting ring buffer hammer End ring buffer hammer Time: 9000349 (usecs) Overruns: 12578640 Read: 5358440 (by events) Entries: 0 Total: 17937080 Missed: 0 Hit: 17937080 Entries per millisec: 1993 501 ns per entry Sleeping for 10 secs Starting ring buffer hammer End ring buffer hammer Time: 9936350 (usecs) Overruns: 0 Read: 28146644 (by pages) Entries: 74 Total: 28146718 Missed: 0 Hit: 28146718 Entries per millisec: 2832 353 ns per entry Sleeping for 10 secs Time: is the time the test ran Overruns: the number of events that were overwritten and not read Read: the number of events read (either by pages or events) Entries: the number of entries left in the buffer (the by pages will only read full pages) Total: Entries + Read + Overruns Missed: the number of entries that failed to write Hit: the number of entries that were written The above example shows that it takes ~353 nanosecs per entry when there is a reader, reading by pages (and no overruns) The event by event reader slowed the producer down to 501 nanosecs. [ Impact: see how changes to the ring buffer affect stability and performance ] Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2009-05-06 10:47:18 +08:00
ret = ring_buffer_read_page(buffer, &bpage, PAGE_SIZE, cpu, 1);
if (ret >= 0) {
rpage = bpage;
commit = local_read(&rpage->commit);
for (i = 0; i < commit && !kill_test; i += inc) {
if (i >= (PAGE_SIZE - offsetof(struct rb_page, data))) {
KILL_TEST();
break;
}
inc = -1;
event = (void *)&rpage->data[i];
switch (event->type_len) {
case RINGBUF_TYPE_PADDING:
ring-buffer: have benchmark test handle discarded events With the addition of commit: c7b0930857e2278f2e7714db6294e94c57f623b0 ring-buffer: prevent adding write in discarded area The ring buffer may now add discarded events when a write passes the end of a buffer page. Before, a discarded event was only added when the tracer deliberately created one. The ring buffer benchmark test does not handle discarded events when it reads the buffer and fails when it encounters one. Also fix the increment for large data entries (luckily, the test did not add any yet). [ Impact: fix false failure of ring buffer self test ] Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2009-06-16 23:46:09 +08:00
/* failed writes may be discarded events */
if (!event->time_delta)
KILL_TEST();
inc = event->array[0] + 4;
ring-buffer: add benchmark and tester This patch adds code that can benchmark the ring buffer as well as test it. This code can be compiled into the kernel (not recommended) or as a module. A separate ring buffer is used to not interfer with other users, like ftrace. It creates a producer and a consumer (option to disable creation of the consumer) and will run for 10 seconds, then sleep for 10 seconds and then repeat. While running, the producer will write 10 byte loads into the ring buffer with just putting in the current CPU number. The reader will continually try to read the buffer. The reader will alternate from reading the buffer via event by event, or by full pages. The output is a pr_info, thus it will fill up the syslogs. Starting ring buffer hammer End ring buffer hammer Time: 9000349 (usecs) Overruns: 12578640 Read: 5358440 (by events) Entries: 0 Total: 17937080 Missed: 0 Hit: 17937080 Entries per millisec: 1993 501 ns per entry Sleeping for 10 secs Starting ring buffer hammer End ring buffer hammer Time: 9936350 (usecs) Overruns: 0 Read: 28146644 (by pages) Entries: 74 Total: 28146718 Missed: 0 Hit: 28146718 Entries per millisec: 2832 353 ns per entry Sleeping for 10 secs Time: is the time the test ran Overruns: the number of events that were overwritten and not read Read: the number of events read (either by pages or events) Entries: the number of entries left in the buffer (the by pages will only read full pages) Total: Entries + Read + Overruns Missed: the number of entries that failed to write Hit: the number of entries that were written The above example shows that it takes ~353 nanosecs per entry when there is a reader, reading by pages (and no overruns) The event by event reader slowed the producer down to 501 nanosecs. [ Impact: see how changes to the ring buffer affect stability and performance ] Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2009-05-06 10:47:18 +08:00
break;
case RINGBUF_TYPE_TIME_EXTEND:
inc = 8;
break;
case 0:
entry = ring_buffer_event_data(event);
if (*entry != cpu) {
KILL_TEST();
break;
}
read++;
if (!event->array[0]) {
KILL_TEST();
break;
}
ring-buffer: have benchmark test handle discarded events With the addition of commit: c7b0930857e2278f2e7714db6294e94c57f623b0 ring-buffer: prevent adding write in discarded area The ring buffer may now add discarded events when a write passes the end of a buffer page. Before, a discarded event was only added when the tracer deliberately created one. The ring buffer benchmark test does not handle discarded events when it reads the buffer and fails when it encounters one. Also fix the increment for large data entries (luckily, the test did not add any yet). [ Impact: fix false failure of ring buffer self test ] Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2009-06-16 23:46:09 +08:00
inc = event->array[0] + 4;
ring-buffer: add benchmark and tester This patch adds code that can benchmark the ring buffer as well as test it. This code can be compiled into the kernel (not recommended) or as a module. A separate ring buffer is used to not interfer with other users, like ftrace. It creates a producer and a consumer (option to disable creation of the consumer) and will run for 10 seconds, then sleep for 10 seconds and then repeat. While running, the producer will write 10 byte loads into the ring buffer with just putting in the current CPU number. The reader will continually try to read the buffer. The reader will alternate from reading the buffer via event by event, or by full pages. The output is a pr_info, thus it will fill up the syslogs. Starting ring buffer hammer End ring buffer hammer Time: 9000349 (usecs) Overruns: 12578640 Read: 5358440 (by events) Entries: 0 Total: 17937080 Missed: 0 Hit: 17937080 Entries per millisec: 1993 501 ns per entry Sleeping for 10 secs Starting ring buffer hammer End ring buffer hammer Time: 9936350 (usecs) Overruns: 0 Read: 28146644 (by pages) Entries: 74 Total: 28146718 Missed: 0 Hit: 28146718 Entries per millisec: 2832 353 ns per entry Sleeping for 10 secs Time: is the time the test ran Overruns: the number of events that were overwritten and not read Read: the number of events read (either by pages or events) Entries: the number of entries left in the buffer (the by pages will only read full pages) Total: Entries + Read + Overruns Missed: the number of entries that failed to write Hit: the number of entries that were written The above example shows that it takes ~353 nanosecs per entry when there is a reader, reading by pages (and no overruns) The event by event reader slowed the producer down to 501 nanosecs. [ Impact: see how changes to the ring buffer affect stability and performance ] Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2009-05-06 10:47:18 +08:00
break;
default:
entry = ring_buffer_event_data(event);
if (*entry != cpu) {
KILL_TEST();
break;
}
read++;
inc = ((event->type_len + 1) * 4);
}
if (kill_test)
break;
if (inc <= 0) {
KILL_TEST();
break;
}
}
}
ring_buffer_free_read_page(buffer, bpage);
if (ret < 0)
return EVENT_DROPPED;
return EVENT_FOUND;
}
static void ring_buffer_consumer(void)
{
/* toggle between reading pages and events */
read_events ^= 1;
read = 0;
while (!reader_finish && !kill_test) {
int found;
do {
int cpu;
found = 0;
for_each_online_cpu(cpu) {
enum event_status stat;
if (read_events)
stat = read_event(cpu);
else
stat = read_page(cpu);
if (kill_test)
break;
if (stat == EVENT_FOUND)
found = 1;
}
} while (found && !kill_test);
set_current_state(TASK_INTERRUPTIBLE);
if (reader_finish)
break;
schedule();
__set_current_state(TASK_RUNNING);
}
reader_finish = 0;
complete(&read_done);
}
static void ring_buffer_producer(void)
{
struct timeval start_tv;
struct timeval end_tv;
unsigned long long time;
unsigned long long entries;
unsigned long long overruns;
unsigned long missed = 0;
unsigned long hit = 0;
unsigned long avg;
int cnt = 0;
/*
* Hammer the buffer for 10 secs (this may
* make the system stall)
*/
ring-buffer: have benchmark test print to trace buffer Currently the output of the ring buffer benchmark/test prints to the console. This test runs for ten seconds every ten seconds and ouputs the result after every iteration. This needlessly fills up the logs. This patch makes the ring buffer benchmark/test print to the ftrace buffer using trace_printk. To view the test results, you must examine the debug/tracing/trace file. Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2009-06-18 05:01:09 +08:00
trace_printk("Starting ring buffer hammer\n");
ring-buffer: add benchmark and tester This patch adds code that can benchmark the ring buffer as well as test it. This code can be compiled into the kernel (not recommended) or as a module. A separate ring buffer is used to not interfer with other users, like ftrace. It creates a producer and a consumer (option to disable creation of the consumer) and will run for 10 seconds, then sleep for 10 seconds and then repeat. While running, the producer will write 10 byte loads into the ring buffer with just putting in the current CPU number. The reader will continually try to read the buffer. The reader will alternate from reading the buffer via event by event, or by full pages. The output is a pr_info, thus it will fill up the syslogs. Starting ring buffer hammer End ring buffer hammer Time: 9000349 (usecs) Overruns: 12578640 Read: 5358440 (by events) Entries: 0 Total: 17937080 Missed: 0 Hit: 17937080 Entries per millisec: 1993 501 ns per entry Sleeping for 10 secs Starting ring buffer hammer End ring buffer hammer Time: 9936350 (usecs) Overruns: 0 Read: 28146644 (by pages) Entries: 74 Total: 28146718 Missed: 0 Hit: 28146718 Entries per millisec: 2832 353 ns per entry Sleeping for 10 secs Time: is the time the test ran Overruns: the number of events that were overwritten and not read Read: the number of events read (either by pages or events) Entries: the number of entries left in the buffer (the by pages will only read full pages) Total: Entries + Read + Overruns Missed: the number of entries that failed to write Hit: the number of entries that were written The above example shows that it takes ~353 nanosecs per entry when there is a reader, reading by pages (and no overruns) The event by event reader slowed the producer down to 501 nanosecs. [ Impact: see how changes to the ring buffer affect stability and performance ] Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2009-05-06 10:47:18 +08:00
do_gettimeofday(&start_tv);
do {
struct ring_buffer_event *event;
int *entry;
event = ring_buffer_lock_reserve(buffer, 10);
if (!event) {
missed++;
} else {
hit++;
entry = ring_buffer_event_data(event);
*entry = smp_processor_id();
ring_buffer_unlock_commit(buffer, event);
}
do_gettimeofday(&end_tv);
ring-buffer: only periodically call cond_resched to ring-buffer-benchmark Calling cond_resched at every iteration of the loop adds a bit of overhead to the benchmark. This patch does two things. 1) only calls cond-resched when CONFIG_PREEMPT is not enabled 2) only calls cond-resched after so many traces has been performed. [ Impact: less overhead to the ring-buffer-benchmark ] Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2009-05-08 02:20:28 +08:00
cnt++;
if (consumer && !(cnt % wakeup_interval))
ring-buffer: add benchmark and tester This patch adds code that can benchmark the ring buffer as well as test it. This code can be compiled into the kernel (not recommended) or as a module. A separate ring buffer is used to not interfer with other users, like ftrace. It creates a producer and a consumer (option to disable creation of the consumer) and will run for 10 seconds, then sleep for 10 seconds and then repeat. While running, the producer will write 10 byte loads into the ring buffer with just putting in the current CPU number. The reader will continually try to read the buffer. The reader will alternate from reading the buffer via event by event, or by full pages. The output is a pr_info, thus it will fill up the syslogs. Starting ring buffer hammer End ring buffer hammer Time: 9000349 (usecs) Overruns: 12578640 Read: 5358440 (by events) Entries: 0 Total: 17937080 Missed: 0 Hit: 17937080 Entries per millisec: 1993 501 ns per entry Sleeping for 10 secs Starting ring buffer hammer End ring buffer hammer Time: 9936350 (usecs) Overruns: 0 Read: 28146644 (by pages) Entries: 74 Total: 28146718 Missed: 0 Hit: 28146718 Entries per millisec: 2832 353 ns per entry Sleeping for 10 secs Time: is the time the test ran Overruns: the number of events that were overwritten and not read Read: the number of events read (either by pages or events) Entries: the number of entries left in the buffer (the by pages will only read full pages) Total: Entries + Read + Overruns Missed: the number of entries that failed to write Hit: the number of entries that were written The above example shows that it takes ~353 nanosecs per entry when there is a reader, reading by pages (and no overruns) The event by event reader slowed the producer down to 501 nanosecs. [ Impact: see how changes to the ring buffer affect stability and performance ] Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2009-05-06 10:47:18 +08:00
wake_up_process(consumer);
ring-buffer: only periodically call cond_resched to ring-buffer-benchmark Calling cond_resched at every iteration of the loop adds a bit of overhead to the benchmark. This patch does two things. 1) only calls cond-resched when CONFIG_PREEMPT is not enabled 2) only calls cond-resched after so many traces has been performed. [ Impact: less overhead to the ring-buffer-benchmark ] Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2009-05-08 02:20:28 +08:00
#ifndef CONFIG_PREEMPT
ring-buffer: remove complex calculations in ring-buffer-test Ingo Molnar thought that the code to calculate the time in cond_resched is a bit too ugly and is not needed. This patch removes it and replaces it with a simple call to cond_resched. I kept the comment that explains the reason for the cond_resched. [ Impact: remove ugly code ] Reported-by: Ingo Molnar <mingo@elte.hu> Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2009-05-07 23:13:42 +08:00
/*
* If we are a non preempt kernel, the 10 second run will
* stop everything while it runs. Instead, we will call
* cond_resched and also add any time that was lost by a
* rescedule.
ring-buffer: only periodically call cond_resched to ring-buffer-benchmark Calling cond_resched at every iteration of the loop adds a bit of overhead to the benchmark. This patch does two things. 1) only calls cond-resched when CONFIG_PREEMPT is not enabled 2) only calls cond-resched after so many traces has been performed. [ Impact: less overhead to the ring-buffer-benchmark ] Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2009-05-08 02:20:28 +08:00
*
* Do a cond resched at the same frequency we would wake up
* the reader.
ring-buffer: remove complex calculations in ring-buffer-test Ingo Molnar thought that the code to calculate the time in cond_resched is a bit too ugly and is not needed. This patch removes it and replaces it with a simple call to cond_resched. I kept the comment that explains the reason for the cond_resched. [ Impact: remove ugly code ] Reported-by: Ingo Molnar <mingo@elte.hu> Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2009-05-07 23:13:42 +08:00
*/
ring-buffer: only periodically call cond_resched to ring-buffer-benchmark Calling cond_resched at every iteration of the loop adds a bit of overhead to the benchmark. This patch does two things. 1) only calls cond-resched when CONFIG_PREEMPT is not enabled 2) only calls cond-resched after so many traces has been performed. [ Impact: less overhead to the ring-buffer-benchmark ] Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2009-05-08 02:20:28 +08:00
if (cnt % wakeup_interval)
cond_resched();
#endif
ring-buffer: change test to be more latency friendly The ring buffer benchmark/test runs a producer for 10 seconds. This is done with preemption and interrupts enabled. But if the kernel is not compiled with CONFIG_PREEMPT, it basically stops everything but interrupts for 10 seconds. Although this is just a test and is not for production, this attribute can be quite annoying. It can also spawn badness elsewhere. This patch solves the issues by calling "cond_resched" when the system is not compiled with CONFIG_PREEMPT. It also keeps track of the time spent to call cond_resched such that it does not go against the time calculations. That is, if the task schedules away, the time scheduled out is removed from the test data. Note, this only works for non PREEMPT because we do not know when the task is scheduled out if we have PREEMPT enabled. [ Impact: prevent test from stopping the world for 10 seconds ] Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2009-05-07 06:36:59 +08:00
ring-buffer: add benchmark and tester This patch adds code that can benchmark the ring buffer as well as test it. This code can be compiled into the kernel (not recommended) or as a module. A separate ring buffer is used to not interfer with other users, like ftrace. It creates a producer and a consumer (option to disable creation of the consumer) and will run for 10 seconds, then sleep for 10 seconds and then repeat. While running, the producer will write 10 byte loads into the ring buffer with just putting in the current CPU number. The reader will continually try to read the buffer. The reader will alternate from reading the buffer via event by event, or by full pages. The output is a pr_info, thus it will fill up the syslogs. Starting ring buffer hammer End ring buffer hammer Time: 9000349 (usecs) Overruns: 12578640 Read: 5358440 (by events) Entries: 0 Total: 17937080 Missed: 0 Hit: 17937080 Entries per millisec: 1993 501 ns per entry Sleeping for 10 secs Starting ring buffer hammer End ring buffer hammer Time: 9936350 (usecs) Overruns: 0 Read: 28146644 (by pages) Entries: 74 Total: 28146718 Missed: 0 Hit: 28146718 Entries per millisec: 2832 353 ns per entry Sleeping for 10 secs Time: is the time the test ran Overruns: the number of events that were overwritten and not read Read: the number of events read (either by pages or events) Entries: the number of entries left in the buffer (the by pages will only read full pages) Total: Entries + Read + Overruns Missed: the number of entries that failed to write Hit: the number of entries that were written The above example shows that it takes ~353 nanosecs per entry when there is a reader, reading by pages (and no overruns) The event by event reader slowed the producer down to 501 nanosecs. [ Impact: see how changes to the ring buffer affect stability and performance ] Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2009-05-06 10:47:18 +08:00
} while (end_tv.tv_sec < (start_tv.tv_sec + RUN_TIME) && !kill_test);
ring-buffer: have benchmark test print to trace buffer Currently the output of the ring buffer benchmark/test prints to the console. This test runs for ten seconds every ten seconds and ouputs the result after every iteration. This needlessly fills up the logs. This patch makes the ring buffer benchmark/test print to the ftrace buffer using trace_printk. To view the test results, you must examine the debug/tracing/trace file. Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2009-06-18 05:01:09 +08:00
trace_printk("End ring buffer hammer\n");
ring-buffer: add benchmark and tester This patch adds code that can benchmark the ring buffer as well as test it. This code can be compiled into the kernel (not recommended) or as a module. A separate ring buffer is used to not interfer with other users, like ftrace. It creates a producer and a consumer (option to disable creation of the consumer) and will run for 10 seconds, then sleep for 10 seconds and then repeat. While running, the producer will write 10 byte loads into the ring buffer with just putting in the current CPU number. The reader will continually try to read the buffer. The reader will alternate from reading the buffer via event by event, or by full pages. The output is a pr_info, thus it will fill up the syslogs. Starting ring buffer hammer End ring buffer hammer Time: 9000349 (usecs) Overruns: 12578640 Read: 5358440 (by events) Entries: 0 Total: 17937080 Missed: 0 Hit: 17937080 Entries per millisec: 1993 501 ns per entry Sleeping for 10 secs Starting ring buffer hammer End ring buffer hammer Time: 9936350 (usecs) Overruns: 0 Read: 28146644 (by pages) Entries: 74 Total: 28146718 Missed: 0 Hit: 28146718 Entries per millisec: 2832 353 ns per entry Sleeping for 10 secs Time: is the time the test ran Overruns: the number of events that were overwritten and not read Read: the number of events read (either by pages or events) Entries: the number of entries left in the buffer (the by pages will only read full pages) Total: Entries + Read + Overruns Missed: the number of entries that failed to write Hit: the number of entries that were written The above example shows that it takes ~353 nanosecs per entry when there is a reader, reading by pages (and no overruns) The event by event reader slowed the producer down to 501 nanosecs. [ Impact: see how changes to the ring buffer affect stability and performance ] Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2009-05-06 10:47:18 +08:00
if (consumer) {
/* Init both completions here to avoid races */
init_completion(&read_start);
init_completion(&read_done);
/* the completions must be visible before the finish var */
smp_wmb();
reader_finish = 1;
/* finish var visible before waking up the consumer */
smp_wmb();
wake_up_process(consumer);
wait_for_completion(&read_done);
}
time = end_tv.tv_sec - start_tv.tv_sec;
ring-buffer: replace constants with time macros in ring-buffer-benchmark The use of numeric constants is discouraged. It is cleaner and more descriptive to use macros for constant time conversions. This patch also removes an extra new line. [ Impact: more descriptive time conversions ] Reported-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2009-05-08 22:56:33 +08:00
time *= USEC_PER_SEC;
ring-buffer: add benchmark and tester This patch adds code that can benchmark the ring buffer as well as test it. This code can be compiled into the kernel (not recommended) or as a module. A separate ring buffer is used to not interfer with other users, like ftrace. It creates a producer and a consumer (option to disable creation of the consumer) and will run for 10 seconds, then sleep for 10 seconds and then repeat. While running, the producer will write 10 byte loads into the ring buffer with just putting in the current CPU number. The reader will continually try to read the buffer. The reader will alternate from reading the buffer via event by event, or by full pages. The output is a pr_info, thus it will fill up the syslogs. Starting ring buffer hammer End ring buffer hammer Time: 9000349 (usecs) Overruns: 12578640 Read: 5358440 (by events) Entries: 0 Total: 17937080 Missed: 0 Hit: 17937080 Entries per millisec: 1993 501 ns per entry Sleeping for 10 secs Starting ring buffer hammer End ring buffer hammer Time: 9936350 (usecs) Overruns: 0 Read: 28146644 (by pages) Entries: 74 Total: 28146718 Missed: 0 Hit: 28146718 Entries per millisec: 2832 353 ns per entry Sleeping for 10 secs Time: is the time the test ran Overruns: the number of events that were overwritten and not read Read: the number of events read (either by pages or events) Entries: the number of entries left in the buffer (the by pages will only read full pages) Total: Entries + Read + Overruns Missed: the number of entries that failed to write Hit: the number of entries that were written The above example shows that it takes ~353 nanosecs per entry when there is a reader, reading by pages (and no overruns) The event by event reader slowed the producer down to 501 nanosecs. [ Impact: see how changes to the ring buffer affect stability and performance ] Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2009-05-06 10:47:18 +08:00
time += (long long)((long)end_tv.tv_usec - (long)start_tv.tv_usec);
entries = ring_buffer_entries(buffer);
overruns = ring_buffer_overruns(buffer);
if (kill_test)
ring-buffer: have benchmark test print to trace buffer Currently the output of the ring buffer benchmark/test prints to the console. This test runs for ten seconds every ten seconds and ouputs the result after every iteration. This needlessly fills up the logs. This patch makes the ring buffer benchmark/test print to the ftrace buffer using trace_printk. To view the test results, you must examine the debug/tracing/trace file. Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2009-06-18 05:01:09 +08:00
trace_printk("ERROR!\n");
trace_printk("Time: %lld (usecs)\n", time);
trace_printk("Overruns: %lld\n", overruns);
ring-buffer: add benchmark and tester This patch adds code that can benchmark the ring buffer as well as test it. This code can be compiled into the kernel (not recommended) or as a module. A separate ring buffer is used to not interfer with other users, like ftrace. It creates a producer and a consumer (option to disable creation of the consumer) and will run for 10 seconds, then sleep for 10 seconds and then repeat. While running, the producer will write 10 byte loads into the ring buffer with just putting in the current CPU number. The reader will continually try to read the buffer. The reader will alternate from reading the buffer via event by event, or by full pages. The output is a pr_info, thus it will fill up the syslogs. Starting ring buffer hammer End ring buffer hammer Time: 9000349 (usecs) Overruns: 12578640 Read: 5358440 (by events) Entries: 0 Total: 17937080 Missed: 0 Hit: 17937080 Entries per millisec: 1993 501 ns per entry Sleeping for 10 secs Starting ring buffer hammer End ring buffer hammer Time: 9936350 (usecs) Overruns: 0 Read: 28146644 (by pages) Entries: 74 Total: 28146718 Missed: 0 Hit: 28146718 Entries per millisec: 2832 353 ns per entry Sleeping for 10 secs Time: is the time the test ran Overruns: the number of events that were overwritten and not read Read: the number of events read (either by pages or events) Entries: the number of entries left in the buffer (the by pages will only read full pages) Total: Entries + Read + Overruns Missed: the number of entries that failed to write Hit: the number of entries that were written The above example shows that it takes ~353 nanosecs per entry when there is a reader, reading by pages (and no overruns) The event by event reader slowed the producer down to 501 nanosecs. [ Impact: see how changes to the ring buffer affect stability and performance ] Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2009-05-06 10:47:18 +08:00
if (disable_reader)
ring-buffer: have benchmark test print to trace buffer Currently the output of the ring buffer benchmark/test prints to the console. This test runs for ten seconds every ten seconds and ouputs the result after every iteration. This needlessly fills up the logs. This patch makes the ring buffer benchmark/test print to the ftrace buffer using trace_printk. To view the test results, you must examine the debug/tracing/trace file. Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2009-06-18 05:01:09 +08:00
trace_printk("Read: (reader disabled)\n");
ring-buffer: add benchmark and tester This patch adds code that can benchmark the ring buffer as well as test it. This code can be compiled into the kernel (not recommended) or as a module. A separate ring buffer is used to not interfer with other users, like ftrace. It creates a producer and a consumer (option to disable creation of the consumer) and will run for 10 seconds, then sleep for 10 seconds and then repeat. While running, the producer will write 10 byte loads into the ring buffer with just putting in the current CPU number. The reader will continually try to read the buffer. The reader will alternate from reading the buffer via event by event, or by full pages. The output is a pr_info, thus it will fill up the syslogs. Starting ring buffer hammer End ring buffer hammer Time: 9000349 (usecs) Overruns: 12578640 Read: 5358440 (by events) Entries: 0 Total: 17937080 Missed: 0 Hit: 17937080 Entries per millisec: 1993 501 ns per entry Sleeping for 10 secs Starting ring buffer hammer End ring buffer hammer Time: 9936350 (usecs) Overruns: 0 Read: 28146644 (by pages) Entries: 74 Total: 28146718 Missed: 0 Hit: 28146718 Entries per millisec: 2832 353 ns per entry Sleeping for 10 secs Time: is the time the test ran Overruns: the number of events that were overwritten and not read Read: the number of events read (either by pages or events) Entries: the number of entries left in the buffer (the by pages will only read full pages) Total: Entries + Read + Overruns Missed: the number of entries that failed to write Hit: the number of entries that were written The above example shows that it takes ~353 nanosecs per entry when there is a reader, reading by pages (and no overruns) The event by event reader slowed the producer down to 501 nanosecs. [ Impact: see how changes to the ring buffer affect stability and performance ] Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2009-05-06 10:47:18 +08:00
else
ring-buffer: have benchmark test print to trace buffer Currently the output of the ring buffer benchmark/test prints to the console. This test runs for ten seconds every ten seconds and ouputs the result after every iteration. This needlessly fills up the logs. This patch makes the ring buffer benchmark/test print to the ftrace buffer using trace_printk. To view the test results, you must examine the debug/tracing/trace file. Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2009-06-18 05:01:09 +08:00
trace_printk("Read: %ld (by %s)\n", read,
ring-buffer: add benchmark and tester This patch adds code that can benchmark the ring buffer as well as test it. This code can be compiled into the kernel (not recommended) or as a module. A separate ring buffer is used to not interfer with other users, like ftrace. It creates a producer and a consumer (option to disable creation of the consumer) and will run for 10 seconds, then sleep for 10 seconds and then repeat. While running, the producer will write 10 byte loads into the ring buffer with just putting in the current CPU number. The reader will continually try to read the buffer. The reader will alternate from reading the buffer via event by event, or by full pages. The output is a pr_info, thus it will fill up the syslogs. Starting ring buffer hammer End ring buffer hammer Time: 9000349 (usecs) Overruns: 12578640 Read: 5358440 (by events) Entries: 0 Total: 17937080 Missed: 0 Hit: 17937080 Entries per millisec: 1993 501 ns per entry Sleeping for 10 secs Starting ring buffer hammer End ring buffer hammer Time: 9936350 (usecs) Overruns: 0 Read: 28146644 (by pages) Entries: 74 Total: 28146718 Missed: 0 Hit: 28146718 Entries per millisec: 2832 353 ns per entry Sleeping for 10 secs Time: is the time the test ran Overruns: the number of events that were overwritten and not read Read: the number of events read (either by pages or events) Entries: the number of entries left in the buffer (the by pages will only read full pages) Total: Entries + Read + Overruns Missed: the number of entries that failed to write Hit: the number of entries that were written The above example shows that it takes ~353 nanosecs per entry when there is a reader, reading by pages (and no overruns) The event by event reader slowed the producer down to 501 nanosecs. [ Impact: see how changes to the ring buffer affect stability and performance ] Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2009-05-06 10:47:18 +08:00
read_events ? "events" : "pages");
ring-buffer: have benchmark test print to trace buffer Currently the output of the ring buffer benchmark/test prints to the console. This test runs for ten seconds every ten seconds and ouputs the result after every iteration. This needlessly fills up the logs. This patch makes the ring buffer benchmark/test print to the ftrace buffer using trace_printk. To view the test results, you must examine the debug/tracing/trace file. Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2009-06-18 05:01:09 +08:00
trace_printk("Entries: %lld\n", entries);
trace_printk("Total: %lld\n", entries + overruns + read);
trace_printk("Missed: %ld\n", missed);
trace_printk("Hit: %ld\n", hit);
ring-buffer: add benchmark and tester This patch adds code that can benchmark the ring buffer as well as test it. This code can be compiled into the kernel (not recommended) or as a module. A separate ring buffer is used to not interfer with other users, like ftrace. It creates a producer and a consumer (option to disable creation of the consumer) and will run for 10 seconds, then sleep for 10 seconds and then repeat. While running, the producer will write 10 byte loads into the ring buffer with just putting in the current CPU number. The reader will continually try to read the buffer. The reader will alternate from reading the buffer via event by event, or by full pages. The output is a pr_info, thus it will fill up the syslogs. Starting ring buffer hammer End ring buffer hammer Time: 9000349 (usecs) Overruns: 12578640 Read: 5358440 (by events) Entries: 0 Total: 17937080 Missed: 0 Hit: 17937080 Entries per millisec: 1993 501 ns per entry Sleeping for 10 secs Starting ring buffer hammer End ring buffer hammer Time: 9936350 (usecs) Overruns: 0 Read: 28146644 (by pages) Entries: 74 Total: 28146718 Missed: 0 Hit: 28146718 Entries per millisec: 2832 353 ns per entry Sleeping for 10 secs Time: is the time the test ran Overruns: the number of events that were overwritten and not read Read: the number of events read (either by pages or events) Entries: the number of entries left in the buffer (the by pages will only read full pages) Total: Entries + Read + Overruns Missed: the number of entries that failed to write Hit: the number of entries that were written The above example shows that it takes ~353 nanosecs per entry when there is a reader, reading by pages (and no overruns) The event by event reader slowed the producer down to 501 nanosecs. [ Impact: see how changes to the ring buffer affect stability and performance ] Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2009-05-06 10:47:18 +08:00
ring-buffer: replace constants with time macros in ring-buffer-benchmark The use of numeric constants is discouraged. It is cleaner and more descriptive to use macros for constant time conversions. This patch also removes an extra new line. [ Impact: more descriptive time conversions ] Reported-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2009-05-08 22:56:33 +08:00
/* Convert time from usecs to millisecs */
do_div(time, USEC_PER_MSEC);
ring-buffer: add benchmark and tester This patch adds code that can benchmark the ring buffer as well as test it. This code can be compiled into the kernel (not recommended) or as a module. A separate ring buffer is used to not interfer with other users, like ftrace. It creates a producer and a consumer (option to disable creation of the consumer) and will run for 10 seconds, then sleep for 10 seconds and then repeat. While running, the producer will write 10 byte loads into the ring buffer with just putting in the current CPU number. The reader will continually try to read the buffer. The reader will alternate from reading the buffer via event by event, or by full pages. The output is a pr_info, thus it will fill up the syslogs. Starting ring buffer hammer End ring buffer hammer Time: 9000349 (usecs) Overruns: 12578640 Read: 5358440 (by events) Entries: 0 Total: 17937080 Missed: 0 Hit: 17937080 Entries per millisec: 1993 501 ns per entry Sleeping for 10 secs Starting ring buffer hammer End ring buffer hammer Time: 9936350 (usecs) Overruns: 0 Read: 28146644 (by pages) Entries: 74 Total: 28146718 Missed: 0 Hit: 28146718 Entries per millisec: 2832 353 ns per entry Sleeping for 10 secs Time: is the time the test ran Overruns: the number of events that were overwritten and not read Read: the number of events read (either by pages or events) Entries: the number of entries left in the buffer (the by pages will only read full pages) Total: Entries + Read + Overruns Missed: the number of entries that failed to write Hit: the number of entries that were written The above example shows that it takes ~353 nanosecs per entry when there is a reader, reading by pages (and no overruns) The event by event reader slowed the producer down to 501 nanosecs. [ Impact: see how changes to the ring buffer affect stability and performance ] Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2009-05-06 10:47:18 +08:00
if (time)
hit /= (long)time;
else
ring-buffer: have benchmark test print to trace buffer Currently the output of the ring buffer benchmark/test prints to the console. This test runs for ten seconds every ten seconds and ouputs the result after every iteration. This needlessly fills up the logs. This patch makes the ring buffer benchmark/test print to the ftrace buffer using trace_printk. To view the test results, you must examine the debug/tracing/trace file. Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2009-06-18 05:01:09 +08:00
trace_printk("TIME IS ZERO??\n");
ring-buffer: add benchmark and tester This patch adds code that can benchmark the ring buffer as well as test it. This code can be compiled into the kernel (not recommended) or as a module. A separate ring buffer is used to not interfer with other users, like ftrace. It creates a producer and a consumer (option to disable creation of the consumer) and will run for 10 seconds, then sleep for 10 seconds and then repeat. While running, the producer will write 10 byte loads into the ring buffer with just putting in the current CPU number. The reader will continually try to read the buffer. The reader will alternate from reading the buffer via event by event, or by full pages. The output is a pr_info, thus it will fill up the syslogs. Starting ring buffer hammer End ring buffer hammer Time: 9000349 (usecs) Overruns: 12578640 Read: 5358440 (by events) Entries: 0 Total: 17937080 Missed: 0 Hit: 17937080 Entries per millisec: 1993 501 ns per entry Sleeping for 10 secs Starting ring buffer hammer End ring buffer hammer Time: 9936350 (usecs) Overruns: 0 Read: 28146644 (by pages) Entries: 74 Total: 28146718 Missed: 0 Hit: 28146718 Entries per millisec: 2832 353 ns per entry Sleeping for 10 secs Time: is the time the test ran Overruns: the number of events that were overwritten and not read Read: the number of events read (either by pages or events) Entries: the number of entries left in the buffer (the by pages will only read full pages) Total: Entries + Read + Overruns Missed: the number of entries that failed to write Hit: the number of entries that were written The above example shows that it takes ~353 nanosecs per entry when there is a reader, reading by pages (and no overruns) The event by event reader slowed the producer down to 501 nanosecs. [ Impact: see how changes to the ring buffer affect stability and performance ] Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2009-05-06 10:47:18 +08:00
ring-buffer: have benchmark test print to trace buffer Currently the output of the ring buffer benchmark/test prints to the console. This test runs for ten seconds every ten seconds and ouputs the result after every iteration. This needlessly fills up the logs. This patch makes the ring buffer benchmark/test print to the ftrace buffer using trace_printk. To view the test results, you must examine the debug/tracing/trace file. Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2009-06-18 05:01:09 +08:00
trace_printk("Entries per millisec: %ld\n", hit);
ring-buffer: add benchmark and tester This patch adds code that can benchmark the ring buffer as well as test it. This code can be compiled into the kernel (not recommended) or as a module. A separate ring buffer is used to not interfer with other users, like ftrace. It creates a producer and a consumer (option to disable creation of the consumer) and will run for 10 seconds, then sleep for 10 seconds and then repeat. While running, the producer will write 10 byte loads into the ring buffer with just putting in the current CPU number. The reader will continually try to read the buffer. The reader will alternate from reading the buffer via event by event, or by full pages. The output is a pr_info, thus it will fill up the syslogs. Starting ring buffer hammer End ring buffer hammer Time: 9000349 (usecs) Overruns: 12578640 Read: 5358440 (by events) Entries: 0 Total: 17937080 Missed: 0 Hit: 17937080 Entries per millisec: 1993 501 ns per entry Sleeping for 10 secs Starting ring buffer hammer End ring buffer hammer Time: 9936350 (usecs) Overruns: 0 Read: 28146644 (by pages) Entries: 74 Total: 28146718 Missed: 0 Hit: 28146718 Entries per millisec: 2832 353 ns per entry Sleeping for 10 secs Time: is the time the test ran Overruns: the number of events that were overwritten and not read Read: the number of events read (either by pages or events) Entries: the number of entries left in the buffer (the by pages will only read full pages) Total: Entries + Read + Overruns Missed: the number of entries that failed to write Hit: the number of entries that were written The above example shows that it takes ~353 nanosecs per entry when there is a reader, reading by pages (and no overruns) The event by event reader slowed the producer down to 501 nanosecs. [ Impact: see how changes to the ring buffer affect stability and performance ] Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2009-05-06 10:47:18 +08:00
if (hit) {
ring-buffer: replace constants with time macros in ring-buffer-benchmark The use of numeric constants is discouraged. It is cleaner and more descriptive to use macros for constant time conversions. This patch also removes an extra new line. [ Impact: more descriptive time conversions ] Reported-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2009-05-08 22:56:33 +08:00
/* Calculate the average time in nanosecs */
avg = NSEC_PER_MSEC / hit;
ring-buffer: have benchmark test print to trace buffer Currently the output of the ring buffer benchmark/test prints to the console. This test runs for ten seconds every ten seconds and ouputs the result after every iteration. This needlessly fills up the logs. This patch makes the ring buffer benchmark/test print to the ftrace buffer using trace_printk. To view the test results, you must examine the debug/tracing/trace file. Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2009-06-18 05:01:09 +08:00
trace_printk("%ld ns per entry\n", avg);
ring-buffer: add benchmark and tester This patch adds code that can benchmark the ring buffer as well as test it. This code can be compiled into the kernel (not recommended) or as a module. A separate ring buffer is used to not interfer with other users, like ftrace. It creates a producer and a consumer (option to disable creation of the consumer) and will run for 10 seconds, then sleep for 10 seconds and then repeat. While running, the producer will write 10 byte loads into the ring buffer with just putting in the current CPU number. The reader will continually try to read the buffer. The reader will alternate from reading the buffer via event by event, or by full pages. The output is a pr_info, thus it will fill up the syslogs. Starting ring buffer hammer End ring buffer hammer Time: 9000349 (usecs) Overruns: 12578640 Read: 5358440 (by events) Entries: 0 Total: 17937080 Missed: 0 Hit: 17937080 Entries per millisec: 1993 501 ns per entry Sleeping for 10 secs Starting ring buffer hammer End ring buffer hammer Time: 9936350 (usecs) Overruns: 0 Read: 28146644 (by pages) Entries: 74 Total: 28146718 Missed: 0 Hit: 28146718 Entries per millisec: 2832 353 ns per entry Sleeping for 10 secs Time: is the time the test ran Overruns: the number of events that were overwritten and not read Read: the number of events read (either by pages or events) Entries: the number of entries left in the buffer (the by pages will only read full pages) Total: Entries + Read + Overruns Missed: the number of entries that failed to write Hit: the number of entries that were written The above example shows that it takes ~353 nanosecs per entry when there is a reader, reading by pages (and no overruns) The event by event reader slowed the producer down to 501 nanosecs. [ Impact: see how changes to the ring buffer affect stability and performance ] Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2009-05-06 10:47:18 +08:00
}
ring-buffer: add total count in ring-buffer-benchmark It is nice to see the overhead of the benchmark test when tracing is disabled. That is, we turn off the ring buffer just to see what the cost of running the loop that calls into the ring buffer is. Currently, if no entries wer made, we get 0. This is not informative. This patch changes it to check if we had any "missed" (non recorded) events. If so, a total count is also reported. [ Impact: evaluate the over head of the ring buffer benchmark test ] Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2009-05-08 07:52:20 +08:00
if (missed) {
if (time)
missed /= (long)time;
ring-buffer: have benchmark test print to trace buffer Currently the output of the ring buffer benchmark/test prints to the console. This test runs for ten seconds every ten seconds and ouputs the result after every iteration. This needlessly fills up the logs. This patch makes the ring buffer benchmark/test print to the ftrace buffer using trace_printk. To view the test results, you must examine the debug/tracing/trace file. Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2009-06-18 05:01:09 +08:00
trace_printk("Total iterations per millisec: %ld\n",
hit + missed);
ring-buffer: add total count in ring-buffer-benchmark It is nice to see the overhead of the benchmark test when tracing is disabled. That is, we turn off the ring buffer just to see what the cost of running the loop that calls into the ring buffer is. Currently, if no entries wer made, we get 0. This is not informative. This patch changes it to check if we had any "missed" (non recorded) events. If so, a total count is also reported. [ Impact: evaluate the over head of the ring buffer benchmark test ] Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2009-05-08 07:52:20 +08:00
ring-buffer: check for divide by zero in ring-buffer-benchmark Although we check if "missed" is not zero, we divide by hit + missed, and the addition can possible overflow and become a divide by zero. This patch checks for this case, and will report it when it happens then modify "hit" to make the calculation be non zero. [ Impact: prevent possible divide by zero in ring-buffer-benchmark ] Reported-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2009-05-08 23:03:57 +08:00
/* it is possible that hit + missed will overflow and be zero */
if (!(hit + missed)) {
ring-buffer: have benchmark test print to trace buffer Currently the output of the ring buffer benchmark/test prints to the console. This test runs for ten seconds every ten seconds and ouputs the result after every iteration. This needlessly fills up the logs. This patch makes the ring buffer benchmark/test print to the ftrace buffer using trace_printk. To view the test results, you must examine the debug/tracing/trace file. Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2009-06-18 05:01:09 +08:00
trace_printk("hit + missed overflowed and totalled zero!\n");
ring-buffer: check for divide by zero in ring-buffer-benchmark Although we check if "missed" is not zero, we divide by hit + missed, and the addition can possible overflow and become a divide by zero. This patch checks for this case, and will report it when it happens then modify "hit" to make the calculation be non zero. [ Impact: prevent possible divide by zero in ring-buffer-benchmark ] Reported-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2009-05-08 23:03:57 +08:00
hit--; /* make it non zero */
}
ring-buffer: replace constants with time macros in ring-buffer-benchmark The use of numeric constants is discouraged. It is cleaner and more descriptive to use macros for constant time conversions. This patch also removes an extra new line. [ Impact: more descriptive time conversions ] Reported-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2009-05-08 22:56:33 +08:00
/* Caculate the average time in nanosecs */
avg = NSEC_PER_MSEC / (hit + missed);
ring-buffer: have benchmark test print to trace buffer Currently the output of the ring buffer benchmark/test prints to the console. This test runs for ten seconds every ten seconds and ouputs the result after every iteration. This needlessly fills up the logs. This patch makes the ring buffer benchmark/test print to the ftrace buffer using trace_printk. To view the test results, you must examine the debug/tracing/trace file. Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2009-06-18 05:01:09 +08:00
trace_printk("%ld ns per entry\n", avg);
ring-buffer: add total count in ring-buffer-benchmark It is nice to see the overhead of the benchmark test when tracing is disabled. That is, we turn off the ring buffer just to see what the cost of running the loop that calls into the ring buffer is. Currently, if no entries wer made, we get 0. This is not informative. This patch changes it to check if we had any "missed" (non recorded) events. If so, a total count is also reported. [ Impact: evaluate the over head of the ring buffer benchmark test ] Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2009-05-08 07:52:20 +08:00
}
ring-buffer: add benchmark and tester This patch adds code that can benchmark the ring buffer as well as test it. This code can be compiled into the kernel (not recommended) or as a module. A separate ring buffer is used to not interfer with other users, like ftrace. It creates a producer and a consumer (option to disable creation of the consumer) and will run for 10 seconds, then sleep for 10 seconds and then repeat. While running, the producer will write 10 byte loads into the ring buffer with just putting in the current CPU number. The reader will continually try to read the buffer. The reader will alternate from reading the buffer via event by event, or by full pages. The output is a pr_info, thus it will fill up the syslogs. Starting ring buffer hammer End ring buffer hammer Time: 9000349 (usecs) Overruns: 12578640 Read: 5358440 (by events) Entries: 0 Total: 17937080 Missed: 0 Hit: 17937080 Entries per millisec: 1993 501 ns per entry Sleeping for 10 secs Starting ring buffer hammer End ring buffer hammer Time: 9936350 (usecs) Overruns: 0 Read: 28146644 (by pages) Entries: 74 Total: 28146718 Missed: 0 Hit: 28146718 Entries per millisec: 2832 353 ns per entry Sleeping for 10 secs Time: is the time the test ran Overruns: the number of events that were overwritten and not read Read: the number of events read (either by pages or events) Entries: the number of entries left in the buffer (the by pages will only read full pages) Total: Entries + Read + Overruns Missed: the number of entries that failed to write Hit: the number of entries that were written The above example shows that it takes ~353 nanosecs per entry when there is a reader, reading by pages (and no overruns) The event by event reader slowed the producer down to 501 nanosecs. [ Impact: see how changes to the ring buffer affect stability and performance ] Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2009-05-06 10:47:18 +08:00
}
static void wait_to_die(void)
{
set_current_state(TASK_INTERRUPTIBLE);
while (!kthread_should_stop()) {
schedule();
set_current_state(TASK_INTERRUPTIBLE);
}
__set_current_state(TASK_RUNNING);
}
static int ring_buffer_consumer_thread(void *arg)
{
while (!kthread_should_stop() && !kill_test) {
complete(&read_start);
ring_buffer_consumer();
set_current_state(TASK_INTERRUPTIBLE);
if (kthread_should_stop() || kill_test)
break;
schedule();
__set_current_state(TASK_RUNNING);
}
__set_current_state(TASK_RUNNING);
if (kill_test)
wait_to_die();
return 0;
}
static int ring_buffer_producer_thread(void *arg)
{
init_completion(&read_start);
while (!kthread_should_stop() && !kill_test) {
ring_buffer_reset(buffer);
if (consumer) {
smp_wmb();
wake_up_process(consumer);
wait_for_completion(&read_start);
}
ring_buffer_producer();
ring-buffer: have benchmark test print to trace buffer Currently the output of the ring buffer benchmark/test prints to the console. This test runs for ten seconds every ten seconds and ouputs the result after every iteration. This needlessly fills up the logs. This patch makes the ring buffer benchmark/test print to the ftrace buffer using trace_printk. To view the test results, you must examine the debug/tracing/trace file. Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2009-06-18 05:01:09 +08:00
trace_printk("Sleeping for 10 secs\n");
ring-buffer: add benchmark and tester This patch adds code that can benchmark the ring buffer as well as test it. This code can be compiled into the kernel (not recommended) or as a module. A separate ring buffer is used to not interfer with other users, like ftrace. It creates a producer and a consumer (option to disable creation of the consumer) and will run for 10 seconds, then sleep for 10 seconds and then repeat. While running, the producer will write 10 byte loads into the ring buffer with just putting in the current CPU number. The reader will continually try to read the buffer. The reader will alternate from reading the buffer via event by event, or by full pages. The output is a pr_info, thus it will fill up the syslogs. Starting ring buffer hammer End ring buffer hammer Time: 9000349 (usecs) Overruns: 12578640 Read: 5358440 (by events) Entries: 0 Total: 17937080 Missed: 0 Hit: 17937080 Entries per millisec: 1993 501 ns per entry Sleeping for 10 secs Starting ring buffer hammer End ring buffer hammer Time: 9936350 (usecs) Overruns: 0 Read: 28146644 (by pages) Entries: 74 Total: 28146718 Missed: 0 Hit: 28146718 Entries per millisec: 2832 353 ns per entry Sleeping for 10 secs Time: is the time the test ran Overruns: the number of events that were overwritten and not read Read: the number of events read (either by pages or events) Entries: the number of entries left in the buffer (the by pages will only read full pages) Total: Entries + Read + Overruns Missed: the number of entries that failed to write Hit: the number of entries that were written The above example shows that it takes ~353 nanosecs per entry when there is a reader, reading by pages (and no overruns) The event by event reader slowed the producer down to 501 nanosecs. [ Impact: see how changes to the ring buffer affect stability and performance ] Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2009-05-06 10:47:18 +08:00
set_current_state(TASK_INTERRUPTIBLE);
schedule_timeout(HZ * SLEEP_TIME);
__set_current_state(TASK_RUNNING);
}
if (kill_test)
wait_to_die();
return 0;
}
static int __init ring_buffer_benchmark_init(void)
{
int ret;
/* make a one meg buffer in overwite mode */
buffer = ring_buffer_alloc(1000000, RB_FL_OVERWRITE);
if (!buffer)
return -ENOMEM;
if (!disable_reader) {
consumer = kthread_create(ring_buffer_consumer_thread,
NULL, "rb_consumer");
ret = PTR_ERR(consumer);
if (IS_ERR(consumer))
goto out_fail;
}
producer = kthread_run(ring_buffer_producer_thread,
NULL, "rb_producer");
ret = PTR_ERR(producer);
if (IS_ERR(producer))
goto out_kill;
return 0;
out_kill:
if (consumer)
kthread_stop(consumer);
out_fail:
ring_buffer_free(buffer);
return ret;
}
static void __exit ring_buffer_benchmark_exit(void)
{
kthread_stop(producer);
if (consumer)
kthread_stop(consumer);
ring_buffer_free(buffer);
}
module_init(ring_buffer_benchmark_init);
module_exit(ring_buffer_benchmark_exit);
MODULE_AUTHOR("Steven Rostedt");
MODULE_DESCRIPTION("ring_buffer_benchmark");
MODULE_LICENSE("GPL");
Copy Permalink