summaryrefslogtreecommitdiffstats
path: root/kernel/trace/ring_buffer_benchmark.c
AgeCommit message (Collapse)AuthorFilesLines
2014-02-27trace: Replace hardcoding of 19 with MAX_NICEDongsheng Yang1-3/+3
Use MAX_NICE instead of the value 19 for ring_buffer_benchmark. Signed-off-by: Dongsheng Yang <yangds.fnst@cn.fujitsu.com> Signed-off-by: Peter Zijlstra <peterz@infradead.org> Acked-by: Steven Rostedt <rostedt@goodmis.org> Cc: Frederic Weisbecker <fweisbec@gmail.com> Link: http://lkml.kernel.org/r/1393251121-25534-1-git-send-email-yangds.fnst@cn.fujitsu.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
2011-06-14tracing: Use NUMA allocation for per-cpu ring buffer pagesVaibhav Nagarnaik1-1/+1
The tracing ring buffer is a group of per-cpu ring buffers where allocation and logging is done on a per-cpu basis. The events that are generated on a particular CPU are logged in the corresponding buffer. This is to provide wait-free writes between CPUs and good NUMA node locality while accessing the ring buffer. However, the allocation routines consider NUMA locality only for buffer page metadata and not for the actual buffer page. This causes the pages to be allocated on the NUMA node local to the CPU where the allocation routine is running at the time. This patch fixes the problem by using a NUMA node specific allocation routine so that the pages are allocated from a NUMA node local to the logging CPU. I tested with the getuid_microbench from autotest. It is a simple binary that calls getuid() in a loop and measures the average time for the syscall to complete. The following command was used to test: $ getuid_microbench 1000000 Compared the numbers found on kernel with and without this patch and found that logging latency decreases by 30-50 ns/call. tracing with non-NUMA allocation - 569 ns/call tracing with NUMA allocation - 512 ns/call Signed-off-by: Vaibhav Nagarnaik <vnagarnaik@google.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Michael Rubin <mrubin@google.com> Cc: David Sharp <dhsharp@google.com> Link: http://lkml.kernel.org/r/1304470602-20366-1-git-send-email-vnagarnaik@google.com Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2010-04-27ring-buffer: Make benchmark handle missed eventsSteven Rostedt1-1/+2
With the addition of the "missed events" flags that is stored in the commit field of the ring buffer page, the ring_buffer_benchmark was not updated to handle this. If events are missed, then the missed events flag is set in the ring buffer page, the benchmark will count that flag as part of the size of the page and will hit the BUG() when it tries to read beyond the page. The solution is simply to have the ring buffer benchmark mask off the extra bits. Reported-by: Ingo Molnar <mingo@elte.hu> Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2010-03-31ring-buffer: Add place holder recording of dropped eventsSteven Rostedt1-1/+1
Currently, when the ring buffer drops events, it does not record the fact that it did so. It does inform the writer that the event was dropped by returning a NULL event, but it does not put in any place holder where the event was dropped. This is not a trivial thing to add because the ring buffer mostly runs in overwrite (flight recorder) mode. That is, when the ring buffer is full, new data will overwrite old data. In a produce/consumer mode, where new data is simply dropped when the ring buffer is full, it is trivial to add the placeholder for dropped events. When there's more room to write new data, then a special event can be added to notify the reader about the dropped events. But in overwrite mode, any new write can overwrite events. A place holder can not be inserted into the ring buffer since there never may be room. A reader could also come in at anytime and miss the placeholder. Luckily, the way the ring buffer works, the read side can find out if events were lost or not, and how many events. Everytime a write takes place, if it overwrites the header page (the next read) it updates a "overrun" variable that keeps track of the number of lost events. When a reader swaps out a page from the ring buffer, it can record this number, perfom the swap, and then check to see if the number changed, and take the diff if it has, which would be the number of events dropped. This can be stored by the reader and returned to callers of the reader. Since the reader page swap will fail if the writer moved the head page since the time the reader page set up the swap, this gives room to record the overruns without worrying about races. If the reader sets up the pages, records the overrun, than performs the swap, if the swap succeeds, then the overrun variable has not been updated since the setup before the swap. For binary readers of the ring buffer, a flag is set in the header of each sub page (sub buffer) of the ring buffer. This flag is embedded in the size field of the data on the sub buffer, in the 31st bit (the size can be 32 or 64 bits depending on the architecture), but only 27 bits needs to be used for the actual size (less actually). We could add a new field in the sub buffer header to also record the number of events dropped since the last read, but this will change the format of the binary ring buffer a bit too much. Perhaps this change can be made if the information on the number of events dropped is considered important enough. Note, the notification of dropped events is only used by consuming reads or peeking at the ring buffer. Iterating over the ring buffer does not keep this information because the necessary data is only available when a page swap is made, and the iterator does not swap out pages. Cc: Robert Richter <robert.richter@amd.com> Cc: Andi Kleen <andi@firstfloor.org> Cc: Li Zefan <lizf@cn.fujitsu.com> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: "Luis Claudio R. Goncalves" <lclaudio@uudg.org> Cc: Frederic Weisbecker <fweisbec@gmail.com> Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2010-01-05local_t: Move local.h include to ringbuffer.c and ring_buffer_benchmark.cChristoph Lameter1-0/+1
ringbuffer*.c are the last users of local.h. Remove the include from modules.h and add it to ringbuffer files. Signed-off-by: Christoph Lameter <cl@linux-foundation.org> Signed-off-by: Tejun Heo <tj@kernel.org>
2009-11-25ring-buffer-benchmark: Add parameters to set produce/consumer prioritiesSteven Rostedt1-2/+56
Running the ring-buffer-benchmark's threads at the lowest priority may work well for keeping it in the background, but it is not appropriate for the benchmarks. This patch adds 4 parameters to the module: consumer_fifo consumer_nice producer_fifo producer_nice By default the consumer and producer still run at nice +19. If the *_fifo options are set, they will override the *_nice values. modprobe ring_buffer_benchmark consumer_nice=0 producer_fifo=10 The above will set the consumer thread to a nice value of 0, and the producer thread to a RT SCHED_FIFO priority of 10. Note, this patch also fixes a bug where calling set_user_nice on the consumer thread would oops the kernel when the parameter "disable_reader" is set. Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2009-11-23ring-buffer benchmark: Run producer/consumer threads at nice +19Ingo Molnar1-0/+6
The ring-buffer benchmark threads run on nice 0 by default, using up a lot of CPU time and slowing down the system: PID USER PR NI VIRT RES SHR S %CPU %MEM TIME+ COMMAND 1024 root 20 0 0 0 0 D 95.3 0.0 4:01.67 rb_producer 1023 root 20 0 0 0 0 R 93.5 0.0 2:54.33 rb_consumer 21569 mingo 40 0 14852 1048 772 R 3.6 0.1 0:00.05 top 1 root 40 0 4080 928 668 S 0.0 0.0 0:23.98 init Renice them to +19 to make them less intrusive. Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> LKML-Reference: <new-submission> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-11-11ring-buffer: Add multiple iterations between benchmark timestampsSteven Rostedt1-9/+16
The ring_buffer_benchmark does a gettimeofday after every write to the ring buffer in its measurements. This adds the overhead of the call to gettimeofday to the measurements and does not give an accurate picture of the length of time it takes to record a trace. This was first noticed with perf top: ------------------------------------------------------------------------------ PerfTop: 679 irqs/sec kernel:99.9% [1000Hz cpu-clock-msecs], (all, 4 CPUs) ------------------------------------------------------------------------------ samples pcnt kernel function _______ _____ _______________ 1673.00 - 27.8% : trace_clock_local 806.00 - 13.4% : do_gettimeofday 590.00 - 9.8% : rb_reserve_next_event 554.00 - 9.2% : native_read_tsc 431.00 - 7.2% : ring_buffer_lock_reserve 365.00 - 6.1% : __rb_reserve_next 355.00 - 5.9% : rb_end_commit 322.00 - 5.4% : getnstimeofday 268.00 - 4.5% : ring_buffer_unlock_commit 262.00 - 4.4% : ring_buffer_producer_thread [ring_buffer_benchmark] 113.00 - 1.9% : read_tsc 91.00 - 1.5% : debug_smp_processor_id 69.00 - 1.1% : trace_recursive_unlock 66.00 - 1.1% : ring_buffer_event_data 25.00 - 0.4% : _spin_unlock_irq And the length of each write to the ring buffer measured at 310ns. This patch adds a new module parameter called "write_interval" which is defaulted to 50. This is the number of writes performed between timestamps. After this patch perf top shows: ------------------------------------------------------------------------------ PerfTop: 244 irqs/sec kernel:100.0% [1000Hz cpu-clock-msecs], (all, 4 CPUs) ------------------------------------------------------------------------------ samples pcnt kernel function _______ _____ _______________ 2842.00 - 40.4% : trace_clock_local 1043.00 - 14.8% : rb_reserve_next_event 784.00 - 11.1% : ring_buffer_lock_reserve 600.00 - 8.5% : __rb_reserve_next 579.00 - 8.2% : rb_end_commit 440.00 - 6.3% : ring_buffer_unlock_commit 290.00 - 4.1% : ring_buffer_producer_thread [ring_buffer_benchmark] 155.00 - 2.2% : debug_smp_processor_id 117.00 - 1.7% : trace_recursive_unlock 103.00 - 1.5% : ring_buffer_event_data 28.00 - 0.4% : do_gettimeofday 22.00 - 0.3% : _spin_unlock_irq 14.00 - 0.2% : native_read_tsc 11.00 - 0.2% : getnstimeofday do_gettimeofday dropped from 13% usage to a mere 0.4%! (using the default 50 interval) The measurement for each timestamp went from 310ns to 210ns. That's 100ns (1/3rd) overhead that the gettimeofday call was introducing. Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2009-06-17ring-buffer: have benchmark test print to trace bufferSteven Rostedt1-18/+19
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>
2009-06-16ring-buffer: have benchmark test handle discarded eventsSteven Rostedt1-3/+5
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>
2009-05-11ring-buffer: check for divide by zero in ring-buffer-benchmarkSteven Rostedt1-0/+6
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>
2009-05-11ring-buffer: replace constants with time macros in ring-buffer-benchmarkSteven Rostedt1-5/+7
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>
2009-05-07ring-buffer: add total count in ring-buffer-benchmarkSteven Rostedt1-0/+11
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>
2009-05-07ring-buffer: only periodically call cond_resched to ring-buffer-benchmarkSteven Rostedt1-2/+9
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>
2009-05-07ring-buffer: remove complex calculations in ring-buffer-testSteven Rostedt1-30/+7
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>
2009-05-06ring-buffer: change test to be more latency friendlySteven Rostedt1-0/+31
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>
2009-05-06ring-buffer: check for failed allocation in ring buffer benchmarkSteven Rostedt1-0/+3
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>
2009-05-06ring-buffer: add benchmark and testerSteven Rostedt1-0/+379
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>