mirror of
https://github.com/AuxXxilium/linux_dsm_epyc7002.git
synced 2024-12-04 05:16:44 +07:00
5092dbc96f
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>
51 lines
1.8 KiB
Makefile
51 lines
1.8 KiB
Makefile
|
|
# Do not instrument the tracer itself:
|
|
|
|
ifdef CONFIG_FUNCTION_TRACER
|
|
ORIG_CFLAGS := $(KBUILD_CFLAGS)
|
|
KBUILD_CFLAGS = $(subst -pg,,$(ORIG_CFLAGS))
|
|
|
|
# selftest needs instrumentation
|
|
CFLAGS_trace_selftest_dynamic.o = -pg
|
|
obj-y += trace_selftest_dynamic.o
|
|
endif
|
|
|
|
# If unlikely tracing is enabled, do not trace these files
|
|
ifdef CONFIG_TRACING_BRANCHES
|
|
KBUILD_CFLAGS += -DDISABLE_BRANCH_PROFILING
|
|
endif
|
|
|
|
obj-$(CONFIG_FUNCTION_TRACER) += libftrace.o
|
|
obj-$(CONFIG_RING_BUFFER) += ring_buffer.o
|
|
obj-$(CONFIG_RING_BUFFER_BENCHMARK) += ring_buffer_benchmark.o
|
|
|
|
obj-$(CONFIG_TRACING) += trace.o
|
|
obj-$(CONFIG_TRACING) += trace_clock.o
|
|
obj-$(CONFIG_TRACING) += trace_output.o
|
|
obj-$(CONFIG_TRACING) += trace_stat.o
|
|
obj-$(CONFIG_TRACING) += trace_printk.o
|
|
obj-$(CONFIG_CONTEXT_SWITCH_TRACER) += trace_sched_switch.o
|
|
obj-$(CONFIG_SYSPROF_TRACER) += trace_sysprof.o
|
|
obj-$(CONFIG_FUNCTION_TRACER) += trace_functions.o
|
|
obj-$(CONFIG_IRQSOFF_TRACER) += trace_irqsoff.o
|
|
obj-$(CONFIG_PREEMPT_TRACER) += trace_irqsoff.o
|
|
obj-$(CONFIG_SCHED_TRACER) += trace_sched_wakeup.o
|
|
obj-$(CONFIG_NOP_TRACER) += trace_nop.o
|
|
obj-$(CONFIG_STACK_TRACER) += trace_stack.o
|
|
obj-$(CONFIG_MMIOTRACE) += trace_mmiotrace.o
|
|
obj-$(CONFIG_BOOT_TRACER) += trace_boot.o
|
|
obj-$(CONFIG_FUNCTION_GRAPH_TRACER) += trace_functions_graph.o
|
|
obj-$(CONFIG_TRACE_BRANCH_PROFILING) += trace_branch.o
|
|
obj-$(CONFIG_HW_BRANCH_TRACER) += trace_hw_branches.o
|
|
obj-$(CONFIG_POWER_TRACER) += trace_power.o
|
|
obj-$(CONFIG_KMEMTRACE) += kmemtrace.o
|
|
obj-$(CONFIG_WORKQUEUE_TRACER) += trace_workqueue.o
|
|
obj-$(CONFIG_BLK_DEV_IO_TRACE) += blktrace.o
|
|
obj-$(CONFIG_EVENT_TRACING) += trace_events.o
|
|
obj-$(CONFIG_EVENT_TRACING) += trace_export.o
|
|
obj-$(CONFIG_FTRACE_SYSCALLS) += trace_syscalls.o
|
|
obj-$(CONFIG_EVENT_PROFILE) += trace_event_profile.o
|
|
obj-$(CONFIG_EVENT_TRACING) += trace_events_filter.o
|
|
|
|
libftrace-y := ftrace.o
|