Merge tag 'perf-core-for-mingo' of... (156d2238) · Commits · 戴 / test

tools/build/Makefile.feature

+2 −0

Original line number	Diff line number	Diff line
		@@ -46,6 +46,7 @@ FEATURE_TESTS_BASIC := \
		libpython \
		libpython-version \
		libslang \
		libcrypto \
		libunwind \
		pthread-attr-setaffinity-np \
		stackprotector-all \
		@@ -87,6 +88,7 @@ FEATURE_DISPLAY ?= \
		libperl \
		libpython \
		libslang \
		libcrypto \
		libunwind \
		libdw-dwarf-unwind \
		zlib \

tools/build/feature/Makefile

+4 −0

Original line number	Diff line number	Diff line
		@@ -23,6 +23,7 @@ FILES= \
		test-libpython.bin \
		test-libpython-version.bin \
		test-libslang.bin \
		test-libcrypto.bin \
		test-libunwind.bin \
		test-libunwind-debug-frame.bin \
		test-pthread-attr-setaffinity-np.bin \
		@@ -105,6 +106,9 @@ $(OUTPUT)test-libaudit.bin:
		$(OUTPUT)test-libslang.bin:
		$(BUILD) -I/usr/include/slang -lslang

		$(OUTPUT)test-libcrypto.bin:
		$(BUILD) -lcrypto

		$(OUTPUT)test-gtk2.bin:
		$(BUILD) $(shell $(PKG_CONFIG) --libs --cflags gtk+-2.0 2>/dev/null)

tools/build/feature/test-all.c

+5 −0

Original line number	Diff line number	Diff line
		@@ -129,6 +129,10 @@
		# include "test-bpf.c"
		#undef main

		#define main main_test_libcrypto
		# include "test-libcrypto.c"
		#undef main

		int main(int argc, char *argv[])
		{
		main_test_libpython();
		@@ -158,6 +162,7 @@ int main(int argc, char *argv[])
		main_test_lzma();
		main_test_get_cpuid();
		main_test_bpf();
		main_test_libcrypto();

		return 0;
		}

tools/build/feature/test-libcrypto.c

0 → 100644

+17 −0

Original line number	Diff line number	Diff line
		#include <openssl/sha.h>
		#include <openssl/md5.h>

		int main(void)
		{
		MD5_CTX context;
		unsigned char md[MD5_DIGEST_LENGTH + SHA_DIGEST_LENGTH];
		unsigned char dat[] = "12345";

		MD5_Init(&context);
		MD5_Update(&context, &dat[0], sizeof(dat));
		MD5_Final(&md[0], &context);

		SHA1(&dat[0], sizeof(dat), &md[0]);

		return 0;
		}

tools/perf/Documentation/perf-config.txt

+143 −0

Original line number	Diff line number	Diff line
		@@ -296,6 +296,149 @@ hist.*::
		and 'baz' to 50.00% for each, while 'absolute' would show their
		current overhead (33.33%).

		ui.*::
		ui.show-headers::
		This option controls display of column headers (like 'Overhead' and 'Symbol')
		in 'report' and 'top'. If this option is false, they are hidden.
		This option is only applied to TUI.

		call-graph.*::
		When sub-commands 'top' and 'report' work with -g/—-children
		there're options in control of call-graph.

		call-graph.record-mode::
		The record-mode can be 'fp' (frame pointer), 'dwarf' and 'lbr'.
		The value of 'dwarf' is effective only if perf detect needed library
		(libunwind or a recent version of libdw).
		'lbr' only work for cpus that support it.

		call-graph.dump-size::
		The size of stack to dump in order to do post-unwinding. Default is 8192 (byte).
		When using dwarf into record-mode, the default size will be used if omitted.

		call-graph.print-type::
		The print-types can be graph (graph absolute), fractal (graph relative),
		flat and folded. This option controls a way to show overhead for each callchain
		entry. Suppose a following example.

		Overhead Symbols
		........ .......
		40.00% foo
		\|
		---foo
		\|
		\|--50.00%--bar
		\| main
		\|
		--50.00%--baz
		main

		This output is a 'fractal' format. The 'foo' came from 'bar' and 'baz' exactly
		half and half so 'fractal' shows 50.00% for each
		(meaning that it assumes 100% total overhead of 'foo').

		The 'graph' uses absolute overhead value of 'foo' as total so each of
		'bar' and 'baz' callchain will have 20.00% of overhead.
		If 'flat' is used, single column and linear exposure of call chains.
		'folded' mean call chains are displayed in a line, separated by semicolons.

		call-graph.order::
		This option controls print order of callchains. The default is
		'callee' which means callee is printed at top and then followed by its
		caller and so on. The 'caller' prints it in reverse order.

		If this option is not set and report.children or top.children is
		set to true (or the equivalent command line option is given),
		the default value of this option is changed to 'caller' for the
		execution of 'perf report' or 'perf top'. Other commands will
		still default to 'callee'.

		call-graph.sort-key::
		The callchains are merged if they contain same information.
		The sort-key option determines a way to compare the callchains.
		A value of 'sort-key' can be 'function' or 'address'.
		The default is 'function'.

		call-graph.threshold::
		When there're many callchains it'd print tons of lines. So perf omits
		small callchains under a certain overhead (threshold) and this option
		control the threshold. Default is 0.5 (%). The overhead is calculated
		by value depends on call-graph.print-type.

		call-graph.print-limit::
		This is a maximum number of lines of callchain printed for a single
		histogram entry. Default is 0 which means no limitation.

		report.*::
		report.percent-limit::
		This one is mostly the same as call-graph.threshold but works for
		histogram entries. Entries having an overhead lower than this
		percentage will not be printed. Default is '0'. If percent-limit
		is '10', only entries which have more than 10% of overhead will be
		printed.

		report.queue-size::
		This option sets up the maximum allocation size of the internal
		event queue for ordering events. Default is 0, meaning no limit.

		report.children::
		'Children' means functions called from another function.
		If this option is true, 'perf report' cumulates callchains of children
		and show (accumulated) total overhead as well as 'Self' overhead.
		Please refer to the 'perf report' manual. The default is 'true'.

		report.group::
		This option is to show event group information together.
		Example output with this turned on, notice that there is one column
		per event in the group, ref-cycles and cycles:

		# group: {ref-cycles,cycles}
		# ========
		#
		# Samples: 7K of event 'anon group { ref-cycles, cycles }'
		# Event count (approx.): 6876107743
		#
		# Overhead Command Shared Object Symbol
		# ................ ....... ................. ...................
		#
		99.84% 99.76% noploop noploop [.] main
		0.07% 0.00% noploop ld-2.15.so [.] strcmp
		0.03% 0.00% noploop [kernel.kallsyms] [k] timerqueue_del

		top.*::
		top.children::
		Same as 'report.children'. So if it is enabled, the output of 'top'
		command will have 'Children' overhead column as well as 'Self' overhead
		column by default.
		The default is 'true'.

		man.*::
		man.viewer::
		This option can assign a tool to view manual pages when 'help'
		subcommand was invoked. Supported tools are 'man', 'woman'
		(with emacs client) and 'konqueror'. Default is 'man'.

		New man viewer tool can be also added using 'man.<tool>.cmd'
		or use different path using 'man.<tool>.path' config option.

		pager.*::
		pager.<subcommand>::
		When the subcommand is run on stdio, determine whether it uses
		pager or not based on this value. Default is 'unspecified'.

		kmem.*::
		kmem.default::
		This option decides which allocator is to be analyzed if neither
		'--slab' nor '--page' option is used. Default is 'slab'.

		record.*::
		record.build-id::
		This option can be 'cache', 'no-cache' or 'skip'.
		'cache' is to post-process data and save/update the binaries into
		the build-id cache (in ~/.debug). This is the default.
		But if this option is 'no-cache', it will not update the build-id cache.
		'skip' skips post-processing and does not update the cache.

		SEE ALSO
		--------
		linkperf:perf[1]

Admin message