perf: Add 'perf bench numa mem' NUMA performance measurement suite

Add a suite of NUMA performance benchmarks.

The goal was simulate the behavior and access patterns of real NUMA
workloads, via a wide range of parameters, so this tool goes well
beyond simple bzero() measurements that most NUMA micro-benchmarks use:

 - It processes the data and creates a chain of data dependencies,
   like a real workload would. Neither the compiler, nor the
   kernel (via KSM and other optimizations) nor the CPU can
   eliminate parts of the workload.

 - It randomizes the initial state and also randomizes the target
   addresses of the processing - it's not a simple forward scan
   of addresses.

 - It provides flexible options to set process, thread and memory
   relationship information: -G sets "global" memory shared between
   all test processes, -P sets "process" memory shared by all
   threads of a process and -T sets "thread" private memory.

 - There's a NUMA convergence monitoring and convergence latency
   measurement option via -c and -m.

 - Micro-sleeps and synchronization can be injected to provoke lock
   contention and scheduling, via the -u and -S options. This simulates
   IO and contention.

 - The -x option instructs the workload to 'perturb' itself artificially
   every N seconds, by moving to the first and last CPU of the system
   periodically. This way the stability of convergence equilibrium and
   the number of steps taken for the scheduler to reach equilibrium again
   can be measured.

 - The amount of work can be specified via the -l loop count, and/or
   via a -s seconds-timeout value.

 - CPU and node memory binding options, to test hard binding scenarios.
   THP can be turned on and off via madvise() calls.

 - Live reporting of convergence progress in an 'at glance' output format.
   Printing of convergence and deconvergence events.

The 'perf bench numa mem -a' option will start an array of about 30
individual tests that will each output such measurements:

 # Running  5x5-bw-thread, "perf bench numa mem -p 5 -t 5 -P 512 -s 20 -zZ0q --thp  1"
  5x5-bw-thread,                         20.276, secs,           runtime-max/thread
  5x5-bw-thread,                         20.004, secs,           runtime-min/thread
  5x5-bw-thread,                         20.155, secs,           runtime-avg/thread
  5x5-bw-thread,                          0.671, %,              spread-runtime/thread
  5x5-bw-thread,                         21.153, GB,             data/thread
  5x5-bw-thread,                        528.818, GB,             data-total
  5x5-bw-thread,                          0.959, nsecs,          runtime/byte/thread
  5x5-bw-thread,                          1.043, GB/sec,         thread-speed
  5x5-bw-thread,                         26.081, GB/sec,         total-speed

See the help text and the code for more details.

Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Rik van Riel <riel@redhat.com>
Cc: Mel Gorman <mgorman@suse.de>
Cc: Hugh Dickins <hughd@google.com>
Signed-off-by: NIngo Molnar <mingo@kernel.org>

tools/perf/Makefile

@@ -103,7 +103,7 @@ ifdef PARSER_DEBUG
 endif
 
 CFLAGS = -fno-omit-frame-pointer -ggdb3 -funwind-tables -Wall -Wextra -std=gnu99 $(CFLAGS_WERROR) $(CFLAGS_OPTIMIZE) $(EXTRA_WARNINGS) $(EXTRA_CFLAGS) $(PARSER_DEBUG_CFLAGS)
-EXTLIBS = -lpthread -lrt -lelf -lm
+EXTLIBS = -lpthread -lrt -lelf -lm -lnuma
 ALL_CFLAGS = $(CFLAGS) -D_LARGEFILE64_SOURCE -D_FILE_OFFSET_BITS=64 -D_GNU_SOURCE
 ALL_LDFLAGS = $(LDFLAGS)
 STRIP ?= strip
@@ -492,6 +492,7 @@ LIB_OBJS += $(OUTPUT)tests/python-use.o
 BUILTIN_OBJS += $(OUTPUT)builtin-annotate.o
 BUILTIN_OBJS += $(OUTPUT)builtin-bench.o
 # Benchmark modules
+BUILTIN_OBJS += $(OUTPUT)bench/numa.o
 BUILTIN_OBJS += $(OUTPUT)bench/sched-messaging.o
 BUILTIN_OBJS += $(OUTPUT)bench/sched-pipe.o
 ifeq ($(RAW_ARCH),x86_64)

tools/perf/bench/bench.h

 #ifndef BENCH_H
 #define BENCH_H
 
+extern int bench_numa(int argc, const char **argv, const char *prefix);
 extern int bench_sched_messaging(int argc, const char **argv, const char *prefix);
 extern int bench_sched_pipe(int argc, const char **argv, const char *prefix);
 extern int bench_mem_memcpy(int argc, const char **argv,

tools/perf/builtin-bench.c

@@ -35,6 +35,16 @@ struct bench_suite {
 /* sentinel: easy for help */
 #define suite_all { "all", "Test all benchmark suites", NULL }
 
+static struct bench_suite numa_suites[] = {
+	{ "mem",
+	  "Benchmark for NUMA workloads",
+	  bench_numa },
+	suite_all,
+	{ NULL,
+	  NULL,
+	  NULL                  }
+};
+
 static struct bench_suite sched_suites[] = {
 	{ "messaging",
 	  "Benchmark for scheduler and IPC mechanisms",
@@ -68,6 +78,9 @@ struct bench_subsys {
 };
 
 static struct bench_subsys subsystems[] = {
+	{ "numa",
+	  "NUMA scheduling and MM behavior",
+	  numa_suites },
 	{ "sched",
 	  "scheduler and IPC mechanism",
 	  sched_suites },