[PATCH v3] Perf Bench: Locking Microbenchmark

[Tuan Bui <tuan.d.bui@hp.com>]

Subject: [PATCH] Perf Bench: Locking Microbenchmark

In response to this thread https://lkml.org/lkml/2014/2/11/93, this is
a micro benchmark that stresses locking contention in the kernel with
creat(2) system call by spawning multiple processes to spam this system
call.  This workload generate similar results and contentions in AIM7
fserver workload but can generate outputs within seconds.

With the creat system call the contention vary on what locks are used
in the particular file system. I have ran this benchmark only on ext4
and xfs file system.

Running the creat workload on ext4 show contention in the mutex lock
that is used by ext4_orphan_add() and ext4_orphan_del() to add or delete
an inode from the list of inodes. At the same time running the creat
workload on xfs show contention in the spinlock that is used by
xsf_log_commit_cil() to commit a transaction to the Committed Item List.

Here is a comparison of this benchmark with AIM7 running fserver workload
at 500-1000 users along with a perf trace running on ext4 file system.

Test machine is a 8-sockets 80 cores Westmere system HT-off on v3.17-rc6.

	AIM7		AIM7		perf-bench	perf-bench
Users	Jobs/min	Jobs/min/child	Ops/sec		Ops/sec/child
500	119668.25	239.34		104249		208
600	126074.90	210.12		106136		176
700	128662.42	183.80		106175		151
800	119822.05	149.78		106290		132
900	106150.25	117.94		105230		116
1000	104681.29	104.68		106489		106

Perf report for AIM7 fserver:
14.51%	reaim  		[kernel.kallsyms]	[k] osq_lock
4.98%	reaim  		reaim			[.] add_long
4.98%	reaim  		reaim			[.] add_int
4.31%	reaim  		[kernel.kallsyms]	[k] mutex_spin_on_owner
...

Perf report of perf bench locking vfs
22.37%	locking-creat  [kernel.kallsyms]	[k] osq_lock
5.77%	locking-creat  [kernel.kallsyms]	[k] mutex_spin_on_owner
5.31%	locking-creat  [kernel.kallsyms]	[k] _raw_spin_lock
5.15%	locking-creat  [jbd2]			[k] jbd2_journal_put_journal_head
...

Example:

[root@u64 ~]# perf bench
Usage:
        perf bench [<common options>] <collection> <benchmark> [<options>]

        # List of all available benchmark collections:

         sched: Scheduler and IPC benchmarks
           mem: Memory access benchmarks
          numa: NUMA scheduling and MM benchmarks
         futex: Futex stressing benchmarks
       locking: Kernel locking benchmarks
           all: All benchmarks

[root@u64 ~]# perf bench locking

        # List of available benchmarks for collection 'locking':

           vfs: Benchmark vfs using creat(2)
           all: Run all benchmarks in this suite

[root@u64 ~]# perf bench locking vfs
# Running 'locking/vfs' benchmark:

   100 processes: throughput = 342506 average opts/sec all processes
   100 processes: throughput = 3425 average opts/sec per process

   200 processes: throughput = 341309 average opts/sec all processes
   200 processes: throughput = 1706 average opts/sec per process
   ...

Changes since v2:
- Added code to clean up tmp files when user issue sigint.
- Added a tmp directory that hold all tmp files generated by benchmark.
- Edited changelog to include example output per Arnaldo's request.

Changes since v1:
- Added -j options to specified jobs per processes.
- Change name of microbenchmark from creat to vfs.
- Change all instances of threads to proccess.

Signed-off-by: Tuan Bui <tuan.d.bui@hp.com>
---
 tools/perf/Documentation/perf-bench.txt |   8 +
 tools/perf/Makefile.perf                |   1 +
 tools/perf/bench/bench.h                |   1 +
 tools/perf/bench/locking.c              | 336 ++++++++++++++++++++++++++++++++
 tools/perf/builtin-bench.c              |   8 +
 5 files changed, 354 insertions(+)
 create mode 100644 tools/perf/bench/locking.c

diff --git a/tools/perf/Documentation/perf-bench.txt b/tools/perf/Documentation/perf-bench.txt
index f6480cb..5c0c8e7 100644
--- a/tools/perf/Documentation/perf-bench.txt
+++ b/tools/perf/Documentation/perf-bench.txt
@@ -58,6 +58,9 @@ SUBSYSTEM
 'futex'::
 	Futex stressing benchmarks.
 
+'locking'::
+        Locking stressing benchmarks that produce similar result as AIM7 fserver.
+
 'all'::
 	All benchmark subsystems.
 
@@ -213,6 +216,11 @@ Suite for evaluating wake calls.
 *requeue*::
 Suite for evaluating requeue calls.
 
+SUITES FOR 'locking'
+~~~~~~~~~~~~~~~~~~
+*vfs*::
+Suite for evaluating vfs locking contention through creat(2).
+
 SEE ALSO
 --------
 linkperf:perf[1]
diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf
index 262916f..c8bee04 100644
--- a/tools/perf/Makefile.perf
+++ b/tools/perf/Makefile.perf
@@ -443,6 +443,7 @@ BUILTIN_OBJS += $(OUTPUT)bench/mem-memset.o
 BUILTIN_OBJS += $(OUTPUT)bench/futex-hash.o
 BUILTIN_OBJS += $(OUTPUT)bench/futex-wake.o
 BUILTIN_OBJS += $(OUTPUT)bench/futex-requeue.o
+BUILTIN_OBJS += $(OUTPUT)bench/locking.o
 
 BUILTIN_OBJS += $(OUTPUT)builtin-diff.o
 BUILTIN_OBJS += $(OUTPUT)builtin-evlist.o
diff --git a/tools/perf/bench/bench.h b/tools/perf/bench/bench.h
index 3c4dd44..19468c5 100644
--- a/tools/perf/bench/bench.h
+++ b/tools/perf/bench/bench.h
@@ -34,6 +34,7 @@ extern int bench_mem_memset(int argc, const char **argv, const char *prefix);
 extern int bench_futex_hash(int argc, const char **argv, const char *prefix);
 extern int bench_futex_wake(int argc, const char **argv, const char *prefix);
 extern int bench_futex_requeue(int argc, const char **argv, const char *prefix);
+extern int bench_locking_vfs(int argc, const char **argv, const char *prefix);
 
 #define BENCH_FORMAT_DEFAULT_STR	"default"
 #define BENCH_FORMAT_DEFAULT		0
diff --git a/tools/perf/bench/locking.c b/tools/perf/bench/locking.c
new file mode 100644
index 0000000..70222bb
--- /dev/null
+++ b/tools/perf/bench/locking.c
@@ -0,0 +1,336 @@
+/*
+ * locking.c
+ *
+ * Simple micro benchmark that stress kernel locking contention with
+ * creat(2) system call by spawning multiple processes to call
+ * this system call.
+ *
+ * Results output are average operations/sec for all processes and
+ * average operations/sec per process.
+ *
+ * Tuan Bui <tuan.d.bui@hp.com>
+ */
+
+#include "../perf.h"
+#include "../util/util.h"
+#include "../util/stat.h"
+#include "../util/parse-options.h"
+#include "../util/header.h"
+#include "bench.h"
+
+#include <err.h>
+#include <stdlib.h>
+#include <sys/time.h>
+#include <unistd.h>
+#include <sys/resource.h>
+#include <linux/futex.h>
+#include <sys/mman.h>
+#include <sys/syscall.h>
+#include <sys/types.h>
+#include <signal.h>
+#include <dirent.h>
+
+#define NOTSET -1
+struct worker {
+	pid_t pid;
+	unsigned int order_id;
+	char str[50];
+};
+
+struct timeval start, end, total;
+static unsigned int start_nr = 100;
+static unsigned int end_nr = 1100;
+static unsigned int increment_by = 100;
+static int bench_dur = NOTSET;
+static int num_jobs = NOTSET;
+static bool run_jobs;
+static int n_pro;
+
+/* Shared variables between fork processes*/
+unsigned int *finished, *setup;
+unsigned long long *shared_workers;
+char *tmp_dir;
+pid_t *p_id;
+/* all processes will block on the same futex */
+u_int32_t *futex;
+
+static const struct option options[] = {
+	OPT_UINTEGER('s', "start", &start_nr, "Number of processes to start"),
+	OPT_UINTEGER('e', "end", &end_nr, "Number of processes to end"),
+	OPT_UINTEGER('i', "increment", &increment_by, "Numbers of processes to increment)"),
+	OPT_INTEGER('r', "runtime", &bench_dur, "Specify benchmark runtime in seconds"),
+	OPT_INTEGER('j', "jobs", &num_jobs, "Specify number of jobs per process"),
+	OPT_END()
+};
+
+static const char * const bench_locking_vfs_usage[] = {
+	"perf bench locking vfs <options>",
+	NULL
+};
+
+/* Clean up if SIGINT is raised */
+static void sigint_handler(int sig __maybe_unused,
+			siginfo_t *info __maybe_unused,
+			void *uc __maybe_unused)
+{
+	DIR *dir;
+	struct dirent *file;
+	char fp[50];
+	int i;
+
+	/* If child process exit*/
+	if (getpid() != *p_id)
+		exit(0);
+	/* if parent process wait for all child processes to exit and then clean up */
+	else {
+		/* Wait for all child processes exit before cleaning up the dir */
+		for (i = 0; i < n_pro; i++)
+			wait(NULL);
+
+		dir = opendir(tmp_dir);
+		if (dir == NULL)
+			err(EXIT_FAILURE, "opendir");
+		while ((file = readdir(dir))) {
+			sprintf(fp, "%s/%s", tmp_dir, file->d_name);
+			unlink(fp);
+		}
+		if ((rmdir(tmp_dir)) < 0)
+			err(EXIT_FAILURE, "rmdir");
+		exit(0);
+	}
+}
+
+/* Running bench vfs workload */
+static void *run_bench_vfs(struct worker *workers)
+{
+	int fd;
+	unsigned long long nr_ops = 0;
+	int jobs = num_jobs;
+
+	sprintf(workers->str, "%s/%d-XXXXXX", tmp_dir, getpid());
+	if ((mkstemp(workers->str)) < 0)
+		err(EXIT_FAILURE, "mkstemp");
+
+	/* Signal to parent process and wait till all processes/ are ready run */
+	setup[workers->order_id] = 1;
+	syscall(SYS_futex, futex, FUTEX_WAIT, 0, NULL, NULL, 0);
+
+	/* Start of the benchmark keep looping till parent process signal completion */
+	while ((run_jobs ? (jobs > 0) : (!*finished))) {
+		fd = creat(workers->str, S_IRWXU);
+		if (fd < 0)
+			err(EXIT_FAILURE, "creat");
+		nr_ops++;
+		if (run_jobs)
+			jobs--;
+		close(fd);
+	}
+
+	if ((unlink(workers->str)) < 0)
+		err(EXIT_FAILURE, "unlink");
+	shared_workers[workers->order_id] = nr_ops;
+	setup[workers->order_id] = 0;
+	exit(0);
+}
+
+/* Setting shared variable finished and shared_workers */
+static void setup_shared(void)
+{
+	unsigned int *finished_tmp, *setup_tmp;
+	unsigned long long *shared_workers_tmp;
+	u_int32_t *futex_tmp;
+
+
+	/* finished shared var is use to signal start and end of benchmark */
+	finished_tmp = (void *)mmap(0, sizeof(unsigned int), PROT_READ|PROT_WRITE,
+			MAP_SHARED|MAP_ANONYMOUS, -1, 0);
+	if (finished_tmp == (void *) -1)
+		err(EXIT_FAILURE, "mmap finished");
+	finished = finished_tmp;
+
+	/* shared_workers is an array of ops perform by each process */
+	shared_workers_tmp = (void *)mmap(0, sizeof(unsigned long long)*end_nr,
+			PROT_READ|PROT_WRITE, MAP_SHARED|MAP_ANONYMOUS, -1, 0);
+	if (shared_workers_tmp == (void *) -1)
+		err(EXIT_FAILURE, "mmap shared_workers");
+	shared_workers = shared_workers_tmp;
+
+	/* setup is use for each processes to signal that it is done
+	 * setting up for the benchmark and is ready to run */
+	setup_tmp = (void *)mmap(0, sizeof(unsigned int)*end_nr,
+			PROT_READ|PROT_WRITE, MAP_SHARED|MAP_ANONYMOUS, -1, 0);
+	if (setup_tmp == (void *) -1)
+		err(EXIT_FAILURE, "mmap setup");
+	setup = setup_tmp;
+
+	/* Processes will sleep on this futex until all other processes
+	 * are done setting up and are ready to run */
+	futex_tmp = (void *)mmap(0, sizeof(u_int32_t), PROT_READ|PROT_WRITE,
+			MAP_SHARED|MAP_ANONYMOUS, -1, 0);
+	if (futex_tmp == (void *) -1)
+		err(EXIT_FAILURE, "mmap futex");
+	futex = futex_tmp;
+	(*futex) = 0;
+
+	/* Setting a tmp dir for all processes to write to */
+	tmp_dir = (void *)mmap(0, sizeof(char) * 255, PROT_READ|PROT_WRITE,
+			MAP_SHARED|MAP_ANONYMOUS, -1, 0);
+	if (tmp_dir == (void *) -1)
+		err(EXIT_FAILURE, "mmap finished");
+
+	/* Setting up parent id to handle sigint */
+	p_id = (void *)mmap(0, sizeof(pid_t), PROT_READ|PROT_WRITE,
+			MAP_SHARED|MAP_ANONYMOUS, -1, 0);
+	if (p_id == (void *) -1)
+		err(EXIT_FAILURE, "mmap p_id");
+	*p_id = getpid();
+
+	/* Creating tmp dir for all process to write to */
+	sprintf(tmp_dir, "%d-XXXXXX", *p_id);
+	if ((mkdtemp(tmp_dir)) == NULL)
+		err(EXIT_FAILURE, "mkdtemp");
+}
+
+/* Freeing shared variables */
+static void free_resources(void)
+{
+	if ((rmdir(tmp_dir)) == -1)
+		err(EXIT_FAILURE, "rmdir");
+
+	if ((munmap(finished, sizeof(unsigned int)) == -1))
+		err(EXIT_FAILURE, "munmap finished");
+
+	if ((munmap(shared_workers, sizeof(unsigned long long) * end_nr) == -1))
+		err(EXIT_FAILURE, "munmap shared_workers");
+
+	if ((munmap(setup, sizeof(unsigned int) * end_nr) == -1))
+		err(EXIT_FAILURE, "munmap setup");
+
+	if ((munmap(futex, sizeof(u_int32_t))) == -1)
+		err(EXIT_FAILURE, "munmap futex");
+
+	if ((munmap(tmp_dir, sizeof(char) * 50) == -1))
+		err(EXIT_FAILURE, "munmap tmp_dir");
+
+	if ((munmap(p_id, sizeof(pid_t)) == -1))
+		err(EXIT_FAILURE, "munmap p_id");
+}
+
+/* Start to spawn workers and wait till all workers have been
+ * created before starting workload */
+static void spawn_workers(void *(*bench_ptr) (struct worker *))
+{
+	pid_t child;
+	unsigned int i, j, k;
+	struct worker workers;
+	unsigned long long total_ops;
+	unsigned int total_workers;
+
+	setup_shared();
+
+	/* This loop through all the run each is increment by increment_by */
+	for (i = start_nr; i <= end_nr; i += increment_by) {
+
+		for (j = 0; j < i; j++) {
+			if (!fork())
+				break;
+		}
+
+		child = getpid();
+		/* Initialize child worker struct and run benchmark */
+		if (child != *p_id) {
+			workers.order_id = j;
+			workers.pid = child;
+			bench_ptr(&workers);
+		}
+		/* Parent to sleep during the duration of benchmark */
+		else{
+			n_pro = i;
+			/* Make sure all child process are created and setup
+			 * before starting benchmark for bench_dur durations */
+			do {
+				total_workers = 0;
+				for (k = 0; k < i; k++)
+					total_workers = total_workers + setup[k];
+			} while (total_workers != i);
+
+			/* Wake up all sleeping process to run the benchmark */
+			(*futex) = 1;
+			syscall(SYS_futex, futex, FUTEX_WAKE, i, NULL, NULL, 0);
+
+			/* If run time parameters is set */
+			if (!run_jobs) {
+				/* All proccesses are ready signal them to run */
+				gettimeofday(&start, NULL);
+				sleep(bench_dur);
+				(*finished) = 1;
+				gettimeofday(&end, NULL);
+				timersub(&end, &start, &total);
+
+				for (k = 0; k < i; k++)
+					wait(NULL);
+			}
+			/* If jobs per proccesses is set */
+			else {
+				/* All proccesses are ready signal them to run */
+				gettimeofday(&start, NULL);
+				/* Wait for all process to terminate before getting outputs */
+				for (k = 0; k < i; k++)
+					wait(NULL);
+				gettimeofday(&end, NULL);
+				timersub(&end, &start, &total);
+			}
+
+			/* Sum up all the ops by each process and report */
+			total_ops = 0;
+			for (k = 0; k < i; k++)
+				total_ops = total_ops + shared_workers[k];
+
+			printf("\n%6d processes: throughput = %llu average opts/sec all processes\n",
+				i, (total_ops / (!total.tv_sec ? 1 : total.tv_sec)));
+
+			printf("%6d processes: throughput = %llu average opts/sec per process\n",
+				i, ((total_ops/(!total.tv_sec ? 1 : total.tv_sec))/(!i ? 1 : i)));
+
+			/* Reset back to 0 for next run */
+			(*finished) = 0;
+			(*futex) = 0;
+		}
+	}
+	free_resources();
+}
+
+int bench_locking_vfs(int argc, const char **argv,
+			const char *prefix __maybe_unused)
+{
+	struct sigaction sa;
+
+	sigfillset(&sa.sa_mask);
+	sa.sa_sigaction = sigint_handler;
+	sa.sa_flags = SA_SIGINFO;
+	sigaction(SIGINT, &sa, NULL);
+
+	argc = parse_options(argc, argv, options, bench_locking_vfs_usage, 0);
+
+	/* If errors parsing options */
+	if (argc || ((bench_dur != NOTSET) && (num_jobs != NOTSET))) {
+		usage_with_options(bench_locking_vfs_usage, options);
+		exit(EXIT_FAILURE);
+	}
+	/* If both run time and job per process is set */
+	if (argc || ((bench_dur != NOTSET) && (num_jobs != NOTSET))) {
+		fprintf(stderr, "\n runtime and jobs options can not both be specified\n");
+		usage_with_options(bench_locking_vfs_usage, options);
+		exit(EXIT_FAILURE);
+	}
+
+	/* If both run time and jobs options is not set default to run time only*/
+	if ((bench_dur == NOTSET) && (num_jobs == NOTSET))
+		bench_dur = 5;
+
+	if (num_jobs != NOTSET)
+		run_jobs = true;
+
+	spawn_workers(run_bench_vfs);
+	return 0;
+}
diff --git a/tools/perf/builtin-bench.c b/tools/perf/builtin-bench.c
index b9a56fa..fdfb089 100644
--- a/tools/perf/builtin-bench.c
+++ b/tools/perf/builtin-bench.c
@@ -63,6 +63,13 @@ static struct bench futex_benchmarks[] = {
 	{ NULL,		NULL,						NULL			}
 };
 
+static struct bench locking_benchmarks[] = {
+	{ "vfs",	"Benchmark vfs using creat(2)",			bench_locking_vfs	},
+	{ "all",        "Run all benchmarks in this suite",		NULL			},
+	{ NULL,		NULL,						NULL			}
+};
+
+
 struct collection {
 	const char	*name;
 	const char	*summary;
@@ -76,6 +83,7 @@ static struct collection collections[] = {
 	{ "numa",	"NUMA scheduling and MM benchmarks",		numa_benchmarks		},
 #endif
 	{"futex",       "Futex stressing benchmarks",                   futex_benchmarks        },
+	{"locking",     "Kernel locking benchmarks",                    locking_benchmarks      },
 	{ "all",	"All benchmarks",				NULL			},
 	{ NULL,		NULL,						NULL			}
 };
-- 
1.9.1