16c00db4bb
Pull AFS fixes from David Howells: "Here's a set of patches that fix a number of bugs in the in-kernel AFS client, including: - Fix directory locking to not use individual page locks for directory reading/scanning but rather to use a semaphore on the afs_vnode struct as the directory contents must be read in a single blob and data from different reads must not be mixed as the entire contents may be shuffled about between reads. - Fix address list parsing to handle port specifiers correctly. - Only give up callback records on a server if we actually talked to that server (we might not be able to access a server). - Fix some callback handling bugs, including refcounting, whole-volume callbacks and when callbacks actually get broken in response to a CB.CallBack op. - Fix some server/address rotation bugs, including giving up if we can't probe a server; giving up if a server says it doesn't have a volume, but there are more servers to try. - Fix the decoding of fetched statuses to be OpenAFS compatible. - Fix the handling of server lookups in Cache Manager ops (such as CB.InitCallBackState3) to use a UUID if possible and to handle no server being found. - Fix a bug in server lookup where not all addresses are compared. - Fix the non-encryption of calls that prevents some servers from being accessed (this also requires an AF_RXRPC patch that has already gone in through the net tree). There's also a patch that adds tracepoints to log Cache Manager ops that don't find a matching server, either by UUID or by address" * tag 'afs-fixes-20180514' of git://git.kernel.org/pub/scm/linux/kernel/git/dhowells/linux-fs: afs: Fix the non-encryption of calls afs: Fix CB.CallBack handling afs: Fix whole-volume callback handling afs: Fix afs_find_server search loop afs: Fix the handling of an unfound server in CM operations afs: Add a tracepoint to record callbacks from unlisted servers afs: Fix the handling of CB.InitCallBackState3 to find the server by UUID afs: Fix VNOVOL handling in address rotation afs: Fix AFSFetchStatus decoder to provide OpenAFS compatibility afs: Fix server rotation's handling of fileserver probe failure afs: Fix refcounting in callback registration afs: Fix giving up callbacks on server destruction afs: Fix address list parsing afs: Fix directory page locking
221 lines
5.9 KiB
C
221 lines
5.9 KiB
C
// SPDX-License-Identifier: GPL-2.0
|
|
/*
|
|
* Copyright (C) 2013 Davidlohr Bueso <davidlohr@hp.com>
|
|
*
|
|
* futex-requeue: Block a bunch of threads on futex1 and requeue them
|
|
* on futex2, N at a time.
|
|
*
|
|
* This program is particularly useful to measure the latency of nthread
|
|
* requeues without waking up any tasks -- thus mimicking a regular futex_wait.
|
|
*/
|
|
|
|
/* For the CLR_() macros */
|
|
#include <string.h>
|
|
#include <pthread.h>
|
|
|
|
#include <signal.h>
|
|
#include "../util/stat.h"
|
|
#include <subcmd/parse-options.h>
|
|
#include <linux/compiler.h>
|
|
#include <linux/kernel.h>
|
|
#include <linux/time64.h>
|
|
#include <errno.h>
|
|
#include "bench.h"
|
|
#include "futex.h"
|
|
#include "cpumap.h"
|
|
|
|
#include <err.h>
|
|
#include <stdlib.h>
|
|
#include <sys/time.h>
|
|
|
|
static u_int32_t futex1 = 0, futex2 = 0;
|
|
|
|
/*
|
|
* How many tasks to requeue at a time.
|
|
* Default to 1 in order to make the kernel work more.
|
|
*/
|
|
static unsigned int nrequeue = 1;
|
|
|
|
static pthread_t *worker;
|
|
static bool done = false, silent = false, fshared = false;
|
|
static pthread_mutex_t thread_lock;
|
|
static pthread_cond_t thread_parent, thread_worker;
|
|
static struct stats requeuetime_stats, requeued_stats;
|
|
static unsigned int threads_starting, nthreads = 0;
|
|
static int futex_flag = 0;
|
|
|
|
static const struct option options[] = {
|
|
OPT_UINTEGER('t', "threads", &nthreads, "Specify amount of threads"),
|
|
OPT_UINTEGER('q', "nrequeue", &nrequeue, "Specify amount of threads to requeue at once"),
|
|
OPT_BOOLEAN( 's', "silent", &silent, "Silent mode: do not display data/details"),
|
|
OPT_BOOLEAN( 'S', "shared", &fshared, "Use shared futexes instead of private ones"),
|
|
OPT_END()
|
|
};
|
|
|
|
static const char * const bench_futex_requeue_usage[] = {
|
|
"perf bench futex requeue <options>",
|
|
NULL
|
|
};
|
|
|
|
static void print_summary(void)
|
|
{
|
|
double requeuetime_avg = avg_stats(&requeuetime_stats);
|
|
double requeuetime_stddev = stddev_stats(&requeuetime_stats);
|
|
unsigned int requeued_avg = avg_stats(&requeued_stats);
|
|
|
|
printf("Requeued %d of %d threads in %.4f ms (+-%.2f%%)\n",
|
|
requeued_avg,
|
|
nthreads,
|
|
requeuetime_avg / USEC_PER_MSEC,
|
|
rel_stddev_stats(requeuetime_stddev, requeuetime_avg));
|
|
}
|
|
|
|
static void *workerfn(void *arg __maybe_unused)
|
|
{
|
|
pthread_mutex_lock(&thread_lock);
|
|
threads_starting--;
|
|
if (!threads_starting)
|
|
pthread_cond_signal(&thread_parent);
|
|
pthread_cond_wait(&thread_worker, &thread_lock);
|
|
pthread_mutex_unlock(&thread_lock);
|
|
|
|
futex_wait(&futex1, 0, NULL, futex_flag);
|
|
return NULL;
|
|
}
|
|
|
|
static void block_threads(pthread_t *w,
|
|
pthread_attr_t thread_attr, struct cpu_map *cpu)
|
|
{
|
|
cpu_set_t cpuset;
|
|
unsigned int i;
|
|
|
|
threads_starting = nthreads;
|
|
|
|
/* create and block all threads */
|
|
for (i = 0; i < nthreads; i++) {
|
|
CPU_ZERO(&cpuset);
|
|
CPU_SET(cpu->map[i % cpu->nr], &cpuset);
|
|
|
|
if (pthread_attr_setaffinity_np(&thread_attr, sizeof(cpu_set_t), &cpuset))
|
|
err(EXIT_FAILURE, "pthread_attr_setaffinity_np");
|
|
|
|
if (pthread_create(&w[i], &thread_attr, workerfn, NULL))
|
|
err(EXIT_FAILURE, "pthread_create");
|
|
}
|
|
}
|
|
|
|
static void toggle_done(int sig __maybe_unused,
|
|
siginfo_t *info __maybe_unused,
|
|
void *uc __maybe_unused)
|
|
{
|
|
done = true;
|
|
}
|
|
|
|
int bench_futex_requeue(int argc, const char **argv)
|
|
{
|
|
int ret = 0;
|
|
unsigned int i, j;
|
|
struct sigaction act;
|
|
pthread_attr_t thread_attr;
|
|
struct cpu_map *cpu;
|
|
|
|
argc = parse_options(argc, argv, options, bench_futex_requeue_usage, 0);
|
|
if (argc)
|
|
goto err;
|
|
|
|
cpu = cpu_map__new(NULL);
|
|
if (!cpu)
|
|
err(EXIT_FAILURE, "cpu_map__new");
|
|
|
|
sigfillset(&act.sa_mask);
|
|
act.sa_sigaction = toggle_done;
|
|
sigaction(SIGINT, &act, NULL);
|
|
|
|
if (!nthreads)
|
|
nthreads = cpu->nr;
|
|
|
|
worker = calloc(nthreads, sizeof(*worker));
|
|
if (!worker)
|
|
err(EXIT_FAILURE, "calloc");
|
|
|
|
if (!fshared)
|
|
futex_flag = FUTEX_PRIVATE_FLAG;
|
|
|
|
if (nrequeue > nthreads)
|
|
nrequeue = nthreads;
|
|
|
|
printf("Run summary [PID %d]: Requeuing %d threads (from [%s] %p to %p), "
|
|
"%d at a time.\n\n", getpid(), nthreads,
|
|
fshared ? "shared":"private", &futex1, &futex2, nrequeue);
|
|
|
|
init_stats(&requeued_stats);
|
|
init_stats(&requeuetime_stats);
|
|
pthread_attr_init(&thread_attr);
|
|
pthread_mutex_init(&thread_lock, NULL);
|
|
pthread_cond_init(&thread_parent, NULL);
|
|
pthread_cond_init(&thread_worker, NULL);
|
|
|
|
for (j = 0; j < bench_repeat && !done; j++) {
|
|
unsigned int nrequeued = 0;
|
|
struct timeval start, end, runtime;
|
|
|
|
/* create, launch & block all threads */
|
|
block_threads(worker, thread_attr, cpu);
|
|
|
|
/* make sure all threads are already blocked */
|
|
pthread_mutex_lock(&thread_lock);
|
|
while (threads_starting)
|
|
pthread_cond_wait(&thread_parent, &thread_lock);
|
|
pthread_cond_broadcast(&thread_worker);
|
|
pthread_mutex_unlock(&thread_lock);
|
|
|
|
usleep(100000);
|
|
|
|
/* Ok, all threads are patiently blocked, start requeueing */
|
|
gettimeofday(&start, NULL);
|
|
while (nrequeued < nthreads) {
|
|
/*
|
|
* Do not wakeup any tasks blocked on futex1, allowing
|
|
* us to really measure futex_wait functionality.
|
|
*/
|
|
nrequeued += futex_cmp_requeue(&futex1, 0, &futex2, 0,
|
|
nrequeue, futex_flag);
|
|
}
|
|
|
|
gettimeofday(&end, NULL);
|
|
timersub(&end, &start, &runtime);
|
|
|
|
update_stats(&requeued_stats, nrequeued);
|
|
update_stats(&requeuetime_stats, runtime.tv_usec);
|
|
|
|
if (!silent) {
|
|
printf("[Run %d]: Requeued %d of %d threads in %.4f ms\n",
|
|
j + 1, nrequeued, nthreads, runtime.tv_usec / (double)USEC_PER_MSEC);
|
|
}
|
|
|
|
/* everybody should be blocked on futex2, wake'em up */
|
|
nrequeued = futex_wake(&futex2, nrequeued, futex_flag);
|
|
if (nthreads != nrequeued)
|
|
warnx("couldn't wakeup all tasks (%d/%d)", nrequeued, nthreads);
|
|
|
|
for (i = 0; i < nthreads; i++) {
|
|
ret = pthread_join(worker[i], NULL);
|
|
if (ret)
|
|
err(EXIT_FAILURE, "pthread_join");
|
|
}
|
|
}
|
|
|
|
/* cleanup & report results */
|
|
pthread_cond_destroy(&thread_parent);
|
|
pthread_cond_destroy(&thread_worker);
|
|
pthread_mutex_destroy(&thread_lock);
|
|
pthread_attr_destroy(&thread_attr);
|
|
|
|
print_summary();
|
|
|
|
free(worker);
|
|
return ret;
|
|
err:
|
|
usage_with_options(bench_futex_requeue_usage, options);
|
|
exit(EXIT_FAILURE);
|
|
}
|