/* Copyright (c) 2016 Facebook * * This program is free software; you can redistribute it and/or * modify it under the terms of version 2 of the GNU General Public * License as published by the Free Software Foundation. */ #define _GNU_SOURCE #include #include #include #include #include #include #include #include #include #include #include #include #include #include "libbpf.h" #include "bpf_load.h" #define MAX_CNT 1000000 static __u64 time_get_ns(void) { struct timespec ts; clock_gettime(CLOCK_MONOTONIC, &ts); return ts.tv_sec * 1000000000ull + ts.tv_nsec; } #define HASH_PREALLOC (1 << 0) #define PERCPU_HASH_PREALLOC (1 << 1) #define HASH_KMALLOC (1 << 2) #define PERCPU_HASH_KMALLOC (1 << 3) #define LRU_HASH_PREALLOC (1 << 4) #define PERCPU_LRU_HASH_PREALLOC (1 << 5) static int test_flags = ~0; static void test_hash_prealloc(int cpu) { __u64 start_time; int i; start_time = time_get_ns(); for (i = 0; i < MAX_CNT; i++) syscall(__NR_getuid); printf("%d:hash_map_perf pre-alloc %lld events per sec\n", cpu, MAX_CNT * 1000000000ll / (time_get_ns() - start_time)); } static void test_lru_hash_prealloc(int cpu) { __u64 start_time; int i; start_time = time_get_ns(); for (i = 0; i < MAX_CNT; i++) syscall(__NR_getpid); printf("%d:lru_hash_map_perf pre-alloc %lld events per sec\n", cpu, MAX_CNT * 1000000000ll / (time_get_ns() - start_time)); } static void test_percpu_lru_hash_prealloc(int cpu) { __u64 start_time; int i; start_time = time_get_ns(); for (i = 0; i < MAX_CNT; i++) syscall(__NR_getppid); printf("%d:lru_hash_map_perf pre-alloc %lld events per sec\n", cpu, MAX_CNT * 1000000000ll / (time_get_ns() - start_time)); } static void test_percpu_hash_prealloc(int cpu) { __u64 start_time; int i; start_time = time_get_ns(); for (i = 0; i < MAX_CNT; i++) syscall(__NR_geteuid); printf("%d:percpu_hash_map_perf pre-alloc %lld events per sec\n", cpu, MAX_CNT * 1000000000ll / (time_get_ns() - start_time)); } static void test_hash_kmalloc(int cpu) { __u64 start_time; int i; start_time = time_get_ns(); for (i = 0; i < MAX_CNT; i++) syscall(__NR_getgid); printf("%d:hash_map_perf kmalloc %lld events per sec\n", cpu, MAX_CNT * 1000000000ll / (time_get_ns() - start_time)); } static void test_percpu_hash_kmalloc(int cpu) { __u64 start_time; int i; start_time = time_get_ns(); for (i = 0; i < MAX_CNT; i++) syscall(__NR_getegid); printf("%d:percpu_hash_map_perf kmalloc %lld events per sec\n", cpu, MAX_CNT * 1000000000ll / (time_get_ns() - start_time)); } static void loop(int cpu) { cpu_set_t cpuset; CPU_ZERO(&cpuset); CPU_SET(cpu, &cpuset); sched_setaffinity(0, sizeof(cpuset), &cpuset); if (test_flags & HASH_PREALLOC) test_hash_prealloc(cpu); if (test_flags & PERCPU_HASH_PREALLOC) test_percpu_hash_prealloc(cpu); if (test_flags & HASH_KMALLOC) test_hash_kmalloc(cpu); if (test_flags & PERCPU_HASH_KMALLOC) test_percpu_hash_kmalloc(cpu); if (test_flags & LRU_HASH_PREALLOC) test_lru_hash_prealloc(cpu); if (test_flags & PERCPU_LRU_HASH_PREALLOC) test_percpu_lru_hash_prealloc(cpu); } static void run_perf_test(int tasks) { pid_t pid[tasks]; int i; for (i = 0; i < tasks; i++) { pid[i] = fork(); if (pid[i] == 0) { loop(i); exit(0); } else if (pid[i] == -1) { printf("couldn't spawn #%d process\n", i); exit(1); } } for (i = 0; i < tasks; i++) { int status; assert(waitpid(pid[i], &status, 0) == pid[i]); assert(status == 0); } } int main(int argc, char **argv) { struct rlimit r = {RLIM_INFINITY, RLIM_INFINITY}; char filename[256]; int num_cpu = 8; snprintf(filename, sizeof(filename), "%s_kern.o", argv[0]); setrlimit(RLIMIT_MEMLOCK, &r); if (argc > 1) test_flags = atoi(argv[1]) ? : test_flags; if (argc > 2) num_cpu = atoi(argv[2]) ? : num_cpu; if (load_bpf_file(filename)) { printf("%s", bpf_log_buf); return 1; } run_perf_test(num_cpu); return 0; } el'>mode:
authorThomas Gleixner <tglx@linutronix.de>2017-01-31 23:58:38 +0100
committerIngo Molnar <mingo@kernel.org>2017-02-01 08:37:27 +0100
commitdd86e373e09fb16b83e8adf5c48c421a4ca76468 (patch)
tree55703c2ea8584e303e342090614e0aab3509ab21 /include/rdma/ib_cm.h
parent0b3589be9b98994ce3d5aeca52445d1f5627c4ba (diff)
perf/x86/intel/rapl: Make package handling more robust
The package management code in RAPL relies on package mapping being available before a CPU is started. This changed with: 9d85eb9119f4 ("x86/smpboot: Make logical package management more robust") because the ACPI/BIOS information turned out to be unreliable, but that left RAPL in broken state. This was not noticed because on a regular boot all CPUs are online before RAPL is initialized. A possible fix would be to reintroduce the mess which allocates a package data structure in CPU prepare and when it turns out to already exist in starting throw it away later in the CPU online callback. But that's a horrible hack and not required at all because RAPL becomes functional for perf only in the CPU online callback. That's correct because user space is not yet informed about the CPU being onlined, so nothing caan rely on RAPL being available on that particular CPU. Move the allocation to the CPU online callback and simplify the hotplug handling. At this point the package mapping is established and correct. This also adds a missing check for available package data in the event_init() function. Reported-by: Yasuaki Ishimatsu <yasu.isimatu@gmail.com> Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Sebastian Siewior <bigeasy@linutronix.de> Cc: Stephane Eranian <eranian@google.com> Cc: Vince Weaver <vincent.weaver@maine.edu> Fixes: 9d85eb9119f4 ("x86/smpboot: Make logical package management more robust") Link: http://lkml.kernel.org/r/20170131230141.212593966@linutronix.de Signed-off-by: Ingo Molnar <mingo@kernel.org>
Diffstat (limited to 'include/rdma/ib_cm.h')