Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S934315AbZJMULV (ORCPT ); Tue, 13 Oct 2009 16:11:21 -0400 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S934282AbZJMULT (ORCPT ); Tue, 13 Oct 2009 16:11:19 -0400 Received: from smtp2.ultrahosting.com ([74.213.174.253]:43646 "EHLO smtp.ultrahosting.com" rhost-flags-OK-OK-OK-FAIL) by vger.kernel.org with ESMTP id S934284AbZJMULP (ORCPT ); Tue, 13 Oct 2009 16:11:15 -0400 X-Amavis-Alert: BAD HEADER, Header field occurs more than once: "Cc" occurs 7 times Message-Id: <20091013200302.142601669@gentwo.org> References: <20091013200233.260324963@gentwo.org> User-Agent: quilt/0.46-1 Date: Tue, 13 Oct 2009 16:02:34 -0400 From: Christoph Lameter To: Mel Gorman Cc: linux-kernel@vger.kernel.org Cc: Pekka Enberg Cc: Tejun Heo Cc: Mathieu Desnoyers Cc: akpm@linux-foundation.org Cc: Ingo Molnar Cc: Eric Dumazet Subject: [RFC In-kernel benchmarks 1/3] Add slab performance tests Content-Disposition: inline; filename=0001-Add-slab-performance-tests.patch Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Length: 11667 Lines: 471 This is a test of slab allocator performance tests. Run modprobe slab_test to execute. Output will be written to the syslog. Signed-off-by: Christoph Lameter --- Makefile | 2 include/Kbuild | 1 lib/Kconfig.debug | 1 tests/Kconfig | 19 ++ tests/Makefile | 2 tests/slab_test.c | 373 ++++++++++++++++++++++++++++++++++++++++++++++++++++++ 6 files changed, 397 insertions(+), 1 deletion(-) create mode 100644 tests/Makefile create mode 100644 tests/slab_test.c Index: linux-2.6/Makefile =================================================================== --- linux-2.6.orig/Makefile 2009-10-12 15:32:26.000000000 -0500 +++ linux-2.6/Makefile 2009-10-12 15:32:30.000000000 -0500 @@ -686,7 +686,7 @@ export mod_strip_cmd ifeq ($(KBUILD_EXTMOD),) -core-y += kernel/ mm/ fs/ ipc/ security/ crypto/ block/ +core-y += kernel/ mm/ fs/ ipc/ security/ crypto/ block/ tests/ vmlinux-dirs := $(patsubst %/,%,$(filter %/, $(init-y) $(init-m) \ $(core-y) $(core-m) $(drivers-y) $(drivers-m) \ Index: linux-2.6/include/Kbuild =================================================================== --- linux-2.6.orig/include/Kbuild 2009-10-12 15:32:26.000000000 -0500 +++ linux-2.6/include/Kbuild 2009-10-12 15:32:30.000000000 -0500 @@ -10,3 +10,4 @@ header-y += video/ header-y += drm/ header-y += xen/ header-y += scsi/ +header-y += tests/ Index: linux-2.6/tests/Makefile =================================================================== --- /dev/null 1970-01-01 00:00:00.000000000 +0000 +++ linux-2.6/tests/Makefile 2009-10-12 15:32:30.000000000 -0500 @@ -0,0 +1,2 @@ +obj-$(CONFIG_BENCHMARK_SLAB) += slab_test.o + Index: linux-2.6/tests/slab_test.c =================================================================== --- /dev/null 1970-01-01 00:00:00.000000000 +0000 +++ linux-2.6/tests/slab_test.c 2009-10-12 15:32:47.000000000 -0500 @@ -0,0 +1,373 @@ +/* test-slab.c + * + * Test module for synthetic in kernel slab allocator testing. + * + * The test is triggered by loading the module (which will fail). + * + * (C) 2009 Linux Foundation + */ + + +#include +#include +#include +#include +#include +#include +#include + +#define TEST_COUNT 10000 + +#ifdef CONFIG_SMP +#include +#include +#include +#include + +static struct test_struct { + struct task_struct *task; + int cpu; + int size; + int count; + void **v; + void (*test_p1)(struct test_struct *); + void (*test_p2)(struct test_struct *); + unsigned long start1; + unsigned long stop1; + unsigned long start2; + unsigned long stop2; +} test[NR_CPUS]; + +/* + * Allocate TEST_COUNT objects on cpus > 0 and then all the + * objects later on cpu 0 + */ +static void remote_free_test_p1(struct test_struct *t) +{ + int i; + + /* Perform no allocations on cpu 0 */ + for (i = 0; i < t->count; i++) { + u8 *p; + + if (smp_processor_id()) { + p = kmalloc(t->size, GFP_KERNEL); + /* Use object */ + *p = 17; + } else + p = NULL; + t->v[i] = p; + } +} + +static void remote_free_test_p2(struct test_struct *t) +{ + int i; + int cpu; + + /* All frees are completed on cpu zero */ + if (smp_processor_id()) + return; + + for_each_online_cpu(cpu) + for (i = 0; i < t->count; i++) { + u8 *p = test[cpu].v[i]; + + if (!p) + continue; + + *p = 16; + kfree(p); + } +} + +/* + * Allocate TEST_COUNT objects on cpu 0 and free them immediately on the + * other processors. + */ +static void alloc_n_free_test_p1(struct test_struct *t) +{ + int i; + int cpu; + char *p; + + if (smp_processor_id()) { + /* Consumer */ + for (i = 0; i < t->count / num_online_cpus(); i++) { + do { + p = t->v[i]; + if (!p) + cpu_relax(); + else + *p = 17; + } while (!p); + kfree(p); + t->v[i] = NULL; + } + return; + } + /* Producer */ + for (i = 0; i < t->count; i++) { + for_each_online_cpu(cpu) { + if (cpu) { + p = kmalloc(t->size, GFP_KERNEL); + /* Use object */ + *p = 17; + test[cpu].v[i] = p; + } + } + } +} + +/* + * Allocate TEST_COUNT objects and later free them all again + */ +static void kmalloc_alloc_then_free_test_p1(struct test_struct *t) +{ + int i; + + for (i = 0; i < t->count; i++) { + u8 *p = kmalloc(t->size, GFP_KERNEL); + + *p = 14; + t->v[i] = p; + } +} + +static void kmalloc_alloc_then_free_test_p2(struct test_struct *t) +{ + int i; + + for (i = 0; i < t->count; i++) { + u8 *p = t->v[i]; + + *p = 13; + kfree(p); + } +} + +/* + * Allocate TEST_COUNT objects. Free them immediately. + */ +static void kmalloc_alloc_free_test_p1(struct test_struct *t) +{ + int i; + + for (i = 0; i < TEST_COUNT; i++) { + u8 *p = kmalloc(t->size, GFP_KERNEL); + + *p = 12; + kfree(p); + } +} + +static atomic_t tests_running; +static atomic_t phase1_complete; +static DECLARE_COMPLETION(completion1); +static DECLARE_COMPLETION(completion2); +static int started; + +static int test_func(void *private) +{ + struct test_struct *t = private; + cpumask_t newmask = CPU_MASK_NONE; + + cpu_set(t->cpu, newmask); + set_cpus_allowed(current, newmask); + t->v = kzalloc(t->count * sizeof(void *), GFP_KERNEL); + + atomic_inc(&tests_running); + wait_for_completion(&completion1); + t->start1 = get_cycles(); + t->test_p1(t); + t->stop1 = get_cycles(); + atomic_inc(&phase1_complete); + wait_for_completion(&completion2); + t->start2 = get_cycles(); + if (t->test_p2) + t->test_p2(t); + t->stop2 = get_cycles(); + kfree(t->v); + atomic_dec(&tests_running); + set_current_state(TASK_UNINTERRUPTIBLE); + schedule(); + return 0; +} + +static void do_concurrent_test(void (*p1)(struct test_struct *), + void (*p2)(struct test_struct *), + int size, const char *name) +{ + int cpu; + unsigned long time1 = 0; + unsigned long time2 = 0; + unsigned long sum1 = 0; + unsigned long sum2 = 0; + + atomic_set(&tests_running, 0); + atomic_set(&phase1_complete, 0); + started = 0; + init_completion(&completion1); + init_completion(&completion2); + + for_each_online_cpu(cpu) { + struct test_struct *t = &test[cpu]; + + t->cpu = cpu; + t->count = TEST_COUNT; + t->test_p1 = p1; + t->test_p2 = p2; + t->size = size; + t->task = kthread_run(test_func, t, "test%d", cpu); + if (IS_ERR(t->task)) { + printk("Failed to start test func\n"); + return; + } + } + + /* Wait till all processes are running */ + while (atomic_read(&tests_running) < num_online_cpus()) { + set_current_state(TASK_UNINTERRUPTIBLE); + schedule_timeout(10); + } + complete_all(&completion1); + + /* Wait till all processes have completed phase 1 */ + while (atomic_read(&phase1_complete) < num_online_cpus()) { + set_current_state(TASK_UNINTERRUPTIBLE); + schedule_timeout(10); + } + complete_all(&completion2); + + while (atomic_read(&tests_running)) { + set_current_state(TASK_UNINTERRUPTIBLE); + schedule_timeout(10); + } + + for_each_online_cpu(cpu) + kthread_stop(test[cpu].task); + + printk(KERN_ALERT "%s(%d):", name, size); + for_each_online_cpu(cpu) { + struct test_struct *t = &test[cpu]; + + time1 = t->stop1 - t->start1; + time2 = t->stop2 - t->start2; + sum1 += time1; + sum2 += time2; + printk(" %d=%lu", cpu, time1 / TEST_COUNT); + if (p2) + printk("/%lu", time2 / TEST_COUNT); + } + printk(" Average=%lu", sum1 / num_online_cpus() / TEST_COUNT); + if (p2) + printk("/%lu", sum2 / num_online_cpus() / TEST_COUNT); + printk("\n"); + schedule_timeout(200); +} +#endif + +static int slab_test_init(void) +{ + void **v = kmalloc(TEST_COUNT * sizeof(void *), GFP_KERNEL); + unsigned int i; + cycles_t time1, time2, time; + int rem; + int size; + + printk(KERN_ALERT "test init\n"); + + printk(KERN_ALERT "Single thread testing\n"); + printk(KERN_ALERT "=====================\n"); + printk(KERN_ALERT "1. Kmalloc: Repeatedly allocate then free test\n"); + for (size = 8; size <= PAGE_SIZE << 2; size <<= 1) { + time1 = get_cycles(); + for (i = 0; i < TEST_COUNT; i++) { + u8 *p = kmalloc(size, GFP_KERNEL); + + *p = 22; + v[i] = p; + } + time2 = get_cycles(); + time = time2 - time1; + + printk(KERN_ALERT "%i times kmalloc(%d) ", i, size); + time = div_u64_rem(time, TEST_COUNT, &rem); + printk("-> %llu cycles ", time); + + time1 = get_cycles(); + for (i = 0; i < TEST_COUNT; i++) { + u8 *p = v[i]; + + *p = 23; + kfree(p); + } + time2 = get_cycles(); + time = time2 - time1; + + printk("kfree "); + time = div_u64_rem(time, TEST_COUNT, &rem); + printk("-> %llu cycles\n", time); + } + + printk(KERN_ALERT "2. Kmalloc: alloc/free test\n"); + for (size = 8; size <= PAGE_SIZE << 2; size <<= 1) { + time1 = get_cycles(); + for (i = 0; i < TEST_COUNT; i++) { + u8 *p = kmalloc(size, GFP_KERNEL); + + kfree(p); + } + time2 = get_cycles(); + time = time2 - time1; + + printk(KERN_ALERT "%i times kmalloc(%d)/kfree ", i, size); + time = div_u64_rem(time, TEST_COUNT, &rem); + printk("-> %llu cycles\n", time); + } + kfree(v); +#ifdef CONFIG_SMP + printk(KERN_INFO "Concurrent allocs\n"); + printk(KERN_INFO "=================\n"); + for (i = 3; i <= PAGE_SHIFT; i++) { + do_concurrent_test(kmalloc_alloc_then_free_test_p1, + kmalloc_alloc_then_free_test_p2, + 1 << i, "Kmalloc N*alloc N*free"); + } + for (i = 3; i <= PAGE_SHIFT; i++) { + do_concurrent_test(kmalloc_alloc_free_test_p1, NULL, + 1 << i, "Kmalloc N*(alloc free)"); + } + + printk(KERN_INFO "Remote free test\n"); + printk(KERN_INFO "================\n"); + for (i = 3; i <= PAGE_SHIFT; i++) { + do_concurrent_test(remote_free_test_p1, + remote_free_test_p2, + 1 << i, "N*remote free"); + } + + printk(KERN_INFO "1 alloc N free test\n"); + printk(KERN_INFO "===================\n"); + for (i = 3; i <= PAGE_SHIFT; i++) { + do_concurrent_test(alloc_n_free_test_p1, + NULL, + 1 << i, "1 alloc N free"); + } + +#endif + return -EAGAIN; /* Fail will directly unload the module */ +} + +static void slab_test_exit(void) +{ + printk(KERN_ALERT "test exit\n"); +} + +module_init(slab_test_init) +module_exit(slab_test_exit) + +MODULE_LICENSE("GPL"); +MODULE_AUTHOR("Christoph Lameter and Mathieu Desnoyers"); +MODULE_DESCRIPTION("SLAB test"); + Index: linux-2.6/lib/Kconfig.debug =================================================================== --- linux-2.6.orig/lib/Kconfig.debug 2009-10-12 15:32:26.000000000 -0500 +++ linux-2.6/lib/Kconfig.debug 2009-10-12 15:32:30.000000000 -0500 @@ -920,6 +920,7 @@ config SYSCTL_SYSCALL_CHECK source mm/Kconfig.debug source kernel/trace/Kconfig +source tests/Kconfig config PROVIDE_OHCI1394_DMA_INIT bool "Remote debugging over FireWire early on boot" Index: linux-2.6/tests/Kconfig =================================================================== --- /dev/null 1970-01-01 00:00:00.000000000 +0000 +++ linux-2.6/tests/Kconfig 2009-10-12 15:32:30.000000000 -0500 @@ -0,0 +1,19 @@ +menuconfig BENCHMARKS + bool "In kernel benchmarks" + def_bool n + help + Includes in kernel benchmark modules in the build. These modules can + be loaded later to trigger benchmarking kernel subsystems. + Output will be generated in the system log. + +if BENCHMARKS + +config BENCHMARK_SLAB + tristate "Slab allocator Benchmark" + depends on m + default m + help + A benchmark that measures slab allocator performance. + +endif # BENCHMARKS + -- -- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/