mirror of
https://github.com/torvalds/linux.git
synced 2024-11-24 05:02:12 +00:00
ca96ab859a
In case the call side is not providing a swap function, we either use a
32 bit or a generic swap function. When swapping around pointers on 64
bit architectures falling back to use the generic swap function seems
like an unnecessary waste.
There at least 9 users ('sort' is of difficult to grep for) of sort()
and all of them use the sort function without a customized swap
function. Furthermore, they are all using pointers to swap around:
arch/x86/kernel/e820.c:sanitize_e820_map()
arch/x86/mm/extable.c:sort_extable()
drivers/acpi/fan.c:acpi_fan_get_fps()
fs/btrfs/super.c:btrfs_descending_sort_devices()
fs/xfs/libxfs/xfs_dir2_block.c:xfs_dir2_sf_to_block()
kernel/range.c:clean_sort_range()
mm/memcontrol.c:__mem_cgroup_usage_register_event()
sound/pci/hda/hda_auto_parser.c:snd_hda_parse_pin_defcfg()
sound/pci/hda/hda_auto_parser.c:sort_pins_by_sequence()
Obviously, we could improve the swap for other sizes as well
but this is overkill at this point.
A simple test shows sorting a 400 element array (try to stay in one
page) with either with u32_swap() or u64_swap() show that the theory
actually works. This test was done on a x86_64 (Intel Xeon E5-4610)
machine.
- swap_32:
NumSamples = 100; Min = 48.00; Max = 49.00
Mean = 48.320000; Variance = 0.217600; SD = 0.466476; Median 48.000000
each * represents a count of 1
48.0000 - 48.1000 [ 68]: ********************************************************************
48.1000 - 48.2000 [ 0]:
48.2000 - 48.3000 [ 0]:
48.3000 - 48.4000 [ 0]:
48.4000 - 48.5000 [ 0]:
48.5000 - 48.6000 [ 0]:
48.6000 - 48.7000 [ 0]:
48.7000 - 48.8000 [ 0]:
48.8000 - 48.9000 [ 0]:
48.9000 - 49.0000 [ 32]: ********************************
- swap_64:
NumSamples = 100; Min = 44.00; Max = 63.00
Mean = 48.250000; Variance = 18.687500; SD = 4.322904; Median 47.000000
each * represents a count of 1
44.0000 - 45.9000 [ 15]: ***************
45.9000 - 47.8000 [ 37]: *************************************
47.8000 - 49.7000 [ 39]: ***************************************
49.7000 - 51.6000 [ 0]:
51.6000 - 53.5000 [ 0]:
53.5000 - 55.4000 [ 0]:
55.4000 - 57.3000 [ 0]:
57.3000 - 59.2000 [ 1]: *
59.2000 - 61.1000 [ 3]: ***
61.1000 - 63.0000 [ 5]: *****
- swap_72:
NumSamples = 100; Min = 53.00; Max = 71.00
Mean = 55.070000; Variance = 21.565100; SD = 4.643824; Median 53.000000
each * represents a count of 1
53.0000 - 54.8000 [ 73]: *************************************************************************
54.8000 - 56.6000 [ 9]: *********
56.6000 - 58.4000 [ 9]: *********
58.4000 - 60.2000 [ 0]:
60.2000 - 62.0000 [ 0]:
62.0000 - 63.8000 [ 0]:
63.8000 - 65.6000 [ 0]:
65.6000 - 67.4000 [ 1]: *
67.4000 - 69.2000 [ 4]: ****
69.2000 - 71.0000 [ 4]: ****
- test program:
static int cmp_32(const void *a, const void *b)
{
u32 l = *(u32 *)a;
u32 r = *(u32 *)b;
if (l < r)
return -1;
if (l > r)
return 1;
return 0;
}
static int cmp_64(const void *a, const void *b)
{
u64 l = *(u64 *)a;
u64 r = *(u64 *)b;
if (l < r)
return -1;
if (l > r)
return 1;
return 0;
}
static int cmp_72(const void *a, const void *b)
{
u32 l = get_unaligned((u32 *) a);
u32 r = get_unaligned((u32 *) b);
if (l < r)
return -1;
if (l > r)
return 1;
return 0;
}
static void init_array32(void *array)
{
u32 *a = array;
int i;
a[0] = 3821;
for (i = 1; i < ARRAY_ELEMENTS; i++)
a[i] = next_pseudo_random32(a[i-1]);
}
static void init_array64(void *array)
{
u64 *a = array;
int i;
a[0] = 3821;
for (i = 1; i < ARRAY_ELEMENTS; i++)
a[i] = next_pseudo_random32(a[i-1]);
}
static void init_array72(void *array)
{
char *p;
u32 v;
int i;
v = 3821;
for (i = 0; i < ARRAY_ELEMENTS; i++) {
p = (char *)array + (i * 9);
put_unaligned(v, (u32*) p);
v = next_pseudo_random32(v);
}
}
static void sort_test(void (*init)(void *array),
int (*cmp) (const void *, const void *),
void *array, size_t size)
{
ktime_t start, stop;
int i;
for (i = 0; i < 10000; i++) {
init(array);
local_irq_disable();
start = ktime_get();
sort(array, ARRAY_ELEMENTS, size, cmp, NULL);
stop = ktime_get();
local_irq_enable();
if (i > 10000 - 101)
pr_info("%lld\n", ktime_to_us(ktime_sub(stop, start)));
}
}
static void *create_array(size_t size)
{
void *array;
array = kmalloc(ARRAY_ELEMENTS * size, GFP_KERNEL);
if (!array)
return NULL;
return array;
}
static int perform_test(size_t size)
{
void *array;
array = create_array(size);
if (!array)
return -ENOMEM;
pr_info("test element size %d bytes\n", (int)size);
switch (size) {
case 4:
sort_test(init_array32, cmp_32, array, size);
break;
case 8:
sort_test(init_array64, cmp_64, array, size);
break;
case 9:
sort_test(init_array72, cmp_72, array, size);
break;
}
kfree(array);
return 0;
}
static int __init sort_tests_init(void)
{
int err;
err = perform_test(sizeof(u32));
if (err)
return err;
err = perform_test(sizeof(u64));
if (err)
return err;
err = perform_test(sizeof(u64)+1);
if (err)
return err;
return 0;
}
static void __exit sort_tests_exit(void)
{
}
module_init(sort_tests_init);
module_exit(sort_tests_exit);
MODULE_LICENSE("GPL v2");
MODULE_AUTHOR("Daniel Wagner");
MODULE_DESCRIPTION("sort perfomance tests");
Signed-off-by: Daniel Wagner <daniel.wagner@bmw-carit.de>
Cc: Rasmus Villemoes <linux@rasmusvillemoes.dk>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
|
||
|---|---|---|
| .. | ||
| 842 | ||
| fonts | ||
| lz4 | ||
| lzo | ||
| mpi | ||
| raid6 | ||
| reed_solomon | ||
| xz | ||
| zlib_deflate | ||
| zlib_inflate | ||
| .gitignore | ||
| argv_split.c | ||
| asn1_decoder.c | ||
| assoc_array.c | ||
| atomic64_test.c | ||
| atomic64.c | ||
| audit.c | ||
| average.c | ||
| bcd.c | ||
| bch.c | ||
| bitmap.c | ||
| bitrev.c | ||
| bsearch.c | ||
| btree.c | ||
| bug.c | ||
| build_OID_registry | ||
| bust_spinlocks.c | ||
| check_signature.c | ||
| checksum.c | ||
| clz_ctz.c | ||
| clz_tab.c | ||
| cmdline.c | ||
| compat_audit.c | ||
| cordic.c | ||
| cpu_rmap.c | ||
| cpu-notifier-error-inject.c | ||
| cpumask.c | ||
| crc7.c | ||
| crc8.c | ||
| crc16.c | ||
| crc32.c | ||
| crc32defs.h | ||
| crc-ccitt.c | ||
| crc-itu-t.c | ||
| crc-t10dif.c | ||
| ctype.c | ||
| debug_locks.c | ||
| debugobjects.c | ||
| dec_and_lock.c | ||
| decompress_bunzip2.c | ||
| decompress_inflate.c | ||
| decompress_unlz4.c | ||
| decompress_unlzma.c | ||
| decompress_unlzo.c | ||
| decompress_unxz.c | ||
| decompress.c | ||
| devres.c | ||
| digsig.c | ||
| div64.c | ||
| dma-debug.c | ||
| dump_stack.c | ||
| dynamic_debug.c | ||
| dynamic_queue_limits.c | ||
| earlycpio.c | ||
| extable.c | ||
| fault-inject.c | ||
| fdt_empty_tree.c | ||
| fdt_ro.c | ||
| fdt_rw.c | ||
| fdt_strerror.c | ||
| fdt_sw.c | ||
| fdt_wip.c | ||
| fdt.c | ||
| find_bit.c | ||
| flex_array.c | ||
| flex_proportions.c | ||
| gcd.c | ||
| gen_crc32table.c | ||
| genalloc.c | ||
| glob.c | ||
| halfmd4.c | ||
| hexdump.c | ||
| hweight.c | ||
| idr.c | ||
| inflate.c | ||
| int_sqrt.c | ||
| interval_tree_test.c | ||
| interval_tree.c | ||
| iomap_copy.c | ||
| iomap.c | ||
| iommu-common.c | ||
| iommu-helper.c | ||
| ioremap.c | ||
| iov_iter.c | ||
| irq_regs.c | ||
| is_single_threaded.c | ||
| jedec_ddr_data.c | ||
| kasprintf.c | ||
| Kconfig | ||
| Kconfig.debug | ||
| Kconfig.kasan | ||
| Kconfig.kgdb | ||
| Kconfig.kmemcheck | ||
| kfifo.c | ||
| klist.c | ||
| kobject_uevent.c | ||
| kobject.c | ||
| kstrtox.c | ||
| kstrtox.h | ||
| lcm.c | ||
| libcrc32c.c | ||
| list_debug.c | ||
| list_sort.c | ||
| llist.c | ||
| locking-selftest-hardirq.h | ||
| locking-selftest-mutex.h | ||
| locking-selftest-rlock-hardirq.h | ||
| locking-selftest-rlock-softirq.h | ||
| locking-selftest-rlock.h | ||
| locking-selftest-rsem.h | ||
| locking-selftest-softirq.h | ||
| locking-selftest-spin-hardirq.h | ||
| locking-selftest-spin-softirq.h | ||
| locking-selftest-spin.h | ||
| locking-selftest-wlock-hardirq.h | ||
| locking-selftest-wlock-softirq.h | ||
| locking-selftest-wlock.h | ||
| locking-selftest-wsem.h | ||
| locking-selftest.c | ||
| lockref.c | ||
| lru_cache.c | ||
| Makefile | ||
| md5.c | ||
| memory-notifier-error-inject.c | ||
| memweight.c | ||
| net_utils.c | ||
| nlattr.c | ||
| notifier-error-inject.c | ||
| notifier-error-inject.h | ||
| of-reconfig-notifier-error-inject.c | ||
| oid_registry.c | ||
| parser.c | ||
| pci_iomap.c | ||
| percpu_counter.c | ||
| percpu_ida.c | ||
| percpu_test.c | ||
| percpu-refcount.c | ||
| plist.c | ||
| pm-notifier-error-inject.c | ||
| proportions.c | ||
| radix-tree.c | ||
| random32.c | ||
| ratelimit.c | ||
| rational.c | ||
| rbtree_test.c | ||
| rbtree.c | ||
| reciprocal_div.c | ||
| rhashtable.c | ||
| scatterlist.c | ||
| seq_buf.c | ||
| sha1.c | ||
| show_mem.c | ||
| smp_processor_id.c | ||
| sort.c | ||
| stmp_device.c | ||
| string_helpers.c | ||
| string.c | ||
| strncpy_from_user.c | ||
| strnlen_user.c | ||
| swiotlb.c | ||
| syscall.c | ||
| test_bpf.c | ||
| test_firmware.c | ||
| test_kasan.c | ||
| test_module.c | ||
| test_rhashtable.c | ||
| test_user_copy.c | ||
| test-hexdump.c | ||
| test-kstrtox.c | ||
| test-string_helpers.c | ||
| textsearch.c | ||
| timerqueue.c | ||
| ts_bm.c | ||
| ts_fsm.c | ||
| ts_kmp.c | ||
| ucs2_string.c | ||
| usercopy.c | ||
| uuid.c | ||
| vsprintf.c | ||