summaryrefslogtreecommitdiffstats
path: root/lib/sort.c
AgeCommit message (Collapse)AuthorFilesLines
2017-02-24lib: add CONFIG_TEST_SORT to enable self-test of sort()Kostenzer Felix1-39/+2
Along with the addition made to Kconfig.debug, the prior existing but permanently disabled test function has been slightly refactored. Patch has been tested using QEMU 2.1.2 with a .config obtained through 'make defconfig' (x86_64) and manually enabling the option. [arnd@arndb.de: move sort self-test into a separate file] Link: http://lkml.kernel.org/r/20170112110657.3123790-1-arnd@arndb.de Link: http://lkml.kernel.org/r/HE1PR09MB0394B0418D504DCD27167D4FD49B0@HE1PR09MB0394.eurprd09.prod.outlook.com Signed-off-by: Kostenzer Felix <fkostenzer@live.at> Signed-off-by: Arnd Bergmann <arnd@arndb.de> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2015-06-25lib/sort: Add 64 bit swap functionDaniel Wagner1-2/+21
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>
2015-02-12lib/sort.c: move include inside #if 0Rasmus Villemoes1-1/+1
The sort function and its helpers don't do memory allocation, so the slab.h include is redundant. Move it inside the #if 0 protecting the self-test, similar to how it is done in lib/list_sort.c. This removes over 450 lines from the generated dependency file. Signed-off-by: Rasmus Villemoes <linux@rasmusvillemoes.dk> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2015-02-12lib/sort.c: use simpler includesRasmus Villemoes1-2/+2
sort.c doesn't use facilities from kernel.h, but does use some types defined in linux/types.h. Include the latter directly instead of relying on some other header doing it. Similarly, include linux/export.h directly instead of through module.h. This removes 80 lines from the dependency file .sort.o.cmd. Signed-off-by: Rasmus Villemoes <linux@rasmusvillemoes.dk> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-01-08generic swap(): lib/sort.c: rename swap to swap_funcWu Fengguang1-14/+16
This is to avoid name clashes for the introduction of a global swap() macro. Signed-off-by: Wu Fengguang <fengguang.wu@intel.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-10-17lib/sort.c optimizationSubbaiah Venkata1-1/+1
Hello, I fixed and tested a small bug in lib/sort.c file, heap sort function. The fix avoids unnecessary swap of contents when i is 0 (saves few loads and stores), which happens every time sort function is called. I felt the fix is worth bringing it to your attention given the importance and frequent use of the sort function. Acked-by: Matt Mackall <mpm@selenic.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-02-11[PATCH] Numerous fixes to kernel-doc info in source files.Robert P. J. Day1-1/+1
A variety of (mostly) innocuous fixes to the embedded kernel-doc content in source files, including: * make multi-line initial descriptions single line * denote some function names, constants and structs as such * change erroneous opening '/*' to '/**' in a few places * reword some text for clarity Signed-off-by: Robert P. J. Day <rpjday@mindspring.com> Cc: "Randy.Dunlap" <rdunlap@xenotime.net> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2006-10-03[PATCH] low performance of lib/sort.ckeios1-5/+5
It is a non-standard heap-sort algorithm implementation because the index of child node is wrong . The sort function still outputs right result, but the performance is O( n * ( log(n) + 1 ) ) , about 10% ~ 20% worse than standard algorithm. Signed-off-by: keios <keios.cn@gmail.com> Acked-by: Matt Mackall <mpm@selenic.com> Acked-by: Zou Nan hai <nanhai.zou@intel.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2005-10-30[PATCH] fix missing includesTim Schmielau1-0/+1
I recently picked up my older work to remove unnecessary #includes of sched.h, starting from a patch by Dave Jones to not include sched.h from module.h. This reduces the number of indirect includes of sched.h by ~300. Another ~400 pointless direct includes can be removed after this disentangling (patch to follow later). However, quite a few indirect includes need to be fixed up for this. In order to feed the patches through -mm with as little disturbance as possible, I've split out the fixes I accumulated up to now (complete for i386 and x86_64, more archs to follow later) and post them before the real patch. This way this large part of the patch is kept simple with only adding #includes, and all hunks are independent of each other. So if any hunk rejects or gets in the way of other patches, just drop it. My scripts will pick it up again in the next round. Signed-off-by: Tim Schmielau <tim@physik3.uni-rostock.de> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2005-09-10[PATCH] lib/sort.c: small cleanupsAdrian Bunk1-2/+3
This patch contains the following small cleanups: - make two needlessly global functions static - every file should #include the header files containing the prototypes of it's global functions Signed-off-by: Adrian Bunk <bunk@stusta.de> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2005-05-05[PATCH] fix lib/sort regression testDomen Puncer1-1/+1
The regression test in lib/sort.c is currently worthless because the array that is generated for sorting will be all zeros. This patch fixes things so that the array that is generated will contain unsorted integers (that are not all identical) as was probably intended. Signed-off-by Daniel Dickman <didickman@yahoo.com> Signed-off-by: Domen Puncer <domen@coderock.org> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2005-04-16Linux-2.6.12-rc2v2.6.12-rc2Linus Torvalds1-0/+119
Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!