Eric Dumazet
6a2d7a955d
[PATCH] SLAB: use a multiply instead of a divide in obj_to_index()
...
When some objects are allocated by one CPU but freed by another CPU we can
consume lot of cycles doing divides in obj_to_index().
(Typical load on a dual processor machine where network interrupts are
handled by one particular CPU (allocating skbufs), and the other CPU is
running the application (consuming and freeing skbufs))
Here on one production server (dual-core AMD Opteron 285), I noticed this
divide took 1.20 % of CPU_CLK_UNHALTED events in kernel. But Opteron are
quite modern cpus and the divide is much more expensive on oldest
architectures :
On a 200 MHz sparcv9 machine, the division takes 64 cycles instead of 1
cycle for a multiply.
Doing some math, we can use a reciprocal multiplication instead of a divide.
If we want to compute V = (A / B) (A and B being u32 quantities)
we can instead use :
V = ((u64)A * RECIPROCAL(B)) >> 32 ;
where RECIPROCAL(B) is precalculated to ((1LL << 32) + (B - 1)) / B
Note :
I wrote pure C code for clarity. gcc output for i386 is not optimal but
acceptable :
mull 0x14(%ebx)
mov %edx,%eax // part of the >> 32
xor %edx,%edx // useless
mov %eax,(%esp) // could be avoided
mov %edx,0x4(%esp) // useless
mov (%esp),%ebx
[akpm@osdl.org: small cleanups]
Signed-off-by: Eric Dumazet <dada1@cosmosbay.com>
Cc: Christoph Lameter <clameter@sgi.com>
Cc: David Miller <davem@davemloft.net>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-12-13 09:05:49 -08:00
..
reed_solomon
fix file specification in comments
2006-10-03 23:01:26 +02:00
zlib_deflate
[PATCH] zlib_inflate: Upgrade library code to a recent version
2006-06-22 15:05:58 -07:00
zlib_inflate
[PATCH] Fix ppc32 zImage inflate
2006-07-31 13:28:37 -07:00
.gitignore
Add some basic .gitignore files
2005-10-18 08:26:15 -07:00
audit.c
[PATCH] fix missing ifdefs in syscall classes hookup for generic targets
2006-09-22 17:48:56 -07:00
bitmap.c
[PATCH] bitmap: parse input from kernel and user buffers
2006-10-11 11:14:22 -07:00
bitrev.c
[PATCH] add MODULE_* attributes to bit reversal library
2006-12-10 10:07:52 -08:00
bug.c
[PATCH] Generic BUG implementation
2006-12-08 08:28:39 -08:00
bust_spinlocks.c
Remove obsolete #include <linux/config.h>
2006-06-30 19:25:36 +02:00
cmdline.c
[PATCH] get_options to allow a hypenated range for isolcpus
2006-12-07 08:39:35 -08:00
cpumask.c
[PATCH] highest_possible_node_id() linkage fix
2006-10-20 10:26:43 -07:00
crc-ccitt.c
[PATCH] kernel-doc for lib/crc*.c
2006-06-25 10:01:20 -07:00
crc16.c
[PATCH] kernel-doc for lib/crc*.c
2006-06-25 10:01:20 -07:00
crc32.c
[PATCH] crc32: replace bitreverse by bitrev32
2006-12-08 08:28:39 -08:00
crc32defs.h
Linux-2.6.12-rc2
2005-04-16 15:20:36 -07:00
ctype.c
Linux-2.6.12-rc2
2005-04-16 15:20:36 -07:00
debug_locks.c
[PATCH] lockdep: better lock debugging
2006-07-03 15:27:01 -07:00
dec_and_lock.c
[PATCH] atomic: dec_and_lock use atomic primitives
2006-01-08 20:13:48 -08:00
div64.c
Linux-2.6.12-rc2
2005-04-16 15:20:36 -07:00
dump_stack.c
Linux-2.6.12-rc2
2005-04-16 15:20:36 -07:00
extable.c
Remove obsolete #include <linux/config.h>
2006-06-30 19:25:36 +02:00
fault-inject.c
[PATCH] fault-injection: optimize and simplify should_fail()
2006-12-08 08:29:03 -08:00
find_next_bit.c
[PATCH] bitops: generic ext2_{set,clear,test,find_first_zero,find_next_zero}_bit()
2006-03-26 08:57:11 -08:00
gen_crc32table.c
Linux-2.6.12-rc2
2005-04-16 15:20:36 -07:00
genalloc.c
[PATCH] make genpool allocator adhere to kernel-doc standards
2006-10-02 07:57:12 -07:00
halfmd4.c
Linux-2.6.12-rc2
2005-04-16 15:20:36 -07:00
hweight.c
[PATCH] optimize hweight64 for x86_64
2006-09-26 10:52:38 +02:00
idr.c
[PATCH] slab: remove kmem_cache_t
2006-12-07 08:39:25 -08:00
inflate.c
[PATCH] Update in-kernel zlib routines
2005-08-05 16:23:21 -07:00
int_sqrt.c
[PATCH] lib: Fix bug in int_sqrt() for 64 bit longs
2006-02-03 08:32:08 -08:00
iomap.c
[PATCH] Arch provides generic iomap missing accessors
2006-12-04 15:59:52 +11:00
iomap_copy.c
[PATCH] add __iowrite64_copy
2006-06-20 20:24:58 -07:00
ioremap.c
[PATCH] Generic ioremap_page_range: flush_cache_vmap
2006-10-01 00:39:31 -07:00
irq_regs.c
[PATCH] irq_reqs: export __irq_regs
2006-10-06 08:53:40 -07:00
Kconfig
[PATCH] crc32: replace bitreverse by bitrev32
2006-12-08 08:28:39 -08:00
Kconfig.debug
Fix typo in new debug options.
2006-12-12 20:16:36 +01:00
kernel_lock.c
[PATCH] lockdep: prove spinlock rwlock locking correctness
2006-07-03 15:27:04 -07:00
klist.c
Driver core: Don't call put methods while holding a spinlock
2006-09-25 21:08:40 -07:00
kobject.c
[PATCH] kernel core: replace kmalloc+memset with kzalloc
2006-12-07 08:39:41 -08:00
kobject_uevent.c
driver core: Introduce device_move(): move a device to a new parent.
2006-12-01 14:52:01 -08:00
kref.c
[PATCH] kref: avoid an atomic operation in kref_put()
2006-03-20 13:42:57 -08:00
libcrc32c.c
[PATCH] constify libcrc32c table
2006-06-25 10:01:09 -07:00
list_debug.c
[PATCH] More list debugging context
2006-12-07 08:39:35 -08:00
locking-selftest-hardirq.h
[PATCH] lockdep: locking API self tests
2006-07-03 15:27:03 -07:00
locking-selftest-mutex.h
[PATCH] lockdep: locking API self tests
2006-07-03 15:27:03 -07:00
locking-selftest-rlock-hardirq.h
[PATCH] lockdep: locking API self tests
2006-07-03 15:27:03 -07:00
locking-selftest-rlock-softirq.h
[PATCH] lockdep: locking API self tests
2006-07-03 15:27:03 -07:00
locking-selftest-rlock.h
[PATCH] lockdep: locking API self tests
2006-07-03 15:27:03 -07:00
locking-selftest-rsem.h
[PATCH] lockdep: locking API self tests
2006-07-03 15:27:03 -07:00
locking-selftest-softirq.h
[PATCH] lockdep: locking API self tests
2006-07-03 15:27:03 -07:00
locking-selftest-spin-hardirq.h
[PATCH] lockdep: locking API self tests
2006-07-03 15:27:03 -07:00
locking-selftest-spin-softirq.h
[PATCH] lockdep: locking API self tests
2006-07-03 15:27:03 -07:00
locking-selftest-spin.h
[PATCH] lockdep: locking API self tests
2006-07-03 15:27:03 -07:00
locking-selftest-wlock-hardirq.h
[PATCH] lockdep: locking API self tests
2006-07-03 15:27:03 -07:00
locking-selftest-wlock-softirq.h
[PATCH] lockdep: locking API self tests
2006-07-03 15:27:03 -07:00
locking-selftest-wlock.h
[PATCH] lockdep: locking API self tests
2006-07-03 15:27:03 -07:00
locking-selftest-wsem.h
[PATCH] lockdep: locking API self tests
2006-07-03 15:27:03 -07:00
locking-selftest.c
[PATCH] lockdep: show more details about self-test failures
2006-12-07 08:39:43 -08:00
Makefile
[PATCH] SLAB: use a multiply instead of a divide in obj_to_index()
2006-12-13 09:05:49 -08:00
parser.c
Linux-2.6.12-rc2
2005-04-16 15:20:36 -07:00
percpu_counter.c
[PATCH] percpu counter data type changes to suppport more than 2**31 ext3 free blocks counter
2006-06-23 07:43:06 -07:00
plist.c
[PATCH] pi-futex: add plist implementation
2006-06-27 17:32:46 -07:00
prio_tree.c
Linux-2.6.12-rc2
2005-04-16 15:20:36 -07:00
radix-tree.c
[PATCH] hotplug CPU: clean up hotcpu_notifier() use
2006-12-07 08:39:39 -08:00
random32.c
[PATCH] severing module.h->sched.h
2006-12-04 02:00:22 -05:00
rbtree.c
[PATCH] rbtree: fixed reversed RB_EMPTY_NODE and rb_next/prev
2006-09-30 20:26:56 +02:00
reciprocal_div.c
[PATCH] SLAB: use a multiply instead of a divide in obj_to_index()
2006-12-13 09:05:49 -08:00
rwsem-spinlock.c
Lockdep: add lockdep_set_class_and_subclass() and lockdep_set_subclass()
2006-10-11 01:45:14 -04:00
rwsem.c
Lockdep: add lockdep_set_class_and_subclass() and lockdep_set_subclass()
2006-10-11 01:45:14 -04:00
semaphore-sleepers.c
Remove obsolete #include <linux/config.h>
2006-06-30 19:25:36 +02:00
sha1.c
[PATCH] lib/sha1.c: fix sparse warning
2005-06-25 16:25:02 -07:00
smp_processor_id.c
[PATCH] fix missing includes
2005-10-30 17:37:32 -08:00
sort.c
[PATCH] low performance of lib/sort.c
2006-10-03 08:03:41 -07:00
spinlock_debug.c
[PATCH] x86: all cpu backtrace
2006-12-07 02:14:01 +01:00
string.c
[PATCH] strstrip remove last blank fix
2006-10-28 11:30:54 -07:00
swiotlb.c
BUG_ON() Conversion in lib/swiotlb.c
2006-03-24 18:47:11 +01:00
textsearch.c
Fix typos in doc and comments
2006-11-30 05:32:19 +01:00
ts_bm.c
[TEXTSEARCH]: Fix Boyer Moore initialization bug
2006-08-22 14:33:58 -07:00
ts_fsm.c
[PATCH] lib/ts_fsm.c: constify structs
2006-09-29 09:18:23 -07:00
ts_kmp.c
Remove obsolete #include <linux/config.h>
2006-06-30 19:25:36 +02:00
vsprintf.c
Fix vsnprintf off-by-one bug
2006-06-28 17:09:34 -07:00