Re: [PATCH] SLUB use cmpxchg_local

From: Christoph Lameter
Date: Mon Aug 27 2007 - 21:26:22 EST

Measurements on IA64 slub w/per cpu vs slub w/per cpu/cmpxchg_local
emulation. Results are not good:

slub/per cpu
10000 times kmalloc(8)/kfree -> 105 cycles
10000 times kmalloc(16)/kfree -> 104 cycles
10000 times kmalloc(32)/kfree -> 105 cycles
10000 times kmalloc(64)/kfree -> 104 cycles
10000 times kmalloc(128)/kfree -> 104 cycles
10000 times kmalloc(256)/kfree -> 115 cycles
10000 times kmalloc(512)/kfree -> 116 cycles
10000 times kmalloc(1024)/kfree -> 115 cycles
10000 times kmalloc(2048)/kfree -> 115 cycles
10000 times kmalloc(4096)/kfree -> 115 cycles
10000 times kmalloc(8192)/kfree -> 117 cycles
10000 times kmalloc(16384)/kfree -> 439 cycles
10000 times kmalloc(32768)/kfree -> 800 cycles


slub/per cpu + cmpxchg_local emulation
10000 times kmalloc(8)/kfree -> 143 cycles
10000 times kmalloc(16)/kfree -> 143 cycles
10000 times kmalloc(32)/kfree -> 143 cycles
10000 times kmalloc(64)/kfree -> 143 cycles
10000 times kmalloc(128)/kfree -> 143 cycles
10000 times kmalloc(256)/kfree -> 154 cycles
10000 times kmalloc(512)/kfree -> 154 cycles
10000 times kmalloc(1024)/kfree -> 154 cycles
10000 times kmalloc(2048)/kfree -> 154 cycles
10000 times kmalloc(4096)/kfree -> 155 cycles
10000 times kmalloc(8192)/kfree -> 155 cycles
10000 times kmalloc(16384)/kfree -> 440 cycles
10000 times kmalloc(32768)/kfree -> 819 cycles
10000 times kmalloc(65536)/kfree -> 902 cycles


Parallel allocs:

Kmalloc N*alloc N*free(16): 0=102/136 1=97/136 2=99/140 3=98/140 4=100/138
5=99/139 6=100/139 7=101/141 Average=99/139

cmpxchg_local emulation
Kmalloc N*alloc N*free(16): 0=116/147 1=116/145 2=115/151 3=115/147
4=115/149 5=117/147 6=116/148 7=116/146 Average=116/147

Patch used:

Index: linux-2.6/include/asm-ia64/atomic.h
===================================================================
--- linux-2.6.orig/include/asm-ia64/atomic.h 2007-08-27 16:42:02.000000000 -0700
+++ linux-2.6/include/asm-ia64/atomic.h 2007-08-27 17:50:24.000000000 -0700
@@ -223,4 +223,17 @@ atomic64_add_negative (__s64 i, atomic64
#define smp_mb__after_atomic_inc() barrier()

#include <asm-generic/atomic.h>
+
+static inline void *cmpxchg_local(void **p, void *old, void *new)
+{
+ unsigned long flags;
+ void *before;
+
+ local_irq_save(flags);
+ before = *p;
+ if (likely(before == old))
+ *p = new;
+ local_irq_restore(flags);
+ return before;
+}
#endif /* _ASM_IA64_ATOMIC_H */

kmem_cache_alloc before

0000000000008900 <kmem_cache_alloc>:
8900: 01 28 31 0e 80 05 [MII] alloc r37=ar.pfs,12,7,0
8906: 40 02 00 62 00 00 mov r36=b0
890c: 00 00 04 00 nop.i 0x0;;
8910: 0b 18 01 00 25 04 [MMI] mov r35=psr;;
8916: 00 00 04 0e 00 00 rsm 0x4000
891c: 00 00 04 00 nop.i 0x0;;
8920: 08 50 90 1b 19 21 [MMI] adds r10=3300,r13
8926: 70 02 80 00 42 40 mov r39=r32
892c: 05 00 c4 00 mov r42=b0
8930: 09 40 01 42 00 21 [MMI] mov r40=r33
8936: 00 00 00 02 00 20 nop.m 0x0
893c: f5 e7 ff 9f mov r41=-1;;
8940: 0b 48 00 14 10 10 [MMI] ld4 r9=[r10];;
8946: 00 00 00 02 00 00 nop.m 0x0
894c: 01 48 58 00 sxt4 r8=r9;;
8950: 0b 18 20 40 12 20 [MMI] shladd r3=r8,3,r32;;
8956: 20 80 0f 82 48 00 addl r2=8432,r3
895c: 00 00 04 00 nop.i 0x0;;
8960: 0a 00 01 04 18 10 [MMI] ld8 r32=[r2];;
8966: e0 a0 80 00 42 60 adds r14=20,r32
896c: 05 00 01 84 mov r43=r32
8970: 0b 10 01 40 18 10 [MMI] ld8 r34=[r32];;
8976: 70 00 88 0c 72 00 cmp.eq p7,p6=0,r34
897c: 00 00 04 00 nop.i 0x0;;
8980: cb 70 00 1c 10 90 [MMI] (p06) ld4 r14=[r14];;
8986: e1 70 88 24 40 00 (p06) shladd r14=r14,3,r34
898c: 00 00 04 00 nop.i 0x0;;
8990: c2 70 00 1c 18 10 [MII] (p06) ld8 r14=[r14]
8996: 00 00 00 02 00 00 nop.i 0x0;;
899c: 00 00 04 00 nop.i 0x0
89a0: d8 00 38 40 98 11 [MMB] (p06) st8 [r32]=r14
89a6: 00 00 00 02 00 03 nop.m 0x0
89ac: 30 00 00 40 (p06) br.cond.sptk.few 89d0 <kmem_cache_alloc+0xd0>
89b0: 11 00 00 00 01 00 [MIB] nop.m 0x0
89b6: 00 00 00 02 00 00 nop.i 0x0
89bc: 18 d8 ff 58 br.call.sptk.many b0=61c0 <__slab_alloc>;;
89c0: 08 10 01 10 00 21 [MMI] mov r34=r8
89c6: 00 00 00 02 00 00 nop.m 0x0
89cc: 00 00 04 00 nop.i 0x0
89d0: 03 00 00 00 01 00 [MII] nop.m 0x0
89d6: 20 01 00 00 49 20 mov r18=16384;;
89dc: 22 19 31 80 and r17=r18,r35;;
89e0: 0a 38 44 00 06 b8 [MMI] cmp.eq p7,p6=r17,r0;;
89e6: 01 00 04 0c 00 00 (p06) ssm 0x4000
89ec: 00 00 04 00 nop.i 0x0
89f0: eb 00 00 02 07 80 [MMI] (p07) rsm 0x4000;;
89f6: 01 00 00 60 00 00 (p06) srlz.d
89fc: 00 00 04 00 nop.i 0x0;;
8a00: 08 00 00 00 01 00 [MMI] nop.m 0x0
8a06: b0 00 88 14 72 e0 cmp.eq p11,p10=0,r34
8a0c: e1 09 01 52 extr.u r15=r33,15,1
8a10: 09 58 60 40 00 21 [MMI] adds r11=24,r32
8a16: 70 02 88 00 42 00 mov r39=r34
8a1c: 05 00 00 84 mov r40=r0;;
8a20: 42 71 04 00 00 e4 [MII] (p10) mov r14=1
8a26: e2 00 00 00 42 00 (p11) mov r14=r0;;
8a2c: 00 00 04 00 nop.i 0x0
8a30: 0b 80 3c 1c 0c 20 [MMI] and r16=r15,r14;;
8a36: 80 00 40 12 73 00 cmp4.eq p8,p9=0,r16
8a3c: 00 00 04 00 nop.i 0x0;;
8a40: 31 49 01 16 10 10 [MIB] (p09) ld4 r41=[r11]
8a46: 00 00 00 02 80 04 nop.i 0x0
8a4c: 08 00 00 51 (p09) br.call.spnt.many b0=8a40 <kmem_cache_alloc+0x140>;;
8a50: 08 00 00 00 01 00 [MMI] nop.m 0x0
8a56: 80 00 88 00 42 00 mov r8=r34
8a5c: 40 0a 00 07 mov b0=r36
8a60: 11 00 00 00 01 00 [MIB] nop.m 0x0
8a66: 00 28 01 55 00 80 mov.i ar.pfs=r37
8a6c: 08 00 84 00 br.ret.sptk.many b0;;
8a70: 08 00 00 00 01 00 [MMI] nop.m 0x0
8a76: 00 00 00 02 00 00 nop.m 0x0
8a7c: 00 00 04 00 nop.i 0x0

kmem_cache_alloc with cmpxchg emulation:

0000000000008da0 <kmem_cache_alloc>:
8da0: 09 28 31 0e 80 05 [MMI] alloc r37=ar.pfs,12,7,0
8da6: a0 80 36 32 42 80 adds r10=3280,r13
8dac: 04 00 c4 00 mov r36=b0;;
8db0: 02 00 00 00 01 00 [MII] nop.m 0x0
8db6: 00 41 29 00 42 00 adds r16=40,r10;;
8dbc: 00 00 04 00 nop.i 0x0
8dc0: 0a 58 00 20 10 10 [MMI] ld4 r11=[r16];;
8dc6: e0 08 2c 00 42 00 adds r14=1,r11
8dcc: 00 00 04 00 nop.i 0x0
8dd0: 0b 00 00 00 01 00 [MMI] nop.m 0x0;;
8dd6: 00 70 40 20 23 00 st4 [r16]=r14
8ddc: 00 00 04 00 nop.i 0x0;;
8de0: 09 78 50 14 00 21 [MMI] adds r15=20,r10
8de6: 00 00 00 02 00 40 nop.m 0x0
8dec: 02 00 00 92 mov r18=16384;;
8df0: 0b 48 00 1e 10 10 [MMI] ld4 r9=[r15];;
8df6: 00 00 00 02 00 00 nop.m 0x0
8dfc: 01 48 58 00 sxt4 r8=r9;;
8e00: 0b 18 20 40 12 20 [MMI] shladd r3=r8,3,r32;;
8e06: 20 80 0f 82 48 00 addl r2=8432,r3
8e0c: 00 00 04 00 nop.i 0x0;;
8e10: 02 10 01 04 18 10 [MII] ld8 r34=[r2]
8e16: 00 00 00 02 00 20 nop.i 0x0;;
8e1c: 42 11 01 84 adds r17=20,r34
8e20: 09 00 00 00 01 00 [MMI] nop.m 0x0
8e26: f0 00 88 30 20 00 ld8 r15=[r34]
8e2c: 00 00 04 00 nop.i 0x0;;
8e30: 10 00 00 00 01 00 [MIB] nop.m 0x0
8e36: 60 00 3c 0e 72 03 cmp.eq p6,p7=0,r15
8e3c: 20 01 00 41 (p06) br.cond.spnt.few 8f50 <kmem_cache_alloc+0x1b0>
8e40: 0a b8 00 22 10 10 [MMI] ld4 r23=[r17];;
8e46: 60 b9 3c 24 40 00 shladd r22=r23,3,r15
8e4c: 00 00 04 00 nop.i 0x0
8e50: 0b 00 00 00 01 00 [MMI] nop.m 0x0;;
8e56: 40 01 58 30 20 00 ld8 r20=[r22]
8e5c: 00 00 04 00 nop.i 0x0;;
8e60: 0b a8 00 00 25 04 [MMI] mov r21=psr;;
8e66: 00 00 04 0e 00 00 rsm 0x4000
8e6c: 00 00 04 00 nop.i 0x0;;
8e70: 02 18 01 44 18 10 [MII] ld8 r35=[r34]
8e76: 30 91 54 18 40 00 and r19=r18,r21;;
8e7c: 00 00 04 00 nop.i 0x0
8e80: 0b 48 3c 46 08 78 [MMI] cmp.eq p9,p8=r15,r35;;
8e86: 02 a0 88 30 23 00 (p09) st8 [r34]=r20
8e8c: 00 00 04 00 nop.i 0x0;;
8e90: 0a 38 4c 00 06 b8 [MMI] cmp.eq p7,p6=r19,r0;;
8e96: 01 00 04 0c 00 00 (p06) ssm 0x4000
8e9c: 00 00 04 00 nop.i 0x0
8ea0: eb 00 00 02 07 80 [MMI] (p07) rsm 0x4000;;
8ea6: 01 00 00 60 00 00 (p06) srlz.d
8eac: 00 00 04 00 nop.i 0x0;;
8eb0: 11 00 00 00 01 00 [MIB] nop.m 0x0
8eb6: 00 00 00 02 00 04 nop.i 0x0
8ebc: 70 ff ff 49 (p08) br.cond.spnt.few 8e20 <kmem_cache_alloc+0x80>;;
8ec0: 03 00 00 00 01 00 [MII] nop.m 0x0
8ec6: 80 81 36 32 42 20 adds r24=3280,r13;;
8ecc: 83 c2 00 84 adds r25=40,r24;;
8ed0: 0a d8 00 32 10 10 [MMI] ld4 r27=[r25];;
8ed6: a0 f9 6f 7e 46 00 adds r26=-1,r27
8edc: 00 00 04 00 nop.i 0x0
8ee0: 0b 00 00 00 01 00 [MMI] nop.m 0x0;;
8ee6: 00 d0 64 20 23 00 st4 [r25]=r26
8eec: 00 00 04 00 nop.i 0x0;;
8ef0: 0b 90 40 30 00 21 [MMI] adds r18=16,r24;;
8ef6: 10 01 48 60 21 00 ld4.acq r17=[r18]
8efc: 00 00 04 00 nop.i 0x0;;
8f00: 11 00 00 00 01 00 [MIB] nop.m 0x0
8f06: c0 10 44 1a a8 06 tbit.z p12,p13=r17,1
8f0c: 08 00 00 51 (p13) br.call.spnt.many b0=8f00 <kmem_cache_alloc+0x160>;;
8f10: 02 00 00 00 01 00 [MII] nop.m 0x0
8f16: a0 f0 84 16 a8 c5 tbit.z p10,p11=r33,15;;
8f1c: 81 11 01 84 (p11) adds r14=24,r34
8f20: 62 39 01 46 00 e1 [MII] (p11) mov r39=r35
8f26: 82 02 00 00 42 00 (p11) mov r40=r0;;
8f2c: 00 00 04 00 nop.i 0x0
8f30: 79 49 01 1c 10 10 [MMB] (p11) ld4 r41=[r14]
8f36: 00 00 00 02 80 05 nop.m 0x0
8f3c: 08 00 00 51 (p11) br.call.spnt.many b0=8f30 <kmem_cache_alloc+0x190>;;
8f40: 10 00 00 00 01 00 [MIB] nop.m 0x0
8f46: 80 00 8c 00 42 00 mov r8=r35
8f4c: 30 00 00 40 br.few 8f70 <kmem_cache_alloc+0x1d0>
8f50: 08 38 01 40 00 21 [MMI] mov r39=r32
8f56: 80 02 84 00 42 40 mov r40=r33
8f5c: 05 20 01 84 mov r42=r36
8f60: 19 58 01 44 00 21 [MMB] mov r43=r34
8f66: 90 fa f3 ff 4f 00 mov r41=-1
8f6c: 28 d3 ff 58 br.call.sptk.many b0=6280 <__slab_alloc>;;
8f70: 00 00 00 00 01 00 [MII] nop.m 0x0
8f76: 00 20 05 80 03 00 mov b0=r36
8f7c: 00 00 04 00 nop.i 0x0
8f80: 11 00 00 00 01 00 [MIB] nop.m 0x0
8f86: 00 28 01 55 00 80 mov.i ar.pfs=r37
8f8c: 08 00 84 00 br.ret.sptk.many b0;;
8f90: 08 00 00 00 01 00 [MMI] nop.m 0x0
8f96: 00 00 00 02 00 00 nop.m 0x0
8f9c: 00 00 04 00 nop.i 0x0

-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/