Re: [PATCH 0/6] ipc/sem.c: performance improvements, FIFO

From: Mike Galbraith
Date: Sat Jun 15 2013 - 07:37:39 EST

On Sat, 2013-06-15 at 13:10 +0200, Manfred Spraul wrote:
> On 06/14/2013 09:05 PM, Mike Galbraith wrote:
> > # Events: 802K cycles
> > #
> > # Overhead Symbol
> > # ........ ..........................................
> > #
> > 18.42% [k] SYSC_semtimedop
> > 15.39% [k] sem_lock
> > 10.26% [k] _raw_spin_lock
> > 9.00% [k] perform_atomic_semop
> > 7.89% [k] system_call
> > 7.70% [k] ipc_obtain_object_check
> > 6.95% [k] ipcperms
> > 6.62% [k] copy_user_generic_string
> > 4.16% [.] __semop
> > 2.57% [.] worker_thread(void*)
> > 2.30% [k] copy_from_user
> > 1.75% [k] sem_unlock
> > 1.25% [k] ipc_obtain_object
> ~ 280 mio ops.
> 2.3% copy_from_user,
> 9% perform_atomic_semop.
>
> > # Events: 802K cycles
> > #
> > # Overhead Symbol
> > # ........ ...............................
> > #
> > 17.38% [k] SYSC_semtimedop
> > 13.26% [k] system_call
> > 11.31% [k] copy_user_generic_string
> > 7.62% [.] __semop
> > 7.18% [k] _raw_spin_lock
> > 5.66% [k] ipcperms
> > 5.40% [k] sem_lock
> > 4.65% [k] perform_atomic_semop
> > 4.22% [k] ipc_obtain_object_check
> > 4.08% [.] worker_thread(void*)
> > 4.06% [k] copy_from_user
> > 2.40% [k] ipc_obtain_object
> > 1.98% [k] pid_vnr
> > 1.45% [k] wake_up_sem_queue_do
> > 1.39% [k] sys_semop
> > 1.35% [k] sys_semtimedop
> > 1.30% [k] sem_unlock
> > 1.14% [k] security_ipc_permission
> ~ 700 mio ops.
> 4% copy_from_user -> as expected a bit more
> 4.6% perform_atomic_semop --> less.
>
> Thus: Could you send the oprofile output from perform_atomic_semop()?

Ok, newly profiled 32 core run.


Percent | Source code & Disassembly of vmlinux
------------------------------------------------
:
:
:
: Disassembly of section .text:
:
: ffffffff812584d0 <perform_atomic_semop>:
: * Negative values are error codes.
: */
:
: static int perform_atomic_semop(struct sem_array *sma, struct sembuf *sops,
: int nsops, struct sem_undo *un, int pid)
: {
3.70 : ffffffff812584d0: 55 push %rbp
0.00 : ffffffff812584d1: 48 89 e5 mov %rsp,%rbp
0.00 : ffffffff812584d4: 41 54 push %r12
3.40 : ffffffff812584d6: 53 push %rbx
0.00 : ffffffff812584d7: e8 64 dc 35 00 callq ffffffff815b6140 <mcount>
: int result, sem_op;
: struct sembuf *sop;
: struct sem * curr;
:
: for (sop = sops; sop < sops + nsops; sop++) {
0.00 : ffffffff812584dc: 48 63 d2 movslq %edx,%rdx
: * Negative values are error codes.
: */
:
: static int perform_atomic_semop(struct sem_array *sma, struct sembuf *sops,
: int nsops, struct sem_undo *un, int pid)
: {
0.00 : ffffffff812584df: 45 89 c4 mov %r8d,%r12d
3.62 : ffffffff812584e2: 48 89 cb mov %rcx,%rbx
: int result, sem_op;
: struct sembuf *sop;
: struct sem * curr;
:
: for (sop = sops; sop < sops + nsops; sop++) {
0.00 : ffffffff812584e5: 48 8d 14 52 lea (%rdx,%rdx,2),%rdx
0.00 : ffffffff812584e9: 49 89 f2 mov %rsi,%r10
0.00 : ffffffff812584ec: 4c 8d 04 56 lea (%rsi,%rdx,2),%r8
3.53 : ffffffff812584f0: 4c 39 c6 cmp %r8,%rsi
0.00 : ffffffff812584f3: 0f 83 17 01 00 00 jae ffffffff81258610 <perform_atomic_semop+0x140>
: curr = sma->sem_base + sop->sem_num;
0.00 : ffffffff812584f9: 0f b7 0e movzwl (%rsi),%ecx
: sem_op = sop->sem_op;
0.00 : ffffffff812584fc: 0f bf 56 02 movswl 0x2(%rsi),%edx
: int result, sem_op;
: struct sembuf *sop;
: struct sem * curr;
:
: for (sop = sops; sop < sops + nsops; sop++) {
: curr = sma->sem_base + sop->sem_num;
0.00 : ffffffff81258500: 49 89 c9 mov %rcx,%r9
3.75 : ffffffff81258503: 49 c1 e1 06 shl $0x6,%r9
0.00 : ffffffff81258507: 4c 03 4f 40 add 0x40(%rdi),%r9
: sem_op = sop->sem_op;
: result = curr->semval;
:
: if (!sem_op && result)
4.52 : ffffffff8125850b: 85 d2 test %edx,%edx
: struct sem * curr;
:
: for (sop = sops; sop < sops + nsops; sop++) {
: curr = sma->sem_base + sop->sem_num;
: sem_op = sop->sem_op;
: result = curr->semval;
0.00 : ffffffff8125850d: 41 8b 01 mov (%r9),%eax
:
: if (!sem_op && result)
18.66 : ffffffff81258510: 0f 84 e2 00 00 00 je ffffffff812585f8 <perform_atomic_semop+0x128>
: goto would_block;
:
: result += sem_op;
: if (result < 0)
3.52 : ffffffff81258516: 41 89 d3 mov %edx,%r11d
0.00 : ffffffff81258519: 41 01 c3 add %eax,%r11d
0.00 : ffffffff8125851c: 0f 88 de 00 00 00 js ffffffff81258600 <perform_atomic_semop+0x130>
: goto would_block;
: if (result > SEMVMX)
0.00 : ffffffff81258522: 41 81 fb ff 7f 00 00 cmp $0x7fff,%r11d
3.84 : ffffffff81258529: 49 89 f2 mov %rsi,%r10
0.00 : ffffffff8125852c: 0f 8f bb 00 00 00 jg ffffffff812585ed <perform_atomic_semop+0x11d>
0.00 : ffffffff81258532: 66 0f 1f 44 00 00 nopw 0x0(%rax,%rax,1)
: goto out_of_range;
: if (sop->sem_flg & SEM_UNDO) {
0.00 : ffffffff81258538: 41 f6 42 05 10 testb $0x10,0x5(%r10)
3.66 : ffffffff8125853d: 74 1a je ffffffff81258559 <perform_atomic_semop+0x89>
: int undo = un->semadj[sop->sem_num] - sem_op;
: /*
: * Exceeding the undo range is an error.
: */
: if (undo < (-SEMAEM - 1) || undo > SEMAEM)
0.00 : ffffffff8125853f: 48 8b 43 40 mov 0x40(%rbx),%rax
0.00 : ffffffff81258543: 0f bf 04 48 movswl (%rax,%rcx,2),%eax
0.00 : ffffffff81258547: 29 d0 sub %edx,%eax
0.00 : ffffffff81258549: 05 00 80 00 00 add $0x8000,%eax
0.00 : ffffffff8125854e: 3d ff ff 00 00 cmp $0xffff,%eax
0.00 : ffffffff81258553: 0f 87 94 00 00 00 ja ffffffff812585ed <perform_atomic_semop+0x11d>
: {
: int result, sem_op;
: struct sembuf *sop;
: struct sem * curr;
:
: for (sop = sops; sop < sops + nsops; sop++) {
3.70 : ffffffff81258559: 49 83 c2 06 add $0x6,%r10
: * Exceeding the undo range is an error.
: */
: if (undo < (-SEMAEM - 1) || undo > SEMAEM)
: goto out_of_range;
: }
: curr->semval = result;
0.01 : ffffffff8125855d: 45 89 19 mov %r11d,(%r9)
: {
: int result, sem_op;
: struct sembuf *sop;
: struct sem * curr;
:
: for (sop = sops; sop < sops + nsops; sop++) {
0.01 : ffffffff81258560: 4d 39 c2 cmp %r8,%r10
0.00 : ffffffff81258563: 0f 83 a7 00 00 00 jae ffffffff81258610 <perform_atomic_semop+0x140>
: curr = sma->sem_base + sop->sem_num;
0.00 : ffffffff81258569: 41 0f b7 0a movzwl (%r10),%ecx
: sem_op = sop->sem_op;
0.00 : ffffffff8125856d: 41 0f bf 52 02 movswl 0x2(%r10),%edx
: int result, sem_op;
: struct sembuf *sop;
: struct sem * curr;
:
: for (sop = sops; sop < sops + nsops; sop++) {
: curr = sma->sem_base + sop->sem_num;
0.00 : ffffffff81258572: 49 89 c9 mov %rcx,%r9
0.00 : ffffffff81258575: 49 c1 e1 06 shl $0x6,%r9
0.00 : ffffffff81258579: 4c 03 4f 40 add 0x40(%rdi),%r9
: sem_op = sop->sem_op;
: result = curr->semval;
:
: if (!sem_op && result)
0.00 : ffffffff8125857d: 85 d2 test %edx,%edx
: struct sem * curr;
:
: for (sop = sops; sop < sops + nsops; sop++) {
: curr = sma->sem_base + sop->sem_num;
: sem_op = sop->sem_op;
: result = curr->semval;
0.00 : ffffffff8125857f: 41 8b 01 mov (%r9),%eax
:
: if (!sem_op && result)
0.00 : ffffffff81258582: 75 54 jne ffffffff812585d8 <perform_atomic_semop+0x108>
0.00 : ffffffff81258584: 85 c0 test %eax,%eax
0.00 : ffffffff81258586: 74 50 je ffffffff812585d8 <perform_atomic_semop+0x108>
:
: out_of_range:
: result = -ERANGE;
: goto undo;
:
: would_block:
0.00 : ffffffff81258588: 4c 89 d0 mov %r10,%rax
: if (sop->sem_flg & IPC_NOWAIT)
0.00 : ffffffff8125858b: 0f bf 40 04 movswl 0x4(%rax),%eax
0.00 : ffffffff8125858f: 25 00 08 00 00 and $0x800,%eax
0.00 : ffffffff81258594: 83 f8 01 cmp $0x1,%eax
0.00 : ffffffff81258597: 45 19 c0 sbb %r8d,%r8d
0.00 : ffffffff8125859a: 41 83 e0 0c and $0xc,%r8d
0.00 : ffffffff8125859e: 41 83 e8 0b sub $0xb,%r8d
: result = -EAGAIN;
: else
: result = 1;
:
: undo:
: sop--;
0.00 : ffffffff812585a2: 49 8d 4a fa lea -0x6(%r10),%rcx
: while (sop >= sops) {
0.00 : ffffffff812585a6: 48 39 ce cmp %rcx,%rsi
0.00 : ffffffff812585a9: 77 1f ja ffffffff812585ca <perform_atomic_semop+0xfa>
0.00 : ffffffff812585ab: 0f 1f 44 00 00 nopl 0x0(%rax,%rax,1)
: sma->sem_base[sop->sem_num].semval -= sop->sem_op;
0.00 : ffffffff812585b0: 0f b7 01 movzwl (%rcx),%eax
0.00 : ffffffff812585b3: 0f bf 51 02 movswl 0x2(%rcx),%edx
: sop--;
0.00 : ffffffff812585b7: 48 83 e9 06 sub $0x6,%rcx
: result = 1;
:
: undo:
: sop--;
: while (sop >= sops) {
: sma->sem_base[sop->sem_num].semval -= sop->sem_op;
0.00 : ffffffff812585bb: 48 c1 e0 06 shl $0x6,%rax
0.00 : ffffffff812585bf: 48 03 47 40 add 0x40(%rdi),%rax
0.00 : ffffffff812585c3: 29 10 sub %edx,(%rax)
: else
: result = 1;
:
: undo:
: sop--;
: while (sop >= sops) {
0.00 : ffffffff812585c5: 48 39 ce cmp %rcx,%rsi
0.00 : ffffffff812585c8: 76 e6 jbe ffffffff812585b0 <perform_atomic_semop+0xe0>
: sma->sem_base[sop->sem_num].semval -= sop->sem_op;
: sop--;
: }
:
: return result;
: }
0.00 : ffffffff812585ca: 5b pop %rbx
0.00 : ffffffff812585cb: 44 89 c0 mov %r8d,%eax
0.00 : ffffffff812585ce: 41 5c pop %r12
0.00 : ffffffff812585d0: c9 leaveq
0.00 : ffffffff812585d1: c3 retq
0.00 : ffffffff812585d2: 66 0f 1f 44 00 00 nopw 0x0(%rax,%rax,1)
:
: if (!sem_op && result)
: goto would_block;
:
: result += sem_op;
: if (result < 0)
0.00 : ffffffff812585d8: 41 89 d3 mov %edx,%r11d
0.00 : ffffffff812585db: 41 01 c3 add %eax,%r11d
0.00 : ffffffff812585de: 78 a8 js ffffffff81258588 <perform_atomic_semop+0xb8>
: goto would_block;
: if (result > SEMVMX)
0.00 : ffffffff812585e0: 41 81 fb ff 7f 00 00 cmp $0x7fff,%r11d
0.00 : ffffffff812585e7: 0f 8e 4b ff ff ff jle ffffffff81258538 <perform_atomic_semop+0x68>
: if (sop->sem_flg & IPC_NOWAIT)
: result = -EAGAIN;
: else
: result = 1;
:
: undo:
0.00 : ffffffff812585ed: 41 b8 de ff ff ff mov $0xffffffde,%r8d
0.00 : ffffffff812585f3: eb ad jmp ffffffff812585a2 <perform_atomic_semop+0xd2>
0.00 : ffffffff812585f5: 0f 1f 00 nopl (%rax)
: for (sop = sops; sop < sops + nsops; sop++) {
: curr = sma->sem_base + sop->sem_num;
: sem_op = sop->sem_op;
: result = curr->semval;
:
: if (!sem_op && result)
3.56 : ffffffff812585f8: 85 c0 test %eax,%eax
0.00 : ffffffff812585fa: 0f 84 16 ff ff ff je ffffffff81258516 <perform_atomic_semop+0x46>
:
: out_of_range:
: result = -ERANGE;
: goto undo;
:
: would_block:
0.00 : ffffffff81258600: 48 89 f0 mov %rsi,%rax
0.00 : ffffffff81258603: 49 89 f2 mov %rsi,%r10
0.00 : ffffffff81258606: e9 80 ff ff ff jmpq ffffffff8125858b <perform_atomic_semop+0xbb>
0.00 : ffffffff8125860b: 0f 1f 44 00 00 nopl 0x0(%rax,%rax,1)
: goto out_of_range;
: }
: curr->semval = result;
: }
:
: sop--;
3.58 : ffffffff81258610: 4d 8d 4a fa lea -0x6(%r10),%r9
: while (sop >= sops) {
0.00 : ffffffff81258614: 4c 39 ce cmp %r9,%rsi
0.00 : ffffffff81258617: 77 3b ja ffffffff81258654 <perform_atomic_semop+0x184>
0.00 : ffffffff81258619: 0f 1f 80 00 00 00 00 nopl 0x0(%rax)
: sma->sem_base[sop->sem_num].sempid = pid;
0.00 : ffffffff81258620: 41 0f b7 01 movzwl (%r9),%eax
3.51 : ffffffff81258624: 48 8b 57 40 mov 0x40(%rdi),%rdx
22.37 : ffffffff81258628: 48 c1 e0 06 shl $0x6,%rax
0.00 : ffffffff8125862c: 44 89 64 02 04 mov %r12d,0x4(%rdx,%rax,1)
: if (sop->sem_flg & SEM_UNDO)
3.79 : ffffffff81258631: 41 f6 41 05 10 testb $0x10,0x5(%r9)
0.00 : ffffffff81258636: 74 13 je ffffffff8125864b <perform_atomic_semop+0x17b>
: un->semadj[sop->sem_num] -= sop->sem_op;
0.00 : ffffffff81258638: 41 0f b7 01 movzwl (%r9),%eax
0.00 : ffffffff8125863c: 41 0f b7 51 02 movzwl 0x2(%r9),%edx
0.00 : ffffffff81258641: 48 01 c0 add %rax,%rax
0.00 : ffffffff81258644: 48 03 43 40 add 0x40(%rbx),%rax
0.00 : ffffffff81258648: 66 29 10 sub %dx,(%rax)
: sop--;
3.58 : ffffffff8125864b: 49 83 e9 06 sub $0x6,%r9
: }
: curr->semval = result;
: }
:
: sop--;
: while (sop >= sops) {
0.00 : ffffffff8125864f: 4c 39 ce cmp %r9,%rsi
0.00 : ffffffff81258652: 76 cc jbe ffffffff81258620 <perform_atomic_semop+0x150>
: sma->sem_base[sop->sem_num].semval -= sop->sem_op;
: sop--;
: }
:
: return result;
: }
0.00 : ffffffff81258654: 5b pop %rbx
: else
: result = 1;
:
: undo:
: sop--;
: while (sop >= sops) {
0.00 : ffffffff81258655: 45 31 c0 xor %r8d,%r8d
: sma->sem_base[sop->sem_num].semval -= sop->sem_op;
: sop--;
: }
:
: return result;
: }
3.67 : ffffffff81258658: 44 89 c0 mov %r8d,%eax
0.00 : ffffffff8125865b: 41 5c pop %r12
0.00 : ffffffff8125865d: c9 leaveq


--
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/