Re: eth_type_trans(): Re: [Bug #11308] tbench regression on each kernel release from 2.6.22 -> 2.6.28

[Eric Dumazet <dada1@cosmosbay.com>]

Ingo Molnar a écrit :
> * Ingo Molnar <mingo@elte.hu> wrote:
> 
>> 100.000000 total
>> ................
>>   1.717771 eth_type_trans
> 
>                       hits (total: 171777)
>                  .........
> ffffffff8049e215:      457 <eth_type_trans>:
> ffffffff8049e215:      457 	41 54                	push   %r12
> ffffffff8049e217:     6514 	55                   	push   %rbp
> ffffffff8049e218:        0 	48 89 f5             	mov    %rsi,%rbp
> ffffffff8049e21b:        0 	53                   	push   %rbx
> ffffffff8049e21c:      441 	48 8b 87 d8 00 00 00 	mov    0xd8(%rdi),%rax
> ffffffff8049e223:        5 	48 89 fb             	mov    %rdi,%rbx
> ffffffff8049e226:        0 	2b 87 d0 00 00 00    	sub    0xd0(%rdi),%eax
> ffffffff8049e22c:      493 	48 89 73 20          	mov    %rsi,0x20(%rbx)
> ffffffff8049e230:        2 	be 0e 00 00 00       	mov    $0xe,%esi
> ffffffff8049e235:        0 	89 87 c0 00 00 00    	mov    %eax,0xc0(%rdi)
> ffffffff8049e23b:      472 	e8 2c 98 fe ff       	callq  ffffffff80487a6c <skb_pull>
> ffffffff8049e240:      501 	44 8b a3 c0 00 00 00 	mov    0xc0(%rbx),%r12d
> ffffffff8049e247:      763 	4c 03 a3 d0 00 00 00 	add    0xd0(%rbx),%r12
> ffffffff8049e24e:        0 	41 f6 04 24 01       	testb  $0x1,(%r12)
> ffffffff8049e253:      497 	74 26                	je     ffffffff8049e27b <eth_type_trans+0x66>
> ffffffff8049e255:        0 	48 8d b5 38 02 00 00 	lea    0x238(%rbp),%rsi
> ffffffff8049e25c:        0 	4c 89 e7             	mov    %r12,%rdi
> ffffffff8049e25f:        0 	e8 49 fc ff ff       	callq  ffffffff8049dead <compare_ether_addr>
> ffffffff8049e264:        0 	85 c0                	test   %eax,%eax
> ffffffff8049e266:        0 	8a 43 7d             	mov    0x7d(%rbx),%al
> ffffffff8049e269:        0 	75 08                	jne    ffffffff8049e273 <eth_type_trans+0x5e>
> ffffffff8049e26b:        0 	83 e0 f8             	and    $0xfffffffffffffff8,%eax
> ffffffff8049e26e:        0 	83 c8 01             	or     $0x1,%eax
> ffffffff8049e271:        0 	eb 24                	jmp    ffffffff8049e297 <eth_type_trans+0x82>
> ffffffff8049e273:        0 	83 e0 f8             	and    $0xfffffffffffffff8,%eax
> ffffffff8049e276:        0 	83 c8 02             	or     $0x2,%eax
> ffffffff8049e279:        0 	eb 1c                	jmp    ffffffff8049e297 <eth_type_trans+0x82>
> ffffffff8049e27b:       82 	48 8d b5 18 02 00 00 	lea    0x218(%rbp),%rsi
> ffffffff8049e282:     8782 	4c 89 e7             	mov    %r12,%rdi
> ffffffff8049e285:     1752 	e8 23 fc ff ff       	callq  ffffffff8049dead <compare_ether_addr>
> ffffffff8049e28a:        0 	85 c0                	test   %eax,%eax
> ffffffff8049e28c:      757 	74 0c                	je     ffffffff8049e29a <eth_type_trans+0x85>
> ffffffff8049e28e:        0 	8a 43 7d             	mov    0x7d(%rbx),%al
> ffffffff8049e291:        0 	83 e0 f8             	and    $0xfffffffffffffff8,%eax
> ffffffff8049e294:        0 	83 c8 03             	or     $0x3,%eax
> ffffffff8049e297:        0 	88 43 7d             	mov    %al,0x7d(%rbx)
> ffffffff8049e29a:      107 	66 41 8b 44 24 0c    	mov    0xc(%r12),%ax
> ffffffff8049e2a0:     1031 	0f b7 c8             	movzwl %ax,%ecx
> ffffffff8049e2a3:      518 	66 c1 e8 08          	shr    $0x8,%ax
> ffffffff8049e2a7:        0 	89 ca                	mov    %ecx,%edx
> ffffffff8049e2a9:        0 	c1 e2 08             	shl    $0x8,%edx
> ffffffff8049e2ac:      484 	09 d0                	or     %edx,%eax
> ffffffff8049e2ae:        0 	0f b7 c0             	movzwl %ax,%eax
> ffffffff8049e2b1:        0 	3d ff 05 00 00       	cmp    $0x5ff,%eax
> ffffffff8049e2b6:      468 	7f 18                	jg     ffffffff8049e2d0 <eth_type_trans+0xbb>
> ffffffff8049e2b8:        0 	48 8b 83 d8 00 00 00 	mov    0xd8(%rbx),%rax
> ffffffff8049e2bf:        0 	b9 00 01 00 00       	mov    $0x100,%ecx
> ffffffff8049e2c4:        0 	66 83 38 ff          	cmpw   $0xffffffffffffffff,(%rax)
> ffffffff8049e2c8:        0 	b8 00 04 00 00       	mov    $0x400,%eax
> ffffffff8049e2cd:        0 	0f 45 c8             	cmovne %eax,%ecx
> ffffffff8049e2d0:        0 	5b                   	pop    %rbx
> ffffffff8049e2d1:    85064 	5d                   	pop    %rbp
> ffffffff8049e2d2:    63776 	41 5c                	pop    %r12
> ffffffff8049e2d4:        1 	89 c8                	mov    %ecx,%eax
> ffffffff8049e2d6:      474 	c3                   	retq   
> 
> small function, big bang - 1.7% of the total overhead.
> 
> 90% of this function's cost is in the closing sequence. My guess would 
> be that it originates from ffffffff8049e2ae (the branch after that is 
> not taken), which corresponds to this source code context:
> 
> (gdb) list *0xffffffff8049e2ae
> 0xffffffff8049e2ae is in eth_type_trans (net/ethernet/eth.c:199).
> 194		if (netdev_uses_dsa_tags(dev))
> 195			return htons(ETH_P_DSA);
> 196		if (netdev_uses_trailer_tags(dev))
> 197			return htons(ETH_P_TRAILER);
> 198	
> 199		if (ntohs(eth->h_proto) >= 1536)
> 200			return eth->h_proto;
> 201	
> 202		rawp = skb->data;
> 203	
> 
> eth->h_proto access.
> 
> Given that this workload does localhost networking, my guess would be 
> that eth->h_proto is bouncing around between 16 CPUs? At minimum this 
> read-mostly field should be separated from the bouncing bits.
> 

"eth" is on the frame itself, so each cpu is handling a skb it owns.
If there is a cache line miss, then scheduler might have done a wrong schedule ?
(tbench server and tbench client on different cpus)

But seeing your disassembly, I can see compare_ether_addr() is not inlined.

This sucks.

/**
 * compare_ether_addr - Compare two Ethernet addresses
 * @addr1: Pointer to a six-byte array containing the Ethernet address
 * @addr2: Pointer other six-byte array containing the Ethernet address
 *
 * Compare two ethernet addresses, returns 0 if equal
 */
static inline unsigned compare_ether_addr(const u8 *addr1, const u8 *addr2)
{
        const u16 *a = (const u16 *) addr1;
        const u16 *b = (const u16 *) addr2;

        BUILD_BUG_ON(ETH_ALEN != 6);
        return ((a[0] ^ b[0]) | (a[1] ^ b[1]) | (a[2] ^ b[2])) != 0;
}

On my machine/compiler, it is inlined, that makes a big difference.

c0420750 <eth_type_trans>: /* eth_type_trans total:  14417  0.4101 */