dev.dpdk.org archive mirror
 help / color / mirror / Atom feed
From: Ray Kinsella <mdr@ashroe.eu>
To: Pavan Nikhilesh Bhagavatula <pbhagavatula@marvell.com>,
	Jerin Jacob Kollanukkaran <jerinj@marvell.com>,
	Nithin Kumar Dabilpuram <ndabilpuram@marvell.com>
Cc: "dev@dpdk.org" <dev@dpdk.org>,
	"thomas@monjalon.net" <thomas@monjalon.net>,
	"david.marchand@redhat.com" <david.marchand@redhat.com>,
	"mattias.ronnblom@ericsson.com" <mattias.ronnblom@ericsson.com>,
	Kiran Kumar Kokkilagadda <kirankumark@marvell.com>
Subject: Re: [dpdk-dev] [EXT] Re: [PATCH v1 20/26] node: ipv4 lookup for x86
Date: Tue, 24 Mar 2020 14:38:27 +0000	[thread overview]
Message-ID: <7a6842d9-43fd-1746-113f-887d6afb16e5@ashroe.eu> (raw)
In-Reply-To: <CY4PR1801MB18638826B6A256A7CB9C1A23DEF10@CY4PR1801MB1863.namprd18.prod.outlook.com>



On 24/03/2020 09:40, Pavan Nikhilesh Bhagavatula wrote:
> Hi Ray, 
> 
> I have tried to avoid hand unrolling loops and found the following observations.
> 
> 1. Although it decreases LOC it also takes away readability too.
> 	Example: 
> 	Avoiding unrolled code below
[SNIP] 
> 	Which is kind of unreadable.

I am confused - isn't it exactly the same code?
You still haven't completely unrolled the loop either?

I don't know how one is readable and the other is not. 

> 
> 2. Not all compilers are made equal. I found that most of the compilers don’t 
>      Unroll the loop above even when compiled with `-funroll-all-loops`.
>      I have checked with following compilers:
> 	GCC 9.2.0
> 	Clang 9.0.1
> 	Aarch64 GCC 7.3.0
> 	Aarch64 GCC 9.2.0

Compilers have been unrolling fixed length loops for as long time - this isn't new technology.

If the compiler isn't unrolling you are doing something that makes it think it is a bad idea.
Hand unrolling the loop isn't the solution, understanding what the compiler is doing is a better idea.

In front of your for loop insert, to indicate to the compiler what you want to do. 
#pragma unroll BUF_PER_LOOP 

With clang you can ask it why it is not unrolling the loop with the following switches. 
(output is verbose, but the reason is in there). 

-Rpass=loop-unroll -Rpass-missed=loop-unroll
 			
> 
> 3. Performance wise I see a lot of degradation on our platform at least 13%.

Is the loop being unrolled?

>     On IA with a Broadwell(Xeon E5-2690) and i40e the performance remain same w.r.t Rx/Tx since the 
>     hotspot is in the Tx path of the driver which limits the per core capability.
>     But the performance difference in number of cycles per node can be seen below:
> 
> 	Hand unrolling:
> +-------------------------------+---------------+---------------+---------------+---------------+---------------+-----------+
> |Node                           |calls          |objs           |realloc_count  |objs/call      |objs/sec(10E6) |cycles/call|
> +-------------------------------+---------------+---------------+---------------+---------------+---------------+-----------+
> |ip4_lookup                     |7765918        |248509344      |1              |32.000         |27.725408      |779.0000   |
> |ip4_rewrite                    |7765925        |248509568      |1              |32.000         |27.725408      |425.0000   |
> |ethdev_tx-1                    |7765927        |204056223      |1              |26.000         |22.762720      |597.0000   |
> |pkt_drop                       |1389170        |44453409       |1              |32.000         |4.962688       |298.0000   |
> |ethdev_rx-0-0                  |63604111       |248509792      |2              |32.000         |27.725408      |982.0000   |
> +-------------------------------+---------------+---------------+---------------+---------------+---------------+-----------+
> 	
> 	W/o unrolling:
> 
> +-------------------------------+---------------+---------------+---------------+---------------+---------------+-----------+
> |Node                           |calls          |objs           |realloc_count  |objs/call      |objs/sec(10E6) |cycles/call|
> +-------------------------------+---------------+---------------+---------------+---------------+---------------+-----------+
> |ip4_lookup                     |18864640       |603668448      |1              |32.000         |26.051328      |828.0000   |
> |ip4_rewrite                    |18864646       |603668640      |1              |32.000         |26.051328      |534.0000   |
> |ethdev_tx-1                    |18864648       |527874175      |1              |27.000         |22.780256      |633.0000   |
> |pkt_drop                       |2368580        |75794529       |1              |32.000         |3.271072       |286.0000   |
> |ethdev_rx-0-0                  |282058226      |603668864      |2              |32.000         |26.051328      |994.0000   |
> +-------------------------------+---------------+---------------+---------------+---------------+---------------+-----------+
> 
> Considering the above findings we would like to continue unrolling the loops by hand.
> 
> Regards,
> Pavan.
> 
>> -----Original Message-----
>> From: Ray Kinsella <mdr@ashroe.eu>
>> Sent: Friday, March 20, 2020 2:44 PM
>> To: Pavan Nikhilesh Bhagavatula <pbhagavatula@marvell.com>; Jerin
>> Jacob Kollanukkaran <jerinj@marvell.com>; Nithin Kumar Dabilpuram
>> <ndabilpuram@marvell.com>
>> Cc: dev@dpdk.org; thomas@monjalon.net;
>> david.marchand@redhat.com; mattias.ronnblom@ericsson.com; Kiran
>> Kumar Kokkilagadda <kirankumark@marvell.com>
>> Subject: Re: [EXT] Re: [dpdk-dev] [PATCH v1 20/26] node: ipv4 lookup
>> for x86
>>
>>
>>
>> On 19/03/2020 16:13, Pavan Nikhilesh Bhagavatula wrote:
>>>
>>>
>>>> -----Original Message-----
>>>> From: Ray Kinsella <mdr@ashroe.eu>
>>>> Sent: Thursday, March 19, 2020 9:21 PM
>>>> To: Pavan Nikhilesh Bhagavatula <pbhagavatula@marvell.com>;
>> Jerin
>>>> Jacob Kollanukkaran <jerinj@marvell.com>; Nithin Kumar
>> Dabilpuram
>>>> <ndabilpuram@marvell.com>
>>>> Cc: dev@dpdk.org; thomas@monjalon.net;
>>>> david.marchand@redhat.com; mattias.ronnblom@ericsson.com;
>> Kiran
>>>> Kumar Kokkilagadda <kirankumark@marvell.com>
>>>> Subject: Re: [EXT] Re: [dpdk-dev] [PATCH v1 20/26] node: ipv4
>> lookup
>>>> for x86
>>>>
>>>>
>>>>
>>>> On 19/03/2020 14:22, Pavan Nikhilesh Bhagavatula wrote:
>>>>>> On 18/03/2020 21:35, jerinj@marvell.com wrote:
>>>>>>> From: Pavan Nikhilesh <pbhagavatula@marvell.com>
>>>>>>>
>>>>>>> Add IPv4 lookup process function for ip4_lookup
>>>>>>> rte_node. This node performs LPM lookup using x86_64
>>>>>>> vector supported RTE_LPM API on every packet received
>>>>>>> and forwards it to a next node that is identified by
>>>>>>> lookup result.
>>>>>>>
>>>>>>> Signed-off-by: Pavan Nikhilesh <pbhagavatula@marvell.com>
>>>>>>> Signed-off-by: Nithin Dabilpuram <ndabilpuram@marvell.com>
>>>>>>> Signed-off-by: Kiran Kumar K <kirankumark@marvell.com>
>>>>>>> ---
>>>>>>>  lib/librte_node/ip4_lookup.c | 245
>>>>>> +++++++++++++++++++++++++++++++++++
>>>>>>>  1 file changed, 245 insertions(+)
>>>>>>>
>>>>>>> diff --git a/lib/librte_node/ip4_lookup.c
>>>>>> b/lib/librte_node/ip4_lookup.c
>>>>>>> index d7fcd1158..c003e9c91 100644
>>>>>>> --- a/lib/librte_node/ip4_lookup.c
>>>>>>> +++ b/lib/librte_node/ip4_lookup.c
>>>>>>> @@ -264,6 +264,251 @@ ip4_lookup_node_process(struct
>>>> rte_graph
>>>>>> *graph, struct rte_node *node,
>>>>>>>  	return nb_objs;
>>>>>>>  }
>>>>>>>
>>>>>>> +#elif defined(RTE_ARCH_X86)
>>>>>>> +
>>>>>>> +/* X86 SSE */
>>>>>>> +static uint16_t
>>>>>>> +ip4_lookup_node_process(struct rte_graph *graph, struct
>>>> rte_node
>>>>>> *node,
>>>>>>> +			void **objs, uint16_t nb_objs)
>>>>>>> +{
>>>>>>> +	struct rte_mbuf *mbuf0, *mbuf1, *mbuf2, *mbuf3,
>> **pkts;
>>>>>>> +	rte_edge_t next0, next1, next2, next3, next_index;
>>>>>>> +	struct rte_ipv4_hdr *ipv4_hdr;
>>>>>>> +	struct rte_ether_hdr *eth_hdr;
>>>>>>> +	uint32_t ip0, ip1, ip2, ip3;
>>>>>>> +	void **to_next, **from;
>>>>>>> +	uint16_t last_spec = 0;
>>>>>>> +	uint16_t n_left_from;
>>>>>>> +	struct rte_lpm *lpm;
>>>>>>> +	uint16_t held = 0;
>>>>>>> +	uint32_t drop_nh;
>>>>>>> +	rte_xmm_t dst;
>>>>>>> +	__m128i dip; /* SSE register */
>>>>>>> +	int rc, i;
>>>>>>> +
>>>>>>> +	/* Speculative next */
>>>>>>> +	next_index =
>> RTE_NODE_IP4_LOOKUP_NEXT_REWRITE;
>>>>>>> +	/* Drop node */
>>>>>>> +	drop_nh =
>>>>>> ((uint32_t)RTE_NODE_IP4_LOOKUP_NEXT_PKT_DROP) << 16;
>>>>>>> +
>>>>>>> +	/* Get socket specific LPM from ctx */
>>>>>>> +	lpm = *((struct rte_lpm **)node->ctx);
>>>>>>> +
>>>>>>> +	pkts = (struct rte_mbuf **)objs;
>>>>>>> +	from = objs;
>>>>>>> +	n_left_from = nb_objs;
>>>>>>
>>>>>> I doubt this initial prefetch of the first 4 packets has any benefit.
>>>>>
>>>>> Ack will remove in v2 for x86.
>>>>>
>>>>>>
>>>>>>> +	if (n_left_from >= 4) {
>>>>>>> +		for (i = 0; i < 4; i++) {
>>>>>>> +
>> 	rte_prefetch0(rte_pktmbuf_mtod(pkts[i],
>>>>>>> +						       struct
>> rte_ether_hdr
>>>>>> *) +
>>>>>>> +				      1);
>>>>>>> +		}
>>>>>>> +	}
>>>>>>> +
>>>>>>> +	/* Get stream for the speculated next node */
>>>>>>> +	to_next = rte_node_next_stream_get(graph, node,
>>>>>> next_index, nb_objs);
>>>>>>
>>>>>> Suggest you don't reuse the hand-unrolling optimization from
>> FD.io
>>>>>> VPP.
>>>>>> I have never found any performance benefit from them, and they
>>>>>> make the code unnecessarily verbose.
>>>>>>
>>>>>
>>>>> How would be take the benefit of rte_lpm_lookupx4 without
>>>> unrolling the loop?.
>>>>> Also, in future if we are using rte_rib and fib with a CPU supporting
>>>> wider SIMD we might
>>>>> need to unroll them further (AVX256 AND 512 currently
>>>> rte_lpm_lookup uses only 128bit
>>>>> since it is only uses SSE extension).
>>>>
>>>> Let the compiler do it for you, but using a constant vector length.
>>>> for (int i=0; i < 4; ++i) { ... }
>>>>
>>>
>>> Ok, I think I misunderstood the previous comment.
>>> It was only for the prefetches in the loop right?
>>
>>
>> no, it was for all the needless repetition.
>> hand-unrolling loops serve no purpose but to add verbosity.
>>
>>>
>>>>>
>>>>>>
>>>>>>> +	while (n_left_from >= 4) {
>>>>>>> +		/* Prefetch next-next mbufs */
>>>>>>> +		if (likely(n_left_from >= 11)) {
>>>>>>> +			rte_prefetch0(pkts[8]);
>>>>>>> +			rte_prefetch0(pkts[9]);
>>>>>>> +			rte_prefetch0(pkts[10]);
>>>>>>> +			rte_prefetch0(pkts[11]);
>>>>>>> +		}
>>>>>>> +
>>>>>>> +		/* Prefetch next mbuf data */
>>>>>>> +		if (likely(n_left_from >= 7)) {
>>>>>>> +
>> 	rte_prefetch0(rte_pktmbuf_mtod(pkts[4],
>>>>>>> +						       struct
>> rte_ether_hdr
>>>>>> *) +
>>>>>>> +				      1);
>>>>>>> +
>> 	rte_prefetch0(rte_pktmbuf_mtod(pkts[5],
>>>>>>> +						       struct
>> rte_ether_hdr
>>>>>> *) +
>>>>>>> +				      1);
>>>>>>> +
>> 	rte_prefetch0(rte_pktmbuf_mtod(pkts[6],
>>>>>>> +						       struct
>> rte_ether_hdr
>>>>>> *) +
>>>>>>> +				      1);
>>>>>>> +
>> 	rte_prefetch0(rte_pktmbuf_mtod(pkts[7],
>>>>>>> +						       struct
>> rte_ether_hdr
>>>>>> *) +
>>>>>>> +				      1);
>>>>>>> +		}
>>>>>>> +
>>>>>>> +		mbuf0 = pkts[0];
>>>>>>> +		mbuf1 = pkts[1];
>>>>>>> +		mbuf2 = pkts[2];
>>>>>>> +		mbuf3 = pkts[3];
>>>>>>> +
>>>>>>> +		pkts += 4;
>>>>>>> +		n_left_from -= 4;
>>>>>>> +
>>>>>>> +		/* Extract DIP of mbuf0 */
>>>>>>> +		eth_hdr = rte_pktmbuf_mtod(mbuf0, struct
>>>>>> rte_ether_hdr *);
>>>>>>> +		ipv4_hdr = (struct rte_ipv4_hdr *)(eth_hdr + 1);
>>>>>>> +		ip0 = ipv4_hdr->dst_addr;
>>>>>>> +		/* Extract cksum, ttl as ipv4 hdr is in cache */
>>>>>>> +		rte_node_mbuf_priv1(mbuf0)->cksum =
>> ipv4_hdr-
>>>>>>> hdr_checksum;
>>>>>>> +		rte_node_mbuf_priv1(mbuf0)->ttl = ipv4_hdr-
>>>>>>> time_to_live;
>>>>>>> +
>>>>>>> +		/* Extract DIP of mbuf1 */
>>>>>>> +		eth_hdr = rte_pktmbuf_mtod(mbuf1, struct
>>>>>> rte_ether_hdr *);
>>>>>>> +		ipv4_hdr = (struct rte_ipv4_hdr *)(eth_hdr + 1);
>>>>>>> +		ip1 = ipv4_hdr->dst_addr;
>>>>>>> +		/* Extract cksum, ttl as ipv4 hdr is in cache */
>>>>>>> +		rte_node_mbuf_priv1(mbuf1)->cksum =
>> ipv4_hdr-
>>>>>>> hdr_checksum;
>>>>>>> +		rte_node_mbuf_priv1(mbuf1)->ttl = ipv4_hdr-
>>>>>>> time_to_live;
>>>>>>> +
>>>>>>> +		/* Extract DIP of mbuf2 */
>>>>>>> +		eth_hdr = rte_pktmbuf_mtod(mbuf2, struct
>>>>>> rte_ether_hdr *);
>>>>>>> +		ipv4_hdr = (struct rte_ipv4_hdr *)(eth_hdr + 1);
>>>>>>> +		ip2 = ipv4_hdr->dst_addr;
>>>>>>> +		/* Extract cksum, ttl as ipv4 hdr is in cache */
>>>>>>> +		rte_node_mbuf_priv1(mbuf2)->cksum =
>> ipv4_hdr-
>>>>>>> hdr_checksum;
>>>>>>> +		rte_node_mbuf_priv1(mbuf2)->ttl = ipv4_hdr-
>>>>>>> time_to_live;
>>>>>>> +
>>>>>>> +		/* Extract DIP of mbuf3 */
>>>>>>> +		eth_hdr = rte_pktmbuf_mtod(mbuf3, struct
>>>>>> rte_ether_hdr *);
>>>>>>> +		ipv4_hdr = (struct rte_ipv4_hdr *)(eth_hdr + 1);
>>>>>>> +		ip3 = ipv4_hdr->dst_addr;
>>>>>>> +
>>>>>>> +		/* Prepare for lookup x4 */
>>>>>>> +		dip = _mm_set_epi32(ip3, ip2, ip1, ip0);
>>>>>>> +
>>>>>>> +		/* Byte swap 4 IPV4 addresses. */
>>>>>>> +		const __m128i bswap_mask = _mm_set_epi8(
>>>>>>> +			12, 13, 14, 15, 8, 9, 10, 11, 4, 5, 6, 7, 0, 1,
>> 2, 3);
>>>>>>> +		dip = _mm_shuffle_epi8(dip, bswap_mask);
>>>>>>> +
>>>>>>> +		/* Extract cksum, ttl as ipv4 hdr is in cache */
>>>>>>> +		rte_node_mbuf_priv1(mbuf3)->cksum =
>> ipv4_hdr-
>>>>>>> hdr_checksum;
>>>>>>> +		rte_node_mbuf_priv1(mbuf3)->ttl = ipv4_hdr-
>>>>>>> time_to_live;
>>>>>>> +
>>>>>>> +		/* Perform LPM lookup to get NH and next
>> node */
>>>>>>> +		rte_lpm_lookupx4(lpm, dip, dst.u32, drop_nh);
>>>>>>> +
>>>>>>> +		/* Extract next node id and NH */
>>>>>>> +		rte_node_mbuf_priv1(mbuf0)->nh = dst.u32[0]
>> &
>>>>>> 0xFFFF;
>>>>>>> +		next0 = (dst.u32[0] >> 16);
>>>>>>> +
>>>>>>> +		rte_node_mbuf_priv1(mbuf1)->nh = dst.u32[1]
>> &
>>>>>> 0xFFFF;
>>>>>>> +		next1 = (dst.u32[1] >> 16);
>>>>>>> +
>>>>>>> +		rte_node_mbuf_priv1(mbuf2)->nh = dst.u32[2]
>> &
>>>>>> 0xFFFF;
>>>>>>> +		next2 = (dst.u32[2] >> 16);
>>>>>>> +
>>>>>>> +		rte_node_mbuf_priv1(mbuf3)->nh = dst.u32[3]
>> &
>>>>>> 0xFFFF;
>>>>>>> +		next3 = (dst.u32[3] >> 16);
>>>>>>> +
>>>>>>> +		/* Enqueue four to next node */
>>>>>>> +		rte_edge_t fix_spec =
>>>>>>> +			(next_index ^ next0) | (next_index ^
>> next1) |
>>>>>>> +			(next_index ^ next2) | (next_index ^
>> next3);
>>>>>>> +
>>>>>>> +		if (unlikely(fix_spec)) {
>>>>>>> +			/* Copy things successfully speculated
>> till now
>>>>>> */
>>>>>>> +			rte_memcpy(to_next, from, last_spec *
>>>>>> sizeof(from[0]));
>>>>>>> +			from += last_spec;
>>>>>>> +			to_next += last_spec;
>>>>>>> +			held += last_spec;
>>>>>>> +			last_spec = 0;
>>>>>>> +
>>>>>>> +			/* Next0 */
>>>>>>> +			if (next_index == next0) {
>>>>>>> +				to_next[0] = from[0];
>>>>>>> +				to_next++;
>>>>>>> +				held++;
>>>>>>> +			} else {
>>>>>>> +				rte_node_enqueue_x1(graph,
>> node,
>>>>>> next0,
>>>>>>> +						    from[0]);
>>>>>>> +			}
>>>>>>> +
>>>>>>> +			/* Next1 */
>>>>>>> +			if (next_index == next1) {
>>>>>>> +				to_next[0] = from[1];
>>>>>>> +				to_next++;
>>>>>>> +				held++;
>>>>>>> +			} else {
>>>>>>> +				rte_node_enqueue_x1(graph,
>> node,
>>>>>> next1,
>>>>>>> +						    from[1]);
>>>>>>> +			}
>>>>>>> +
>>>>>>> +			/* Next2 */
>>>>>>> +			if (next_index == next2) {
>>>>>>> +				to_next[0] = from[2];
>>>>>>> +				to_next++;
>>>>>>> +				held++;
>>>>>>> +			} else {
>>>>>>> +				rte_node_enqueue_x1(graph,
>> node,
>>>>>> next2,
>>>>>>> +						    from[2]);
>>>>>>> +			}
>>>>>>> +
>>>>>>> +			/* Next3 */
>>>>>>> +			if (next_index == next3) {
>>>>>>> +				to_next[0] = from[3];
>>>>>>> +				to_next++;
>>>>>>> +				held++;
>>>>>>> +			} else {
>>>>>>> +				rte_node_enqueue_x1(graph,
>> node,
>>>>>> next3,
>>>>>>> +						    from[3]);
>>>>>>> +			}
>>>>>>> +
>>>>>>> +			from += 4;
>>>>>>> +
>>>>>>> +		} else {
>>>>>>> +			last_spec += 4;
>>>>>>> +		}
>>>>>>> +	}
>>>>>>> +
>>>>>>> +	while (n_left_from > 0) {
>>>>>>> +		uint32_t next_hop;
>>>>>>> +
>>>>>>> +		mbuf0 = pkts[0];
>>>>>>> +
>>>>>>> +		pkts += 1;
>>>>>>> +		n_left_from -= 1;
>>>>>>> +
>>>>>>> +		/* Extract DIP of mbuf0 */
>>>>>>> +		eth_hdr = rte_pktmbuf_mtod(mbuf0, struct
>>>>>> rte_ether_hdr *);
>>>>>>> +		ipv4_hdr = (struct rte_ipv4_hdr *)(eth_hdr + 1);
>>>>>>> +		/* Extract cksum, ttl as ipv4 hdr is in cache */
>>>>>>> +		rte_node_mbuf_priv1(mbuf0)->cksum =
>> ipv4_hdr-
>>>>>>> hdr_checksum;
>>>>>>> +		rte_node_mbuf_priv1(mbuf0)->ttl = ipv4_hdr-
>>>>>>> time_to_live;
>>>>>>> +
>>>>>>> +		rc = rte_lpm_lookup(lpm,
>> rte_be_to_cpu_32(ipv4_hdr-
>>>>>>> dst_addr),
>>>>>>> +				    &next_hop);
>>>>>>> +		next_hop = (rc == 0) ? next_hop : drop_nh;
>>>>>>> +
>>>>>>> +		rte_node_mbuf_priv1(mbuf0)->nh = next_hop
>> &
>>>>>> 0xFFFF;
>>>>>>> +		next0 = (next_hop >> 16);
>>>>>>> +
>>>>>>> +		if (unlikely(next_index ^ next0)) {
>>>>>>> +			/* Copy things successfully speculated
>> till now
>>>>>> */
>>>>>>> +			rte_memcpy(to_next, from, last_spec *
>>>>>> sizeof(from[0]));
>>>>>>> +			from += last_spec;
>>>>>>> +			to_next += last_spec;
>>>>>>> +			held += last_spec;
>>>>>>> +			last_spec = 0;
>>>>>>> +
>>>>>>> +			rte_node_enqueue_x1(graph, node,
>> next0,
>>>>>> from[0]);
>>>>>>> +			from += 1;
>>>>>>> +		} else {
>>>>>>> +			last_spec += 1;
>>>>>>> +		}
>>>>>>> +	}
>>>>>>> +
>>>>>>> +	/* !!! Home run !!! */
>>>>>>> +	if (likely(last_spec == nb_objs)) {
>>>>>>> +		rte_node_next_stream_move(graph, node,
>>>>>> next_index);
>>>>>>> +		return nb_objs;
>>>>>>> +	}
>>>>>>> +
>>>>>>> +	held += last_spec;
>>>>>>> +	/* Copy things successfully speculated till now */
>>>>>>> +	rte_memcpy(to_next, from, last_spec *
>> sizeof(from[0]));
>>>>>>> +	rte_node_next_stream_put(graph, node, next_index,
>> held);
>>>>>>> +
>>>>>>> +	return nb_objs;
>>>>>>> +}
>>>>>>> +
>>>>>>>  #else
>>>>>>>
>>>>>>>  static uint16_t
>>>>>>>

  reply	other threads:[~2020-03-24 14:38 UTC|newest]

Thread overview: 219+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2020-03-18 21:35 [dpdk-dev] [PATCH v1 00/26] graph: introduce graph subsystem jerinj
2020-03-18 21:35 ` [dpdk-dev] [PATCH v1 01/26] graph: define the public API for graph support jerinj
2020-03-18 21:35 ` [dpdk-dev] [PATCH v1 02/26] graph: implement node registration jerinj
2020-03-18 21:35 ` [dpdk-dev] [PATCH v1 03/26] graph: implement node operations jerinj
2020-03-18 21:35 ` [dpdk-dev] [PATCH v1 04/26] graph: implement node debug routines jerinj
2020-03-18 21:35 ` [dpdk-dev] [PATCH v1 05/26] graph: implement internal graph operation helpers jerinj
2020-03-18 21:35 ` [dpdk-dev] [PATCH v1 06/26] graph: populate fastpath memory for graph reel jerinj
2020-03-18 21:35 ` [dpdk-dev] [PATCH v1 07/26] graph: implement create and destroy APIs jerinj
2020-03-18 21:35 ` [dpdk-dev] [PATCH v1 08/26] graph: implement graph operation APIs jerinj
2020-03-18 21:35 ` [dpdk-dev] [PATCH v1 09/26] graph: implement Graphviz export jerinj
2020-03-18 21:35 ` [dpdk-dev] [PATCH v1 10/26] graph: implement debug routines jerinj
2020-03-18 21:35 ` [dpdk-dev] [PATCH v1 11/26] graph: implement stats support jerinj
2020-03-18 21:35 ` [dpdk-dev] [PATCH v1 12/26] graph: implement fastpath API routines jerinj
2020-03-18 21:35 ` [dpdk-dev] [PATCH v1 13/26] graph: add unit test case jerinj
2020-03-18 21:35 ` [dpdk-dev] [PATCH v1 14/26] graph: add performance testcase jerinj
2020-03-18 21:35 ` [dpdk-dev] [PATCH v1 15/26] node: add log infra and null node jerinj
2020-03-18 21:35 ` [dpdk-dev] [PATCH v1 16/26] node: add ethdev Rx node jerinj
2020-03-18 21:35 ` [dpdk-dev] [PATCH v1 17/26] node: add ethdev Tx node jerinj
2020-03-18 21:35 ` [dpdk-dev] [PATCH v1 18/26] node: add ethdev Rx and Tx node ctrl API jerinj
2020-03-18 21:35 ` [dpdk-dev] [PATCH v1 19/26] node: ipv4 lookup for arm64 jerinj
2020-03-18 21:35 ` [dpdk-dev] [PATCH v1 20/26] node: ipv4 lookup for x86 jerinj
2020-03-19 12:25   ` Ray Kinsella
2020-03-19 14:22     ` [dpdk-dev] [EXT] " Pavan Nikhilesh Bhagavatula
2020-03-19 15:50       ` Ray Kinsella
2020-03-19 16:13         ` Pavan Nikhilesh Bhagavatula
2020-03-20  9:14           ` Ray Kinsella
2020-03-24  9:40             ` Pavan Nikhilesh Bhagavatula
2020-03-24 14:38               ` Ray Kinsella [this message]
2020-03-26  9:56                 ` Pavan Nikhilesh Bhagavatula
2020-03-26 16:54                   ` Ray Kinsella
2020-03-18 21:35 ` [dpdk-dev] [PATCH v1 21/26] node: add ipv4 rewrite node jerinj
2020-03-18 21:35 ` [dpdk-dev] [PATCH v1 22/26] node: add ipv4 rewrite and lookup ctrl API jerinj
2020-03-18 21:35 ` [dpdk-dev] [PATCH v1 23/26] node: add pkt drop node jerinj
2020-03-18 21:35 ` [dpdk-dev] [PATCH v1 24/26] l3fwd-graph: add graph based l3fwd skeleton jerinj
2020-03-18 21:35 ` [dpdk-dev] [PATCH v1 25/26] l3fwd-graph: add ethdev configuration changes jerinj
2020-03-18 21:35 ` [dpdk-dev] [PATCH v1 26/26] l3fwd-graph: add graph config and main loop jerinj
2020-03-26 16:56 ` [dpdk-dev] [PATCH v2 00/28] graph: introduce graph subsystem jerinj
2020-03-26 16:56   ` [dpdk-dev] [PATCH v2 01/28] graph: define the public API for graph support jerinj
2020-03-26 16:56   ` [dpdk-dev] [PATCH v2 02/28] graph: implement node registration jerinj
2020-03-26 16:56   ` [dpdk-dev] [PATCH v2 03/28] graph: implement node operations jerinj
2020-03-26 16:56   ` [dpdk-dev] [PATCH v2 04/28] graph: implement node debug routines jerinj
2020-03-26 16:56   ` [dpdk-dev] [PATCH v2 05/28] graph: implement internal graph operation helpers jerinj
2020-03-26 16:56   ` [dpdk-dev] [PATCH v2 06/28] graph: populate fastpath memory for graph reel jerinj
2020-03-26 16:56   ` [dpdk-dev] [PATCH v2 07/28] graph: implement create and destroy APIs jerinj
2020-03-26 16:56   ` [dpdk-dev] [PATCH v2 08/28] graph: implement graph operation APIs jerinj
2020-03-26 16:56   ` [dpdk-dev] [PATCH v2 09/28] graph: implement Graphviz export jerinj
2020-03-26 16:56   ` [dpdk-dev] [PATCH v2 10/28] graph: implement debug routines jerinj
2020-03-26 16:56   ` [dpdk-dev] [PATCH v2 11/28] graph: implement stats support jerinj
2020-03-26 16:56   ` [dpdk-dev] [PATCH v2 12/28] graph: implement fastpath API routines jerinj
2020-03-26 16:56   ` [dpdk-dev] [PATCH v2 13/28] graph: add unit test case jerinj
2020-03-26 16:56   ` [dpdk-dev] [PATCH v2 14/28] graph: add performance testcase jerinj
2020-03-26 16:56   ` [dpdk-dev] [PATCH v2 15/28] node: add log infra and null node jerinj
2020-03-26 16:56   ` [dpdk-dev] [PATCH v2 16/28] node: add ethdev Rx node jerinj
2020-03-26 16:56   ` [dpdk-dev] [PATCH v2 17/28] node: add ethdev Tx node jerinj
2020-03-26 16:56   ` [dpdk-dev] [PATCH v2 18/28] node: add ethdev Rx and Tx node ctrl API jerinj
2020-03-26 16:56   ` [dpdk-dev] [PATCH v2 19/28] node: ipv4 lookup for arm64 jerinj
2020-03-26 16:56   ` [dpdk-dev] [PATCH v2 20/28] node: ipv4 lookup for x86 jerinj
2020-03-27  8:40     ` Jerin Jacob
2020-03-26 16:56   ` [dpdk-dev] [PATCH v2 21/28] node: add ipv4 rewrite node jerinj
2020-03-26 16:56   ` [dpdk-dev] [PATCH v2 22/28] node: add ipv4 rewrite and lookup ctrl API jerinj
2020-03-26 16:56   ` [dpdk-dev] [PATCH v2 23/28] node: add pkt drop node jerinj
2020-03-26 16:56   ` [dpdk-dev] [PATCH v2 24/28] l3fwd-graph: add graph based l3fwd skeleton jerinj
2020-03-26 16:56   ` [dpdk-dev] [PATCH v2 25/28] l3fwd-graph: add ethdev configuration changes jerinj
2020-03-26 16:56   ` [dpdk-dev] [PATCH v2 26/28] l3fwd-graph: add graph config and main loop jerinj
2020-03-26 16:56   ` [dpdk-dev] [PATCH v2 27/28] doc: add graph library programmer's guide guide jerinj
2020-03-26 16:56   ` [dpdk-dev] [PATCH v2 28/28] doc: add l3fwd graph application user guide jerinj
2020-03-27  6:49   ` [dpdk-dev] [PATCH v2 00/28] graph: introduce graph subsystem Jerin Jacob
2020-03-27 10:42     ` Thomas Monjalon
2020-03-31 19:29   ` [dpdk-dev] [PATCH v3 00/29] " jerinj
2020-03-31 19:29     ` [dpdk-dev] [PATCH v3 01/29] graph: define the public API for graph support jerinj
2020-04-03  9:26       ` Wang, Xiao W
2020-04-04 12:15         ` Jerin Jacob
2020-04-06 12:36       ` Andrzej Ostruszka
2020-04-06 14:59         ` Jerin Jacob
2020-04-06 16:09           ` Andrzej Ostruszka
2020-04-07 10:27             ` Jerin Jacob
2020-03-31 19:29     ` [dpdk-dev] [PATCH v3 02/29] graph: implement node registration jerinj
2020-04-03 10:44       ` Wang, Xiao W
2020-04-04 12:29         ` Jerin Jacob
2020-03-31 19:29     ` [dpdk-dev] [PATCH v3 03/29] graph: implement node operations jerinj
2020-04-03 10:54       ` Wang, Xiao W
2020-04-04 13:07         ` Jerin Jacob
2020-03-31 19:29     ` [dpdk-dev] [PATCH v3 04/29] graph: implement node debug routines jerinj
2020-04-04  7:57       ` Wang, Xiao W
2020-04-04 13:12         ` Jerin Jacob
2020-03-31 19:29     ` [dpdk-dev] [PATCH v3 05/29] graph: implement internal graph operation helpers jerinj
2020-04-06 13:47       ` Wang, Xiao W
2020-04-06 14:08         ` Jerin Jacob
2020-03-31 19:29     ` [dpdk-dev] [PATCH v3 06/29] graph: populate fastpath memory for graph reel jerinj
2020-03-31 19:29     ` [dpdk-dev] [PATCH v3 07/29] graph: implement create and destroy APIs jerinj
2020-03-31 19:29     ` [dpdk-dev] [PATCH v3 08/29] graph: implement graph operation APIs jerinj
2020-03-31 19:29     ` [dpdk-dev] [PATCH v3 09/29] graph: implement Graphviz export jerinj
2020-03-31 19:29     ` [dpdk-dev] [PATCH v3 10/29] graph: implement debug routines jerinj
2020-03-31 19:29     ` [dpdk-dev] [PATCH v3 11/29] graph: implement stats support jerinj
2020-03-31 19:29     ` [dpdk-dev] [PATCH v3 12/29] graph: implement fastpath API routines jerinj
2020-03-31 19:29     ` [dpdk-dev] [PATCH v3 13/29] graph: add unit test case jerinj
2020-03-31 19:29     ` [dpdk-dev] [PATCH v3 14/29] graph: add performance testcase jerinj
2020-03-31 19:29     ` [dpdk-dev] [PATCH v3 15/29] node: add log infra and null node jerinj
2020-03-31 19:29     ` [dpdk-dev] [PATCH v3 16/29] node: add ethdev Rx node jerinj
2020-03-31 19:29     ` [dpdk-dev] [PATCH v3 17/29] node: add ethdev Tx node jerinj
2020-03-31 19:29     ` [dpdk-dev] [PATCH v3 18/29] node: add ethdev Rx and Tx node ctrl API jerinj
2020-03-31 19:29     ` [dpdk-dev] [PATCH v3 19/29] node: add generic ipv4 lookup node jerinj
2020-03-31 19:29     ` [dpdk-dev] [PATCH v3 20/29] node: ipv4 lookup for arm64 jerinj
2020-03-31 19:29     ` [dpdk-dev] [PATCH v3 21/29] node: ipv4 lookup for x86 jerinj
2020-03-31 19:29     ` [dpdk-dev] [PATCH v3 22/29] node: add ipv4 rewrite node jerinj
2020-03-31 19:29     ` [dpdk-dev] [PATCH v3 23/29] node: add ipv4 rewrite and lookup ctrl API jerinj
2020-03-31 19:29     ` [dpdk-dev] [PATCH v3 24/29] node: add packet drop node jerinj
2020-03-31 19:29     ` [dpdk-dev] [PATCH v3 25/29] l3fwd-graph: add graph based l3fwd skeleton jerinj
2020-03-31 19:29     ` [dpdk-dev] [PATCH v3 26/29] l3fwd-graph: add ethdev configuration changes jerinj
2020-03-31 19:29     ` [dpdk-dev] [PATCH v3 27/29] l3fwd-graph: add graph config and main loop jerinj
2020-03-31 19:29     ` [dpdk-dev] [PATCH v3 28/29] doc: add graph library programmer's guide guide jerinj
2020-03-31 19:29     ` [dpdk-dev] [PATCH v3 29/29] doc: add l3fwd graph application user guide jerinj
2020-04-05  8:55     ` [dpdk-dev] [PATCH v4 00/29] graph: introduce graph subsystem jerinj
2020-04-05  8:55       ` [dpdk-dev] [PATCH v4 01/29] graph: define the public API for graph support jerinj
2020-04-05  8:55       ` [dpdk-dev] [PATCH v4 02/29] graph: implement node registration jerinj
2020-04-05  8:55       ` [dpdk-dev] [PATCH v4 03/29] graph: implement node operations jerinj
2020-04-06 17:57         ` Andrzej Ostruszka
2020-04-07  2:43           ` [dpdk-dev] [EXT] " Kiran Kumar Kokkilagadda
2020-04-07  8:47             ` Andrzej Ostruszka
2020-04-07 10:20             ` Jerin Jacob
2020-04-05  8:55       ` [dpdk-dev] [PATCH v4 04/29] graph: implement node debug routines jerinj
2020-04-06 18:17         ` Andrzej Ostruszka
2020-04-07 10:22           ` Jerin Jacob
2020-04-07 11:50             ` Andrzej Ostruszka
2020-04-07 12:09               ` Jerin Jacob
2020-04-07 12:50                 ` Andrzej Ostruszka
2020-04-05  8:55       ` [dpdk-dev] [PATCH v4 05/29] graph: implement internal graph operation helpers jerinj
2020-04-07 12:16         ` Andrzej Ostruszka
2020-04-07 12:27           ` Jerin Jacob
2020-04-07 12:54             ` Andrzej Ostruszka
2020-04-07 13:31               ` Jerin Jacob
2020-04-05  8:55       ` [dpdk-dev] [PATCH v4 06/29] graph: populate fastpath memory for graph reel jerinj
2020-04-08 17:30         ` Andrzej Ostruszka
2020-04-09  2:44           ` Kiran Kumar Kokkilagadda
2020-04-05  8:55       ` [dpdk-dev] [PATCH v4 07/29] graph: implement create and destroy APIs jerinj
2020-04-08 16:57         ` Andrzej Ostruszka
2020-04-08 17:23           ` Jerin Jacob
2020-04-05  8:55       ` [dpdk-dev] [PATCH v4 08/29] graph: implement graph operation APIs jerinj
2020-04-08 17:49         ` Andrzej Ostruszka
2020-04-08 19:18           ` Jerin Jacob
2020-04-05  8:55       ` [dpdk-dev] [PATCH v4 09/29] graph: implement Graphviz export jerinj
2020-04-05  8:55       ` [dpdk-dev] [PATCH v4 10/29] graph: implement debug routines jerinj
2020-04-05  8:55       ` [dpdk-dev] [PATCH v4 11/29] graph: implement stats support jerinj
2020-04-05  8:55       ` [dpdk-dev] [PATCH v4 12/29] graph: implement fastpath API routines jerinj
2020-04-09 23:07         ` Andrzej Ostruszka
2020-04-10  9:18           ` Jerin Jacob
2020-04-05  8:55       ` [dpdk-dev] [PATCH v4 13/29] graph: add unit test case jerinj
2020-04-05  8:55       ` [dpdk-dev] [PATCH v4 14/29] graph: add performance testcase jerinj
2020-04-05  8:55       ` [dpdk-dev] [PATCH v4 15/29] node: add log infra and null node jerinj
2020-04-05  8:56       ` [dpdk-dev] [PATCH v4 16/29] node: add ethdev Rx node jerinj
2020-04-09 23:05         ` Andrzej Ostruszka
2020-04-10  7:00           ` Nithin Dabilpuram
2020-04-05  8:56       ` [dpdk-dev] [PATCH v4 17/29] node: add ethdev Tx node jerinj
2020-04-05  8:56       ` [dpdk-dev] [PATCH v4 18/29] node: add ethdev Rx and Tx node ctrl API jerinj
2020-04-09 23:07         ` Andrzej Ostruszka
2020-04-10  5:09           ` Nithin Dabilpuram
2020-04-10  8:22             ` Nithin Dabilpuram
2020-04-10 12:52             ` Andrzej Ostruszka
2020-04-10 14:54               ` [dpdk-dev] [EXT] " Nithin Dabilpuram
2020-04-05  8:56       ` [dpdk-dev] [PATCH v4 19/29] node: add generic ipv4 lookup node jerinj
2020-04-09 23:07         ` Andrzej Ostruszka
2020-04-10 10:20           ` Nithin Dabilpuram
2020-04-10 14:41             ` Nithin Dabilpuram
2020-04-10 15:17               ` Andrzej Ostruszka
2020-04-05  8:56       ` [dpdk-dev] [PATCH v4 20/29] node: ipv4 lookup for arm64 jerinj
2020-04-05  8:56       ` [dpdk-dev] [PATCH v4 21/29] node: ipv4 lookup for x86 jerinj
2020-04-05  8:56       ` [dpdk-dev] [PATCH v4 22/29] node: add ipv4 rewrite node jerinj
2020-04-05  8:56       ` [dpdk-dev] [PATCH v4 23/29] node: add ipv4 rewrite and lookup ctrl API jerinj
2020-04-09 23:04         ` Andrzej Ostruszka
2020-04-10  7:24           ` Nithin Dabilpuram
2020-04-05  8:56       ` [dpdk-dev] [PATCH v4 24/29] node: add packet drop node jerinj
2020-04-05  8:56       ` [dpdk-dev] [PATCH v4 25/29] l3fwd-graph: add graph based l3fwd skeleton jerinj
2020-04-09 23:04         ` Andrzej Ostruszka
2020-04-10  8:23           ` Nithin Dabilpuram
2020-04-05  8:56       ` [dpdk-dev] [PATCH v4 26/29] l3fwd-graph: add ethdev configuration changes jerinj
2020-04-05  8:56       ` [dpdk-dev] [PATCH v4 27/29] l3fwd-graph: add graph config and main loop jerinj
2020-04-09 23:04         ` Andrzej Ostruszka
2020-04-10  9:29           ` Nithin Dabilpuram
2020-04-05  8:56       ` [dpdk-dev] [PATCH v4 28/29] doc: add graph library programmer's guide guide jerinj
2020-04-05  8:56       ` [dpdk-dev] [PATCH v4 29/29] doc: add l3fwd graph application user guide jerinj
2020-04-09 23:13       ` [dpdk-dev] [PATCH v4 00/29] graph: introduce graph subsystem Andrzej Ostruszka
2020-04-10  9:07         ` Jerin Jacob
2020-04-11 14:13       ` [dpdk-dev] [PATCH v5 " jerinj
2020-04-11 14:14         ` [dpdk-dev] [PATCH v5 01/29] graph: define the public API for graph support jerinj
2020-04-11 14:14         ` [dpdk-dev] [PATCH v5 02/29] graph: implement node registration jerinj
2020-04-11 14:14         ` [dpdk-dev] [PATCH v5 03/29] graph: implement node operations jerinj
2020-04-11 14:14         ` [dpdk-dev] [PATCH v5 04/29] graph: implement node debug routines jerinj
2020-04-11 14:14         ` [dpdk-dev] [PATCH v5 05/29] graph: implement internal graph operation helpers jerinj
2020-04-11 14:14         ` [dpdk-dev] [PATCH v5 06/29] graph: populate fastpath memory for graph reel jerinj
2020-04-11 14:14         ` [dpdk-dev] [PATCH v5 07/29] graph: implement create and destroy APIs jerinj
2020-04-11 14:14         ` [dpdk-dev] [PATCH v5 08/29] graph: implement graph operation APIs jerinj
2020-04-11 14:14         ` [dpdk-dev] [PATCH v5 09/29] graph: implement Graphviz export jerinj
2020-04-11 14:14         ` [dpdk-dev] [PATCH v5 10/29] graph: implement debug routines jerinj
2020-04-11 14:14         ` [dpdk-dev] [PATCH v5 11/29] graph: implement stats support jerinj
2020-04-11 14:14         ` [dpdk-dev] [PATCH v5 12/29] graph: implement fastpath API routines jerinj
2020-04-11 14:14         ` [dpdk-dev] [PATCH v5 13/29] graph: add unit test case jerinj
2020-04-11 14:14         ` [dpdk-dev] [PATCH v5 14/29] graph: add performance testcase jerinj
2020-04-11 14:14         ` [dpdk-dev] [PATCH v5 15/29] node: add log infra and null node jerinj
2020-04-11 14:14         ` [dpdk-dev] [PATCH v5 16/29] node: add ethdev Rx node jerinj
2020-04-11 14:14         ` [dpdk-dev] [PATCH v5 17/29] node: add ethdev Tx node jerinj
2020-04-11 14:14         ` [dpdk-dev] [PATCH v5 18/29] node: add ethdev Rx and Tx node ctrl API jerinj
2020-04-11 14:14         ` [dpdk-dev] [PATCH v5 19/29] node: add generic ipv4 lookup node jerinj
2020-04-11 14:14         ` [dpdk-dev] [PATCH v5 20/29] node: ipv4 lookup for arm64 jerinj
2020-05-12  9:31           ` David Marchand
2020-05-12  9:50             ` [dpdk-dev] [EXT] " Nithin Dabilpuram
2020-04-11 14:14         ` [dpdk-dev] [PATCH v5 21/29] node: ipv4 lookup for x86 jerinj
2020-04-11 14:14         ` [dpdk-dev] [PATCH v5 22/29] node: add ipv4 rewrite node jerinj
2020-04-11 14:14         ` [dpdk-dev] [PATCH v5 23/29] node: add ipv4 rewrite and lookup ctrl API jerinj
2020-04-11 14:14         ` [dpdk-dev] [PATCH v5 24/29] node: add packet drop node jerinj
2020-04-11 14:14         ` [dpdk-dev] [PATCH v5 25/29] l3fwd-graph: add graph based l3fwd skeleton jerinj
2020-04-11 14:14         ` [dpdk-dev] [PATCH v5 26/29] l3fwd-graph: add ethdev configuration changes jerinj
2020-04-11 14:14         ` [dpdk-dev] [PATCH v5 27/29] l3fwd-graph: add graph config and main loop jerinj
2020-04-11 14:14         ` [dpdk-dev] [PATCH v5 28/29] doc: add graph library programmer's guide guide jerinj
2020-05-11  9:27           ` David Marchand
2020-05-11  9:30             ` Jerin Jacob
2020-04-11 14:14         ` [dpdk-dev] [PATCH v5 29/29] doc: add l3fwd graph application user guide jerinj
2020-04-30  8:07         ` [dpdk-dev] [PATCH v5 00/29] graph: introduce graph subsystem Tom Barbette
2020-04-30  8:42           ` Jerin Jacob
2020-05-05 21:44         ` Thomas Monjalon

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=7a6842d9-43fd-1746-113f-887d6afb16e5@ashroe.eu \
    --to=mdr@ashroe.eu \
    --cc=david.marchand@redhat.com \
    --cc=dev@dpdk.org \
    --cc=jerinj@marvell.com \
    --cc=kirankumark@marvell.com \
    --cc=mattias.ronnblom@ericsson.com \
    --cc=ndabilpuram@marvell.com \
    --cc=pbhagavatula@marvell.com \
    --cc=thomas@monjalon.net \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).