* [dpdk-dev] [RFC PATCH] ixgbe: ixgbe_recv_pkts_vec shouldn't override mbuf buffer length
@ 2014-12-05 15:20 Konstantin Ananyev
2014-12-05 16:59 ` Jean-Mickael Guerin
0 siblings, 1 reply; 6+ messages in thread
From: Konstantin Ananyev @ 2014-12-05 15:20 UTC (permalink / raw)
To: dev
That's an alternative way to fix the problem described in the patch:
http://dpdk.org/ml/archives/dev/2014-December/009394.html.
The main difference is:
- move buf_len fields out of rearm_data marker.
- make ixgbe_recv_pkts_vec() not touch buf_len field at all
(as all other RX functions behave).
Signed-off-by: Konstantin Ananyev <konstantin.ananyev@intel.com>
---
lib/librte_mbuf/rte_mbuf.h | 7 +++++--
lib/librte_pmd_ixgbe/ixgbe_rxtx_vec.c | 20 +++++++++++++++-----
2 files changed, 20 insertions(+), 7 deletions(-)
diff --git a/lib/librte_mbuf/rte_mbuf.h b/lib/librte_mbuf/rte_mbuf.h
index 2e5fce5..bb88318 100644
--- a/lib/librte_mbuf/rte_mbuf.h
+++ b/lib/librte_mbuf/rte_mbuf.h
@@ -179,6 +179,8 @@ const char *rte_get_tx_ol_flag_name(uint64_t mask);
typedef void *MARKER[0]; /**< generic marker for a point in a structure */
typedef uint64_t MARKER64[0]; /**< marker that allows us to overwrite 8 bytes
* with a single assignment */
+typedef uint8_t MARKER8[0]; /**< generic marker with 1B alignment */
+
/**
* The generic rte_mbuf, containing a packet mbuf.
*/
@@ -188,9 +190,10 @@ struct rte_mbuf {
void *buf_addr; /**< Virtual address of segment buffer. */
phys_addr_t buf_physaddr; /**< Physical address of segment buffer. */
- /* next 8 bytes are initialised on RX descriptor rearm */
- MARKER64 rearm_data;
uint16_t buf_len; /**< Length of segment buffer. */
+
+ /* next 6 bytes are initialised on RX descriptor rearm */
+ MARKER8 rearm_data;
uint16_t data_off;
/**
diff --git a/lib/librte_pmd_ixgbe/ixgbe_rxtx_vec.c b/lib/librte_pmd_ixgbe/ixgbe_rxtx_vec.c
index 579bc46..d5fc0cc 100644
--- a/lib/librte_pmd_ixgbe/ixgbe_rxtx_vec.c
+++ b/lib/librte_pmd_ixgbe/ixgbe_rxtx_vec.c
@@ -79,13 +79,22 @@ ixgbe_rxq_rearm(struct igb_rx_queue *rxq)
/* Initialize the mbufs in vector, process 2 mbufs in one loop */
for (i = 0; i < RTE_IXGBE_RXQ_REARM_THRESH; i += 2, rxep += 2) {
__m128i vaddr0, vaddr1;
+ uintptr_t p0, p1;
mb0 = rxep[0].mbuf;
mb1 = rxep[1].mbuf;
- /* flush mbuf with pkt template */
- mb0->rearm_data[0] = rxq->mbuf_initializer;
- mb1->rearm_data[0] = rxq->mbuf_initializer;
+ /*
+ * Flush mbuf with pkt template.
+ * Data to be rearmed is 6 bytes long.
+ * Though, RX will overwrite ol_flags that are coming next
+ * anyway. So overwrite whole 8 bytes with one load:
+ * 6 bytes of rearm_data plus first 2 bytes of ol_flags.
+ */
+ p0 = (uintptr_t)&mb0->rearm_data;
+ *(uint64_t *)p0 = rxq->mbuf_initializer;
+ p1 = (uintptr_t)&mb1->rearm_data;
+ *(uint64_t *)p1 = rxq->mbuf_initializer;
/* load buf_addr(lo 64bit) and buf_physaddr(hi 64bit) */
vaddr0 = _mm_loadu_si128((__m128i *)&(mb0->buf_addr));
@@ -732,14 +741,15 @@ static struct ixgbe_txq_ops vec_txq_ops = {
int
ixgbe_rxq_vec_setup(struct igb_rx_queue *rxq)
{
+ uintptr_t p;
struct rte_mbuf mb_def = { .buf_addr = 0 }; /* zeroed mbuf */
mb_def.nb_segs = 1;
mb_def.data_off = RTE_PKTMBUF_HEADROOM;
- mb_def.buf_len = rxq->mb_pool->elt_size - sizeof(struct rte_mbuf);
mb_def.port = rxq->port_id;
rte_mbuf_refcnt_set(&mb_def, 1);
- rxq->mbuf_initializer = *((uint64_t *)&mb_def.rearm_data);
+ p = (uintptr_t)&mb_def.rearm_data;
+ rxq->mbuf_initializer = *(uint64_t *)p;
return 0;
}
--
1.8.3.1
^ permalink raw reply [flat|nested] 6+ messages in thread* Re: [dpdk-dev] [RFC PATCH] ixgbe: ixgbe_recv_pkts_vec shouldn't override mbuf buffer length
2014-12-05 15:20 [dpdk-dev] [RFC PATCH] ixgbe: ixgbe_recv_pkts_vec shouldn't override mbuf buffer length Konstantin Ananyev
@ 2014-12-05 16:59 ` Jean-Mickael Guerin
2014-12-05 17:07 ` Ananyev, Konstantin
0 siblings, 1 reply; 6+ messages in thread
From: Jean-Mickael Guerin @ 2014-12-05 16:59 UTC (permalink / raw)
To: Konstantin Ananyev; +Cc: dev
On 05/12/2014 16:20, Konstantin Ananyev wrote:
> That's an alternative way to fix the problem described in the patch:
> http://dpdk.org/ml/archives/dev/2014-December/009394.html.
> The main difference is:
> - move buf_len fields out of rearm_data marker.
> - make ixgbe_recv_pkts_vec() not touch buf_len field at all
> (as all other RX functions behave).
>
> Signed-off-by: Konstantin Ananyev <konstantin.ananyev@intel.com>
> ---
> lib/librte_mbuf/rte_mbuf.h | 7 +++++--
> lib/librte_pmd_ixgbe/ixgbe_rxtx_vec.c | 20 +++++++++++++++-----
> 2 files changed, 20 insertions(+), 7 deletions(-)
>
> diff --git a/lib/librte_mbuf/rte_mbuf.h b/lib/librte_mbuf/rte_mbuf.h
> index 2e5fce5..bb88318 100644
> --- a/lib/librte_mbuf/rte_mbuf.h
> +++ b/lib/librte_mbuf/rte_mbuf.h
> @@ -179,6 +179,8 @@ const char *rte_get_tx_ol_flag_name(uint64_t mask);
> typedef void *MARKER[0]; /**< generic marker for a point in a structure */
> typedef uint64_t MARKER64[0]; /**< marker that allows us to overwrite 8 bytes
> * with a single assignment */
> +typedef uint8_t MARKER8[0]; /**< generic marker with 1B alignment */
> +
> /**
> * The generic rte_mbuf, containing a packet mbuf.
> */
> @@ -188,9 +190,10 @@ struct rte_mbuf {
> void *buf_addr; /**< Virtual address of segment buffer. */
> phys_addr_t buf_physaddr; /**< Physical address of segment buffer. */
>
> - /* next 8 bytes are initialised on RX descriptor rearm */
> - MARKER64 rearm_data;
> uint16_t buf_len; /**< Length of segment buffer. */
> +
> + /* next 6 bytes are initialised on RX descriptor rearm */
> + MARKER8 rearm_data;
> uint16_t data_off;
>
> /**
> diff --git a/lib/librte_pmd_ixgbe/ixgbe_rxtx_vec.c b/lib/librte_pmd_ixgbe/ixgbe_rxtx_vec.c
> index 579bc46..d5fc0cc 100644
> --- a/lib/librte_pmd_ixgbe/ixgbe_rxtx_vec.c
> +++ b/lib/librte_pmd_ixgbe/ixgbe_rxtx_vec.c
> @@ -79,13 +79,22 @@ ixgbe_rxq_rearm(struct igb_rx_queue *rxq)
> /* Initialize the mbufs in vector, process 2 mbufs in one loop */
> for (i = 0; i < RTE_IXGBE_RXQ_REARM_THRESH; i += 2, rxep += 2) {
> __m128i vaddr0, vaddr1;
> + uintptr_t p0, p1;
>
> mb0 = rxep[0].mbuf;
> mb1 = rxep[1].mbuf;
>
> - /* flush mbuf with pkt template */
> - mb0->rearm_data[0] = rxq->mbuf_initializer;
> - mb1->rearm_data[0] = rxq->mbuf_initializer;
> + /*
> + * Flush mbuf with pkt template.
> + * Data to be rearmed is 6 bytes long.
> + * Though, RX will overwrite ol_flags that are coming next
> + * anyway. So overwrite whole 8 bytes with one load:
> + * 6 bytes of rearm_data plus first 2 bytes of ol_flags.
> + */
> + p0 = (uintptr_t)&mb0->rearm_data;
> + *(uint64_t *)p0 = rxq->mbuf_initializer;
> + p1 = (uintptr_t)&mb1->rearm_data;
> + *(uint64_t *)p1 = rxq->mbuf_initializer;
>
> /* load buf_addr(lo 64bit) and buf_physaddr(hi 64bit) */
> vaddr0 = _mm_loadu_si128((__m128i *)&(mb0->buf_addr));
> @@ -732,14 +741,15 @@ static struct ixgbe_txq_ops vec_txq_ops = {
> int
> ixgbe_rxq_vec_setup(struct igb_rx_queue *rxq)
> {
> + uintptr_t p;
> struct rte_mbuf mb_def = { .buf_addr = 0 }; /* zeroed mbuf */
>
> mb_def.nb_segs = 1;
> mb_def.data_off = RTE_PKTMBUF_HEADROOM;
> - mb_def.buf_len = rxq->mb_pool->elt_size - sizeof(struct rte_mbuf);
> mb_def.port = rxq->port_id;
> rte_mbuf_refcnt_set(&mb_def, 1);
> - rxq->mbuf_initializer = *((uint64_t *)&mb_def.rearm_data);
> + p = (uintptr_t)&mb_def.rearm_data;
> + rxq->mbuf_initializer = *(uint64_t *)p;
> return 0;
> }
>
>
The patch introduces writes on unaligned data, but we can assume no
performance penalty on intel hw, correct?
^ permalink raw reply [flat|nested] 6+ messages in thread* Re: [dpdk-dev] [RFC PATCH] ixgbe: ixgbe_recv_pkts_vec shouldn't override mbuf buffer length
2014-12-05 16:59 ` Jean-Mickael Guerin
@ 2014-12-05 17:07 ` Ananyev, Konstantin
2014-12-05 18:02 ` Thomas Monjalon
2014-12-05 18:03 ` Jean-Mickael Guerin
0 siblings, 2 replies; 6+ messages in thread
From: Ananyev, Konstantin @ 2014-12-05 17:07 UTC (permalink / raw)
To: Jean-Mickael Guerin; +Cc: dev
> -----Original Message-----
> From: Jean-Mickael Guerin [mailto:jean-mickael.guerin@6wind.com]
> Sent: Friday, December 05, 2014 4:59 PM
> To: Ananyev, Konstantin
> Cc: dev@dpdk.org
> Subject: Re: [dpdk-dev] [RFC PATCH] ixgbe: ixgbe_recv_pkts_vec shouldn't override mbuf buffer length
>
> On 05/12/2014 16:20, Konstantin Ananyev wrote:
> > That's an alternative way to fix the problem described in the patch:
> > http://dpdk.org/ml/archives/dev/2014-December/009394.html.
> > The main difference is:
> > - move buf_len fields out of rearm_data marker.
> > - make ixgbe_recv_pkts_vec() not touch buf_len field at all
> > (as all other RX functions behave).
> >
> > Signed-off-by: Konstantin Ananyev <konstantin.ananyev@intel.com>
> > ---
> > lib/librte_mbuf/rte_mbuf.h | 7 +++++--
> > lib/librte_pmd_ixgbe/ixgbe_rxtx_vec.c | 20 +++++++++++++++-----
> > 2 files changed, 20 insertions(+), 7 deletions(-)
> >
> > diff --git a/lib/librte_mbuf/rte_mbuf.h b/lib/librte_mbuf/rte_mbuf.h
> > index 2e5fce5..bb88318 100644
> > --- a/lib/librte_mbuf/rte_mbuf.h
> > +++ b/lib/librte_mbuf/rte_mbuf.h
> > @@ -179,6 +179,8 @@ const char *rte_get_tx_ol_flag_name(uint64_t mask);
> > typedef void *MARKER[0]; /**< generic marker for a point in a structure */
> > typedef uint64_t MARKER64[0]; /**< marker that allows us to overwrite 8 bytes
> > * with a single assignment */
> > +typedef uint8_t MARKER8[0]; /**< generic marker with 1B alignment */
> > +
> > /**
> > * The generic rte_mbuf, containing a packet mbuf.
> > */
> > @@ -188,9 +190,10 @@ struct rte_mbuf {
> > void *buf_addr; /**< Virtual address of segment buffer. */
> > phys_addr_t buf_physaddr; /**< Physical address of segment buffer. */
> >
> > - /* next 8 bytes are initialised on RX descriptor rearm */
> > - MARKER64 rearm_data;
> > uint16_t buf_len; /**< Length of segment buffer. */
> > +
> > + /* next 6 bytes are initialised on RX descriptor rearm */
> > + MARKER8 rearm_data;
> > uint16_t data_off;
> >
> > /**
> > diff --git a/lib/librte_pmd_ixgbe/ixgbe_rxtx_vec.c b/lib/librte_pmd_ixgbe/ixgbe_rxtx_vec.c
> > index 579bc46..d5fc0cc 100644
> > --- a/lib/librte_pmd_ixgbe/ixgbe_rxtx_vec.c
> > +++ b/lib/librte_pmd_ixgbe/ixgbe_rxtx_vec.c
> > @@ -79,13 +79,22 @@ ixgbe_rxq_rearm(struct igb_rx_queue *rxq)
> > /* Initialize the mbufs in vector, process 2 mbufs in one loop */
> > for (i = 0; i < RTE_IXGBE_RXQ_REARM_THRESH; i += 2, rxep += 2) {
> > __m128i vaddr0, vaddr1;
> > + uintptr_t p0, p1;
> >
> > mb0 = rxep[0].mbuf;
> > mb1 = rxep[1].mbuf;
> >
> > - /* flush mbuf with pkt template */
> > - mb0->rearm_data[0] = rxq->mbuf_initializer;
> > - mb1->rearm_data[0] = rxq->mbuf_initializer;
> > + /*
> > + * Flush mbuf with pkt template.
> > + * Data to be rearmed is 6 bytes long.
> > + * Though, RX will overwrite ol_flags that are coming next
> > + * anyway. So overwrite whole 8 bytes with one load:
> > + * 6 bytes of rearm_data plus first 2 bytes of ol_flags.
> > + */
> > + p0 = (uintptr_t)&mb0->rearm_data;
> > + *(uint64_t *)p0 = rxq->mbuf_initializer;
> > + p1 = (uintptr_t)&mb1->rearm_data;
> > + *(uint64_t *)p1 = rxq->mbuf_initializer;
> >
> > /* load buf_addr(lo 64bit) and buf_physaddr(hi 64bit) */
> > vaddr0 = _mm_loadu_si128((__m128i *)&(mb0->buf_addr));
> > @@ -732,14 +741,15 @@ static struct ixgbe_txq_ops vec_txq_ops = {
> > int
> > ixgbe_rxq_vec_setup(struct igb_rx_queue *rxq)
> > {
> > + uintptr_t p;
> > struct rte_mbuf mb_def = { .buf_addr = 0 }; /* zeroed mbuf */
> >
> > mb_def.nb_segs = 1;
> > mb_def.data_off = RTE_PKTMBUF_HEADROOM;
> > - mb_def.buf_len = rxq->mb_pool->elt_size - sizeof(struct rte_mbuf);
> > mb_def.port = rxq->port_id;
> > rte_mbuf_refcnt_set(&mb_def, 1);
> > - rxq->mbuf_initializer = *((uint64_t *)&mb_def.rearm_data);
> > + p = (uintptr_t)&mb_def.rearm_data;
> > + rxq->mbuf_initializer = *(uint64_t *)p;
> > return 0;
> > }
> >
> >
>
> The patch introduces writes on unaligned data, but we can assume no
> performance penalty on intel hw, correct?
>
Yes to both:
it introduces 64bit unaligned store.
I run performance test on IVB board, didn't see any degradation.
Konstantin
^ permalink raw reply [flat|nested] 6+ messages in thread* Re: [dpdk-dev] [RFC PATCH] ixgbe: ixgbe_recv_pkts_vec shouldn't override mbuf buffer length
2014-12-05 17:07 ` Ananyev, Konstantin
@ 2014-12-05 18:02 ` Thomas Monjalon
2014-12-05 18:03 ` Jean-Mickael Guerin
1 sibling, 0 replies; 6+ messages in thread
From: Thomas Monjalon @ 2014-12-05 18:02 UTC (permalink / raw)
To: Ananyev, Konstantin; +Cc: dev
Konstantin,
It would be easier if you sent a v2 of the patchset from Jean-Mickael.
So, the first patch would be included with your rework of the second patch.
Please use --in-reply-to to make tracking from emails or archives easier.
Thanks
--
Thomas
^ permalink raw reply [flat|nested] 6+ messages in thread
* Re: [dpdk-dev] [RFC PATCH] ixgbe: ixgbe_recv_pkts_vec shouldn't override mbuf buffer length
2014-12-05 17:07 ` Ananyev, Konstantin
2014-12-05 18:02 ` Thomas Monjalon
@ 2014-12-05 18:03 ` Jean-Mickael Guerin
2014-12-05 22:13 ` Thomas Monjalon
1 sibling, 1 reply; 6+ messages in thread
From: Jean-Mickael Guerin @ 2014-12-05 18:03 UTC (permalink / raw)
To: Ananyev, Konstantin; +Cc: dev
On 05/12/2014 18:07, Ananyev, Konstantin wrote:
>
>
>> -----Original Message-----
>> From: Jean-Mickael Guerin [mailto:jean-mickael.guerin@6wind.com]
>> Sent: Friday, December 05, 2014 4:59 PM
>> To: Ananyev, Konstantin
>> Cc: dev@dpdk.org
>> Subject: Re: [dpdk-dev] [RFC PATCH] ixgbe: ixgbe_recv_pkts_vec shouldn't override mbuf buffer length
>>
>> On 05/12/2014 16:20, Konstantin Ananyev wrote:
>>> That's an alternative way to fix the problem described in the patch:
>>> http://dpdk.org/ml/archives/dev/2014-December/009394.html.
>>> The main difference is:
>>> - move buf_len fields out of rearm_data marker.
>>> - make ixgbe_recv_pkts_vec() not touch buf_len field at all
>>> (as all other RX functions behave).
>>>
>>> Signed-off-by: Konstantin Ananyev <konstantin.ananyev@intel.com>
>>> ---
>>> lib/librte_mbuf/rte_mbuf.h | 7 +++++--
>>> lib/librte_pmd_ixgbe/ixgbe_rxtx_vec.c | 20 +++++++++++++++-----
>>> 2 files changed, 20 insertions(+), 7 deletions(-)
>>>
>>> diff --git a/lib/librte_mbuf/rte_mbuf.h b/lib/librte_mbuf/rte_mbuf.h
>>> index 2e5fce5..bb88318 100644
>>> --- a/lib/librte_mbuf/rte_mbuf.h
>>> +++ b/lib/librte_mbuf/rte_mbuf.h
>>> @@ -179,6 +179,8 @@ const char *rte_get_tx_ol_flag_name(uint64_t mask);
>>> typedef void *MARKER[0]; /**< generic marker for a point in a structure */
>>> typedef uint64_t MARKER64[0]; /**< marker that allows us to overwrite 8 bytes
>>> * with a single assignment */
>>> +typedef uint8_t MARKER8[0]; /**< generic marker with 1B alignment */
>>> +
>>> /**
>>> * The generic rte_mbuf, containing a packet mbuf.
>>> */
>>> @@ -188,9 +190,10 @@ struct rte_mbuf {
>>> void *buf_addr; /**< Virtual address of segment buffer. */
>>> phys_addr_t buf_physaddr; /**< Physical address of segment buffer. */
>>>
>>> - /* next 8 bytes are initialised on RX descriptor rearm */
>>> - MARKER64 rearm_data;
>>> uint16_t buf_len; /**< Length of segment buffer. */
>>> +
>>> + /* next 6 bytes are initialised on RX descriptor rearm */
>>> + MARKER8 rearm_data;
>>> uint16_t data_off;
>>>
>>> /**
>>> diff --git a/lib/librte_pmd_ixgbe/ixgbe_rxtx_vec.c b/lib/librte_pmd_ixgbe/ixgbe_rxtx_vec.c
>>> index 579bc46..d5fc0cc 100644
>>> --- a/lib/librte_pmd_ixgbe/ixgbe_rxtx_vec.c
>>> +++ b/lib/librte_pmd_ixgbe/ixgbe_rxtx_vec.c
>>> @@ -79,13 +79,22 @@ ixgbe_rxq_rearm(struct igb_rx_queue *rxq)
>>> /* Initialize the mbufs in vector, process 2 mbufs in one loop */
>>> for (i = 0; i < RTE_IXGBE_RXQ_REARM_THRESH; i += 2, rxep += 2) {
>>> __m128i vaddr0, vaddr1;
>>> + uintptr_t p0, p1;
>>>
>>> mb0 = rxep[0].mbuf;
>>> mb1 = rxep[1].mbuf;
>>>
>>> - /* flush mbuf with pkt template */
>>> - mb0->rearm_data[0] = rxq->mbuf_initializer;
>>> - mb1->rearm_data[0] = rxq->mbuf_initializer;
>>> + /*
>>> + * Flush mbuf with pkt template.
>>> + * Data to be rearmed is 6 bytes long.
>>> + * Though, RX will overwrite ol_flags that are coming next
>>> + * anyway. So overwrite whole 8 bytes with one load:
>>> + * 6 bytes of rearm_data plus first 2 bytes of ol_flags.
>>> + */
>>> + p0 = (uintptr_t)&mb0->rearm_data;
>>> + *(uint64_t *)p0 = rxq->mbuf_initializer;
>>> + p1 = (uintptr_t)&mb1->rearm_data;
>>> + *(uint64_t *)p1 = rxq->mbuf_initializer;
>>>
>>> /* load buf_addr(lo 64bit) and buf_physaddr(hi 64bit) */
>>> vaddr0 = _mm_loadu_si128((__m128i *)&(mb0->buf_addr));
>>> @@ -732,14 +741,15 @@ static struct ixgbe_txq_ops vec_txq_ops = {
>>> int
>>> ixgbe_rxq_vec_setup(struct igb_rx_queue *rxq)
>>> {
>>> + uintptr_t p;
>>> struct rte_mbuf mb_def = { .buf_addr = 0 }; /* zeroed mbuf */
>>>
>>> mb_def.nb_segs = 1;
>>> mb_def.data_off = RTE_PKTMBUF_HEADROOM;
>>> - mb_def.buf_len = rxq->mb_pool->elt_size - sizeof(struct rte_mbuf);
>>> mb_def.port = rxq->port_id;
>>> rte_mbuf_refcnt_set(&mb_def, 1);
>>> - rxq->mbuf_initializer = *((uint64_t *)&mb_def.rearm_data);
>>> + p = (uintptr_t)&mb_def.rearm_data;
>>> + rxq->mbuf_initializer = *(uint64_t *)p;
>>> return 0;
>>> }
>>>
>>>
>>
>> The patch introduces writes on unaligned data, but we can assume no
>> performance penalty on intel hw, correct?
>>
>
> Yes to both:
> it introduces 64bit unaligned store.
> I run performance test on IVB board, didn't see any degradation.
> Konstantin
>
>
OK fine by me:
Acked-by: Jean-Mickael Guerin <jean-mickael.guerin@6wind.com>
^ permalink raw reply [flat|nested] 6+ messages in thread* Re: [dpdk-dev] [RFC PATCH] ixgbe: ixgbe_recv_pkts_vec shouldn't override mbuf buffer length
2014-12-05 18:03 ` Jean-Mickael Guerin
@ 2014-12-05 22:13 ` Thomas Monjalon
0 siblings, 0 replies; 6+ messages in thread
From: Thomas Monjalon @ 2014-12-05 22:13 UTC (permalink / raw)
To: Ananyev, Konstantin; +Cc: dev
2014-12-05 19:03, Jean-Mickael Guerin:
> On 05/12/2014 18:07, Ananyev, Konstantin wrote:
> > From: Jean-Mickael Guerin [mailto:jean-mickael.guerin@6wind.com]
> >> On 05/12/2014 16:20, Konstantin Ananyev wrote:
> >>> That's an alternative way to fix the problem described in the patch:
> >>> http://dpdk.org/ml/archives/dev/2014-December/009394.html.
> >>> The main difference is:
> >>> - move buf_len fields out of rearm_data marker.
> >>> - make ixgbe_recv_pkts_vec() not touch buf_len field at all
> >>> (as all other RX functions behave).
> >>>
> >>> Signed-off-by: Konstantin Ananyev <konstantin.ananyev@intel.com>
> >>
> >> The patch introduces writes on unaligned data, but we can assume no
> >> performance penalty on intel hw, correct?
> >
> > Yes to both:
> > it introduces 64bit unaligned store.
> > I run performance test on IVB board, didn't see any degradation.
> > Konstantin
>
> OK fine by me:
>
> Acked-by: Jean-Mickael Guerin <jean-mickael.guerin@6wind.com>
Applied, even if the patch is RFC, it will be validated as part of -rc3.
Thanks
--
Thomas
^ permalink raw reply [flat|nested] 6+ messages in thread
end of thread, other threads:[~2014-12-05 22:13 UTC | newest]
Thread overview: 6+ messages (download: mbox.gz / follow: Atom feed)
-- links below jump to the message on this page --
2014-12-05 15:20 [dpdk-dev] [RFC PATCH] ixgbe: ixgbe_recv_pkts_vec shouldn't override mbuf buffer length Konstantin Ananyev
2014-12-05 16:59 ` Jean-Mickael Guerin
2014-12-05 17:07 ` Ananyev, Konstantin
2014-12-05 18:02 ` Thomas Monjalon
2014-12-05 18:03 ` Jean-Mickael Guerin
2014-12-05 22:13 ` Thomas Monjalon
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).