From: Jianbo Liu <jianbo.liu@linaro.org>
To: "Ananyev, Konstantin" <konstantin.ananyev@intel.com>
Cc: "Yigit, Ferruh" <ferruh.yigit@intel.com>,
"dev@dpdk.org" <dev@dpdk.org>,
"Zhang, Helin" <helin.zhang@intel.com>,
"jerin.jacob@caviumnetworks.com"
<jerin.jacob@caviumnetworks.com>
Subject: Re: [dpdk-dev] [PATCH v2 1/2] net/ixgbe: calculate the correct number of received packets in bulk alloc function
Date: Thu, 9 Feb 2017 11:49:57 +0800 [thread overview]
Message-ID: <CAP4Qi3-U81igDkicffiSdsxho3UCdcVNL4byJTQkHbjvn7L-fg@mail.gmail.com> (raw)
In-Reply-To: <2601191342CEEE43887BDE71AB9772583F114FBC@irsmsx105.ger.corp.intel.com>
On 9 February 2017 at 03:53, Ananyev, Konstantin
<konstantin.ananyev@intel.com> wrote:
>
>
>> -----Original Message-----
>> From: dev [mailto:dev-bounces@dpdk.org] On Behalf Of Ananyev, Konstantin
>> Sent: Wednesday, February 8, 2017 6:54 PM
>> To: Yigit, Ferruh <ferruh.yigit@intel.com>; Jianbo Liu <jianbo.liu@linaro.org>; dev@dpdk.org; Zhang, Helin <helin.zhang@intel.com>;
>> jerin.jacob@caviumnetworks.com
>> Subject: Re: [dpdk-dev] [PATCH v2 1/2] net/ixgbe: calculate the correct number of received packets in bulk alloc function
>>
>> Hi Ferruh,
>>
>> >
>> > On 2/4/2017 1:26 PM, Ananyev, Konstantin wrote:
>> > >>
>> > >> To get better performance, Rx bulk alloc recv function will scan 8 descs
>> > >> in one time, but the statuses are not consistent on ARM platform because
>> > >> the memory allocated for Rx descriptors is cacheable hugepages.
>> > >> This patch is to calculate the number of received packets by scan DD bit
>> > >> sequentially, and stops when meeting the first packet with DD bit unset.
>> > >>
>> > >> Signed-off-by: Jianbo Liu <jianbo.liu@linaro.org>
>> > >> ---
>> > >> drivers/net/ixgbe/ixgbe_rxtx.c | 16 +++++++++-------
>> > >> 1 file changed, 9 insertions(+), 7 deletions(-)
>> > >>
>> > >> diff --git a/drivers/net/ixgbe/ixgbe_rxtx.c b/drivers/net/ixgbe/ixgbe_rxtx.c
>> > >> index 36f1c02..613890e 100644
>> > >> --- a/drivers/net/ixgbe/ixgbe_rxtx.c
>> > >> +++ b/drivers/net/ixgbe/ixgbe_rxtx.c
>> > >> @@ -1460,17 +1460,19 @@ static inline int __attribute__((always_inline))
>> > >> for (i = 0; i < RTE_PMD_IXGBE_RX_MAX_BURST;
>> > >> i += LOOK_AHEAD, rxdp += LOOK_AHEAD, rxep += LOOK_AHEAD) {
>> > >> /* Read desc statuses backwards to avoid race condition */
>> > >> - for (j = LOOK_AHEAD-1; j >= 0; --j)
>> > >> + for (j = 0; j < LOOK_AHEAD; j++)
>> > >> s[j] = rte_le_to_cpu_32(rxdp[j].wb.upper.status_error);
>> > >>
>> > >> - for (j = LOOK_AHEAD - 1; j >= 0; --j)
>> > >> - pkt_info[j] = rte_le_to_cpu_32(rxdp[j].wb.lower.
>> > >> - lo_dword.data);
>> > >> + rte_smp_rmb();
>> > >>
>> > >> /* Compute how many status bits were set */
>> > >> - nb_dd = 0;
>> > >> - for (j = 0; j < LOOK_AHEAD; ++j)
>> > >> - nb_dd += s[j] & IXGBE_RXDADV_STAT_DD;
>> > >> + for (nb_dd = 0; nb_dd < LOOK_AHEAD &&
>> > >> + (s[nb_dd] & IXGBE_RXDADV_STAT_DD); nb_dd++)
>> > >> + ;
>> > >> +
>> > >> + for (j = 0; j < nb_dd; j++)
>> > >> + pkt_info[j] = rte_le_to_cpu_32(rxdp[j].wb.lower.
>> > >> + lo_dword.data);
>> > >>
>> > >> nb_rx += nb_dd;
>> > >>
>> > >> --
>> > >
>> > > Acked-by: Konstantin Ananyev <konstantin.ananyev@intel.com>
>> >
>> > Hi Konstantin,
>> >
>> > Is the ack valid for v3 and both patches?
>>
>> No, I didn't look into the second one in details.
>> It is ARM specific, and I left it for people who are more familiar with ARM then me :)
>> Konstantin
>
> Actually, I had a quick look after your mail.
>
> + /* A.1 load 1 pkts desc */
> + descs[0] = vld1q_u64((uint64_t *)(rxdp));
> + rte_smp_rmb();
>
> /* B.2 copy 2 mbuf point into rx_pkts */
> vst1q_u64((uint64_t *)&rx_pkts[pos], mbp1);
> @@ -271,10 +270,11 @@
> /* B.1 load 1 mbuf point */
> mbp2 = vld1q_u64((uint64_t *)&sw_ring[pos + 2]);
>
> - descs[2] = vld1q_u64((uint64_t *)(rxdp + 2));
> - /* B.1 load 2 mbuf point */
> descs[1] = vld1q_u64((uint64_t *)(rxdp + 1));
> - descs[0] = vld1q_u64((uint64_t *)(rxdp));
> +
> + /* A.1 load 2 pkts descs */
> + descs[2] = vld1q_u64((uint64_t *)(rxdp + 2));
> + descs[3] = vld1q_u64((uint64_t *)(rxdp + 3));
>
> Assuming that on all ARM-NEON platforms 16B reads are atomic,
> I think there is no need for smp_rmb() after the desc[0] read.
> What looks more appropriate to me:
With checking DDs in sequence, it doesn't matter much where the rmb is.
But there is a little performance improvement (0.02%) in my testing
with your suggestion.
So I'll send a new version. Thanks!
>
> descs[0] = vld1q_u64((uint64_t *)(rxdp));
> descs[1] = vld1q_u64((uint64_t *)(rxdp + 1));
> descs[2] = vld1q_u64((uint64_t *)(rxdp + 2));
> descs[3] = vld1q_u64((uint64_t *)(rxdp + 3));
>
> rte_smp_rmb();
>
> ...
>
> But, as I said would be good if some ARM guys have a look here.
> Konstantin
>
>
>>
>> >
>> > Thanks,
>> > ferruh
>> >
>> > >
>> > >> 1.8.3.1
>> > >
>
next prev parent reply other threads:[~2017-02-09 3:49 UTC|newest]
Thread overview: 25+ messages / expand[flat|nested] mbox.gz Atom feed top
2016-12-19 6:09 [dpdk-dev] [PATCH " Jianbo Liu
2016-12-19 6:09 ` [dpdk-dev] [PATCH 2/2] net/ixgbe: calculate correct number of received packets for ARM NEON-version vPMD Jianbo Liu
2016-12-21 10:08 ` Jerin Jacob
2016-12-21 11:03 ` Bruce Richardson
2016-12-22 1:18 ` Jianbo Liu
2016-12-22 1:05 ` Jianbo Liu
2017-02-01 16:19 ` [dpdk-dev] [PATCH 1/2] net/ixgbe: calculate the correct number of received packets in bulk alloc function Ananyev, Konstantin
2017-02-03 6:22 ` Jianbo Liu
2017-02-03 11:38 ` Ananyev, Konstantin
2017-02-04 3:37 ` Jianbo Liu
2017-02-04 9:37 ` [dpdk-dev] [PATCH v2 " Jianbo Liu
2017-02-04 9:37 ` [dpdk-dev] [PATCH v2 2/2] net/ixgbe: calculate correct number of received packets for ARM NEON-version vPMD Jianbo Liu
2017-02-04 13:26 ` [dpdk-dev] [PATCH v2 1/2] net/ixgbe: calculate the correct number of received packets in bulk alloc function Ananyev, Konstantin
2017-02-08 18:02 ` Ferruh Yigit
2017-02-08 18:53 ` Ananyev, Konstantin
2017-02-08 19:53 ` Ananyev, Konstantin
2017-02-09 3:49 ` Jianbo Liu [this message]
2017-02-04 16:37 ` [dpdk-dev] [PATCH v3 " Jianbo Liu
2017-02-04 16:37 ` [dpdk-dev] [PATCH v3 2/2] net/ixgbe: calculate correct number of received packets for ARM NEON-version vPMD Jianbo Liu
2017-02-04 16:39 ` [dpdk-dev] [PATCH v3 1/2] net/ixgbe: calculate the correct number of received packets in bulk alloc function Jianbo Liu
2017-02-09 4:05 ` [dpdk-dev] [PATCH v4 " Jianbo Liu
2017-02-09 4:05 ` [dpdk-dev] [PATCH v4 2/2] net/ixgbe: calculate correct number of received packets for ARM NEON-version vPMD Jianbo Liu
2017-02-09 12:43 ` Ferruh Yigit
2017-02-09 12:39 ` [dpdk-dev] [PATCH v4 1/2] net/ixgbe: calculate the correct number of received packets in bulk alloc function Ferruh Yigit
2017-02-09 12:42 ` Ferruh Yigit
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=CAP4Qi3-U81igDkicffiSdsxho3UCdcVNL4byJTQkHbjvn7L-fg@mail.gmail.com \
--to=jianbo.liu@linaro.org \
--cc=dev@dpdk.org \
--cc=ferruh.yigit@intel.com \
--cc=helin.zhang@intel.com \
--cc=jerin.jacob@caviumnetworks.com \
--cc=konstantin.ananyev@intel.com \
/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).