DPDK patches and discussions
 help / color / mirror / Atom feed
From: "Min Hu (Connor)" <humin29@huawei.com>
To: Ferruh Yigit <ferruh.yigit@intel.com>, <dev@dpdk.org>
Cc: Ciara Power <ciara.power@intel.com>,
	David Marchand <david.marchand@redhat.com>
Subject: Re: [dpdk-dev] [PATCH v2 1/9] net/hns3: support runtime config to select IO burst func
Date: Fri, 12 Mar 2021 08:59:35 +0800	[thread overview]
Message-ID: <eaaa257a-3ed7-8541-e0cb-931720d1995f@huawei.com> (raw)
In-Reply-To: <ee20d440-aabe-53b5-ea62-ca57413d38c8@intel.com>



在 2021/3/12 1:31, Ferruh Yigit 写道:
> On 3/10/2021 6:16 AM, Min Hu (Connor) wrote:
>> From: Chengwen Feng <fengchengwen@huawei.com>
>>
>> Currently, the driver support multiple IO burst function and auto
>> selection of the most appropriate function based on offload
>> configuration.
>>
>> Most applications such as l2fwd/l3fwd don't provide the means to
>> change offload configuration, so it will use the auto selection's io
>> burst function.
>>
>> This patch support runtime config to select io burst function, which
>> add two config: rx_func_hint and tx_func_hint, both could assign
>> vec/sve/simple/common.
>>
>> The driver will use the following rules to select io burst func:
>> a. if hint equal vec and meet the vec Rx/Tx usage condition then use
>> the neon function.
>> b. if hint equal sve and meet the sve Rx/Tx usage condition then use
>> the sve function.
>> c. if hint equal simple and meet the simple Rx/Tx usage condition then
>> use the simple function.
>> d. if hint equal common then use the common function.
>> e. if hint not set then:
>> e.1. if meet the vec Rx/Tx usage condition then use the neon function.
>> e.2. if meet the simple Rx/Tx usage condition then use the simple
>> function.
>> e.3. else use the common function.
>>
>> Note: the sve Rx/Tx usage condition based on the vec Rx/Tx usage
>> condition and runtime environment (which must support SVE).
>>
>> In the previous versions, driver will preferred use the sve function
>> when meet the sve Rx/Tx usage condition, but in this case driver could
>> get better performance if use the neon function.
>>
>> Signed-off-by: Chengwen Feng <fengchengwen@huawei.com>
>> Signed-off-by: Min Hu (Connor) <humin29@huawei.com>
>> ---
>>   doc/guides/rel_notes/release_21_05.rst |  1 +
>>   drivers/net/hns3/hns3_ethdev.c         | 74 
>> ++++++++++++++++++++++++++++++++++
>>   drivers/net/hns3/hns3_ethdev.h         | 12 ++++++
>>   drivers/net/hns3/hns3_ethdev_vf.c      |  1 +
>>   drivers/net/hns3/hns3_rxtx.c           | 54 ++++++++++++++++++-------
>>   5 files changed, 128 insertions(+), 14 deletions(-)
>>
> 
> Hi Connor,
> 
> There are two recently added APIs to enable user to select vector datapath:
> 'rte_vect_set_max_simd_bitwidth()'
> 'rte_vect_get_max_simd_bitwidth()'
> 
> Also there is an eal parameter around those APIs: 
> '--force-max-simd-bitwidth'
> 
> I wonder these existing APIs can be utilized to select the vector path 
> instead of adding device args to the PMD, can you please check?

Hi, ferruh,
	we will support the two methods to select IO patch. By the way,
the method of "simd bitwidth" will be supported in next patches, thanks.

> Thanks,
> ferruh
> .

  reply	other threads:[~2021-03-12  0:59 UTC|newest]

Thread overview: 34+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2021-03-10  6:16 [dpdk-dev] [PATCH v2 0/9] features and bugfixes for hns3 Min Hu (Connor)
2021-03-10  6:16 ` [dpdk-dev] [PATCH v2 1/9] net/hns3: support runtime config to select IO burst func Min Hu (Connor)
2021-03-11 17:31   ` Ferruh Yigit
2021-03-12  0:59     ` Min Hu (Connor) [this message]
2021-03-11 17:39   ` Ferruh Yigit
2021-03-12  1:01     ` Min Hu (Connor)
2021-03-10  6:16 ` [dpdk-dev] [PATCH v2 2/9] net/hns3: support Tx push quick doorbell to improve perf Min Hu (Connor)
2021-03-11 18:05   ` Ferruh Yigit
2021-03-12 11:02     ` Min Hu (Connor)
2021-03-10  6:16 ` [dpdk-dev] [PATCH v2 3/9] net/hns3: support for outer UDP cksum Min Hu (Connor)
2021-03-10  6:16 ` [dpdk-dev] [PATCH v2 4/9] net/hns3: adjust the format of RAS related structures Min Hu (Connor)
2021-03-11 18:25   ` Ferruh Yigit
2021-03-12  1:51     ` Min Hu (Connor)
2021-03-12 10:02       ` Ferruh Yigit
2021-03-12 10:51         ` Min Hu (Connor)
2021-03-16 11:32           ` Min Hu (Connor)
2021-03-10  6:16 ` [dpdk-dev] [PATCH v2 5/9] net/hns3: delete redundant xstats RAS statistics Min Hu (Connor)
2021-03-10  6:16 ` [dpdk-dev] [PATCH v2 6/9] net/hns3: support imissed stats for PF/VF Min Hu (Connor)
2021-03-10  6:16 ` [dpdk-dev] [PATCH v2 7/9] net/hns3: support oerrors stats in PF Min Hu (Connor)
2021-03-10  6:16 ` [dpdk-dev] [PATCH v2 8/9] net/hns3: support query Tx descriptor status Min Hu (Connor)
2021-03-10  6:16 ` [dpdk-dev] [PATCH v2 9/9] net/hns3: support query Rx " Min Hu (Connor)
2021-03-12 11:51 ` [dpdk-dev] [PATCH v3 0/8] features and bugfixes for hns3 Min Hu (Connor)
2021-03-12 11:51   ` [dpdk-dev] [PATCH v3 1/8] net/hns3: support runtime config to select IO burst func Min Hu (Connor)
2021-03-16 12:40     ` Ferruh Yigit
2021-03-17  1:14       ` Min Hu (Connor)
2021-03-17 15:28         ` Ferruh Yigit
2021-03-19  1:08           ` Min Hu (Connor)
2021-03-12 11:51   ` [dpdk-dev] [PATCH v3 2/8] net/hns3: support for outer UDP cksum Min Hu (Connor)
2021-03-12 11:51   ` [dpdk-dev] [PATCH v3 3/8] net/hns3: adjust the format of RAS related structures Min Hu (Connor)
2021-03-12 11:51   ` [dpdk-dev] [PATCH v3 4/8] net/hns3: delete redundant xstats RAS statistics Min Hu (Connor)
2021-03-12 11:51   ` [dpdk-dev] [PATCH v3 5/8] net/hns3: support imissed stats for PF/VF Min Hu (Connor)
2021-03-12 11:51   ` [dpdk-dev] [PATCH v3 6/8] net/hns3: support oerrors stats in PF Min Hu (Connor)
2021-03-12 11:51   ` [dpdk-dev] [PATCH v3 7/8] net/hns3: support query Tx descriptor status Min Hu (Connor)
2021-03-12 11:51   ` [dpdk-dev] [PATCH v3 8/8] net/hns3: support query Rx " Min Hu (Connor)

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=eaaa257a-3ed7-8541-e0cb-931720d1995f@huawei.com \
    --to=humin29@huawei.com \
    --cc=ciara.power@intel.com \
    --cc=david.marchand@redhat.com \
    --cc=dev@dpdk.org \
    --cc=ferruh.yigit@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).