From: Ferruh Yigit <ferruh.yigit@intel.com>
To: Dharmik Thakkar <Dharmik.Thakkar@arm.com>,
Bruce Richardson <bruce.richardson@intel.com>
Cc: dpdk-dev <dev@dpdk.org>, nd <nd@arm.com>,
Ed Czeck <ed.czeck@atomicrules.com>,
"jerinj@marvell.com" <jerinj@marvell.com>
Subject: Re: [dpdk-dev] [PATCH 0/6] app/testpmd: add runtime config
Date: Wed, 26 Aug 2020 23:06:43 +0100 [thread overview]
Message-ID: <5a0d20ad-1640-5b4d-35c7-416b890018a6@intel.com> (raw)
In-Reply-To: <45704D4E-35E5-4B9A-8C30-10E027F25744@arm.com>
On 8/26/2020 6:07 PM, Dharmik Thakkar wrote:
>
>
>> On Aug 26, 2020, at 11:41 AM, Bruce Richardson <bruce.richardson@intel.com> wrote:
>>
>> On Wed, Aug 26, 2020 at 05:33:20PM +0100, Ferruh Yigit wrote:
>>> On 7/14/2020 10:51 PM, Dharmik Thakkar wrote:
>>>> Meson build system lacks support for
>>>> CONFIG_RTE_TEST_PMD_RECORD_CORE_CYCLES and
>>>> CONFIG_RTE_TEST_PMD_RECORD_BURST_STATS configuration options.
>>>>
>>>> One solution is to add these options within meson_options.txt
>>>>
>>>> Since adding these as runtime config causes no performance impact,
>>>
>>> Hi Dharmik,
>>>
>>> These are on the datapath, and even disable there will be additional
>>> checks, isn't it expected to have some impact? Did you do any
>>> measurements for it?
>
> Hi Ferruh,
>
> In my measurements, I saw a maximum performance degradation of 0.3% for rx and tx throughput (pps)
> with runtime option (both disabled and enabled cases) when compared to compile time option..
> There was no difference in cycles per packet measurement.
> I did these measurements with Mellanox-ConnectX-5 card on N1SDP server with ’set fwd mac retry’ option.
>
Thanks Dharmik,
0.3% does not look a lot, I also don't get any recognizable drop when the stats
are disabled (there is a drop (up to %15) when stats are enabled but that is OK).
And there is a benefit to have the stats runtime configurable.
This minor drop for runtime configuration looks OK to me, but lets wait a little
more if there is any strong objection to it, we can proceed afterwards.
>
>>>
>> Branches that always predict the same way can be very cheap, and unless
>> proven to be a problem, I'd see no issue with having a few on the datapath
>> - especially if it just one or two per burst. If we start seeing a
>> significant number, or ones that occur for every packet, then we perhaps
>> need to be more cautious.
>>
>> I also think that using lots of different CFLAGS for turning things on and
>> off is as bad - or even worse - than using the old build-time config
>> options, just this time we don't have a single list of them somewhere!
>> Therefore, I think we really need to start converting these to runtime
>> options where we can.
>>
>> Regards,
>> /Bruce
>
>
>
next prev parent reply other threads:[~2020-08-26 22:06 UTC|newest]
Thread overview: 62+ messages / expand[flat|nested] mbox.gz Atom feed top
[not found] <CGME20200506215939eucas1p1fd98a671dda83adf884c30d7bf9b77c4@eucas1p1.samsung.com>
2020-05-06 21:58 ` [dpdk-dev] [PATCH 1/5] app/testpmd: print clock with CPU cycles per pkt Dharmik Thakkar
2020-05-06 21:58 ` [dpdk-dev] [PATCH 2/5] app/testpmd: print fractional part in CPU cycles Dharmik Thakkar
2020-05-07 9:50 ` Ananyev, Konstantin
2020-05-07 22:16 ` Dharmik Thakkar
2020-05-08 17:17 ` Ananyev, Konstantin
2020-05-08 17:36 ` Dharmik Thakkar
2020-05-08 18:08 ` Ananyev, Konstantin
2020-05-06 21:58 ` [dpdk-dev] [PATCH 3/5] doc: add cycles per packet in testpmd user guide Dharmik Thakkar
2020-05-07 5:24 ` Jerin Jacob
2020-05-07 22:27 ` Dharmik Thakkar
2020-05-07 14:30 ` Iremonger, Bernard
2020-05-06 21:58 ` [dpdk-dev] [PATCH 4/5] doc: include config options " Dharmik Thakkar
2020-05-07 14:42 ` Iremonger, Bernard
2020-05-06 21:58 ` [dpdk-dev] [PATCH 5/5] doc: add aarch64 generic counter section Dharmik Thakkar
2020-05-07 5:17 ` Jerin Jacob
2020-05-06 22:48 ` [dpdk-dev] [PATCH 1/5] app/testpmd: print clock with CPU cycles per pkt Lukasz Wojciechowski
2020-05-07 13:38 ` Iremonger, Bernard
2020-05-08 22:38 ` [dpdk-dev] [PATCH v2 " Dharmik Thakkar
2020-05-08 22:38 ` [dpdk-dev] [PATCH v2 2/5] app/testpmd: print fractional part in CPU cycles Dharmik Thakkar
2020-05-12 10:19 ` Iremonger, Bernard
2020-05-08 22:38 ` [dpdk-dev] [PATCH v2 3/5] doc: add cycles per packet in testpmd user guide Dharmik Thakkar
2020-05-12 10:20 ` Iremonger, Bernard
2020-05-15 12:15 ` Ferruh Yigit
2020-05-15 20:33 ` Dharmik Thakkar
2020-05-18 9:47 ` Ferruh Yigit
2020-05-18 21:49 ` Dharmik Thakkar
2020-05-19 8:27 ` Ferruh Yigit
2020-05-20 3:20 ` [dpdk-dev] [PATCH v3 1/2] " Dharmik Thakkar
2020-05-20 3:20 ` [dpdk-dev] [PATCH v3 2/2] doc: include config options " Dharmik Thakkar
2020-06-17 18:21 ` Ferruh Yigit
2020-06-17 19:48 ` Thomas Monjalon
2020-06-19 15:38 ` Dharmik Thakkar
2020-06-19 15:43 ` Thomas Monjalon
2020-06-19 16:13 ` Dharmik Thakkar
2020-06-22 15:26 ` Thomas Monjalon
2020-06-29 14:25 ` Dharmik Thakkar
2020-07-14 21:51 ` [dpdk-dev] [PATCH 0/6] app/testpmd: add runtime config Dharmik Thakkar
2020-07-14 21:51 ` [dpdk-dev] [PATCH 1/6] app/testpmd: add record-core-cycles " Dharmik Thakkar
2020-07-14 21:51 ` [dpdk-dev] [PATCH 2/6] doc: add record-core-cycles to testpmd funcs doc Dharmik Thakkar
2020-07-14 21:51 ` [dpdk-dev] [PATCH 3/6] app/testpmd: add record-burst-stats runtime config Dharmik Thakkar
2020-07-14 21:51 ` [dpdk-dev] [PATCH 4/6] doc: add record-burst-stats to testpmd funcs doc Dharmik Thakkar
2020-07-14 21:51 ` [dpdk-dev] [PATCH 5/6] app/testpmd: enable burst stats for noisy vnf mode Dharmik Thakkar
2020-07-14 21:51 ` [dpdk-dev] [PATCH 6/6] app/testpmd: enable empty polls in 5tswap Dharmik Thakkar
2020-07-15 4:29 ` Phil Yang
2020-08-26 16:33 ` [dpdk-dev] [PATCH 0/6] app/testpmd: add runtime config Ferruh Yigit
2020-08-26 16:41 ` Bruce Richardson
2020-08-26 17:07 ` Dharmik Thakkar
2020-08-26 22:06 ` Ferruh Yigit [this message]
2020-09-10 15:06 ` Ferruh Yigit
2020-08-26 21:24 ` Ferruh Yigit
2020-05-20 14:49 ` [dpdk-dev] [PATCH v3 1/2] doc: add cycles per packet in testpmd user guide Ferruh Yigit
2020-05-21 17:41 ` Ferruh Yigit
2020-05-08 22:38 ` [dpdk-dev] [PATCH v2 4/5] doc: include config options " Dharmik Thakkar
2020-05-12 10:20 ` Iremonger, Bernard
2020-05-19 7:42 ` Thomas Monjalon
2020-05-19 22:58 ` Dharmik Thakkar
2020-05-20 7:53 ` Thomas Monjalon
2020-05-20 22:39 ` Dharmik Thakkar
2020-05-19 7:45 ` Thomas Monjalon
2020-05-08 22:38 ` [dpdk-dev] [PATCH v2 5/5] doc: add aarch64 generic counter section Dharmik Thakkar
2020-05-12 10:18 ` [dpdk-dev] [PATCH v2 1/5] app/testpmd: print clock with CPU cycles per pkt Iremonger, Bernard
2020-05-15 12:23 ` 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=5a0d20ad-1640-5b4d-35c7-416b890018a6@intel.com \
--to=ferruh.yigit@intel.com \
--cc=Dharmik.Thakkar@arm.com \
--cc=bruce.richardson@intel.com \
--cc=dev@dpdk.org \
--cc=ed.czeck@atomicrules.com \
--cc=jerinj@marvell.com \
--cc=nd@arm.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).