From: "Verma, Shally" <Shally.Verma@cavium.com>
To: "Jozwiak, TomaszX" <tomaszx.jozwiak@intel.com>,
"Trahe, Fiona" <fiona.trahe@intel.com>,
"Daly, Lee" <lee.daly@intel.com>
Cc: "dev@dpdk.org" <dev@dpdk.org>,
"akhil.goyal@nxp.com" <akhil.goyal@nxp.com>
Subject: Re: [dpdk-dev] [PATCH 2/3] app/compress-perf: add performance measurement
Date: Sun, 2 Dec 2018 06:39:32 +0000 [thread overview]
Message-ID: <SN6PR07MB515275CF05945C4041033657F0AD0@SN6PR07MB5152.namprd07.prod.outlook.com> (raw)
In-Reply-To: <CA70B6012E3ADB4184D44E025E5FF01B4CCBBC46@HASMSX112.ger.corp.intel.com>
Ok. Then to keep it simple can we keep input sz and max-num-segs-sgl at cmd line input. I don't think segsz is required to input then?
Thanks
Shally
>-----Original Message-----
>From: Jozwiak, TomaszX <tomaszx.jozwiak@intel.com>
>Sent: 30 November 2018 20:13
>To: Verma, Shally <Shally.Verma@cavium.com>; Trahe, Fiona <fiona.trahe@intel.com>; Daly, Lee <lee.daly@intel.com>
>Cc: dev@dpdk.org; akhil.goyal@nxp.com
>Subject: RE: [dpdk-dev] [PATCH 2/3] app/compress-perf: add performance measurement
>
>External Email
>
>Hi Shally,
>
>I'm about of sending V5 of compression-perf tool.
>
>Our performance testing shows that the number of sgls in a chain can be a factor in the performance.
>So we want to keep this on the cmd line for the performance tool.
>There are alternatives, like setting the input size and segment size to get the num segments desired, but I prefer
>to have the option to specify the num segments explicitly.
>We'll document that if the max-num-sgl-segs x seg_sz > input size then segments number in the chain will be lower ( to store all the
>data)
>As regards adding the max_nb_segments_per_sgl into the rte_compressdev_info struct we're investigating
>another workaround to this limitation in QAT, so will leave this off the API unless some other PMD needs it.
>In the meantime we'll document the limitation in QAT.
>
>Please let me know your thoughts.
>
>--
>Tomek
>
>> -----Original Message-----
>> From: Verma, Shally [mailto:Shally.Verma@cavium.com]
>> Sent: Wednesday, October 17, 2018 6:48 PM
>> To: Trahe, Fiona <fiona.trahe@intel.com>; Daly, Lee <lee.daly@intel.com>
>> Cc: Jozwiak, TomaszX <tomaszx.jozwiak@intel.com>; dev@dpdk.org;
>> akhil.goyal@nxp.com
>> Subject: RE: [dpdk-dev] [PATCH 2/3] app/compress-perf: add performance
>> measurement
>>
>>
>>
>> >-----Original Message-----
>> >From: Trahe, Fiona <fiona.trahe@intel.com>
>> >Sent: 17 October 2018 22:15
>> >To: Verma, Shally <Shally.Verma@cavium.com>; Daly, Lee
>> ><lee.daly@intel.com>
>> >Cc: Jozwiak, TomaszX <tomaszx.jozwiak@intel.com>; dev@dpdk.org;
>> >akhil.goyal@nxp.com; Trahe, Fiona <fiona.trahe@intel.com>
>> >Subject: RE: [dpdk-dev] [PATCH 2/3] app/compress-perf: add performance
>> >measurement
>> >
>> >External Email
>> >
>> >> -----Original Message-----
>> >> From: Verma, Shally [mailto:Shally.Verma@cavium.com]
>> >> Sent: Wednesday, October 17, 2018 8:43 AM
>> >> To: Trahe, Fiona <fiona.trahe@intel.com>; Daly, Lee
>> >> <lee.daly@intel.com>
>> >> Cc: Jozwiak, TomaszX <tomaszx.jozwiak@intel.com>; dev@dpdk.org;
>> >> akhil.goyal@nxp.com
>> >> Subject: RE: [dpdk-dev] [PATCH 2/3] app/compress-perf: add
>> >> performance measurement
>> >>
>> >>
>> >>
>> >> >-----Original Message-----
>> >> >From: Trahe, Fiona <fiona.trahe@intel.com>
>> >> >Sent: 17 October 2018 20:04
>> >> >To: Daly, Lee <lee.daly@intel.com>; Verma, Shally
>> >> ><Shally.Verma@cavium.com>
>> >> >Cc: Jozwiak, TomaszX <tomaszx.jozwiak@intel.com>; dev@dpdk.org;
>> >> >akhil.goyal@nxp.com; Trahe, Fiona
>> >> <fiona.trahe@intel.com>
>> >> >Subject: RE: [dpdk-dev] [PATCH 2/3] app/compress-perf: add
>> >> >performance measurement
>> >> >
>> >> >External Email
>> >> >
>> >> >Hi Shally, Lee,
>> >> >
>> >> >> -----Original Message-----
>> >> >> From: Daly, Lee
>> >> >> Sent: Monday, October 15, 2018 8:10 AM
>> >> >> To: Verma, Shally <Shally.Verma@cavium.com>
>> >> >> Cc: Jozwiak, TomaszX <tomaszx.jozwiak@intel.com>; dev@dpdk.org;
>> >> >> Trahe, Fiona <fiona.trahe@intel.com>; akhil.goyal@nxp.com
>> >> >> Subject: RE: [dpdk-dev] [PATCH 2/3] app/compress-perf: add
>> >> >> performance measurement
>> >> >>
>> >> >> Thanks for your input Shally see comments below.
>> >> >>
>> >> >>
>> >> >> I will be reviewing these changes while Tomasz is out this week.
>> >> >>
>> >> >> > -----Original Message-----
>> >> >> > From: dev [mailto:dev-bounces@dpdk.org] On Behalf Of Verma,
>> >> >> > Shally
>> >> >> > Sent: Friday, October 12, 2018 11:16 AM
>> >> >> > To: Jozwiak, TomaszX <tomaszx.jozwiak@intel.com>;
>> dev@dpdk.org;
>> >> >> > Trahe, Fiona <fiona.trahe@intel.com>; akhil.goyal@nxp.com; De
>> >> >> > Lara Guarch, Pablo <pablo.de.lara.guarch@intel.com>
>> >> >> > Cc: De@dpdk.org; Lara@dpdk.org; Guarch@dpdk.org
>> >> >> > Subject: Re: [dpdk-dev] [PATCH 2/3] app/compress-perf: add
>> >> >> > performance measurement
>> >> >> >
>> >> >///
>> >> >
>> >> >> >Also, why do we need --max-num-
>> >> >> > sgl-segs as an input option from user? Shouldn't input_sz and
>> >> >> >seg_sz internally decide on num-segs?
>> >> >> > Or is it added to serve some other different purpose?
>> >> >> Will have to get back to you on this one, seems illogical to get
>> >> >> this input from user, But I will have to do further investigation to find if
>> there was a different purpose.
>> >> >
>> >> >[Fiona] Some PMDs have a limit on how many links can be in an sgl
>> >> >chain, e.g. in QAT case the PMD allocates a pool of internal
>> >> >structures of a suitable size during device initialisation, this is not a hard
>> limit but can be configured in .config to give the user control over the
>> memory resources allocated.
>> >> >This perf-tool max-num-sgl-segs is so the user can pick a value <=
>> whatever the PMD's max is.
>> >>
>> >> Then also, I believe this could be taken care internally by an app.
>> >> App can choose convenient number of sgl segs as per PMD capability
>> >> and input sz and chunk sz selected by user.
>> >> Just my thoughts.
>> >[Fiona] Then we'd need to add this capability to the API, e.g. add
>> >uint16_t max_nb_segments_per_sgl into the rte_compressdev_info struct.
>> >Special case 0 means no limit.
>> >We did consider this before, I can't remember why we didn't do it, I think
>> it's needed.
>> >I'll push an API patch for this in 19.02 and we can remove the
>> >--max-num-sgl-segs param from the performance tool and hardcode it in
>> the tool in the meantime.
>> >Ok?
>> Yea. Sounds better.
next prev parent reply other threads:[~2018-12-02 6:39 UTC|newest]
Thread overview: 76+ messages / expand[flat|nested] mbox.gz Atom feed top
2018-10-01 13:27 [dpdk-dev] [PATCH 0/3] app: add initial version of compress-perf Tomasz Jozwiak
2018-10-01 13:27 ` [dpdk-dev] [PATCH 1/3] app/compress-perf: add parser Tomasz Jozwiak
2018-10-01 13:27 ` [dpdk-dev] [PATCH 2/3] app/compress-perf: add performance measurement Tomasz Jozwiak
2018-10-12 10:15 ` Verma, Shally
2018-10-15 15:10 ` Daly, Lee
2018-10-16 5:18 ` Verma, Shally
2018-10-17 14:33 ` Trahe, Fiona
2018-10-17 15:42 ` Verma, Shally
2018-10-17 16:45 ` Trahe, Fiona
2018-10-17 16:47 ` Verma, Shally
2018-11-30 14:43 ` Jozwiak, TomaszX
2018-12-02 6:39 ` Verma, Shally [this message]
2018-12-05 8:51 ` Jozwiak, TomaszX
2018-11-02 9:59 ` Jozwiak, TomaszX
2018-11-05 8:34 ` Verma, Shally
2018-11-06 8:04 ` Jozwiak, TomaszX
2018-11-06 8:15 ` Verma, Shally
2018-11-06 9:05 ` Jozwiak, TomaszX
2018-11-06 15:39 ` Verma, Shally
2018-11-07 10:18 ` Jozwiak, TomaszX
2018-11-10 0:54 ` Trahe, Fiona
2018-11-12 4:45 ` Verma, Shally
2018-10-01 13:27 ` [dpdk-dev] [PATCH 3/3] doc/guides/tools: add doc file Tomasz Jozwiak
2018-10-16 9:26 ` Kovacevic, Marko
2018-11-02 9:43 ` [dpdk-dev] [PATCH v2 0/3] add initial version of compress-perf Tomasz Jozwiak
2018-11-02 9:44 ` [dpdk-dev] [PATCH v2 1/3] app/compress-perf: add parser Tomasz Jozwiak
2018-11-05 8:40 ` Verma, Shally
2018-11-06 8:30 ` Jozwiak, TomaszX
2018-11-06 8:32 ` Verma, Shally
2018-11-02 9:44 ` [dpdk-dev] [PATCH v2 2/3] app/compress-perf: add performance measurement Tomasz Jozwiak
2018-11-05 8:56 ` Verma, Shally
2018-11-06 8:49 ` Jozwiak, TomaszX
2018-11-06 15:37 ` Verma, Shally
2018-11-07 10:14 ` Jozwiak, TomaszX
2018-11-02 9:44 ` [dpdk-dev] [PATCH v2 3/3] doc/guides/tools: add doc files Tomasz Jozwiak
2018-11-05 8:57 ` Verma, Shally
2018-11-06 8:51 ` Jozwiak, TomaszX
2018-11-02 11:04 ` [dpdk-dev] [PATCH v2 0/3] add initial version of compress-perf Bruce Richardson
2018-11-02 11:12 ` Jozwiak, TomaszX
2018-11-23 13:06 ` [dpdk-dev] [PATCH v3 0/5] " Tomasz Jozwiak
2018-11-23 13:06 ` [dpdk-dev] [PATCH v3 1/5] app/compress-perf: add parser Tomasz Jozwiak
2018-11-23 13:06 ` [dpdk-dev] [PATCH v3 2/5] app/compress-perf: add performance measurement Tomasz Jozwiak
2018-11-23 13:06 ` [dpdk-dev] [PATCH v3 3/5] doc/guides/tools: add doc files Tomasz Jozwiak
2018-11-23 14:52 ` Varghese, Vipin
2018-11-23 14:59 ` Jozwiak, TomaszX
2018-11-23 13:06 ` [dpdk-dev] [PATCH v3 4/5] app/compress-perf: add dynamic compression test Tomasz Jozwiak
2018-11-23 13:06 ` [dpdk-dev] [PATCH v3 5/5] app/compress-perf: code refactoring Tomasz Jozwiak
2018-11-23 14:27 ` [dpdk-dev] [PATCH v4 0/5] add initial version of compress-perf Tomasz Jozwiak
2018-11-23 14:27 ` [dpdk-dev] [PATCH v4 1/5] app/compress-perf: add parser Tomasz Jozwiak
2018-11-23 15:10 ` Varghese, Vipin
2018-11-23 15:24 ` Bruce Richardson
2018-11-23 15:42 ` Jozwiak, TomaszX
2018-11-23 14:27 ` [dpdk-dev] [PATCH v4 2/5] app/compress-perf: add performance measurement Tomasz Jozwiak
2018-11-23 14:27 ` [dpdk-dev] [PATCH v4 3/5] doc/guides/tools: add doc files Tomasz Jozwiak
2018-11-23 15:00 ` Varghese, Vipin
2018-11-23 15:12 ` Jozwiak, TomaszX
2018-11-23 15:26 ` Varghese, Vipin
2018-11-23 14:27 ` [dpdk-dev] [PATCH v4 4/5] app/compress-perf: add dynamic compression test Tomasz Jozwiak
2018-11-23 14:27 ` [dpdk-dev] [PATCH v4 5/5] app/compress-perf: code refactoring Tomasz Jozwiak
2018-12-05 8:47 ` [dpdk-dev] [PATCH v5 0/5] add initial version of compress-perf Tomasz Jozwiak
2018-12-05 8:47 ` [dpdk-dev] [PATCH v5 1/5] app/compress-perf: add parser Tomasz Jozwiak
2018-12-05 8:47 ` [dpdk-dev] [PATCH v5 2/5] app/compress-perf: add performance measurement Tomasz Jozwiak
2018-12-05 8:47 ` [dpdk-dev] [PATCH v5 3/5] doc/guides/tools: add doc files Tomasz Jozwiak
2018-12-05 8:47 ` [dpdk-dev] [PATCH v5 4/5] app/compress-perf: add dynamic compression test Tomasz Jozwiak
2018-12-05 8:47 ` [dpdk-dev] [PATCH v5 5/5] app/compress-perf: code refactoring Tomasz Jozwiak
2018-12-05 15:37 ` [dpdk-dev] [PATCH v5 0/5] add initial version of compress-perf Daly, Lee
2018-12-12 11:54 ` [dpdk-dev] [PATCH v6 " Tomasz Jozwiak
2018-12-17 11:11 ` Verma, Shally
2018-12-12 12:08 ` Tomasz Jozwiak
2018-12-12 12:08 ` [dpdk-dev] [PATCH v6 1/5] app/compress-perf: add parser Tomasz Jozwiak
2018-12-12 12:08 ` [dpdk-dev] [PATCH v6 2/5] app/compress-perf: add performance measurement Tomasz Jozwiak
2018-12-12 12:08 ` [dpdk-dev] [PATCH v6 3/5] doc/guides/tools: add doc files Tomasz Jozwiak
2018-12-12 12:08 ` [dpdk-dev] [PATCH v6 4/5] app/compress-perf: add dynamic compression test Tomasz Jozwiak
2018-12-12 12:08 ` [dpdk-dev] [PATCH v6 5/5] app/compress-perf: code refactoring Tomasz Jozwiak
2018-12-14 19:24 ` [dpdk-dev] [PATCH v6 0/5] add initial version of compress-perf Trahe, Fiona
2018-12-18 10:28 ` Akhil Goyal
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=SN6PR07MB515275CF05945C4041033657F0AD0@SN6PR07MB5152.namprd07.prod.outlook.com \
--to=shally.verma@cavium.com \
--cc=akhil.goyal@nxp.com \
--cc=dev@dpdk.org \
--cc=fiona.trahe@intel.com \
--cc=lee.daly@intel.com \
--cc=tomaszx.jozwiak@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).