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 <redacted>
Sent: 30 November 2018 20:13
To: Verma, Shally <redacted>; Trahe, Fiona <redacted>; Daly, Lee <redacted>
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

quoted

-----Original Message-----
From: Verma, Shally [mailto:Shally.Verma@cavium.com]
Sent: Wednesday, October 17, 2018 6:48 PM
To: Trahe, Fiona <redacted>; Daly, Lee <redacted>
Cc: Jozwiak, TomaszX <redacted>; dev@dpdk.org;
akhil.goyal@nxp.com
Subject: RE: [dpdk-dev] [PATCH 2/3] app/compress-perf: add performance
measurement

quoted

-----Original Message-----
From: Trahe, Fiona <redacted>
Sent: 17 October 2018 22:15
To: Verma, Shally <redacted>; Daly, Lee
[off-list ref]
Cc: Jozwiak, TomaszX <redacted>; dev@dpdk.org;
akhil.goyal@nxp.com; Trahe, Fiona [off-list ref]
Subject: RE: [dpdk-dev] [PATCH 2/3] app/compress-perf: add performance
measurement

External Email

quoted

-----Original Message-----
From: Verma, Shally [mailto:Shally.Verma@cavium.com]
Sent: Wednesday, October 17, 2018 8:43 AM
To: Trahe, Fiona <redacted>; Daly, Lee
[off-list ref]
Cc: Jozwiak, TomaszX <redacted>; dev@dpdk.org;
akhil.goyal@nxp.com
Subject: RE: [dpdk-dev] [PATCH 2/3] app/compress-perf: add
performance measurement

quoted

-----Original Message-----
From: Trahe, Fiona <redacted>
Sent: 17 October 2018 20:04
To: Daly, Lee <redacted>; Verma, Shally
[off-list ref]
Cc: Jozwiak, TomaszX <redacted>; dev@dpdk.org;
akhil.goyal@nxp.com; Trahe, Fiona

[off-list ref]

quoted

Subject: RE: [dpdk-dev] [PATCH 2/3] app/compress-perf: add
performance measurement

External Email

Hi Shally, Lee,

quoted

-----Original Message-----
From: Daly, Lee
Sent: Monday, October 15, 2018 8:10 AM
To: Verma, Shally <redacted>
Cc: Jozwiak, TomaszX <redacted>; dev@dpdk.org;
Trahe, Fiona [off-list ref]; 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.

quoted

-----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 <redacted>;

dev@dpdk.org;

quoted

quoted

quoted

quoted

quoted

Trahe, Fiona [off-list ref]; akhil.goyal@nxp.com; De
Lara Guarch, Pablo [off-list ref]
Cc: De@dpdk.org; Lara@dpdk.org; Guarch@dpdk.org
Subject: Re: [dpdk-dev] [PATCH 2/3] app/compress-perf: add
performance measurement

///

quoted

quoted

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.

quoted

quoted

quoted

[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.

quoted

quoted

quoted

This perf-tool max-num-sgl-segs is so the user can pick a value <=

whatever the PMD's max is.

quoted

quoted

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.

quoted

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.

quoted

Ok?

Yea. Sounds better.