DPDK patches and discussions
 help / color / mirror / Atom feed
From: "Morten Brørup" <mb@smartsharesystems.com>
To: "Thomas Monjalon" <thomas@monjalon.net>
Cc: <andrew.rybchenko@oktetlabs.ru>, <fengchengwen@huawei.com>,
	<dev@dpdk.org>
Subject: RE: [PATCH v5] mempool: test performance with larger bursts
Date: Tue, 20 Feb 2024 14:49:28 +0100	[thread overview]
Message-ID: <98CBD80474FA8B44BF855DF32C47DC35E9F237@smartserver.smartshare.dk> (raw)
In-Reply-To: <3522622.fIoEIV5pvu@thomas>

> From: Thomas Monjalon [mailto:thomas@monjalon.net]
> Sent: Sunday, 18 February 2024 19.04
> 
> 24/01/2024 12:21, Morten Brørup:
> > --- a/app/test/test_mempool_perf.c
> > +++ b/app/test/test_mempool_perf.c
> > @@ -1,6 +1,6 @@
> >  /* SPDX-License-Identifier: BSD-3-Clause
> >   * Copyright(c) 2010-2014 Intel Corporation
> > - * Copyright(c) 2022 SmartShare Systems
> > + * Copyright(c) 2022-2024 SmartShare Systems
> 
> You don't need to update copyright year.
> The first year is the only important one.
> 
> reading: https://matija.suklje.name/how-and-why-to-properly-write-
> copyright-statements-in-your-code#why-not-bump-the-year-on-change

Thank you, Thomas. Very informative.
Will fix in next version.

> 
> [...]
> >  REGISTER_PERF_TEST(mempool_perf_autotest, test_mempool_perf);
> > +REGISTER_PERF_TEST(mempool_perf_autotest_1core,
> test_mempool_perf_1core);
> > +REGISTER_PERF_TEST(mempool_perf_autotest_2cores,
> test_mempool_perf_2cores);
> 
> How do we make sure the test is skipped if we have only 1 core?

Good point. Will fix in next version.

> 
> > +REGISTER_PERF_TEST(mempool_perf_autotest_allcores,
> test_mempool_perf_allcores);
> 
> How the test duration is changed after this patch?
> 

On my test machine, the expanded test parameter set increased the duration of one test run from 20 minutes to 100 minutes.
Before the patch, all three test runs were always executed, i.e. a total duration of 60 minutes.

In other words:
The expanded test parameter set increased the test run duration by factor five.
Introducing the ability to optionally only test with a specific number of lcores reduced the total test duration to a third.


  reply	other threads:[~2024-02-20 13:49 UTC|newest]

Thread overview: 15+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2024-01-21  4:52 [PATCH] " Morten Brørup
2024-01-22  7:10 ` fengchengwen
2024-01-22 14:34 ` [PATCH v2] " Morten Brørup
2024-01-24  2:41   ` fengchengwen
2024-01-24  8:58 ` [PATCH v3] " Morten Brørup
2024-01-24  9:10 ` [PATCH v4] " Morten Brørup
2024-01-24 11:21 ` [PATCH v5] " Morten Brørup
2024-02-18 18:03   ` Thomas Monjalon
2024-02-20 13:49     ` Morten Brørup [this message]
2024-02-21 10:22       ` Thomas Monjalon
2024-02-21 10:38         ` Morten Brørup
2024-02-21 10:40           ` Bruce Richardson
2024-02-20 14:01 ` [PATCH v6] " Morten Brørup
2024-03-02 20:04 ` [PATCH v7] " Morten Brørup
2024-04-04  9:26   ` Morten Brørup

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=98CBD80474FA8B44BF855DF32C47DC35E9F237@smartserver.smartshare.dk \
    --to=mb@smartsharesystems.com \
    --cc=andrew.rybchenko@oktetlabs.ru \
    --cc=dev@dpdk.org \
    --cc=fengchengwen@huawei.com \
    --cc=thomas@monjalon.net \
    /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).