From: "Mattias Rönnblom" <hofors@lysator.liu.se>
To: Thomas Monjalon <thomas@monjalon.net>, dev@dpdk.org
Cc: "Mattias Rönnblom" <mattias.ronnblom@ericsson.com>,
"Tyler Retzlaff" <roretzla@linux.microsoft.com>,
"Chengwen Feng" <fengchengwen@huawei.com>,
"Konstantin Ananyev" <konstantin.ananyev@huawei.com>,
"Stephen Hemminger" <stephen@networkplumber.org>,
"Morten Brørup" <mb@smartsharesystems.com>,
"David Marchand" <david.marchand@redhat.com>
Subject: Re: [PATCH] eal: fix lcore variables documentation
Date: Sun, 17 Nov 2024 20:11:43 +0100 [thread overview]
Message-ID: <82fc429d-8a0a-4c51-a68d-90eb7e4cc397@lysator.liu.se> (raw)
In-Reply-To: <20241114170947.35359-1-thomas@monjalon.net>
On 2024-11-14 18:09, Thomas Monjalon wrote:
> The lcore variables API is new in DPDK 24.11,
> that's why the function rte_lcore_var_alloc() was marked experimental.
> To be clearer, the whole header file (including all macros)
> is marked experimental.
>
> A change decreased the default buffer size from 1 MB to 128 kB,
> missing to update the documentation, which is fixed here.
>
> Fixes: 5bce9bed67ad ("eal: add static per-lcore memory allocation facility")
> Fixes: f2fd6c2e080c ("config: limit lcore variable maximum size to 128k")
>
> Signed-off-by: Thomas Monjalon <thomas@monjalon.net>
> ---
> doc/guides/prog_guide/lcore_var.rst | 2 +-
> lib/eal/include/rte_lcore_var.h | 2 ++
> 2 files changed, 3 insertions(+), 1 deletion(-)
>
> diff --git a/doc/guides/prog_guide/lcore_var.rst b/doc/guides/prog_guide/lcore_var.rst
> index b492ad12c6..3d9384bc33 100644
> --- a/doc/guides/prog_guide/lcore_var.rst
> +++ b/doc/guides/prog_guide/lcore_var.rst
> @@ -240,7 +240,7 @@ and huge pages for lcore variables:
> and their use would result in a significant amount of memory going to waste.
> An example: ~256 kB worth of lcore variables are allocated
> by DPDK libraries, PMDs and the application.
> - ``RTE_MAX_LCORE_VAR`` is set to 1 MB and ``RTE_MAX_LCORE`` to 128.
> + ``RTE_MAX_LCORE_VAR`` is set to 128 kB and ``RTE_MAX_LCORE`` to 128.
> With 4 kB OS pages, only the first ~64 pages of each of the 128 per-lcore id slices
> in the (only) ``lcore_var_buffer`` will actually be resident (paged in).
> Here, demand paging saves ~98 MB of memory.
> diff --git a/lib/eal/include/rte_lcore_var.h b/lib/eal/include/rte_lcore_var.h
> index 28d88cd89b..0216a67cab 100644
> --- a/lib/eal/include/rte_lcore_var.h
> +++ b/lib/eal/include/rte_lcore_var.h
> @@ -15,6 +15,8 @@
> *
> * Please refer to the lcore variables' programmer's guide
> * for an overview of this API and its implementation.
> + *
> + * EXPERIMENTAL: this API may change, or be removed, without prior notice.
> */
>
> #include <stddef.h>
Acked-by: Mattias Rönnblom <mattias.ronnblom@ericsson.com>
Thanks!
prev parent reply other threads:[~2024-11-17 19:11 UTC|newest]
Thread overview: 2+ messages / expand[flat|nested] mbox.gz Atom feed top
2024-11-14 17:09 Thomas Monjalon
2024-11-17 19:11 ` Mattias Rönnblom [this message]
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=82fc429d-8a0a-4c51-a68d-90eb7e4cc397@lysator.liu.se \
--to=hofors@lysator.liu.se \
--cc=david.marchand@redhat.com \
--cc=dev@dpdk.org \
--cc=fengchengwen@huawei.com \
--cc=konstantin.ananyev@huawei.com \
--cc=mattias.ronnblom@ericsson.com \
--cc=mb@smartsharesystems.com \
--cc=roretzla@linux.microsoft.com \
--cc=stephen@networkplumber.org \
--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).