From: Panu Matilainen <pmatilai@redhat.com>
To: David Marchand <david.marchand@6wind.com>
Cc: "dev@dpdk.org" <dev@dpdk.org>
Subject: Re: [dpdk-dev] [PATCH] eal: default to one memory channel if not specified
Date: Wed, 14 Oct 2015 15:04:43 +0300 [thread overview]
Message-ID: <561E44DB.9000307@redhat.com> (raw)
In-Reply-To: <CALwxeUuz12PmccAvt=kWCKHYzoO4z5LLXCdZd=j4Pyu-4+Butg@mail.gmail.com>
On 10/14/2015 02:45 PM, David Marchand wrote:
> Hello Panu,
>
> On Wed, Oct 14, 2015 at 12:22 PM, Panu Matilainen <pmatilai@redhat.com
> <mailto:pmatilai@redhat.com>> wrote:
>
> Obtaining the correct value, especially from a running system, can
> be anything from difficult to plain impossible. Since the value is
> merely an optimization and does not affect functionality otherwise,
> its pointless to force such a guess on users initially, such things
> belong to performance tuning phase.
>
> Signed-off-by: Panu Matilainen <pmatilai@redhat.com
> <mailto:pmatilai@redhat.com>>
> ---
> lib/librte_eal/common/eal_common_options.c | 10 ++--------
> 1 file changed, 2 insertions(+), 8 deletions(-)
>
> diff --git a/lib/librte_eal/common/eal_common_options.c
> b/lib/librte_eal/common/eal_common_options.c
> index 1f459ac..28f10a2 100644
> --- a/lib/librte_eal/common/eal_common_options.c
> +++ b/lib/librte_eal/common/eal_common_options.c
> @@ -104,7 +104,7 @@ eal_reset_internal_config(struct internal_config
> *internal_cfg)
>
> internal_cfg->memory = 0;
> internal_cfg->force_nrank = 0;
> - internal_cfg->force_nchannel = 0;
> + internal_cfg->force_nchannel = 1;
>
>
> Well, not too sure about this default value.
>
> - mempool code is already checking for the 0 value.
Yeah, I noticed it already handles the zero case.
> - API already tells for rte_memory_get_nchannel() :
> * @return
> * The number of memory channels on the system. The value is 0 if
> unknown
> * or not the same on all devices.
...but missed this one, and thought it'd be "safer" to return some
non-zero value since callers might be expecting it to be a valid -n value.
>
> So, I would let it 0.
Right, so just drop the default value, reword commit message accordingly
and resend. Will do unless there are other objections.
- Panu -
next prev parent reply other threads:[~2015-10-14 12:04 UTC|newest]
Thread overview: 15+ messages / expand[flat|nested] mbox.gz Atom feed top
2015-10-14 10:22 Panu Matilainen
2015-10-14 11:45 ` David Marchand
2015-10-14 12:04 ` Panu Matilainen [this message]
2015-10-14 13:05 ` Bruce Richardson
2015-10-15 11:49 ` [dpdk-dev] [PATCH 0/2] Provide reasonable default to -n Panu Matilainen
2015-10-15 11:49 ` [dpdk-dev] [PATCH 1/2] mempool: use a better default for number of memory channels Panu Matilainen
2015-10-15 11:49 ` [dpdk-dev] [PATCH 2/2] eal: make the -n argument optional Panu Matilainen
2015-10-15 12:03 ` [dpdk-dev] [PATCH 0/2] Provide reasonable default to -n David Marchand
2015-10-26 16:51 ` Thomas Monjalon
2015-10-15 12:10 ` Mcnamara, John
2015-10-15 12:36 ` Panu Matilainen
2015-10-15 13:12 ` Mcnamara, John
2015-10-26 16:50 ` Thomas Monjalon
2015-10-26 16:56 ` Thomas Monjalon
2015-10-27 7:19 ` Panu Matilainen
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=561E44DB.9000307@redhat.com \
--to=pmatilai@redhat.com \
--cc=david.marchand@6wind.com \
--cc=dev@dpdk.org \
/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).