DPDK patches and discussions
 help / color / mirror / Atom feed
From: Bruce Richardson <bruce.richardson@intel.com>
To: "Morten Brørup" <mb@smartsharesystems.com>
Cc: <dev@dpdk.org>, <ferruh.yigit@amd.com>, <thomas@monjalon.net>
Subject: Re: [RFC PATCH] config: make queues per port a meson config option
Date: Mon, 12 Aug 2024 16:09:08 +0100	[thread overview]
Message-ID: <ZrollIQ-nzYsyAeQ@bricha3-mobl1.ger.corp.intel.com> (raw)
In-Reply-To: <98CBD80474FA8B44BF855DF32C47DC35E9F620@smartserver.smartshare.dk>

On Mon, Aug 12, 2024 at 05:02:11PM +0200, Morten Brørup wrote:
> > From: Bruce Richardson [mailto:bruce.richardson@intel.com]
> > 
> > On Mon, Aug 12, 2024 at 04:10:49PM +0200, Morten Brørup wrote:
> > > > From: Bruce Richardson [mailto:bruce.richardson@intel.com]
> > > >
> > > > The default number of ethernet queues per port is currently set to
> > > > 1k which is more than enough for most applications, but still is lower
> > > > than the total number of queues which may be available on modern NICs.
> > > > Rather than increasing the max queues further, which will increase
> > > > the memory footprint (since the value is used in array dimensioning),
> > > > we can instead make the value a meson tunable option - and reduce the
> > > > default value to 256 in the process.
> > >
> > > Overall, I agree that this tunable is not very exotic, and can be exposed as
> > suggested.
> > > The reduction of the default value must be mentioned in the release notes.
> > >
> > 
> > Yes, good point. I'll add that in any next version.
> 
> ACK.
> 
> > 
> > >
> > > >  # set other values pulled from the build options
> > > >  dpdk_conf.set('RTE_MAX_ETHPORTS', get_option('max_ethports'))
> > > > +dpdk_conf.set('RTE_MAX_QUEUES_PER_PORT',
> > > > get_option('max_queues_per_ethport'))
> > >
> > > Please rename RTE_MAX_QUEUES_PER_PORT to _PER_ETHPORT, so it resembles
> > MAX_ETHPORTS. For API backwards compatibility, you can add:
> > > #define RTE_MAX_QUEUES_PER_PORT RTE_MAX_QUEUES_PER_ETHPORT
> > >
> > 
> > Agree that would more consistent. That would probably best be a separate
> > patch, since we'd want to convert all internal use over. Will make this a
> > two-patch set in next version.
> 
> ACK. And agree about two-patch series.
> 
> > 
> > >
> > > I wonder if it would be possible to have separate max sizes for RX and TX
> > queues? If it can save a non-negligible amount of memory, it might be useful
> > for some applications.
> > >
> > 
> > That is an interesting idea. It would certainly allow saving memory for
> > use-cases where you want a large number of rx queues only, or tx queues
> > only. However, the defaults are still likely to remain the same. The main
> > issue I would have with it, is that it would mean having two build time
> > options rather than 1, and I'm a bit concerned at the number of options we
> > seem to be accumulating in DPDK.
> > 
> > Overall, I'm tending towards suggesting that we not do that split, but I'm
> > open to being convinced on it.
> 
> I would guess that many applications have an asymmetrical split of number of RX/TX queues. So I would argue that:
> The reason to make this configurable in meson is to conserve memory, so why only go half the way if there is more memory to be conserved?
> 
> The distros will use oversize maximums anyway, but custom built applications might benefit.
> 
> Here's a weird thought:
> Perhaps RX and TX maximums can be controlled individually by changing rte_config.h, and they can be overridden via one meson configuration parameter to set both (to the same value).
> 
> > 
> > >
> > > With suggested changes (splitting RX/TX maximums not required),
> > > Acked-by: Morten Brørup <mb@smartsharesystems.com>
> > >
> 
> My ACK remains; splitting RX/TX maximums is not Must Have, it is Nice To Have.
>
Let me see how much in involved in trying to split... 

  reply	other threads:[~2024-08-12 15:09 UTC|newest]

Thread overview: 72+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2024-08-12 13:29 Bruce Richardson
2024-08-12 14:10 ` Morten Brørup
2024-08-12 14:18   ` Bruce Richardson
2024-08-12 15:02     ` Morten Brørup
2024-08-12 15:09       ` Bruce Richardson [this message]
2024-08-13 15:59 ` [RFC PATCH v2 00/26] add meson config options for queues per port Bruce Richardson
2024-08-13 15:59   ` [RFC PATCH v2 01/26] cryptodev: remove use of ethdev max queues definition Bruce Richardson
2024-08-13 15:59   ` [RFC PATCH v2 02/26] eventdev: remove use of ethev queues define Bruce Richardson
2024-08-13 15:59   ` [RFC PATCH v2 03/26] app/test-bbdev: remove use of ethdev queue count value Bruce Richardson
2024-08-13 15:59   ` [RFC PATCH v2 04/26] config: add separate defines for max Rx and Tx queues Bruce Richardson
2024-08-13 15:59   ` [RFC PATCH v2 05/26] ethdev: use separate Rx and Tx queue limits Bruce Richardson
2024-08-13 15:59   ` [RFC PATCH v2 06/26] bpf: " Bruce Richardson
2024-08-13 15:59   ` [RFC PATCH v2 07/26] latencystats: " Bruce Richardson
2024-08-13 15:59   ` [RFC PATCH v2 08/26] pdump: " Bruce Richardson
2024-08-13 15:59   ` [RFC PATCH v2 09/26] power: " Bruce Richardson
2024-08-13 15:59   ` [RFC PATCH v2 10/26] net/af_xdp: " Bruce Richardson
2024-08-13 15:59   ` [RFC PATCH v2 11/26] net/cnxk: " Bruce Richardson
2024-08-13 15:59   ` [RFC PATCH v2 12/26] net/failsafe: " Bruce Richardson
2024-08-13 15:59   ` [RFC PATCH v2 13/26] net/hns3: " Bruce Richardson
2024-08-13 15:59   ` [RFC PATCH v2 14/26] net/mlx5: " Bruce Richardson
2024-08-13 15:59   ` [RFC PATCH v2 15/26] net/null: " Bruce Richardson
2024-08-13 15:59   ` [RFC PATCH v2 16/26] net/sfc: " Bruce Richardson
2024-08-13 15:59   ` [RFC PATCH v2 17/26] net/thunderx: " Bruce Richardson
2024-08-13 15:59   ` [RFC PATCH v2 18/26] net/vhost: " Bruce Richardson
2024-08-13 15:59   ` [RFC PATCH v2 19/26] app/dumpcap: " Bruce Richardson
2024-08-13 15:59   ` [RFC PATCH v2 20/26] app/test-pmd: " Bruce Richardson
2024-08-13 15:59   ` [RFC PATCH v2 21/26] examples/ipsec-secgw: " Bruce Richardson
2024-08-13 15:59   ` [RFC PATCH v2 22/26] examples/l3fwd-power: " Bruce Richardson
2024-08-13 16:00   ` [RFC PATCH v2 23/26] examples/l3fwd: " Bruce Richardson
2024-08-13 16:00   ` [RFC PATCH v2 24/26] examples/vhost: " Bruce Richardson
2024-08-13 16:00   ` [RFC PATCH v2 25/26] config: make queues per port a meson config option Bruce Richardson
2024-08-13 16:00   ` [RFC PATCH v2 26/26] config: add computed max queues define for compatibility Bruce Richardson
2024-08-14 15:01     ` Stephen Hemminger
2024-08-14 15:12       ` Bruce Richardson
2024-08-14  7:43   ` [RFC PATCH v2 00/26] add meson config options for queues per port Morten Brørup
2024-08-14  7:48   ` Morten Brørup
2024-08-14  7:51     ` Bruce Richardson
2024-08-14 10:49 ` [PATCH v3 " Bruce Richardson
2024-08-14 10:49   ` [PATCH v3 01/26] cryptodev: remove use of ethdev max queues definition Bruce Richardson
2024-09-19 13:16     ` David Marchand
2024-08-14 10:49   ` [PATCH v3 02/26] eventdev: remove use of ethev queues define Bruce Richardson
2024-08-14 10:49   ` [PATCH v3 03/26] app/test-bbdev: remove use of ethdev queue count value Bruce Richardson
2024-09-19 13:36     ` David Marchand
2024-08-14 10:49   ` [PATCH v3 04/26] config: add separate defines for max Rx and Tx queues Bruce Richardson
2024-09-10  2:54     ` fengchengwen
2024-10-10 16:27       ` Stephen Hemminger
2024-10-10 16:32         ` Bruce Richardson
2024-08-14 10:49   ` [PATCH v3 05/26] ethdev: use separate Rx and Tx queue limits Bruce Richardson
2024-08-14 10:49   ` [PATCH v3 06/26] bpf: " Bruce Richardson
2024-08-14 10:49   ` [PATCH v3 07/26] latencystats: " Bruce Richardson
2024-08-14 10:49   ` [PATCH v3 08/26] pdump: " Bruce Richardson
2024-08-14 10:49   ` [PATCH v3 09/26] power: " Bruce Richardson
2024-08-14 10:49   ` [PATCH v3 10/26] net/af_xdp: " Bruce Richardson
2024-08-14 10:49   ` [PATCH v3 11/26] net/cnxk: " Bruce Richardson
2024-08-14 10:49   ` [PATCH v3 12/26] net/failsafe: " Bruce Richardson
2024-08-14 10:49   ` [PATCH v3 13/26] net/hns3: " Bruce Richardson
2024-08-14 10:49   ` [PATCH v3 14/26] net/mlx5: " Bruce Richardson
2024-08-14 10:49   ` [PATCH v3 15/26] net/null: " Bruce Richardson
2024-08-14 10:49   ` [PATCH v3 16/26] net/sfc: " Bruce Richardson
2024-08-14 10:49   ` [PATCH v3 17/26] net/thunderx: " Bruce Richardson
2024-08-14 10:49   ` [PATCH v3 18/26] net/vhost: " Bruce Richardson
2024-08-14 10:49   ` [PATCH v3 19/26] app/dumpcap: " Bruce Richardson
2024-10-03 23:38     ` Stephen Hemminger
2024-08-14 10:49   ` [PATCH v3 20/26] app/test-pmd: " Bruce Richardson
2024-08-14 10:49   ` [PATCH v3 21/26] examples/ipsec-secgw: " Bruce Richardson
2024-08-14 10:49   ` [PATCH v3 22/26] examples/l3fwd-power: " Bruce Richardson
2024-08-14 10:49   ` [PATCH v3 23/26] examples/l3fwd: " Bruce Richardson
2024-08-14 10:49   ` [PATCH v3 24/26] examples/vhost: " Bruce Richardson
2024-08-14 10:49   ` [PATCH v3 25/26] config: make queues per port a meson config option Bruce Richardson
2024-08-14 10:49   ` [PATCH v3 26/26] config: add computed max queues define for compatibility Bruce Richardson
2024-09-19 14:14   ` [PATCH v3 00/26] add meson config options for queues per port David Marchand
2024-09-19 15:08     ` Bruce Richardson

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=ZrollIQ-nzYsyAeQ@bricha3-mobl1.ger.corp.intel.com \
    --to=bruce.richardson@intel.com \
    --cc=dev@dpdk.org \
    --cc=ferruh.yigit@amd.com \
    --cc=mb@smartsharesystems.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).