DPDK patches and discussions
 help / color / mirror / Atom feed
From: Patrick Robb <probb@iol.unh.edu>
To: "Morten Brørup" <mb@smartsharesystems.com>
Cc: Nicholas Pratte <npratte@iol.unh.edu>,
	paul.szczepanek@arm.com,  juraj.linkes@pantheon.tech,
	yoan.picchi@foss.arm.com, thomas@monjalon.net,
	 wathsala.vithanage@arm.com, Honnappa.Nagarahalli@arm.com,
	dev@dpdk.org,  Jeremy Spewock <jspewock@iol.unh.edu>
Subject: Re: [PATCH] dts: Change hugepage runtime config to 2MB Exclusively
Date: Sat, 6 Apr 2024 15:20:32 -0400	[thread overview]
Message-ID: <CAJvnSUA2eV46jkVo_5Utn-wbCGrn_CKujEb8SBR20rN2eQFgsA@mail.gmail.com> (raw)
In-Reply-To: <98CBD80474FA8B44BF855DF32C47DC35E9F36D@smartserver.smartshare.dk>

On Sat, Apr 6, 2024 at 4:47 AM Morten Brørup <mb@smartsharesystems.com> wrote:
>
>
> This change seems very CPU specific.
>
> E.g. in x86 32-bit mode, the hugepage size is 4 MB, not 2 MB.
>
> I don't know the recommended hugepage size on other architectures.
>

Thanks Morten, that's an important insight which we weren't aware of
when we initially discussed this ticket.

We read on some dpdk docs that 1gb hugepages should be set at boot (I
think the reason is because that's when you can guarantee there is gbs
of contiguous available memory), and that after boot, only 2gb
hugepages should be set. I assume that even for other arches which
don't support the 2mb pages specifically, we still want to allocate
hugepages using the smallest page size possible per arch (for the same
reason).

So I think we can add some dict which stores the smallest valid
hugepage size per arch. Then during config init, use the config's arch
value to determine that size, and set the total hugepages allocation
based on that size and the hugepages count set in the conf.yaml. Or
maybe we can store the list of all valid hugepgage sizes per arch
(which are also valid to be set post boot), allow for a new
hugepage_size value on the conf.yaml, validate the input at config
init, and then set according to those values. I prefer the former
option though as I don't think the added flexibility offered by the
latter seems important.

  reply	other threads:[~2024-04-06 19:20 UTC|newest]

Thread overview: 20+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2024-04-04 15:31 Nicholas Pratte
2024-04-05 14:27 ` Patrick Robb
2024-04-06  8:47 ` Morten Brørup
2024-04-06 19:20   ` Patrick Robb [this message]
2024-04-06 22:04     ` Morten Brørup
2024-04-08  8:10       ` Bruce Richardson
2024-04-08  9:35         ` Morten Brørup
2024-04-09 16:57           ` Nicholas Pratte
2024-04-09 17:28 ` [PATCH v2] " Nicholas Pratte
2024-04-10  7:23   ` Morten Brørup
2024-04-10 13:50     ` Patrick Robb
2024-04-10 10:43   ` Juraj Linkeš
2024-04-16 18:18 ` [PATCH v3] " Nicholas Pratte
2024-04-16 18:25   ` Morten Brørup
2024-04-16 18:26   ` Nicholas Pratte
2024-04-17 13:46   ` Juraj Linkeš
2024-04-18 16:10 ` [PATCH v4] " Nicholas Pratte
2024-04-25  8:00   ` Juraj Linkeš
2024-04-29 17:26     ` Nicholas Pratte
2024-04-30  8:42       ` Juraj Linkeš

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=CAJvnSUA2eV46jkVo_5Utn-wbCGrn_CKujEb8SBR20rN2eQFgsA@mail.gmail.com \
    --to=probb@iol.unh.edu \
    --cc=Honnappa.Nagarahalli@arm.com \
    --cc=dev@dpdk.org \
    --cc=jspewock@iol.unh.edu \
    --cc=juraj.linkes@pantheon.tech \
    --cc=mb@smartsharesystems.com \
    --cc=npratte@iol.unh.edu \
    --cc=paul.szczepanek@arm.com \
    --cc=thomas@monjalon.net \
    --cc=wathsala.vithanage@arm.com \
    --cc=yoan.picchi@foss.arm.com \
    /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).