DPDK patches and discussions
 help / color / mirror / Atom feed
From: John Levon <john.levon@nutanix.com>
To: Dmitry Kozlyuk <dmitry.kozliuk@gmail.com>
Cc: "anatoly.burakov@intel.com" <anatoly.burakov@intel.com>,
	"dev@dpdk.org" <dev@dpdk.org>,
	"levon@movementarian.org" <levon@movementarian.org>
Subject: Re: [dpdk-dev] [PATCH RESEND] eal: allow hugetlbfs sub-directories
Date: Wed, 7 Jul 2021 21:58:14 +0000	[thread overview]
Message-ID: <20210707215814.GC400666@movementarian.org> (raw)
In-Reply-To: <20210707230605.58a79a47@sovereign>

On Wed, Jul 07, 2021 at 11:06:05PM +0300, Dmitry Kozlyuk wrote:

> > get_hugepage_dir() was implemented in such a way that a --huge-dir option
> > had to exactly match the mountpoint, but there's no reason for this
> > restriction. Fix the implementation to allow a sub-directory within a
> > suitable hugetlbfs mountpoint to be specified.
> > 
> > Signed-off-by: John Levon <john.levon@nutanix.com>
> > ---
> >  lib/eal/linux/eal_hugepage_info.c | 25 +++++++++++++++++++------
> >  1 file changed, 19 insertions(+), 6 deletions(-)
> > 
> > diff --git a/lib/eal/linux/eal_hugepage_info.c b/lib/eal/linux/eal_hugepage_info.c
> > index d97792cad..d7e9918f8 100644
> > --- a/lib/eal/linux/eal_hugepage_info.c
> > +++ b/lib/eal/linux/eal_hugepage_info.c
> > @@ -226,16 +226,29 @@ get_hugepage_dir(uint64_t hugepage_sz, char *hugedir, int len)
> >  		default_size = get_default_hp_size();
> >  
> >  	while (fgets(buf, sizeof(buf), fd)){
> > +		const char *dir;
> > +
> >  		if (rte_strsplit(buf, sizeof(buf), splitstr, _FIELDNAME_MAX,
> >  				split_tok) != _FIELDNAME_MAX) {
> >  			RTE_LOG(ERR, EAL, "Error parsing %s\n", proc_mounts);
> >  			break; /* return NULL */
> >  		}
> >  
> > -		/* we have a specified --huge-dir option, only examine that dir */
> > -		if (internal_conf->hugepage_dir != NULL &&
> > -				strcmp(splitstr[MOUNTPT], internal_conf->hugepage_dir) != 0)
> > -			continue;
> > +		dir = splitstr[MOUNTPT];
> > +
> > +		/*
> > +		 * If a --huge-dir option has been specified, only examine
> > +		 * mounts that contain that directory, and make sure to return
> > +		 * the directory, not the mount.
> > +		 */
> > +		if (internal_conf->hugepage_dir != NULL) {
> > +			if (strncmp(internal_conf->hugepage_dir,
> > +				splitstr[MOUNTPT],
> > +				strlen(splitstr[MOUNTPT])) != 0)
> > +				continue;
> > +
> > +			dir = internal_conf->hugepage_dir;
> > +		}
> 
> Suppose there are /mnt/huge and /mnt/huge-2M mounted with -o pagesize=2M.
> If --huge-dir=/mnt/huge-2M is specified, this code will select /mnt/huge.

Yeah, good spot. I'll change it to prefer closer matches or something.

> The code would be shorter with `splitstr[MOUNTPT]` -> `dir`.

Sure.

regards
john

  reply	other threads:[~2021-07-07 21:58 UTC|newest]

Thread overview: 19+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2021-06-10 21:05 [dpdk-dev] [PATCH] " John Levon
2021-06-25 10:44 ` [dpdk-dev] [PATCH RESEND] " John Levon
2021-07-06  9:43   ` David Marchand
2021-07-07 20:06   ` Dmitry Kozlyuk
2021-07-07 21:58     ` John Levon [this message]
2021-07-08  9:36     ` [dpdk-dev] [PATCH] " John Levon
2021-07-08  9:36       ` John Levon
2021-07-08 10:59     ` [dpdk-dev] [PATCH v3] " John Levon
2021-07-15 22:37       ` Dmitry Kozlyuk
2021-07-22 20:29       ` David Marchand
2021-07-22 21:06         ` John Levon
2021-07-23  7:29           ` Thomas Monjalon
2021-08-09 11:24             ` [dpdk-dev] [PATCH] " John Levon
2021-08-09 13:45               ` Jerin Jacob
2021-08-17 20:05               ` John Levon
2021-10-12 12:38                 ` David Marchand
2021-10-12 16:05                   ` [dpdk-dev] [PATCH] eal/linux: " John Levon
2021-10-12 19:03                     ` David Marchand
2021-10-12 19:58                       ` John Levon

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=20210707215814.GC400666@movementarian.org \
    --to=john.levon@nutanix.com \
    --cc=anatoly.burakov@intel.com \
    --cc=dev@dpdk.org \
    --cc=dmitry.kozliuk@gmail.com \
    --cc=levon@movementarian.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).