DPDK usage discussions
 help / color / mirror / Atom feed
From: "Burakov, Anatoly" <anatoly.burakov@intel.com>
To: "Kinsella, Ray" <ray.kinsella@intel.com>,
	Nick Tian <nick.tian@longsailingsemi.com>,
	"users@dpdk.org" <users@dpdk.org>
Subject: RE: About memory coherency
Date: Tue, 9 Aug 2022 09:25:23 +0000	[thread overview]
Message-ID: <BN6PR11MB125164A08261BFDCD5FBB1D9F7629@BN6PR11MB1251.namprd11.prod.outlook.com> (raw)
In-Reply-To: <PH0PR11MB4776B28D8039FC549FF07BB690629@PH0PR11MB4776.namprd11.prod.outlook.com>

[-- Attachment #1: Type: text/plain, Size: 2361 bytes --]

There are two different issues at play here.

The purpose of “no-huge” flag is to run DPDK without requiring hugepage memory. Originally, this has been done using an anonymous mmap() call – so, this memory was not using any fd’s at all. This presents a problem with vhost-user, because it relies on fd’s for its shared memory implementation. This is what memfd (a relatively recent addition to the kernel) is addressing – it’s enabling usage of vhost-user with no-huge because memfd actually does create an fd to back our memory.

That said, while description says “malloc”, it is technically incorrect because there’s no malloc involved in the process. The “malloc” term is simply shorthand for “use regular memory”, and should be understood in that context.

Thanks,
Anatoly

From: Kinsella, Ray <ray.kinsella@intel.com>
Sent: Tuesday, August 9, 2022 10:04 AM
To: Nick Tian <nick.tian@longsailingsemi.com>; users@dpdk.org
Cc: Burakov, Anatoly <anatoly.burakov@intel.com>
Subject: RE: About memory coherency


I may be incorrect, but is it not simply the case, that when using the no-huge parameter that MAP_HUGETLB is omitted from flags?

Ray K

From: Nick Tian <nick.tian@longsailingsemi.com<mailto:nick.tian@longsailingsemi.com>>
Sent: Tuesday 9 August 2022 03:55
To: users@dpdk.org<mailto:users@dpdk.org>
Subject: About memory coherency

Hi
I am confusing about the "no-huge" option of DPDK 21.11.
The dpdk usage said: --no-huge:Use malloc instead of hugetlbfs.
But when I check the EAL source code, I found some code piece like this:
It's look like "no-huge" option will lead dpdk use memfd_create-->ftruncate-->mmap to reserve memory
and then provide to application with rte_malloc.
Am I right?
If so, what the "malloc" in "use malloc instead of hugelbfs" refer to?

EAL_memory.c
static int eal_legacy_hugepage_init(void){
....
 if (internal_conf->no_hugetlbfs) {
....
#ifdef MEMFD_SUPPORTED
  /* create a memfd and store it in the segment fd table */
  memfd = memfd_create("nohuge", 0);
......
  /* we got an fd - now resize it */
   if (ftruncate(memfd, internal_conf->memory) < 0) {
.....
   fd = memfd;
    flags = MAP_SHARED;   }
....
  prealloc_addr = msl->base_va;
  addr = mmap(prealloc_addr, mem_sz, PROT_READ | PROT_WRITE,
    flags | MAP_FIXED, fd, 0);
...



[-- Attachment #2: Type: text/html, Size: 10204 bytes --]

  reply	other threads:[~2022-08-09  9:25 UTC|newest]

Thread overview: 13+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2022-08-09  2:38 Nick Tian
2022-08-09  2:54 ` Nick Tian
2022-08-09  9:04   ` Kinsella, Ray
2022-08-09  9:25     ` Burakov, Anatoly [this message]
2022-08-09  9:41       ` 回复:RE: " Nick Tian
2022-08-09  9:59         ` Burakov, Anatoly
2022-08-09 11:32         ` 回复:回复:RE: " Nick Tian
2022-08-09 11:44           ` Kinsella, Ray
2022-08-09 11:57             ` Nick Tian
2022-08-09 12:16             ` 回复:回复:RE: " Burakov, Anatoly
2022-08-09 13:05               ` 回复:About memory cohere =?utf-8?Q?ncy ‪nick.tian
2022-08-09 13:13                 ` Burakov, Anatoly
2022-08-09 13:16               ` 回复:回复:RE: About memory coherency Jerin Jacob Kollanukkaran

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=BN6PR11MB125164A08261BFDCD5FBB1D9F7629@BN6PR11MB1251.namprd11.prod.outlook.com \
    --to=anatoly.burakov@intel.com \
    --cc=nick.tian@longsailingsemi.com \
    --cc=ray.kinsella@intel.com \
    --cc=users@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).