DPDK patches and discussions
 help / color / mirror / Atom feed
From: Thomas Monjalon <thomas@monjalon.net>
To: "Morten Brørup" <mb@smartsharesystems.com>
Cc: dev@dpdk.org, olivier.matz@6wind.com,
	andrew.rybchenko@oktetlabs.ru, honnappa.nagarahalli@arm.com,
	konstantin.ananyev@intel.com, bruce.richardson@intel.com,
	ferruh.yigit@intel.com, jerinj@marvell.com, gakhil@marvell.com
Subject: Re: [dpdk-dev] [PATCH] parray: introduce internal API for dynamic arrays
Date: Mon, 14 Jun 2021 15:28:14 +0200	[thread overview]
Message-ID: <4219595.Gpeg8gzPfc@thomas> (raw)
In-Reply-To: <98CBD80474FA8B44BF855DF32C47DC35C6184E@smartserver.smartshare.dk>

14/06/2021 14:22, Morten Brørup:
> > From: dev [mailto:dev-bounces@dpdk.org] On Behalf Of Thomas Monjalon
> > Sent: Monday, 14 June 2021 12.59
> > 
> > Performance of access in a fixed-size array is very good
> > because of cache locality
> > and because there is a single pointer to dereference.
> > The only drawback is the lack of flexibility:
> > the size of such an array cannot be increase at runtime.
> > 
> > An approach to this problem is to allocate the array at runtime,
> > being as efficient as static arrays, but still limited to a maximum.
> > 
> > That's why the API rte_parray is introduced,
> > allowing to declare an array of pointer which can be resized
> > dynamically
> > and automatically at runtime while keeping a good read performance.
> > 
> > After resize, the previous array is kept until the next resize
> > to avoid crashs during a read without any lock.
> > 
> > Each element is a pointer to a memory chunk dynamically allocated.
> > This is not good for cache locality but it allows to keep the same
> > memory per element, no matter how the array is resized.
> > Cache locality could be improved with mempools.
> > The other drawback is having to dereference one more pointer
> > to read an element.
> > 
> > There is not much locks, so the API is for internal use only.
> > This API may be used to completely remove some compilation-time
> > maximums.
> 
> I get the purpose and overall intention of this library.
> 
> I probably already mentioned that I prefer
> "embedded style programming" with fixed size arrays,
> rather than runtime configurability.
> It's my personal opinion, and the DPDK Tech Board clearly prefers
> reducing the amount of compile time configurability,
> so there is no way for me to stop this progress,
> and I do not intend to oppose to this library. :-)

Embedded-style is highly customized and limited.
DPDK is more used in standard servers where
deployment must be easy and dynamically configurable.
That's my view on where we go, but I understand
some can have opposite goals. Thus the discussion :)

> This library is likely to become a core library of DPDK,
> so I think it is important getting it right.
> Could you please mention a few examples where
> you think this internal library should be used,

It could be used for device arrays which are managed
(alloc/free) in the main thread as part of init
and hotplug operations.
Other threads should be readers only.

> and where it should not be used.
> Then it is easier to discuss if the border line
> between control path and data plane is correct.
> E.g. this library is not intended to be used for dynamically
> sized packet queues that grow and shrink in the fast path.

Correct.
If fast path threads need to alloc/free, this is not the right API.
That's not a queue, just a growing array where each element has an index.

> If the library becomes a core DPDK library,
> it should probably be public instead of internal.
> E.g. if the library is used to make RTE_MAX_ETHPORTS dynamic
> instead of compile time fixed,
> then some applications might also need dynamically sized arrays
> for their application specific per-port runtime data,
> and this library could serve that purpose too.

It could be convenient but risky if users don't understand well
the limitations. I am not sure what to do.

> [snip]
> 
> > +
> > +/** Main object representing a dynamic array of pointers. */
> > +struct rte_parray {
> > +	/** Array of pointer to dynamically allocated struct. */
> > +	void **array;
> > +	/** Old array before resize, freed on next resize. */
> > +	void **old_array;
> > +	/* Lock for alloc/free operations. */
> > +	pthread_mutex_t mutex;
> > +	/** Current size of the full array. */
> > +	int32_t size;
> > +	/** Number of allocated elements. */
> > +	int32_t count;
> > +	/** Last allocated element. */
> > +	int32_t last;
> > +};
> 
> Why not uint32_t for size, count and last?

2 reasons:
1/ anyway we are limited to int32_t for the index.
2/ having the same type for all avoid compiler complaining
when comparing values.

> Consider if the hot members of the struct should be moved
> closer together, for increasing the probability
> that they end up in the same cache line
> if the structure is not cache line aligned. Probably not important,
> just wanted to mention it.

The only hot member is the array itself.
Depending on mutex implementation, all could be in a single cacheline.



  parent reply	other threads:[~2021-06-14 13:28 UTC|newest]

Thread overview: 61+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2021-06-14 10:58 Thomas Monjalon
2021-06-14 12:22 ` Morten Brørup
2021-06-14 13:15   ` Bruce Richardson
2021-06-14 13:32     ` Thomas Monjalon
2021-06-14 14:59       ` Ananyev, Konstantin
2021-06-14 15:48         ` Jerin Jacob
2021-06-15  6:52           ` Thomas Monjalon
2021-06-15  8:00             ` Jerin Jacob
2021-06-15  9:18               ` Thomas Monjalon
2021-06-15  9:33             ` Ananyev, Konstantin
2021-06-15  9:50               ` Thomas Monjalon
2021-06-15 10:08                 ` Ananyev, Konstantin
2021-06-15 14:02                   ` Thomas Monjalon
2021-06-15 14:37                     ` Honnappa Nagarahalli
2021-06-14 15:54         ` Ananyev, Konstantin
2021-06-17 13:08           ` Ferruh Yigit
2021-06-17 14:58             ` Ananyev, Konstantin
2021-06-17 15:17               ` Morten Brørup
2021-06-17 16:12                 ` Ferruh Yigit
2021-06-17 16:55                   ` Morten Brørup
2021-06-18 10:21                     ` Ferruh Yigit
2021-06-17 17:05                   ` Ananyev, Konstantin
2021-06-18  9:14                     ` Morten Brørup
2021-06-18 10:47                       ` Ferruh Yigit
2021-06-18 11:16                         ` Morten Brørup
2021-06-18 10:28                     ` Ferruh Yigit
2021-06-17 15:44               ` Ferruh Yigit
2021-06-18 10:41                 ` Ananyev, Konstantin
2021-06-18 10:49                   ` Ferruh Yigit
2021-06-21 11:06                   ` Ananyev, Konstantin
2021-06-21 12:10                     ` Morten Brørup
2021-06-21 12:30                       ` Ananyev, Konstantin
2021-06-21 13:28                         ` Morten Brørup
     [not found]                           ` <DM6PR11MB4491D4F6FAFDD6E8EEC2A78F9A099@DM6PR11MB4491.namprd11.prod.outlook .com>
2021-06-22  8:33                           ` Ananyev, Konstantin
2021-06-22 10:01                             ` Morten Brørup
2021-06-22 12:13                               ` Ananyev, Konstantin
2021-06-22 13:18                                 ` Morten Brørup
2021-06-21 14:10                         ` Ferruh Yigit
2021-06-21 14:38                           ` Ananyev, Konstantin
2021-06-21 15:56                             ` Ferruh Yigit
2021-06-21 18:17                               ` Ananyev, Konstantin
2021-06-21 14:05                     ` Ferruh Yigit
2021-06-21 14:42                       ` Ananyev, Konstantin
2021-06-21 15:32                         ` Ferruh Yigit
2021-06-21 15:37                           ` Ananyev, Konstantin
2021-06-14 15:48       ` Morten Brørup
2021-06-15  6:48         ` Thomas Monjalon
2021-06-15  7:53           ` Morten Brørup
2021-06-15  8:44             ` Bruce Richardson
2021-06-15  9:28               ` Thomas Monjalon
2021-06-16  9:42           ` Jerin Jacob
2021-06-16 11:27             ` Morten Brørup
2021-06-16 12:00               ` Jerin Jacob
2021-06-16 13:02               ` Bruce Richardson
2021-06-16 15:01                 ` Morten Brørup
2021-06-16 17:40                   ` Bruce Richardson
2021-06-16 12:22             ` Burakov, Anatoly
2021-06-16 12:59               ` Jerin Jacob
2021-06-16 22:58                 ` Dmitry Kozlyuk
2021-06-14 13:28   ` Thomas Monjalon [this message]
2021-06-16 11:11 ` Burakov, Anatoly

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=4219595.Gpeg8gzPfc@thomas \
    --to=thomas@monjalon.net \
    --cc=andrew.rybchenko@oktetlabs.ru \
    --cc=bruce.richardson@intel.com \
    --cc=dev@dpdk.org \
    --cc=ferruh.yigit@intel.com \
    --cc=gakhil@marvell.com \
    --cc=honnappa.nagarahalli@arm.com \
    --cc=jerinj@marvell.com \
    --cc=konstantin.ananyev@intel.com \
    --cc=mb@smartsharesystems.com \
    --cc=olivier.matz@6wind.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).