public inbox for linux-kernel@vger.kernel.org
 help / color / mirror / Atom feed
From: Andrew Morton <akpm@osdl.org>
To: David Howells <dhowells@redhat.com>
Cc: torvalds@osdl.org, linux-kernel@vger.kernel.org
Subject: Re: [PATCH 0/4] WorkStruct: Shrink work_struct by two thirds
Date: Mon, 20 Nov 2006 11:17:12 -0800	[thread overview]
Message-ID: <20061120111712.5e399d12.akpm@osdl.org> (raw)
In-Reply-To: <20061120142713.12685.97188.stgit@warthog.cambridge.redhat.com>

On Mon, 20 Nov 2006 14:27:13 +0000
David Howells <dhowells@redhat.com> wrote:

> The workqueue struct is huge, and this limits it's usefulness.  On a 64-bit
> architecture it's nearly 100 bytes in size, of which the timer_list is half.
> These patches shrink work_struct by 8 of the 12 words it ordinarily consumes.
> This is done by:
> 
>  (1) Splitting the timer out so that delayable work items are defined by a
>      separate structure which incorporates a basic work_struct and a timer.
> 
>  (2) Folding the pending bit and wq_data data together
> 
>  (3) Removing the private data.  This can almost always be derived from the
>      address of the work_struct using container_of() and the selection of the
>      work function.  For the cases where the container of the work_struct may
>      go away the moment the pending bit is cleared, it is made possible to
>      defer the release of the structure by deferring the clearing of the
>      pending bit.
> 
> 
> These patches reduce the size of the work_struct thusly:
> 
> 			#WORDS		32-bit arch	64-bit arch
> 			===============	===============	===============
> 	As is		12		48 bytes	96 bytes
> 	Non-delayable	4		16 bytes	32 bytes
> 	Delayable	10		40 bytes	80 bytes
> 
> I've looked through most of the usages of work_structs, and I think that
> probably fewer than half the work_structs used actually require delayability,
> and I'm not sure that it's absolutely necessary in all cases.

via this:

> --- a/include/linux/workqueue.h
> +++ b/include/linux/workqueue.h
> @@ -17,6 +17,10 @@ struct work_struct {
>  	void (*func)(void *);
>  	void *data;
>  	void *wq_data;
> +};
> +
> +struct dwork_struct {
> +	struct work_struct work;
>  	struct timer_list timer;
>  };
>

Could we reduce the migration pain by leaving the work_struct as-is and
defining a new, leaner one and then incrementally migrating stuff over to
it?

struct work_struct_lite {
	unsigned long pending;
	struct list_head entry;
	void (*func)(void *);
	void *data;
	void *wq_data;
};

struct work_struct {
	struct work_struct_lite w;
	struct timer_list timer;
}


or even

struct work_struct {
	union {
		struct work_struct_lite w;
		struct {
			unsigned long pending;
			struct list_head entry;
			void (*func)(void *);
			void *data;
			void *wq_data;
		};
	}
	struct timer_list timer;
};



  parent reply	other threads:[~2006-11-20 19:17 UTC|newest]

Thread overview: 20+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2006-11-20 14:27 [PATCH 0/4] WorkStruct: Shrink work_struct by two thirds David Howells
2006-11-20 14:27 ` [PATCH 1/4] WorkStruct: Separate delayable and non-delayable events David Howells
2006-11-20 15:35   ` Stefan Richter
2006-11-20 15:43     ` David Howells
2006-11-20 18:32     ` Linus Torvalds
2006-11-21 11:30       ` David Howells
2006-11-20 14:27 ` [PATCH 2/4] WorkStruct: Typedef the work function prototype David Howells
2006-11-20 15:38   ` Stefan Richter
2006-11-20 15:47     ` David Howells
2006-11-20 16:13       ` Stefan Richter
2006-11-21 14:53       ` Jan Engelhardt
2006-11-20 14:27 ` [PATCH 3/4] WorkStruct: Merge the pending bit into the wq_data pointer David Howells
2006-11-21  0:34   ` Randy Dunlap
2006-11-20 14:27 ` [PATCH 4/4] WorkStruct: Pass the work_struct pointer instead of context data David Howells
2006-11-20 16:32 ` [PATCH 0/4] WorkStruct: Shrink work_struct by two thirds Trond Myklebust
2006-11-21 10:06   ` Christoph Hellwig
2006-11-21 11:08     ` David Howells
2006-11-20 19:17 ` Andrew Morton [this message]
2006-11-21 11:28   ` David Howells
2006-11-21 13:09   ` Jan Engelhardt

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=20061120111712.5e399d12.akpm@osdl.org \
    --to=akpm@osdl.org \
    --cc=dhowells@redhat.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=torvalds@osdl.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