All of lore.kernel.org
 help / color / mirror / Atom feed
From: Eric Sandeen <sandeen@redhat.com>
To: ext4 development <linux-ext4@vger.kernel.org>
Cc: "Aneesh Kumar K.V" <aneesh.kumar@linux.vnet.ibm.com>
Subject: Re: [PATCH] use percpu data for lg_prealloc_list
Date: Mon, 18 Aug 2008 10:47:40 -0500	[thread overview]
Message-ID: <48A9999C.6070609@redhat.com> (raw)
In-Reply-To: <48A331FA.6070602@redhat.com>

Eric Sandeen wrote:
> lg_prealloc_list seems to cry out for a per-cpu data structure; on a large
> smp system I think this should be better.  I've lightly tested this change
> on a 4-cpu system.  Comments welcome...

Any thoughts on this?  Does this seem to be the right way to go?

Thanks,
-Eric

> Signed-off-by: Eric Sandeen <sandeen@redhat.com>
> ---
> 
> ndex: linux-2.6/fs/ext4/mballoc.c
> ===================================================================
> --- linux-2.6.orig/fs/ext4/mballoc.c	2008-08-04 15:30:30.000000000 -0500
> +++ linux-2.6/fs/ext4/mballoc.c	2008-08-13 13:48:33.224165751 -0500
> @@ -2540,17 +2540,16 @@ int ext4_mb_init(struct super_block *sb,
>  	sbi->s_mb_history_filter = EXT4_MB_HISTORY_DEFAULT;
>  	sbi->s_mb_group_prealloc = MB_DEFAULT_GROUP_PREALLOC;
>  
> -	i = sizeof(struct ext4_locality_group) * nr_cpu_ids;
> -	sbi->s_locality_groups = kmalloc(i, GFP_KERNEL);
> +	sbi->s_locality_groups = alloc_percpu(struct ext4_locality_group);
>  	if (sbi->s_locality_groups == NULL) {
>  		clear_opt(sbi->s_mount_opt, MBALLOC);
>  		kfree(sbi->s_mb_offsets);
>  		kfree(sbi->s_mb_maxs);
>  		return -ENOMEM;
>  	}
> -	for (i = 0; i < nr_cpu_ids; i++) {
> +	for_each_possible_cpu(i) {
>  		struct ext4_locality_group *lg;
> -		lg = &sbi->s_locality_groups[i];
> +		lg = per_cpu_ptr(sbi->s_locality_groups, i);
>  		mutex_init(&lg->lg_mutex);
>  		for (j = 0; j < PREALLOC_TB_SIZE; j++)
>  			INIT_LIST_HEAD(&lg->lg_prealloc_list[j]);
> @@ -2647,8 +2646,7 @@ int ext4_mb_release(struct super_block *
>  				atomic_read(&sbi->s_mb_discarded));
>  	}
>  
> -	kfree(sbi->s_locality_groups);
> -
> +	free_percpu(sbi->s_locality_groups);
>  	ext4_mb_history_release(sb);
>  	ext4_mb_destroy_per_dev_proc(sb);
>  
> @@ -4055,8 +4053,7 @@ static void ext4_mb_group_or_file(struct
>  	 * per cpu locality group is to reduce the contention between block
>  	 * request from multiple CPUs.
>  	 */
> -	ac->ac_lg = &sbi->s_locality_groups[get_cpu()];
> -	put_cpu();
> +	ac->ac_lg = per_cpu_ptr(sbi->s_locality_groups, smp_processor_id());
>  
>  	/* we're going to use group allocation */
>  	ac->ac_flags |= EXT4_MB_HINT_GROUP_ALLOC;
> 
> --
> To unsubscribe from this list: send the line "unsubscribe linux-ext4" in
> the body of a message to majordomo@vger.kernel.org
> More majordomo info at  http://vger.kernel.org/majordomo-info.html


  reply	other threads:[~2008-08-18 15:50 UTC|newest]

Thread overview: 4+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2008-08-13 19:11 [PATCH] use percpu data for lg_prealloc_list Eric Sandeen
2008-08-18 15:47 ` Eric Sandeen [this message]
2008-08-18 15:56   ` Aneesh Kumar K.V
2008-08-18 16:07     ` Eric Sandeen

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=48A9999C.6070609@redhat.com \
    --to=sandeen@redhat.com \
    --cc=aneesh.kumar@linux.vnet.ibm.com \
    --cc=linux-ext4@vger.kernel.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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.