lists.openwall.net   lists  /  announce  owl-users  owl-dev  john-users  john-dev  passwdqc-users  yescrypt  popa3d-users  /  oss-security  kernel-hardening  musl  sabotage  tlsify  passwords  /  crypt-dev  xvendor  /  Bugtraq  Full-Disclosure  linux-kernel  linux-netdev  linux-ext4  linux-hardening  linux-cve-announce  PHC 
Open Source and information security mailing list archives
 
Hash Suite: Windows password security audit tool. GUI, reports in PDF.
[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Date:	Mon, 18 Aug 2008 10:47:40 -0500
From:	Eric Sandeen <sandeen@...hat.com>
To:	ext4 development <linux-ext4@...r.kernel.org>
CC:	"Aneesh Kumar K.V" <aneesh.kumar@...ux.vnet.ibm.com>
Subject: Re: [PATCH] use percpu data for lg_prealloc_list

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@...hat.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@...r.kernel.org
> More majordomo info at  http://vger.kernel.org/majordomo-info.html

--
To unsubscribe from this list: send the line "unsubscribe linux-ext4" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html

Powered by blists - more mailing lists

Powered by Openwall GNU/*/Linux Powered by OpenVZ