[PATCH v2 1/2] ext4: Preallocation is a multiple of stripe size

[PATCH v2 1/2] ext4: Preallocation is a multiple of stripe size

[Dan Ehrenberg]

Previously, if a stripe width was provided, then it would be used
as the preallocation granularity, with no santiy checking and no
way to override this. Now, mb_prealloc_size defaults to the smallest
multiple of stripe size that is greater than or equal to the old
default mb_prealloc_size, and this can be overridden with the sysfs
interface.

Signed-off-by: Dan Ehrenberg <dehrenberg@google.com>
---
 fs/ext4/mballoc.c |   29 ++++++++++++++++++++---------
 1 files changed, 20 insertions(+), 9 deletions(-)

diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c
index 6ed859d..754eb29 100644
--- a/fs/ext4/mballoc.c
+++ b/fs/ext4/mballoc.c
@@ -128,12 +128,13 @@
  * we are doing a group prealloc we try to normalize the request to
  * sbi->s_mb_group_prealloc. Default value of s_mb_group_prealloc is
  * 512 blocks. This can be tuned via
- * /sys/fs/ext4/<partition/mb_group_prealloc. The value is represented in
+ * /sys/fs/ext4/<partition>/mb_group_prealloc. The value is represented in
  * terms of number of blocks. If we have mounted the file system with -O
  * stripe=<value> option the group prealloc request is normalized to the
- * stripe value (sbi->s_stripe)
+ * the smallest multiple of the stripe value (sbi->s_stripe) which is
+ * greater than the default mb_group_prealloc.
  *
- * The regular allocator(using the buddy cache) supports few tunables.
+ * The regular allocator (using the buddy cache) supports a few tunables.
  *
  * /sys/fs/ext4/<partition>/mb_min_to_scan
  * /sys/fs/ext4/<partition>/mb_max_to_scan
@@ -2472,6 +2473,18 @@ int ext4_mb_init(struct super_block *sb, int needs_recovery)
 	sbi->s_mb_stream_request = MB_DEFAULT_STREAM_THRESHOLD;
 	sbi->s_mb_order2_reqs = MB_DEFAULT_ORDER2_REQS;
 	sbi->s_mb_group_prealloc = MB_DEFAULT_GROUP_PREALLOC;
+	/*
+	 * If there is a s_stripe > 1, then we set the s_mb_group_prealloc
+	 * to the lowest multiple of s_stripe which is bigger than
+	 * the s_mb_group_prealloc as determined above. We want
+	 * the preallocation size to be an exact multiple of the
+	 * RAID stripe size so that preallocations don't fragment
+	 * the stripes.
+	 */
+	if (sbi->s_stripe > 1) {
+		sbi->s_mb_group_prealloc = roundup(
+			sbi->s_mb_group_prealloc, sbi->s_stripe);
+	}
 
 	sbi->s_locality_groups = alloc_percpu(struct ext4_locality_group);
 	if (sbi->s_locality_groups == NULL) {
@@ -2830,8 +2843,9 @@ out_err:
 
 /*
  * here we normalize request for locality group
- * Group request are normalized to s_strip size if we set the same via mount
- * option. If not we set it to s_mb_group_prealloc which can be configured via
+ * Group request are normalized to s_mb_group_prealloc, which goes to
+ * s_strip if we set the same via mount option.
+ * s_mb_group_prealloc can be configured via
  * /sys/fs/ext4/<partition>/mb_group_prealloc
  *
  * XXX: should we try to preallocate more than the group has now?
@@ -2842,10 +2856,7 @@ static void ext4_mb_normalize_group_request(struct ext4_allocation_context *ac)
 	struct ext4_locality_group *lg = ac->ac_lg;
 
 	BUG_ON(lg == NULL);
-	if (EXT4_SB(sb)->s_stripe)
-		ac->ac_g_ex.fe_len = EXT4_SB(sb)->s_stripe;
-	else
-		ac->ac_g_ex.fe_len = EXT4_SB(sb)->s_mb_group_prealloc;
+	ac->ac_g_ex.fe_len = EXT4_SB(sb)->s_mb_group_prealloc;
 	mb_debug(1, "#%u: goal %u blocks for locality group\n",
 		current->pid, ac->ac_g_ex.fe_len);
 }
-- 
1.7.3.1

[PATCH v2 2/2] ext4: Ignore a stripe width of 1

[Dan Ehrenberg]

If the stripe width was set to 1, then this patch will ignore
that stripe width and ext4 will act as if the stripe width
were 0 with respect to optimizing allocations.

Signed-off-by: Dan Ehrenberg <dehrenberg@google.com>
---
 fs/ext4/super.c |   22 ++++++++++++++++------
 1 files changed, 16 insertions(+), 6 deletions(-)

diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index 9ea71aa..0a3745b 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -2383,17 +2383,27 @@ static unsigned long ext4_get_stripe_size(struct ext4_sb_info *sbi)
 	unsigned long stride = le16_to_cpu(sbi->s_es->s_raid_stride);
 	unsigned long stripe_width =
 			le32_to_cpu(sbi->s_es->s_raid_stripe_width);
+	int ret;
 
 	if (sbi->s_stripe && sbi->s_stripe <= sbi->s_blocks_per_group)
-		return sbi->s_stripe;
+		ret = sbi->s_stripe;
 
-	if (stripe_width <= sbi->s_blocks_per_group)
-		return stripe_width;
+	else if (stripe_width <= sbi->s_blocks_per_group)
+		ret = stripe_width;
 
-	if (stride <= sbi->s_blocks_per_group)
-		return stride;
+	else if (stride <= sbi->s_blocks_per_group)
+		ret = stride;
+	else
+		ret = 0;
 
-	return 0;
+	/*
+	 * If the stripe width is 1, this makes no sense and
+	 * we set it to 0 to turn off stripe handling code.
+	 */
+	if (ret <= 1)
+		ret = 0;
+
+	return ret;
 }
 
 /* sysfs supprt */
-- 
1.7.3.1

Re: [PATCH v2 2/2] ext4: Ignore a stripe width of 1

[Eric Sandeen]

On 7/15/11 4:41 PM, Dan Ehrenberg wrote:
> If the stripe width was set to 1, then this patch will ignore
> that stripe width and ext4 will act as if the stripe width
> were 0 with respect to optimizing allocations.
> 
> Signed-off-by: Dan Ehrenberg <dehrenberg@google.com>

Thanks, I think this makes sense.

Reviewed-by: Eric Sandeen <sandeen@redhat.com>

> ---
>  fs/ext4/super.c |   22 ++++++++++++++++------
>  1 files changed, 16 insertions(+), 6 deletions(-)
> 
> diff --git a/fs/ext4/super.c b/fs/ext4/super.c
> index 9ea71aa..0a3745b 100644
> --- a/fs/ext4/super.c
> +++ b/fs/ext4/super.c
> @@ -2383,17 +2383,27 @@ static unsigned long ext4_get_stripe_size(struct ext4_sb_info *sbi)
>  	unsigned long stride = le16_to_cpu(sbi->s_es->s_raid_stride);
>  	unsigned long stripe_width =
>  			le32_to_cpu(sbi->s_es->s_raid_stripe_width);
> +	int ret;
>  
>  	if (sbi->s_stripe && sbi->s_stripe <= sbi->s_blocks_per_group)
> -		return sbi->s_stripe;
> +		ret = sbi->s_stripe;
>  
> -	if (stripe_width <= sbi->s_blocks_per_group)
> -		return stripe_width;
> +	else if (stripe_width <= sbi->s_blocks_per_group)
> +		ret = stripe_width;
>  
> -	if (stride <= sbi->s_blocks_per_group)
> -		return stride;
> +	else if (stride <= sbi->s_blocks_per_group)
> +		ret = stride;
> +	else
> +		ret = 0;
>  
> -	return 0;
> +	/*
> +	 * If the stripe width is 1, this makes no sense and
> +	 * we set it to 0 to turn off stripe handling code.
> +	 */
> +	if (ret <= 1)
> +		ret = 0;
> +
> +	return ret;
>  }
>  
>  /* sysfs supprt */

Re: [PATCH v2 2/2] ext4: Ignore a stripe width of 1

[Ted Ts'o]

On Fri, Jul 15, 2011 at 02:41:55PM -0700, Dan Ehrenberg wrote:
> If the stripe width was set to 1, then this patch will ignore
> that stripe width and ext4 will act as if the stripe width
> were 0 with respect to optimizing allocations.
> 
> Signed-off-by: Dan Ehrenberg <dehrenberg@google.com>

Applied to the ext4 tree.  I did make one formatting change.  Please
don't have blank lines between the if and else clauses, like this:

	if (sbi->s_stripe && sbi->s_stripe <= sbi->s_blocks_per_group)
		ret = sbi->s_stripe;

	else if (stripe_width <= sbi->s_blocks_per_group)
		ret = stripe_width;

	else if (stride <= sbi->s_blocks_per_group)
		ret = stride;

it wastes vertical whitespace and makes the control flow harder to
follow.  Eliminate the blank lines, and it's easier to read, I think.

	if (sbi->s_stripe && sbi->s_stripe <= sbi->s_blocks_per_group)
		ret = sbi->s_stripe;
	else if (stripe_width <= sbi->s_blocks_per_group)
		ret = stripe_width;
	else if (stride <= sbi->s_blocks_per_group)
		ret = stride;

						- Ted

Re: [PATCH v2 1/2] ext4: Preallocation is a multiple of stripe size

[Ted Ts'o]

On Fri, Jul 15, 2011 at 02:41:54PM -0700, Dan Ehrenberg wrote:
> Previously, if a stripe width was provided, then it would be used
> as the preallocation granularity, with no santiy checking and no
> way to override this. Now, mb_prealloc_size defaults to the smallest
> multiple of stripe size that is greater than or equal to the old
> default mb_prealloc_size, and this can be overridden with the sysfs
> interface.
> 
> Signed-off-by: Dan Ehrenberg <dehrenberg@google.com>

Added to the ext4 tree, thanks!

					- Ted