[PATCH v2] iomap: avoid memset iomap when iter is done

[PATCH v2] iomap: avoid memset iomap when iter is done

[Fengnan Chang]

When iomap_iter() finishes its iteration (returns <= 0), it is no longer
necessary to memset the entire iomap and srcmap structures.

In high-IOPS scenarios (like 4k randread NVMe polling with io_uring),
where the majority of I/Os complete in a single extent map, this wasted
memory write bandwidth, as the caller will just discard the iterator.
Use this command to test:
taskset -c 30 ./t/io_uring -p1 -d512 -b4096 -s32 -c32 -F1 -B1 -R1 -X1
-n1 -P1 /mnt/testfile
IOPS improve about 5% on ext4 and XFS.

However, we MUST still call iomap_iter_reset_iomap() to release the
folio_batch if IOMAP_F_FOLIO_BATCH is set, otherwise we leak page
references. Therefore, split the cleanup logic: always release the
folio_batch, but skip the memset() when ret <= 0.

Signed-off-by: Fengnan Chang <changfengnan@bytedance.com>
---
 fs/iomap/iter.c | 12 ++++++------
 1 file changed, 6 insertions(+), 6 deletions(-)

diff --git a/fs/iomap/iter.c b/fs/iomap/iter.c
index c04796f6e57f..e4a29829591a 100644
--- a/fs/iomap/iter.c
+++ b/fs/iomap/iter.c
@@ -6,17 +6,13 @@
 #include <linux/iomap.h>
 #include "trace.h"
 
-static inline void iomap_iter_reset_iomap(struct iomap_iter *iter)
+static inline void iomap_iter_clean_fbatch(struct iomap_iter *iter)
 {
 	if (iter->iomap.flags & IOMAP_F_FOLIO_BATCH) {
 		folio_batch_release(iter->fbatch);
 		folio_batch_reinit(iter->fbatch);
 		iter->iomap.flags &= ~IOMAP_F_FOLIO_BATCH;
 	}
-
-	iter->status = 0;
-	memset(&iter->iomap, 0, sizeof(iter->iomap));
-	memset(&iter->srcmap, 0, sizeof(iter->srcmap));
 }
 
 /* Advance the current iterator position and decrement the remaining length */
@@ -102,10 +98,14 @@ int iomap_iter(struct iomap_iter *iter, const struct iomap_ops *ops)
 		ret = 0;
 	else
 		ret = 1;
-	iomap_iter_reset_iomap(iter);
+	iomap_iter_clean_fbatch(iter);
+	iter->status = 0;
 	if (ret <= 0)
 		return ret;
 
+	memset(&iter->iomap, 0, sizeof(iter->iomap));
+	memset(&iter->srcmap, 0, sizeof(iter->srcmap));
+
 begin:
 	ret = ops->iomap_begin(iter->inode, iter->pos, iter->len, iter->flags,
 			       &iter->iomap, &iter->srcmap);
-- 
2.39.5 (Apple Git-154)

Re: [PATCH v2] iomap: avoid memset iomap when iter is done

[Christoph Hellwig]

Looks good:

Reviewed-by: Christoph Hellwig <hch@lst.de>

Re: [PATCH v2] iomap: avoid memset iomap when iter is done

[Brian Foster]

On Mon, Apr 20, 2026 at 02:16:30PM +0800, Fengnan Chang wrote:
> When iomap_iter() finishes its iteration (returns <= 0), it is no longer
> necessary to memset the entire iomap and srcmap structures.
> 
> In high-IOPS scenarios (like 4k randread NVMe polling with io_uring),
> where the majority of I/Os complete in a single extent map, this wasted
> memory write bandwidth, as the caller will just discard the iterator.
> Use this command to test:
> taskset -c 30 ./t/io_uring -p1 -d512 -b4096 -s32 -c32 -F1 -B1 -R1 -X1
> -n1 -P1 /mnt/testfile
> IOPS improve about 5% on ext4 and XFS.
> 
> However, we MUST still call iomap_iter_reset_iomap() to release the
> folio_batch if IOMAP_F_FOLIO_BATCH is set, otherwise we leak page
> references. Therefore, split the cleanup logic: always release the
> folio_batch, but skip the memset() when ret <= 0.
> 
> Signed-off-by: Fengnan Chang <changfengnan@bytedance.com>
> ---

Reviewed-by: Brian Foster <bfoster@redhat.com>

>  fs/iomap/iter.c | 12 ++++++------
>  1 file changed, 6 insertions(+), 6 deletions(-)
> 
> diff --git a/fs/iomap/iter.c b/fs/iomap/iter.c
> index c04796f6e57f..e4a29829591a 100644
> --- a/fs/iomap/iter.c
> +++ b/fs/iomap/iter.c
> @@ -6,17 +6,13 @@
>  #include <linux/iomap.h>
>  #include "trace.h"
>  
> -static inline void iomap_iter_reset_iomap(struct iomap_iter *iter)
> +static inline void iomap_iter_clean_fbatch(struct iomap_iter *iter)
>  {
>  	if (iter->iomap.flags & IOMAP_F_FOLIO_BATCH) {
>  		folio_batch_release(iter->fbatch);
>  		folio_batch_reinit(iter->fbatch);
>  		iter->iomap.flags &= ~IOMAP_F_FOLIO_BATCH;
>  	}
> -
> -	iter->status = 0;
> -	memset(&iter->iomap, 0, sizeof(iter->iomap));
> -	memset(&iter->srcmap, 0, sizeof(iter->srcmap));
>  }
>  
>  /* Advance the current iterator position and decrement the remaining length */
> @@ -102,10 +98,14 @@ int iomap_iter(struct iomap_iter *iter, const struct iomap_ops *ops)
>  		ret = 0;
>  	else
>  		ret = 1;
> -	iomap_iter_reset_iomap(iter);
> +	iomap_iter_clean_fbatch(iter);
> +	iter->status = 0;
>  	if (ret <= 0)
>  		return ret;
>  
> +	memset(&iter->iomap, 0, sizeof(iter->iomap));
> +	memset(&iter->srcmap, 0, sizeof(iter->srcmap));
> +
>  begin:
>  	ret = ops->iomap_begin(iter->inode, iter->pos, iter->len, iter->flags,
>  			       &iter->iomap, &iter->srcmap);
> -- 
> 2.39.5 (Apple Git-154)
> 
>