From: Kairui Song <kasong@tencent.com>
It was used for calculating the iteration number when the swap allocator
wants to scan the whole fragment list. Now the allocator only scans one
fragment cluster at a time, so no one uses this counter anymore.
Remove it as a cleanup; the performance change is marginal:
Build linux kernel using 10G ZRAM, make -j96, defconfig with 2G cgroup
memory limit, on top of tmpfs, 64kB mTHP enabled:
Before: sys time: 6278.45s
After: sys time: 6176.34s
Change to 8G ZRAM:
Before: sys time: 5572.85s
After: sys time: 5531.49s
Signed-off-by: Kairui Song <kasong@tencent.com>
---
include/linux/swap.h | 1 -
mm/swapfile.c | 7 -------
2 files changed, 8 deletions(-)
diff --git a/include/linux/swap.h b/include/linux/swap.h
index 2fe6ed2cc3fd..a060d102e0d1 100644
--- a/include/linux/swap.h
+++ b/include/linux/swap.h
@@ -310,7 +310,6 @@ struct swap_info_struct {
/* list of cluster that contains at least one free slot */
struct list_head frag_clusters[SWAP_NR_ORDERS];
/* list of cluster that are fragmented or contented */
- atomic_long_t frag_cluster_nr[SWAP_NR_ORDERS];
unsigned int pages; /* total of usable pages of swap */
atomic_long_t inuse_pages; /* number of those currently in use */
struct swap_sequential_cluster *global_cluster; /* Use one global cluster for rotating device */
diff --git a/mm/swapfile.c b/mm/swapfile.c
index 1f1110e37f68..5fdb3cb2b8b7 100644
--- a/mm/swapfile.c
+++ b/mm/swapfile.c
@@ -470,11 +470,6 @@ static void move_cluster(struct swap_info_struct *si,
else
list_move_tail(&ci->list, list);
spin_unlock(&si->lock);
-
- if (ci->flags == CLUSTER_FLAG_FRAG)
- atomic_long_dec(&si->frag_cluster_nr[ci->order]);
- else if (new_flags == CLUSTER_FLAG_FRAG)
- atomic_long_inc(&si->frag_cluster_nr[ci->order]);
ci->flags = new_flags;
}
@@ -965,7 +960,6 @@ static unsigned long cluster_alloc_swap_entry(struct swap_info_struct *si, int o
* allocation, but reclaim may drop si->lock and race with another user.
*/
while ((ci = isolate_lock_cluster(si, &si->frag_clusters[o]))) {
- atomic_long_dec(&si->frag_cluster_nr[o]);
found = alloc_swap_scan_cluster(si, ci, cluster_offset(si, ci),
0, usage);
if (found)
@@ -3217,7 +3211,6 @@ static struct swap_cluster_info *setup_clusters(struct swap_info_struct *si,
for (i = 0; i < SWAP_NR_ORDERS; i++) {
INIT_LIST_HEAD(&si->nonfull_clusters[i]);
INIT_LIST_HEAD(&si->frag_clusters[i]);
- atomic_long_set(&si->frag_cluster_nr[i], 0);
}
/*
--
2.50.1Acked-by: Chris Li <chrisl@kernel.org>
Chris
On Wed, Aug 6, 2025 at 9:18 AM Kairui Song <ryncsn@gmail.com> wrote:
>
> From: Kairui Song <kasong@tencent.com>
>
> It was used for calculating the iteration number when the swap allocator
> wants to scan the whole fragment list. Now the allocator only scans one
> fragment cluster at a time, so no one uses this counter anymore.
>
> Remove it as a cleanup; the performance change is marginal:
>
> Build linux kernel using 10G ZRAM, make -j96, defconfig with 2G cgroup
> memory limit, on top of tmpfs, 64kB mTHP enabled:
>
> Before: sys time: 6278.45s
> After: sys time: 6176.34s
>
> Change to 8G ZRAM:
>
> Before: sys time: 5572.85s
> After: sys time: 5531.49s
>
> Signed-off-by: Kairui Song <kasong@tencent.com>
> ---
> include/linux/swap.h | 1 -
> mm/swapfile.c | 7 -------
> 2 files changed, 8 deletions(-)
>
> diff --git a/include/linux/swap.h b/include/linux/swap.h
> index 2fe6ed2cc3fd..a060d102e0d1 100644
> --- a/include/linux/swap.h
> +++ b/include/linux/swap.h
> @@ -310,7 +310,6 @@ struct swap_info_struct {
> /* list of cluster that contains at least one free slot */
> struct list_head frag_clusters[SWAP_NR_ORDERS];
> /* list of cluster that are fragmented or contented */
> - atomic_long_t frag_cluster_nr[SWAP_NR_ORDERS];
> unsigned int pages; /* total of usable pages of swap */
> atomic_long_t inuse_pages; /* number of those currently in use */
> struct swap_sequential_cluster *global_cluster; /* Use one global cluster for rotating device */
> diff --git a/mm/swapfile.c b/mm/swapfile.c
> index 1f1110e37f68..5fdb3cb2b8b7 100644
> --- a/mm/swapfile.c
> +++ b/mm/swapfile.c
> @@ -470,11 +470,6 @@ static void move_cluster(struct swap_info_struct *si,
> else
> list_move_tail(&ci->list, list);
> spin_unlock(&si->lock);
> -
> - if (ci->flags == CLUSTER_FLAG_FRAG)
> - atomic_long_dec(&si->frag_cluster_nr[ci->order]);
> - else if (new_flags == CLUSTER_FLAG_FRAG)
> - atomic_long_inc(&si->frag_cluster_nr[ci->order]);
> ci->flags = new_flags;
> }
>
> @@ -965,7 +960,6 @@ static unsigned long cluster_alloc_swap_entry(struct swap_info_struct *si, int o
> * allocation, but reclaim may drop si->lock and race with another user.
> */
> while ((ci = isolate_lock_cluster(si, &si->frag_clusters[o]))) {
> - atomic_long_dec(&si->frag_cluster_nr[o]);
> found = alloc_swap_scan_cluster(si, ci, cluster_offset(si, ci),
> 0, usage);
> if (found)
> @@ -3217,7 +3211,6 @@ static struct swap_cluster_info *setup_clusters(struct swap_info_struct *si,
> for (i = 0; i < SWAP_NR_ORDERS; i++) {
> INIT_LIST_HEAD(&si->nonfull_clusters[i]);
> INIT_LIST_HEAD(&si->frag_clusters[i]);
> - atomic_long_set(&si->frag_cluster_nr[i], 0);
> }
>
> /*
> --
> 2.50.1
>
Acked-by: Chris Li <chrisl@kernel.org>
Chris
On Wed, Aug 6, 2025 at 9:18 AM Kairui Song <ryncsn@gmail.com> wrote:
>
> From: Kairui Song <kasong@tencent.com>
>
> It was used for calculating the iteration number when the swap allocator
> wants to scan the whole fragment list. Now the allocator only scans one
> fragment cluster at a time, so no one uses this counter anymore.
>
> Remove it as a cleanup; the performance change is marginal:
>
> Build linux kernel using 10G ZRAM, make -j96, defconfig with 2G cgroup
> memory limit, on top of tmpfs, 64kB mTHP enabled:
>
> Before: sys time: 6278.45s
> After: sys time: 6176.34s
>
> Change to 8G ZRAM:
>
> Before: sys time: 5572.85s
> After: sys time: 5531.49s
>
> Signed-off-by: Kairui Song <kasong@tencent.com>
> ---
> include/linux/swap.h | 1 -
> mm/swapfile.c | 7 -------
> 2 files changed, 8 deletions(-)
>
> diff --git a/include/linux/swap.h b/include/linux/swap.h
> index 2fe6ed2cc3fd..a060d102e0d1 100644
> --- a/include/linux/swap.h
> +++ b/include/linux/swap.h
> @@ -310,7 +310,6 @@ struct swap_info_struct {
> /* list of cluster that contains at least one free slot */
> struct list_head frag_clusters[SWAP_NR_ORDERS];
> /* list of cluster that are fragmented or contented */
> - atomic_long_t frag_cluster_nr[SWAP_NR_ORDERS];
> unsigned int pages; /* total of usable pages of swap */
> atomic_long_t inuse_pages; /* number of those currently in use */
> struct swap_sequential_cluster *global_cluster; /* Use one global cluster for rotating device */
> diff --git a/mm/swapfile.c b/mm/swapfile.c
> index 1f1110e37f68..5fdb3cb2b8b7 100644
> --- a/mm/swapfile.c
> +++ b/mm/swapfile.c
> @@ -470,11 +470,6 @@ static void move_cluster(struct swap_info_struct *si,
> else
> list_move_tail(&ci->list, list);
> spin_unlock(&si->lock);
> -
> - if (ci->flags == CLUSTER_FLAG_FRAG)
> - atomic_long_dec(&si->frag_cluster_nr[ci->order]);
> - else if (new_flags == CLUSTER_FLAG_FRAG)
> - atomic_long_inc(&si->frag_cluster_nr[ci->order]);
> ci->flags = new_flags;
> }
>
> @@ -965,7 +960,6 @@ static unsigned long cluster_alloc_swap_entry(struct swap_info_struct *si, int o
> * allocation, but reclaim may drop si->lock and race with another user.
> */
> while ((ci = isolate_lock_cluster(si, &si->frag_clusters[o]))) {
> - atomic_long_dec(&si->frag_cluster_nr[o]);
> found = alloc_swap_scan_cluster(si, ci, cluster_offset(si, ci),
> 0, usage);
> if (found)
> @@ -3217,7 +3211,6 @@ static struct swap_cluster_info *setup_clusters(struct swap_info_struct *si,
> for (i = 0; i < SWAP_NR_ORDERS; i++) {
> INIT_LIST_HEAD(&si->nonfull_clusters[i]);
> INIT_LIST_HEAD(&si->frag_clusters[i]);
> - atomic_long_set(&si->frag_cluster_nr[i], 0);
> }
>
> /*
> --
> 2.50.1
>
>
On Wed, Aug 6, 2025 at 9:18 AM Kairui Song <ryncsn@gmail.com> wrote: > > From: Kairui Song <kasong@tencent.com> > > It was used for calculating the iteration number when the swap allocator > wants to scan the whole fragment list. Now the allocator only scans one > fragment cluster at a time, so no one uses this counter anymore. > > Remove it as a cleanup; the performance change is marginal: > > Build linux kernel using 10G ZRAM, make -j96, defconfig with 2G cgroup > memory limit, on top of tmpfs, 64kB mTHP enabled: > > Before: sys time: 6278.45s > After: sys time: 6176.34s > > Change to 8G ZRAM: > > Before: sys time: 5572.85s > After: sys time: 5531.49s > > Signed-off-by: Kairui Song <kasong@tencent.com> Reviewed-by: Nhat Pham <nphamcs@gmail.com>
© 2016 - 2026 Red Hat, Inc.