mm: swap: mTHP swap allocator base on swap cluster order

Previously, the swap cluster used a cluster index as a pointer to construct a custom single link list type "swap_cluster_list". The next cluster pointer is shared with the cluster->count. It prevents puting the non free cluster into a list.

Change the cluster to use the standard double link list instead. This allows tracing the nonfull cluster in the follow up patch. That way, it is faster to get to the nonfull cluster of that order.

Remove the cluster getter/setter for accessing the cluster struct member.

The list operation is protected by the swap_info_struct->lock.

Change cluster code to use "struct swap_cluster_info *" to reference the cluster rather than by using index. That is more consistent with the list manipulation. It avoids the repeat adding index to the cluser_info. The code is easier to understand.

Remove the cluster next pointer is NULL flag, the double link list can handle the empty list pretty well.

The "swap_cluster_info" struct is two pointer bigger, because 512 swap entries share one swap struct, it has very little impact on the average memory usage per swap entry. For 1TB swapfile, the swap cluster data structure increases from 8MB to 24MB.

Other than the list conversion, there is no real function change in this patch.

Signed-off-by Chris Li <[email protected]>

---
 include/linux/swap.h |  26 +++---
 mm/swapfile.c        | 227 ++++++++++++++-------------------------------------
 2 files changed, 70 insertions(+), 183 deletions(-)

include/linux/swap.h +10 -16

index 3df75d62a835..690a04f06674 100644
@@ -243,22 +243,21 @@ enum {
  * free clusters are organized into a list. We fetch an entry from the list to
  * get a free cluster.
  *
- * The data field stores next cluster if the cluster is free or cluster usage
- * counter otherwise. The flags field determines if a cluster is free. This is
- * protected by swap_info_struct.lock.
+ * The flags field determines if a cluster is free. This is
+ * protected by cluster lock.
  */
 struct swap_cluster_info {
 	spinlock_t lock;	/*
 				 * Protect swap_cluster_info fields
-				 * and swap_info_struct->swap_map
-				 * elements correspond to the swap
-				 * cluster
+				 * other than list, and swap_info_struct->swap_map
+				 * elements correspond to the swap cluster.
 				 */
-	unsigned int data:24;
-	unsigned int flags:8;
+	u16 count;
+	u8 flags;
+	struct list_head list;
 };
 #define CLUSTER_FLAG_FREE 1 /* This cluster is free */
-#define CLUSTER_FLAG_NEXT_NULL 2 /* This cluster has no next cluster */
+
 
 /*
  * The first page in the swap file is the swap header, which is always marked

@@ -283,11 +282,6 @@ struct percpu_cluster {
 	unsigned int next[SWAP_NR_ORDERS]; /* Likely next allocation offset */
 };
 
-struct swap_cluster_list {
-	struct swap_cluster_info head;
-	struct swap_cluster_info tail;
-};
-
 /*
  * The in-memory structure used to track swap areas.
  */

@@ -300,7 +294,7 @@ struct swap_info_struct {
 	unsigned int	max;		/* extent of the swap_map */
 	unsigned char *swap_map;	/* vmalloc'ed array of usage counts */
 	struct swap_cluster_info *cluster_info; /* cluster info. Only for SSD */
-	struct swap_cluster_list free_clusters; /* free clusters list */
+	struct list_head free_clusters; /* free clusters list */
 	unsigned int lowest_bit;	/* index of first free in swap_map */
 	unsigned int highest_bit;	/* index of last free in swap_map */
 	unsigned int pages;		/* total of usable pages of swap */

@@ -331,7 +325,7 @@ struct swap_info_struct {
 					 * list.
 					 */
 	struct work_struct discard_work; /* discard worker */
-	struct swap_cluster_list discard_clusters; /* discard clusters list */
+	struct list_head discard_clusters; /* discard clusters list */
 	struct plist_node avail_lists[]; /*
 					   * entries in swap_avail_heads, one
 					   * entry per node.

mm/swapfile.c +0 -104

index 9c6d8e557c0f..0b11c437f9cc 100644
@@ -290,64 +290,11 @@ static void discard_swap_cluster(struct swap_info_struct *si,
 #endif
 #define LATENCY_LIMIT		256
 
-static inline void cluster_set_flag(struct swap_cluster_info *info,
-	unsigned int flag)
-{
-	info->flags = flag;
-}
-
-static inline unsigned int cluster_count(struct swap_cluster_info *info)
-{
-	return info->data;
-}
-
-static inline void cluster_set_count(struct swap_cluster_info *info,
-				     unsigned int c)
-{
-	info->data = c;
-}
-
-static inline void cluster_set_count_flag(struct swap_cluster_info *info,
-					 unsigned int c, unsigned int f)
-{
-	info->flags = f;
-	info->data = c;
-}
-
-static inline unsigned int cluster_next(struct swap_cluster_info *info)
-{
-	return info->data;
-}
-
-static inline void cluster_set_next(struct swap_cluster_info *info,
-				    unsigned int n)
-{
-	info->data = n;
-}
-
-static inline void cluster_set_next_flag(struct swap_cluster_info *info,
-					 unsigned int n, unsigned int f)
-{
-	info->flags = f;
-	info->data = n;
-}
-
 static inline bool cluster_is_free(struct swap_cluster_info *info)
 {
 	return info->flags & CLUSTER_FLAG_FREE;
 }
 
-static inline bool cluster_is_null(struct swap_cluster_info *info)
-{
-	return info->flags & CLUSTER_FLAG_NEXT_NULL;
-}
-
-static inline void cluster_set_null(struct swap_cluster_info *info)
-{
-	info->flags = CLUSTER_FLAG_NEXT_NULL;
-	info->data = 0;
-}
-
 static inline struct swap_cluster_info *lock_cluster(struct swap_info_struct *si,
 						     unsigned long offset)
 {

@@ -394,65 +341,11 @@ static inline void unlock_cluster_or_swap_info(struct swap_info_struct *si,
 		spin_unlock(&si->lock);
 }
 
-static inline bool cluster_list_empty(struct swap_cluster_list *list)
-{
-	return cluster_is_null(&list->head);
-}
-
-static inline unsigned int cluster_list_first(struct swap_cluster_list *list)
-{
-	return cluster_next(&list->head);
-}
-
-static void cluster_list_init(struct swap_cluster_list *list)
-{
-	cluster_set_null(&list->head);
-	cluster_set_null(&list->tail);
-}
-
-static void cluster_list_add_tail(struct swap_cluster_list *list,
-				  struct swap_cluster_info *ci,
-				  unsigned int idx)
-{
-	if (cluster_list_empty(list)) {
-		cluster_set_next_flag(&list->head, idx, 0);
-		cluster_set_next_flag(&list->tail, idx, 0);
-	} else {
-		struct swap_cluster_info *ci_tail;
-		unsigned int tail = cluster_next(&list->tail);
-
-		/*
-		 * Nested cluster lock, but both cluster locks are
-		 * only acquired when we held swap_info_struct->lock
-		 */
-		ci_tail = ci + tail;
-		spin_lock_nested(&ci_tail->lock, SINGLE_DEPTH_NESTING);
-		cluster_set_next(ci_tail, idx);
-		spin_unlock(&ci_tail->lock);
-		cluster_set_next_flag(&list->tail, idx, 0);
-	}
-}
-
-static unsigned int cluster_list_del_first(struct swap_cluster_list *list,
-					   struct swap_cluster_info *ci)
-{
-	unsigned int idx;
-
-	idx = cluster_next(&list->head);
-	if (cluster_next(&list->tail) == idx) {
-		cluster_set_null(&list->head);
-		cluster_set_null(&list->tail);
-	} else
-		cluster_set_next_flag(&list->head,
-				      cluster_next(&ci[idx]), 0);

mm/swapfile.c +9 -12

 	/*
 	 * If scan_swap_map_slots() can't find a free cluster, it will check
 	 * si->swap_map directly. To make sure the discarding cluster isn't

@@ -462,17 +355,14 @@ static void swap_cluster_schedule_discard(struct swap_info_struct *si,
 	memset(si->swap_map + idx * SWAPFILE_CLUSTER,
 			SWAP_MAP_BAD, SWAPFILE_CLUSTER);
 
-	cluster_list_add_tail(&si->discard_clusters, si->cluster_info, idx);
-
+	list_add_tail(&ci->list, &si->discard_clusters);
 	schedule_work(&si->discard_work);
 }
 
-static void __free_cluster(struct swap_info_struct *si, unsigned long idx)
+static void __free_cluster(struct swap_info_struct *si, struct swap_cluster_info *ci)
 {
-	struct swap_cluster_info *ci = si->cluster_info;
-
-	cluster_set_flag(ci + idx, CLUSTER_FLAG_FREE);
-	cluster_list_add_tail(&si->free_clusters, ci, idx);
+	ci->flags = CLUSTER_FLAG_FREE;
+	list_add_tail(&ci->list, &si->free_clusters);
 }
 
 /*

@@ -481,21 +371,22 @@ static void __free_cluster(struct swap_info_struct *si, unsigned long idx)
 */
 static void swap_do_scheduled_discard(struct swap_info_struct *si)
 {
-	struct swap_cluster_info *info, *ci;
+	struct swap_cluster_info *ci;
 	unsigned int idx;
 
-	info = si->cluster_info;
-
-	while (!cluster_list_empty(&si->discard_clusters)) {
-		idx = cluster_list_del_first(&si->discard_clusters, info);
+	while (!list_empty(&si->discard_clusters)) {
+		ci = list_first_entry(&si->discard_clusters, struct swap_cluster_info, list);
+		list_del(&ci->list);
+		idx = ci - si->cluster_info;

mm/swapfile.c +28 -31

+		__free_cluster(si, ci);
 		memset(si->swap_map + idx * SWAPFILE_CLUSTER,
 				0, SWAPFILE_CLUSTER);
 		unlock_cluster(ci);

@@ -521,20 +412,20 @@ static void swap_users_ref_free(struct percpu_ref *ref)
 	complete(&si->comp);
 }
 
-static void alloc_cluster(struct swap_info_struct *si, unsigned long idx)
+static struct swap_cluster_info *alloc_cluster(struct swap_info_struct *si, unsigned long idx)
 {
-	struct swap_cluster_info *ci = si->cluster_info;
+	struct swap_cluster_info *ci = list_first_entry(&si->free_clusters, struct swap_cluster_info, list);
 
-	VM_BUG_ON(cluster_list_first(&si->free_clusters) != idx);
-	cluster_list_del_first(&si->free_clusters, ci);
-	cluster_set_count_flag(ci + idx, 0, 0);
+	VM_BUG_ON(ci - si->cluster_info != idx);
+	list_del(&ci->list);
+	ci->count = 0;
+	ci->flags = 0;
+	return ci;
 }
 
-static void free_cluster(struct swap_info_struct *si, unsigned long idx)
+static void free_cluster(struct swap_info_struct *si, struct swap_cluster_info *ci)
 {
-	struct swap_cluster_info *ci = si->cluster_info + idx;
-
-	VM_BUG_ON(cluster_count(ci) != 0);
+	VM_BUG_ON(ci->count != 0);
 	/*
 	 * If the swap is discardable, prepare discard the cluster
 	 * instead of free it immediately. The cluster will be freed

@@ -542,11 +433,11 @@ static void free_cluster(struct swap_info_struct *si, unsigned long idx)
 	 */
 	if ((si->flags & (SWP_WRITEOK | SWP_PAGE_DISCARD)) ==
 	    (SWP_WRITEOK | SWP_PAGE_DISCARD)) {
-		swap_cluster_schedule_discard(si, idx);
+		swap_cluster_schedule_discard(si, ci);
 		return;
 	}
 
-	__free_cluster(si, idx);
+	__free_cluster(si, ci);
 }
 
 /*

@@ -559,15 +450,15 @@ static void add_cluster_info_page(struct swap_info_struct *p,
 	unsigned long count)
 {
 	unsigned long idx = page_nr / SWAPFILE_CLUSTER;
+	struct swap_cluster_info *ci = cluster_info + idx;
 
 	if (!cluster_info)
 		return;
-	if (cluster_is_free(&cluster_info[idx]))
+	if (cluster_is_free(ci))
 		alloc_cluster(p, idx);
 
-	VM_BUG_ON(cluster_count(&cluster_info[idx]) + count > SWAPFILE_CLUSTER);
-	cluster_set_count(&cluster_info[idx],
-		cluster_count(&cluster_info[idx]) + count);
+	VM_BUG_ON(ci->count + count > SWAPFILE_CLUSTER);
+	ci->count += count;
 }
 
 /*

@@ -581,24 +472,20 @@ static void inc_cluster_info_page(struct swap_info_struct *p,
 }
 
 /*
- * The cluster corresponding to page_nr decreases one usage. If the usage
- * counter becomes 0, which means no page in the cluster is in using, we can
- * optionally discard the cluster and add it to free cluster list.
+ * The cluster ci decreases one usage. If the usage counter becomes 0,
+ * which means no page in the cluster is in using, we can optionally discard
+ * the cluster and add it to free cluster list.
  */
-static void dec_cluster_info_page(struct swap_info_struct *p,
-	struct swap_cluster_info *cluster_info, unsigned long page_nr)
+static void dec_cluster_info_page(struct swap_info_struct *p, struct swap_cluster_info *ci)
 {
-	unsigned long idx = page_nr / SWAPFILE_CLUSTER;
-
-	if (!cluster_info)
+	if (!p->cluster_info)
 		return;
 
-	VM_BUG_ON(cluster_count(&cluster_info[idx]) == 0);
-	cluster_set_count(&cluster_info[idx],
-		cluster_count(&cluster_info[idx]) - 1);
+	VM_BUG_ON(ci->count == 0);
+	ci->count--;
 
-	if (cluster_count(&cluster_info[idx]) == 0)
-		free_cluster(p, idx);
+	if (!ci->count)
+		free_cluster(p, ci);
 }
 
 /*

@@ -611,10 +498,10 @@ scan_swap_map_ssd_cluster_conflict(struct swap_info_struct *si,
 {
 	struct percpu_cluster *percpu_cluster;
 	bool conflict;
-
+	struct swap_cluster_info *first = list_first_entry(&si->free_clusters, struct swap_cluster_info, list);
 	offset /= SWAPFILE_CLUSTER;
-	conflict = !cluster_list_empty(&si->free_clusters) &&
-		offset != cluster_list_first(&si->free_clusters) &&
+	conflict = !list_empty(&si->free_clusters) &&
+		offset !=  first - si->cluster_info &&
 		cluster_is_free(&si->cluster_info[offset]);
 
 	if (!conflict)

Quoted 230 lines · Chris Li

Previously, the swap cluster used a cluster index as a pointer to construct a custom single link list type "swap_cluster_list". The next cluster pointer is shared with the cluster->count. It prevents puting the non free cluster into a list.

Change the cluster to use the standard double link list instead. This allows tracing the nonfull cluster in the follow up patch. That way, it is faster to get to the nonfull cluster of that order.

Remove the cluster getter/setter for accessing the cluster struct member.

The list operation is protected by the swap_info_struct->lock.

Change cluster code to use "struct swap_cluster_info *" to reference the cluster rather than by using index. That is more consistent with the list manipulation. It avoids the repeat adding index to the cluser_info. The code is easier to understand.

Remove the cluster next pointer is NULL flag, the double link list can handle the empty list pretty well.

The "swap_cluster_info" struct is two pointer bigger, because 512 swap entries share one swap struct, it has very little impact on the average memory usage per swap entry. For 1TB swapfile, the swap cluster data structure increases from 8MB to 24MB.

Other than the list conversion, there is no real function change in this patch.

Signed-off-by Chris Li <[email protected]>

---
 include/linux/swap.h |  26 +++---
 mm/swapfile.c        | 227 ++++++++++++++-------------------------------------
 2 files changed, 70 insertions(+), 183 deletions(-)

include/linux/swap.h +10 -16

index 3df75d62a835..690a04f06674 100644
@@ -243,22 +243,21 @@ enum {
  * free clusters are organized into a list. We fetch an entry from the list to
  * get a free cluster.
  *
- * The data field stores next cluster if the cluster is free or cluster usage
- * counter otherwise. The flags field determines if a cluster is free. This is
- * protected by swap_info_struct.lock.
+ * The flags field determines if a cluster is free. This is
+ * protected by cluster lock.
  */
 struct swap_cluster_info {
      spinlock_t lock;        /*
                               * Protect swap_cluster_info fields
-                              * and swap_info_struct->swap_map
-                              * elements correspond to the swap
-                              * cluster
+                              * other than list, and swap_info_struct->swap_map
+                              * elements correspond to the swap cluster.
                               */
-     unsigned int data:24;
-     unsigned int flags:8;
+     u16 count;
+     u8 flags;
+     struct list_head list;
 };
 #define CLUSTER_FLAG_FREE 1 /* This cluster is free */
-#define CLUSTER_FLAG_NEXT_NULL 2 /* This cluster has no next cluster */
+
 
 /*
  * The first page in the swap file is the swap header, which is always marked

@@ -283,11 +282,6 @@ struct percpu_cluster {
      unsigned int next[SWAP_NR_ORDERS]; /* Likely next allocation offset */
 };
 
-struct swap_cluster_list {
-     struct swap_cluster_info head;
-     struct swap_cluster_info tail;
-};
-
 /*
  * The in-memory structure used to track swap areas.
  */

@@ -300,7 +294,7 @@ struct swap_info_struct {
      unsigned int    max;            /* extent of the swap_map */
      unsigned char *swap_map;        /* vmalloc'ed array of usage counts */
      struct swap_cluster_info *cluster_info; /* cluster info. Only for SSD */
-     struct swap_cluster_list free_clusters; /* free clusters list */
+     struct list_head free_clusters; /* free clusters list */
      unsigned int lowest_bit;        /* index of first free in swap_map */
      unsigned int highest_bit;       /* index of last free in swap_map */
      unsigned int pages;             /* total of usable pages of swap */

@@ -331,7 +325,7 @@ struct swap_info_struct {
                                       * list.
                                       */
      struct work_struct discard_work; /* discard worker */
-     struct swap_cluster_list discard_clusters; /* discard clusters list */
+     struct list_head discard_clusters; /* discard clusters list */
      struct plist_node avail_lists[]; /*
                                         * entries in swap_avail_heads, one
                                         * entry per node.

mm/swapfile.c +0 -108

index 9c6d8e557c0f..0b11c437f9cc 100644
@@ -290,64 +290,11 @@ static void discard_swap_cluster(struct swap_info_struct *si,
 #endif
 #define LATENCY_LIMIT                256
 
-static inline void cluster_set_flag(struct swap_cluster_info *info,
-     unsigned int flag)
-{
-     info->flags = flag;
-}
-
-static inline unsigned int cluster_count(struct swap_cluster_info *info)
-{
-     return info->data;
-}
-
-static inline void cluster_set_count(struct swap_cluster_info *info,
-                                  unsigned int c)
-{
-     info->data = c;
-}
-
-static inline void cluster_set_count_flag(struct swap_cluster_info *info,
-                                      unsigned int c, unsigned int f)
-{
-     info->flags = f;
-     info->data = c;
-}
-
-static inline unsigned int cluster_next(struct swap_cluster_info *info)
-{
-     return info->data;
-}
-
-static inline void cluster_set_next(struct swap_cluster_info *info,
-                                 unsigned int n)
-{
-     info->data = n;
-}
-
-static inline void cluster_set_next_flag(struct swap_cluster_info *info,
-                                      unsigned int n, unsigned int f)
-{
-     info->flags = f;
-     info->data = n;
-}
-
 static inline bool cluster_is_free(struct swap_cluster_info *info)
 {
      return info->flags & CLUSTER_FLAG_FREE;
 }
 
-static inline bool cluster_is_null(struct swap_cluster_info *info)
-{
-     return info->flags & CLUSTER_FLAG_NEXT_NULL;
-}
-
-static inline void cluster_set_null(struct swap_cluster_info *info)
-{
-     info->flags = CLUSTER_FLAG_NEXT_NULL;
-     info->data = 0;
-}
-
 static inline struct swap_cluster_info *lock_cluster(struct swap_info_struct *si,
                                                   unsigned long offset)
 {

@@ -394,65 +341,11 @@ static inline void unlock_cluster_or_swap_info(struct swap_info_struct *si,
              spin_unlock(&si->lock);
 }
 
-static inline bool cluster_list_empty(struct swap_cluster_list *list)
-{
-     return cluster_is_null(&list->head);
-}
-
-static inline unsigned int cluster_list_first(struct swap_cluster_list *list)
-{
-     return cluster_next(&list->head);
-}
-
-static void cluster_list_init(struct swap_cluster_list *list)
-{
-     cluster_set_null(&list->head);
-     cluster_set_null(&list->tail);
-}
-
-static void cluster_list_add_tail(struct swap_cluster_list *list,
-                               struct swap_cluster_info *ci,
-                               unsigned int idx)
-{
-     if (cluster_list_empty(list)) {
-             cluster_set_next_flag(&list->head, idx, 0);
-             cluster_set_next_flag(&list->tail, idx, 0);
-     } else {
-             struct swap_cluster_info *ci_tail;
-             unsigned int tail = cluster_next(&list->tail);
-
-             /*
-              * Nested cluster lock, but both cluster locks are
-              * only acquired when we held swap_info_struct->lock
-              */
-             ci_tail = ci + tail;
-             spin_lock_nested(&ci_tail->lock, SINGLE_DEPTH_NESTING);
-             cluster_set_next(ci_tail, idx);
-             spin_unlock(&ci_tail->lock);
-             cluster_set_next_flag(&list->tail, idx, 0);
-     }
-}
-
-static unsigned int cluster_list_del_first(struct swap_cluster_list *list,
-                                        struct swap_cluster_info *ci)
-{
-     unsigned int idx;
-
-     idx = cluster_next(&list->head);
-     if (cluster_next(&list->tail) == idx) {
-             cluster_set_null(&list->head);
-             cluster_set_null(&list->tail);
-     } else
-             cluster_set_next_flag(&list->head,
-                                   cluster_next(&ci[idx]), 0);
-
-     return idx;
-}
-
 /* Add a cluster to discard list and schedule it to do discard */

mm/swapfile.c static inline void unlock_cluster_or_swap_info(struct swap_info_struct *si, · line 348

Quoted 5 lines

mm/swapfile.c +2 -1

 static void swap_cluster_schedule_discard(struct swap_info_struct *si,
-             unsigned int idx)
+             struct swap_cluster_info *ci)
 {
+     unsigned int idx = ci - si->cluster_info;

IIRC, we have reached consensus that we will add a helper for this pattern.

Quoted 12 lines

mm/swapfile.c +4 -2

-     while (!cluster_list_empty(&si->discard_clusters)) {
-             idx = cluster_list_del_first(&si->discard_clusters, info);
+     while (!list_empty(&si->discard_clusters)) {
+             ci = list_first_entry(&si->discard_clusters, struct swap_cluster_info, list);
+             list_del(&ci->list);
+             idx = ci - si->cluster_info;
              spin_unlock(&si->lock);
 
              discard_swap_cluster(si, idx * SWAPFILE_CLUSTER,
                              SWAPFILE_CLUSTER);

mm/swapfile.c static void __free_cluster(struct swap_info_struct *si, unsigned long idx) · line 388

Quoted 5 lines

              spin_lock(&si->lock);

mm/swapfile.c +2 -2

-             ci = lock_cluster(si, idx * SWAPFILE_CLUSTER);
-             __free_cluster(si, idx);
+
+             spin_lock(&ci->lock);

If you really don't like lock_cluster(), please replace unlock_cluster() below with spin_unlock() too.

Quoted 117 lines

mm/swapfile.c +28 -31

+             __free_cluster(si, ci);
              memset(si->swap_map + idx * SWAPFILE_CLUSTER,
                              0, SWAPFILE_CLUSTER);
              unlock_cluster(ci);

@@ -521,20 +412,20 @@ static void swap_users_ref_free(struct percpu_ref *ref)
      complete(&si->comp);
 }
 
-static void alloc_cluster(struct swap_info_struct *si, unsigned long idx)
+static struct swap_cluster_info *alloc_cluster(struct swap_info_struct *si, unsigned long idx)
 {
-     struct swap_cluster_info *ci = si->cluster_info;
+     struct swap_cluster_info *ci = list_first_entry(&si->free_clusters, struct swap_cluster_info, list);
 
-     VM_BUG_ON(cluster_list_first(&si->free_clusters) != idx);
-     cluster_list_del_first(&si->free_clusters, ci);
-     cluster_set_count_flag(ci + idx, 0, 0);
+     VM_BUG_ON(ci - si->cluster_info != idx);
+     list_del(&ci->list);
+     ci->count = 0;
+     ci->flags = 0;
+     return ci;
 }
 
-static void free_cluster(struct swap_info_struct *si, unsigned long idx)
+static void free_cluster(struct swap_info_struct *si, struct swap_cluster_info *ci)
 {
-     struct swap_cluster_info *ci = si->cluster_info + idx;
-
-     VM_BUG_ON(cluster_count(ci) != 0);
+     VM_BUG_ON(ci->count != 0);
      /*
       * If the swap is discardable, prepare discard the cluster
       * instead of free it immediately. The cluster will be freed

@@ -542,11 +433,11 @@ static void free_cluster(struct swap_info_struct *si, unsigned long idx)
       */
      if ((si->flags & (SWP_WRITEOK | SWP_PAGE_DISCARD)) ==
          (SWP_WRITEOK | SWP_PAGE_DISCARD)) {
-             swap_cluster_schedule_discard(si, idx);
+             swap_cluster_schedule_discard(si, ci);
              return;
      }
 
-     __free_cluster(si, idx);
+     __free_cluster(si, ci);
 }
 
 /*

@@ -559,15 +450,15 @@ static void add_cluster_info_page(struct swap_info_struct *p,
      unsigned long count)
 {
      unsigned long idx = page_nr / SWAPFILE_CLUSTER;
+     struct swap_cluster_info *ci = cluster_info + idx;
 
      if (!cluster_info)
              return;
-     if (cluster_is_free(&cluster_info[idx]))
+     if (cluster_is_free(ci))
              alloc_cluster(p, idx);
 
-     VM_BUG_ON(cluster_count(&cluster_info[idx]) + count > SWAPFILE_CLUSTER);
-     cluster_set_count(&cluster_info[idx],
-             cluster_count(&cluster_info[idx]) + count);
+     VM_BUG_ON(ci->count + count > SWAPFILE_CLUSTER);
+     ci->count += count;
 }
 
 /*

@@ -581,24 +472,20 @@ static void inc_cluster_info_page(struct swap_info_struct *p,
 }
 
 /*
- * The cluster corresponding to page_nr decreases one usage. If the usage
- * counter becomes 0, which means no page in the cluster is in using, we can
- * optionally discard the cluster and add it to free cluster list.
+ * The cluster ci decreases one usage. If the usage counter becomes 0,
+ * which means no page in the cluster is in using, we can optionally discard
+ * the cluster and add it to free cluster list.
  */
-static void dec_cluster_info_page(struct swap_info_struct *p,
-     struct swap_cluster_info *cluster_info, unsigned long page_nr)
+static void dec_cluster_info_page(struct swap_info_struct *p, struct swap_cluster_info *ci)
 {
-     unsigned long idx = page_nr / SWAPFILE_CLUSTER;
-
-     if (!cluster_info)
+     if (!p->cluster_info)
              return;
 
-     VM_BUG_ON(cluster_count(&cluster_info[idx]) == 0);
-     cluster_set_count(&cluster_info[idx],
-             cluster_count(&cluster_info[idx]) - 1);
+     VM_BUG_ON(ci->count == 0);
+     ci->count--;
 
-     if (cluster_count(&cluster_info[idx]) == 0)
-             free_cluster(p, idx);
+     if (!ci->count)
+             free_cluster(p, ci);
 }
 
 /*

@@ -611,10 +498,10 @@ scan_swap_map_ssd_cluster_conflict(struct swap_info_struct *si,
 {
      struct percpu_cluster *percpu_cluster;
      bool conflict;
-
+     struct swap_cluster_info *first = list_first_entry(&si->free_clusters, struct swap_cluster_info, list);
      offset /= SWAPFILE_CLUSTER;
-     conflict = !cluster_list_empty(&si->free_clusters) &&
-             offset != cluster_list_first(&si->free_clusters) &&
+     conflict = !list_empty(&si->free_clusters) &&
+             offset !=  first - si->cluster_info &&
              cluster_is_free(&si->cluster_info[offset]);
 
      if (!conflict)

mm/swapfile.c static bool scan_swap_map_try_ssd_cluster(struct swap_info_struct *si, · line 547

Quoted 10 lines

mm/swapfile.c +3 -4

@@ -655,10 +542,14 @@ static bool scan_swap_map_try_ssd_cluster(struct swap_info_struct *si,
      cluster = this_cpu_ptr(si->percpu_cluster);
      tmp = cluster->next[order];
      if (tmp == SWAP_NEXT_INVALID) {
-             if (!cluster_list_empty(&si->free_clusters)) {
-                     tmp = cluster_next(&si->free_clusters.head) *
-                                     SWAPFILE_CLUSTER;
-             } else if (!cluster_list_empty(&si->discard_clusters)) {
+             if (!list_empty(&si->free_clusters)) {
+                     ci = list_first_entry(&si->free_clusters, struct swap_cluster_info, list);
+                     list_del(&ci->list);

IIRC, we shouldn't delete the cluster from the free list here, because we will delete it later in alloc_cluster().

mm/swapfile.c static bool scan_swap_map_try_ssd_cluster(struct swap_info_struct *si, · line 549

Quoted 2 lines

mm/swapfile.c +2 -0

+                     spin_lock(&ci->lock);
+                     ci->flags = 0;

And also shouldn't set ci->flags here too. Because the cluster may be kept in free list if scan_swap_map_ssd_cluster_conflict() returns true.

mm/swapfile.c static bool scan_swap_map_try_ssd_cluster(struct swap_info_struct *si, · line 555

Quoted 7 lines

mm/swapfile.c +3 -0

+                     spin_unlock(&ci->lock);
+                     tmp = (ci - si->cluster_info) * SWAPFILE_CLUSTER;
+             } else if (!list_empty(&si->discard_clusters)) {
                      /*
                       * we don't have free cluster but have some clusters in
                       * discarding, do discard now and reclaim them, then

[snip]

--
Best Regards,
Huang, Ying

Quoted 233 lines · Ying

Quoted 230 lines · Chris Li

Previously, the swap cluster used a cluster index as a pointer to construct a custom single link list type "swap_cluster_list". The next cluster pointer is shared with the cluster->count. It prevents puting the non free cluster into a list.

Change the cluster to use the standard double link list instead. This allows tracing the nonfull cluster in the follow up patch. That way, it is faster to get to the nonfull cluster of that order.

Remove the cluster getter/setter for accessing the cluster struct member.

The list operation is protected by the swap_info_struct->lock.

Change cluster code to use "struct swap_cluster_info *" to reference the cluster rather than by using index. That is more consistent with the list manipulation. It avoids the repeat adding index to the cluser_info. The code is easier to understand.

Remove the cluster next pointer is NULL flag, the double link list can handle the empty list pretty well.

The "swap_cluster_info" struct is two pointer bigger, because 512 swap entries share one swap struct, it has very little impact on the average memory usage per swap entry. For 1TB swapfile, the swap cluster data structure increases from 8MB to 24MB.

Other than the list conversion, there is no real function change in this patch.

Signed-off-by Chris Li <[email protected]>

---
 include/linux/swap.h |  26 +++---
 mm/swapfile.c        | 227 ++++++++++++++-------------------------------------
 2 files changed, 70 insertions(+), 183 deletions(-)

include/linux/swap.h +10 -16

index 3df75d62a835..690a04f06674 100644
@@ -243,22 +243,21 @@ enum {
  * free clusters are organized into a list. We fetch an entry from the list to
  * get a free cluster.
  *
- * The data field stores next cluster if the cluster is free or cluster usage
- * counter otherwise. The flags field determines if a cluster is free. This is
- * protected by swap_info_struct.lock.
+ * The flags field determines if a cluster is free. This is
+ * protected by cluster lock.
  */
 struct swap_cluster_info {
      spinlock_t lock;        /*
                               * Protect swap_cluster_info fields
-                              * and swap_info_struct->swap_map
-                              * elements correspond to the swap
-                              * cluster
+                              * other than list, and swap_info_struct->swap_map
+                              * elements correspond to the swap cluster.
                               */
-     unsigned int data:24;
-     unsigned int flags:8;
+     u16 count;
+     u8 flags;
+     struct list_head list;
 };
 #define CLUSTER_FLAG_FREE 1 /* This cluster is free */
-#define CLUSTER_FLAG_NEXT_NULL 2 /* This cluster has no next cluster */
+
 
 /*
  * The first page in the swap file is the swap header, which is always marked

@@ -283,11 +282,6 @@ struct percpu_cluster {
      unsigned int next[SWAP_NR_ORDERS]; /* Likely next allocation offset */
 };
 
-struct swap_cluster_list {
-     struct swap_cluster_info head;
-     struct swap_cluster_info tail;
-};
-
 /*
  * The in-memory structure used to track swap areas.
  */

@@ -300,7 +294,7 @@ struct swap_info_struct {
      unsigned int    max;            /* extent of the swap_map */
      unsigned char *swap_map;        /* vmalloc'ed array of usage counts */
      struct swap_cluster_info *cluster_info; /* cluster info. Only for SSD */
-     struct swap_cluster_list free_clusters; /* free clusters list */
+     struct list_head free_clusters; /* free clusters list */
      unsigned int lowest_bit;        /* index of first free in swap_map */
      unsigned int highest_bit;       /* index of last free in swap_map */
      unsigned int pages;             /* total of usable pages of swap */

@@ -331,7 +325,7 @@ struct swap_info_struct {
                                       * list.
                                       */
      struct work_struct discard_work; /* discard worker */
-     struct swap_cluster_list discard_clusters; /* discard clusters list */
+     struct list_head discard_clusters; /* discard clusters list */
      struct plist_node avail_lists[]; /*
                                         * entries in swap_avail_heads, one
                                         * entry per node.

mm/swapfile.c +0 -108

index 9c6d8e557c0f..0b11c437f9cc 100644
@@ -290,64 +290,11 @@ static void discard_swap_cluster(struct swap_info_struct *si,
 #endif
 #define LATENCY_LIMIT                256
 
-static inline void cluster_set_flag(struct swap_cluster_info *info,
-     unsigned int flag)
-{
-     info->flags = flag;
-}
-
-static inline unsigned int cluster_count(struct swap_cluster_info *info)
-{
-     return info->data;
-}
-
-static inline void cluster_set_count(struct swap_cluster_info *info,
-                                  unsigned int c)
-{
-     info->data = c;
-}
-
-static inline void cluster_set_count_flag(struct swap_cluster_info *info,
-                                      unsigned int c, unsigned int f)
-{
-     info->flags = f;
-     info->data = c;
-}
-
-static inline unsigned int cluster_next(struct swap_cluster_info *info)
-{
-     return info->data;
-}
-
-static inline void cluster_set_next(struct swap_cluster_info *info,
-                                 unsigned int n)
-{
-     info->data = n;
-}
-
-static inline void cluster_set_next_flag(struct swap_cluster_info *info,
-                                      unsigned int n, unsigned int f)
-{
-     info->flags = f;
-     info->data = n;
-}
-
 static inline bool cluster_is_free(struct swap_cluster_info *info)
 {
      return info->flags & CLUSTER_FLAG_FREE;
 }
 
-static inline bool cluster_is_null(struct swap_cluster_info *info)
-{
-     return info->flags & CLUSTER_FLAG_NEXT_NULL;
-}
-
-static inline void cluster_set_null(struct swap_cluster_info *info)
-{
-     info->flags = CLUSTER_FLAG_NEXT_NULL;
-     info->data = 0;
-}
-
 static inline struct swap_cluster_info *lock_cluster(struct swap_info_struct *si,
                                                   unsigned long offset)
 {

@@ -394,65 +341,11 @@ static inline void unlock_cluster_or_swap_info(struct swap_info_struct *si,
              spin_unlock(&si->lock);
 }
 
-static inline bool cluster_list_empty(struct swap_cluster_list *list)
-{
-     return cluster_is_null(&list->head);
-}
-
-static inline unsigned int cluster_list_first(struct swap_cluster_list *list)
-{
-     return cluster_next(&list->head);
-}
-
-static void cluster_list_init(struct swap_cluster_list *list)
-{
-     cluster_set_null(&list->head);
-     cluster_set_null(&list->tail);
-}
-
-static void cluster_list_add_tail(struct swap_cluster_list *list,
-                               struct swap_cluster_info *ci,
-                               unsigned int idx)
-{
-     if (cluster_list_empty(list)) {
-             cluster_set_next_flag(&list->head, idx, 0);
-             cluster_set_next_flag(&list->tail, idx, 0);
-     } else {
-             struct swap_cluster_info *ci_tail;
-             unsigned int tail = cluster_next(&list->tail);
-
-             /*
-              * Nested cluster lock, but both cluster locks are
-              * only acquired when we held swap_info_struct->lock
-              */
-             ci_tail = ci + tail;
-             spin_lock_nested(&ci_tail->lock, SINGLE_DEPTH_NESTING);
-             cluster_set_next(ci_tail, idx);
-             spin_unlock(&ci_tail->lock);
-             cluster_set_next_flag(&list->tail, idx, 0);
-     }
-}
-
-static unsigned int cluster_list_del_first(struct swap_cluster_list *list,
-                                        struct swap_cluster_info *ci)
-{
-     unsigned int idx;
-
-     idx = cluster_next(&list->head);
-     if (cluster_next(&list->tail) == idx) {
-             cluster_set_null(&list->head);
-             cluster_set_null(&list->tail);
-     } else
-             cluster_set_next_flag(&list->head,
-                                   cluster_next(&ci[idx]), 0);
-
-     return idx;
-}
-
 /* Add a cluster to discard list and schedule it to do discard */

Quoted 8 lines

mm/swapfile.c static inline void unlock_cluster_or_swap_info(struct swap_info_struct *si, · line 348

Quoted 5 lines

mm/swapfile.c +2 -1

 static void swap_cluster_schedule_discard(struct swap_info_struct *si,
-             unsigned int idx)
+             struct swap_cluster_info *ci)
 {
+     unsigned int idx = ci - si->cluster_info;

IIRC, we have reached consensus that we will add a helper for this pattern.

Yes, sorry about that. When I drop the V2 fixup branch, I forget to update that.

Quoted 12 lines

Quoted 12 lines

mm/swapfile.c +4 -2

-     while (!cluster_list_empty(&si->discard_clusters)) {
-             idx = cluster_list_del_first(&si->discard_clusters, info);
+     while (!list_empty(&si->discard_clusters)) {
+             ci = list_first_entry(&si->discard_clusters, struct swap_cluster_info, list);
+             list_del(&ci->list);
+             idx = ci - si->cluster_info;
              spin_unlock(&si->lock);
 
              discard_swap_cluster(si, idx * SWAPFILE_CLUSTER,
                              SWAPFILE_CLUSTER);

Quoted 9 lines

mm/swapfile.c static void __free_cluster(struct swap_info_struct *si, unsigned long idx) · line 388

Quoted 5 lines

              spin_lock(&si->lock);

mm/swapfile.c +2 -2

-             ci = lock_cluster(si, idx * SWAPFILE_CLUSTER);
-             __free_cluster(si, idx);
+
+             spin_lock(&ci->lock);

If you really don't like lock_cluster(), please replace unlock_cluster() below with spin_unlock() too.

Done. Switch to spin_unlock().

Quoted 134 lines

Quoted 117 lines

mm/swapfile.c +28 -31

+             __free_cluster(si, ci);
              memset(si->swap_map + idx * SWAPFILE_CLUSTER,
                              0, SWAPFILE_CLUSTER);
              unlock_cluster(ci);

@@ -521,20 +412,20 @@ static void swap_users_ref_free(struct percpu_ref *ref)
      complete(&si->comp);
 }
 
-static void alloc_cluster(struct swap_info_struct *si, unsigned long idx)
+static struct swap_cluster_info *alloc_cluster(struct swap_info_struct *si, unsigned long idx)
 {
-     struct swap_cluster_info *ci = si->cluster_info;
+     struct swap_cluster_info *ci = list_first_entry(&si->free_clusters, struct swap_cluster_info, list);
 
-     VM_BUG_ON(cluster_list_first(&si->free_clusters) != idx);
-     cluster_list_del_first(&si->free_clusters, ci);
-     cluster_set_count_flag(ci + idx, 0, 0);
+     VM_BUG_ON(ci - si->cluster_info != idx);
+     list_del(&ci->list);
+     ci->count = 0;
+     ci->flags = 0;
+     return ci;
 }
 
-static void free_cluster(struct swap_info_struct *si, unsigned long idx)
+static void free_cluster(struct swap_info_struct *si, struct swap_cluster_info *ci)
 {
-     struct swap_cluster_info *ci = si->cluster_info + idx;
-
-     VM_BUG_ON(cluster_count(ci) != 0);
+     VM_BUG_ON(ci->count != 0);
      /*
       * If the swap is discardable, prepare discard the cluster
       * instead of free it immediately. The cluster will be freed

@@ -542,11 +433,11 @@ static void free_cluster(struct swap_info_struct *si, unsigned long idx)
       */
      if ((si->flags & (SWP_WRITEOK | SWP_PAGE_DISCARD)) ==
          (SWP_WRITEOK | SWP_PAGE_DISCARD)) {
-             swap_cluster_schedule_discard(si, idx);
+             swap_cluster_schedule_discard(si, ci);
              return;
      }
 
-     __free_cluster(si, idx);
+     __free_cluster(si, ci);
 }
 
 /*

@@ -559,15 +450,15 @@ static void add_cluster_info_page(struct swap_info_struct *p,
      unsigned long count)
 {
      unsigned long idx = page_nr / SWAPFILE_CLUSTER;
+     struct swap_cluster_info *ci = cluster_info + idx;
 
      if (!cluster_info)
              return;
-     if (cluster_is_free(&cluster_info[idx]))
+     if (cluster_is_free(ci))
              alloc_cluster(p, idx);
 
-     VM_BUG_ON(cluster_count(&cluster_info[idx]) + count > SWAPFILE_CLUSTER);
-     cluster_set_count(&cluster_info[idx],
-             cluster_count(&cluster_info[idx]) + count);
+     VM_BUG_ON(ci->count + count > SWAPFILE_CLUSTER);
+     ci->count += count;
 }
 
 /*

@@ -581,24 +472,20 @@ static void inc_cluster_info_page(struct swap_info_struct *p,
 }
 
 /*
- * The cluster corresponding to page_nr decreases one usage. If the usage
- * counter becomes 0, which means no page in the cluster is in using, we can
- * optionally discard the cluster and add it to free cluster list.
+ * The cluster ci decreases one usage. If the usage counter becomes 0,
+ * which means no page in the cluster is in using, we can optionally discard
+ * the cluster and add it to free cluster list.
  */
-static void dec_cluster_info_page(struct swap_info_struct *p,
-     struct swap_cluster_info *cluster_info, unsigned long page_nr)
+static void dec_cluster_info_page(struct swap_info_struct *p, struct swap_cluster_info *ci)
 {
-     unsigned long idx = page_nr / SWAPFILE_CLUSTER;
-
-     if (!cluster_info)
+     if (!p->cluster_info)
              return;
 
-     VM_BUG_ON(cluster_count(&cluster_info[idx]) == 0);
-     cluster_set_count(&cluster_info[idx],
-             cluster_count(&cluster_info[idx]) - 1);
+     VM_BUG_ON(ci->count == 0);
+     ci->count--;
 
-     if (cluster_count(&cluster_info[idx]) == 0)
-             free_cluster(p, idx);
+     if (!ci->count)
+             free_cluster(p, ci);
 }
 
 /*

@@ -611,10 +498,10 @@ scan_swap_map_ssd_cluster_conflict(struct swap_info_struct *si,
 {
      struct percpu_cluster *percpu_cluster;
      bool conflict;
-
+     struct swap_cluster_info *first = list_first_entry(&si->free_clusters, struct swap_cluster_info, list);
      offset /= SWAPFILE_CLUSTER;
-     conflict = !cluster_list_empty(&si->free_clusters) &&
-             offset != cluster_list_first(&si->free_clusters) &&
+     conflict = !list_empty(&si->free_clusters) &&
+             offset !=  first - si->cluster_info &&
              cluster_is_free(&si->cluster_info[offset]);
 
      if (!conflict)

mm/swapfile.c static bool scan_swap_map_try_ssd_cluster(struct swap_info_struct *si, · line 547

Quoted 10 lines

mm/swapfile.c +3 -4

@@ -655,10 +542,14 @@ static bool scan_swap_map_try_ssd_cluster(struct swap_info_struct *si,
      cluster = this_cpu_ptr(si->percpu_cluster);
      tmp = cluster->next[order];
      if (tmp == SWAP_NEXT_INVALID) {
-             if (!cluster_list_empty(&si->free_clusters)) {
-                     tmp = cluster_next(&si->free_clusters.head) *
-                                     SWAPFILE_CLUSTER;
-             } else if (!cluster_list_empty(&si->discard_clusters)) {
+             if (!list_empty(&si->free_clusters)) {
+                     ci = list_first_entry(&si->free_clusters, struct swap_cluster_info, list);
+                     list_del(&ci->list);

IIRC, we shouldn't delete the cluster from the free list here, because we will delete it later in alloc_cluster().

Quoted 2 lines

mm/swapfile.c +2 -0

+                     spin_lock(&ci->lock);
+                     ci->flags = 0;

Quoted 2 lines

And also shouldn't set ci->flags here too. Because the cluster may be kept in free list if scan_swap_map_ssd_cluster_conflict() returns true.

If we both delete the cluster from the free list and clear the flag here. alloc_cluster() will not see this cluster because the flags have been cleared.
Will that work?

Quoted 10 lines

Quoted 8 lines

mm/swapfile.c +3 -0

+                     spin_unlock(&ci->lock);
+                     tmp = (ci - si->cluster_info) * SWAPFILE_CLUSTER;
+             } else if (!list_empty(&si->discard_clusters)) {
                      /*
                       * we don't have free cluster but have some clusters in
                       * discarding, do discard now and reclaim them, then

[snip]

Quoted 409 lines · Chris Li

Quoted 233 lines · Ying

Quoted 230 lines · Chris Li

Previously, the swap cluster used a cluster index as a pointer to construct a custom single link list type "swap_cluster_list". The next cluster pointer is shared with the cluster->count. It prevents puting the non free cluster into a list.

Change the cluster to use the standard double link list instead. This allows tracing the nonfull cluster in the follow up patch. That way, it is faster to get to the nonfull cluster of that order.

Remove the cluster getter/setter for accessing the cluster struct member.

The list operation is protected by the swap_info_struct->lock.

Change cluster code to use "struct swap_cluster_info *" to reference the cluster rather than by using index. That is more consistent with the list manipulation. It avoids the repeat adding index to the cluser_info. The code is easier to understand.

Remove the cluster next pointer is NULL flag, the double link list can handle the empty list pretty well.

The "swap_cluster_info" struct is two pointer bigger, because 512 swap entries share one swap struct, it has very little impact on the average memory usage per swap entry. For 1TB swapfile, the swap cluster data structure increases from 8MB to 24MB.

Other than the list conversion, there is no real function change in this patch.

Signed-off-by Chris Li <[email protected]>

---
 include/linux/swap.h |  26 +++---
 mm/swapfile.c        | 227 ++++++++++++++-------------------------------------
 2 files changed, 70 insertions(+), 183 deletions(-)

include/linux/swap.h +10 -16

index 3df75d62a835..690a04f06674 100644
@@ -243,22 +243,21 @@ enum {
  * free clusters are organized into a list. We fetch an entry from the list to
  * get a free cluster.
  *
- * The data field stores next cluster if the cluster is free or cluster usage
- * counter otherwise. The flags field determines if a cluster is free. This is
- * protected by swap_info_struct.lock.
+ * The flags field determines if a cluster is free. This is
+ * protected by cluster lock.
  */
 struct swap_cluster_info {
      spinlock_t lock;        /*
                               * Protect swap_cluster_info fields
-                              * and swap_info_struct->swap_map
-                              * elements correspond to the swap
-                              * cluster
+                              * other than list, and swap_info_struct->swap_map
+                              * elements correspond to the swap cluster.
                               */
-     unsigned int data:24;
-     unsigned int flags:8;
+     u16 count;
+     u8 flags;
+     struct list_head list;
 };
 #define CLUSTER_FLAG_FREE 1 /* This cluster is free */
-#define CLUSTER_FLAG_NEXT_NULL 2 /* This cluster has no next cluster */
+
 
 /*
  * The first page in the swap file is the swap header, which is always marked

@@ -283,11 +282,6 @@ struct percpu_cluster {
      unsigned int next[SWAP_NR_ORDERS]; /* Likely next allocation offset */
 };
 
-struct swap_cluster_list {
-     struct swap_cluster_info head;
-     struct swap_cluster_info tail;
-};
-
 /*
  * The in-memory structure used to track swap areas.
  */

@@ -300,7 +294,7 @@ struct swap_info_struct {
      unsigned int    max;            /* extent of the swap_map */
      unsigned char *swap_map;        /* vmalloc'ed array of usage counts */
      struct swap_cluster_info *cluster_info; /* cluster info. Only for SSD */
-     struct swap_cluster_list free_clusters; /* free clusters list */
+     struct list_head free_clusters; /* free clusters list */
      unsigned int lowest_bit;        /* index of first free in swap_map */
      unsigned int highest_bit;       /* index of last free in swap_map */
      unsigned int pages;             /* total of usable pages of swap */

@@ -331,7 +325,7 @@ struct swap_info_struct {
                                       * list.
                                       */
      struct work_struct discard_work; /* discard worker */
-     struct swap_cluster_list discard_clusters; /* discard clusters list */
+     struct list_head discard_clusters; /* discard clusters list */
      struct plist_node avail_lists[]; /*
                                         * entries in swap_avail_heads, one
                                         * entry per node.

mm/swapfile.c +0 -108

index 9c6d8e557c0f..0b11c437f9cc 100644
@@ -290,64 +290,11 @@ static void discard_swap_cluster(struct swap_info_struct *si,
 #endif
 #define LATENCY_LIMIT                256
 
-static inline void cluster_set_flag(struct swap_cluster_info *info,
-     unsigned int flag)
-{
-     info->flags = flag;
-}
-
-static inline unsigned int cluster_count(struct swap_cluster_info *info)
-{
-     return info->data;
-}
-
-static inline void cluster_set_count(struct swap_cluster_info *info,
-                                  unsigned int c)
-{
-     info->data = c;
-}
-
-static inline void cluster_set_count_flag(struct swap_cluster_info *info,
-                                      unsigned int c, unsigned int f)
-{
-     info->flags = f;
-     info->data = c;
-}
-
-static inline unsigned int cluster_next(struct swap_cluster_info *info)
-{
-     return info->data;
-}
-
-static inline void cluster_set_next(struct swap_cluster_info *info,
-                                 unsigned int n)
-{
-     info->data = n;
-}
-
-static inline void cluster_set_next_flag(struct swap_cluster_info *info,
-                                      unsigned int n, unsigned int f)
-{
-     info->flags = f;
-     info->data = n;
-}
-
 static inline bool cluster_is_free(struct swap_cluster_info *info)
 {
      return info->flags & CLUSTER_FLAG_FREE;
 }
 
-static inline bool cluster_is_null(struct swap_cluster_info *info)
-{
-     return info->flags & CLUSTER_FLAG_NEXT_NULL;
-}
-
-static inline void cluster_set_null(struct swap_cluster_info *info)
-{
-     info->flags = CLUSTER_FLAG_NEXT_NULL;
-     info->data = 0;
-}
-
 static inline struct swap_cluster_info *lock_cluster(struct swap_info_struct *si,
                                                   unsigned long offset)
 {

@@ -394,65 +341,11 @@ static inline void unlock_cluster_or_swap_info(struct swap_info_struct *si,
              spin_unlock(&si->lock);
 }
 
-static inline bool cluster_list_empty(struct swap_cluster_list *list)
-{
-     return cluster_is_null(&list->head);
-}
-
-static inline unsigned int cluster_list_first(struct swap_cluster_list *list)
-{
-     return cluster_next(&list->head);
-}
-
-static void cluster_list_init(struct swap_cluster_list *list)
-{
-     cluster_set_null(&list->head);
-     cluster_set_null(&list->tail);
-}
-
-static void cluster_list_add_tail(struct swap_cluster_list *list,
-                               struct swap_cluster_info *ci,
-                               unsigned int idx)
-{
-     if (cluster_list_empty(list)) {
-             cluster_set_next_flag(&list->head, idx, 0);
-             cluster_set_next_flag(&list->tail, idx, 0);
-     } else {
-             struct swap_cluster_info *ci_tail;
-             unsigned int tail = cluster_next(&list->tail);
-
-             /*
-              * Nested cluster lock, but both cluster locks are
-              * only acquired when we held swap_info_struct->lock
-              */
-             ci_tail = ci + tail;
-             spin_lock_nested(&ci_tail->lock, SINGLE_DEPTH_NESTING);
-             cluster_set_next(ci_tail, idx);
-             spin_unlock(&ci_tail->lock);
-             cluster_set_next_flag(&list->tail, idx, 0);
-     }
-}
-
-static unsigned int cluster_list_del_first(struct swap_cluster_list *list,
-                                        struct swap_cluster_info *ci)
-{
-     unsigned int idx;
-
-     idx = cluster_next(&list->head);
-     if (cluster_next(&list->tail) == idx) {
-             cluster_set_null(&list->head);
-             cluster_set_null(&list->tail);
-     } else
-             cluster_set_next_flag(&list->head,
-                                   cluster_next(&ci[idx]), 0);
-
-     return idx;
-}
-
 /* Add a cluster to discard list and schedule it to do discard */

Quoted 8 lines

mm/swapfile.c static inline void unlock_cluster_or_swap_info(struct swap_info_struct *si, · line 348

Quoted 5 lines

mm/swapfile.c +2 -1

 static void swap_cluster_schedule_discard(struct swap_info_struct *si,
-             unsigned int idx)
+             struct swap_cluster_info *ci)
 {
+     unsigned int idx = ci - si->cluster_info;

IIRC, we have reached consensus that we will add a helper for this pattern.

Yes, sorry about that. When I drop the V2 fixup branch, I forget to update that.

Quoted 12 lines

Quoted 12 lines

mm/swapfile.c +4 -2

-     while (!cluster_list_empty(&si->discard_clusters)) {
-             idx = cluster_list_del_first(&si->discard_clusters, info);
+     while (!list_empty(&si->discard_clusters)) {
+             ci = list_first_entry(&si->discard_clusters, struct swap_cluster_info, list);
+             list_del(&ci->list);
+             idx = ci - si->cluster_info;
              spin_unlock(&si->lock);
 
              discard_swap_cluster(si, idx * SWAPFILE_CLUSTER,
                              SWAPFILE_CLUSTER);

Quoted 9 lines

mm/swapfile.c static void __free_cluster(struct swap_info_struct *si, unsigned long idx) · line 388

Quoted 5 lines

              spin_lock(&si->lock);

mm/swapfile.c +2 -2

-             ci = lock_cluster(si, idx * SWAPFILE_CLUSTER);
-             __free_cluster(si, idx);
+
+             spin_lock(&ci->lock);

If you really don't like lock_cluster(), please replace unlock_cluster() below with spin_unlock() too.

Done. Switch to spin_unlock().

Quoted 136 lines

Quoted 117 lines

mm/swapfile.c +28 -31

+             __free_cluster(si, ci);
              memset(si->swap_map + idx * SWAPFILE_CLUSTER,
                              0, SWAPFILE_CLUSTER);
              unlock_cluster(ci);

@@ -521,20 +412,20 @@ static void swap_users_ref_free(struct percpu_ref *ref)
      complete(&si->comp);
 }
 
-static void alloc_cluster(struct swap_info_struct *si, unsigned long idx)
+static struct swap_cluster_info *alloc_cluster(struct swap_info_struct *si, unsigned long idx)
 {
-     struct swap_cluster_info *ci = si->cluster_info;
+     struct swap_cluster_info *ci = list_first_entry(&si->free_clusters, struct swap_cluster_info, list);
 
-     VM_BUG_ON(cluster_list_first(&si->free_clusters) != idx);
-     cluster_list_del_first(&si->free_clusters, ci);
-     cluster_set_count_flag(ci + idx, 0, 0);
+     VM_BUG_ON(ci - si->cluster_info != idx);
+     list_del(&ci->list);
+     ci->count = 0;
+     ci->flags = 0;
+     return ci;
 }
 
-static void free_cluster(struct swap_info_struct *si, unsigned long idx)
+static void free_cluster(struct swap_info_struct *si, struct swap_cluster_info *ci)
 {
-     struct swap_cluster_info *ci = si->cluster_info + idx;
-
-     VM_BUG_ON(cluster_count(ci) != 0);
+     VM_BUG_ON(ci->count != 0);
      /*
       * If the swap is discardable, prepare discard the cluster
       * instead of free it immediately. The cluster will be freed

@@ -542,11 +433,11 @@ static void free_cluster(struct swap_info_struct *si, unsigned long idx)
       */
      if ((si->flags & (SWP_WRITEOK | SWP_PAGE_DISCARD)) ==
          (SWP_WRITEOK | SWP_PAGE_DISCARD)) {
-             swap_cluster_schedule_discard(si, idx);
+             swap_cluster_schedule_discard(si, ci);
              return;
      }
 
-     __free_cluster(si, idx);
+     __free_cluster(si, ci);
 }
 
 /*

@@ -559,15 +450,15 @@ static void add_cluster_info_page(struct swap_info_struct *p,
      unsigned long count)
 {
      unsigned long idx = page_nr / SWAPFILE_CLUSTER;
+     struct swap_cluster_info *ci = cluster_info + idx;
 
      if (!cluster_info)
              return;
-     if (cluster_is_free(&cluster_info[idx]))
+     if (cluster_is_free(ci))
              alloc_cluster(p, idx);
 
-     VM_BUG_ON(cluster_count(&cluster_info[idx]) + count > SWAPFILE_CLUSTER);
-     cluster_set_count(&cluster_info[idx],
-             cluster_count(&cluster_info[idx]) + count);
+     VM_BUG_ON(ci->count + count > SWAPFILE_CLUSTER);
+     ci->count += count;
 }
 
 /*

@@ -581,24 +472,20 @@ static void inc_cluster_info_page(struct swap_info_struct *p,
 }
 
 /*
- * The cluster corresponding to page_nr decreases one usage. If the usage
- * counter becomes 0, which means no page in the cluster is in using, we can
- * optionally discard the cluster and add it to free cluster list.
+ * The cluster ci decreases one usage. If the usage counter becomes 0,
+ * which means no page in the cluster is in using, we can optionally discard
+ * the cluster and add it to free cluster list.
  */
-static void dec_cluster_info_page(struct swap_info_struct *p,
-     struct swap_cluster_info *cluster_info, unsigned long page_nr)
+static void dec_cluster_info_page(struct swap_info_struct *p, struct swap_cluster_info *ci)
 {
-     unsigned long idx = page_nr / SWAPFILE_CLUSTER;
-
-     if (!cluster_info)
+     if (!p->cluster_info)
              return;
 
-     VM_BUG_ON(cluster_count(&cluster_info[idx]) == 0);
-     cluster_set_count(&cluster_info[idx],
-             cluster_count(&cluster_info[idx]) - 1);
+     VM_BUG_ON(ci->count == 0);
+     ci->count--;
 
-     if (cluster_count(&cluster_info[idx]) == 0)
-             free_cluster(p, idx);
+     if (!ci->count)
+             free_cluster(p, ci);
 }
 
 /*

@@ -611,10 +498,10 @@ scan_swap_map_ssd_cluster_conflict(struct swap_info_struct *si,
 {
      struct percpu_cluster *percpu_cluster;
      bool conflict;
-
+     struct swap_cluster_info *first = list_first_entry(&si->free_clusters, struct swap_cluster_info, list);
      offset /= SWAPFILE_CLUSTER;
-     conflict = !cluster_list_empty(&si->free_clusters) &&
-             offset != cluster_list_first(&si->free_clusters) &&
+     conflict = !list_empty(&si->free_clusters) &&
+             offset !=  first - si->cluster_info &&
              cluster_is_free(&si->cluster_info[offset]);
 
      if (!conflict)

mm/swapfile.c static bool scan_swap_map_try_ssd_cluster(struct swap_info_struct *si, · line 547

Quoted 10 lines

mm/swapfile.c +3 -4

@@ -655,10 +542,14 @@ static bool scan_swap_map_try_ssd_cluster(struct swap_info_struct *si,
      cluster = this_cpu_ptr(si->percpu_cluster);
      tmp = cluster->next[order];
      if (tmp == SWAP_NEXT_INVALID) {
-             if (!cluster_list_empty(&si->free_clusters)) {
-                     tmp = cluster_next(&si->free_clusters.head) *
-                                     SWAPFILE_CLUSTER;
-             } else if (!cluster_list_empty(&si->discard_clusters)) {
+             if (!list_empty(&si->free_clusters)) {
+                     ci = list_first_entry(&si->free_clusters, struct swap_cluster_info, list);
+                     list_del(&ci->list);

IIRC, we shouldn't delete the cluster from the free list here, because we will delete it later in alloc_cluster().

mm/swapfile.c static bool scan_swap_map_try_ssd_cluster(struct swap_info_struct *si, · line 549

Quoted 2 lines

mm/swapfile.c +2 -0

+                     spin_lock(&ci->lock);
+                     ci->flags = 0;

And also shouldn't set ci->flags here too. Because the cluster may be kept in free list if scan_swap_map_ssd_cluster_conflict() returns true.

Quoted 4 lines

If we both delete the cluster from the free list and clear the flag here. alloc_cluster() will not see this cluster because the flags have been cleared.
Will that work?

You are right. This works.

However, I think that it's better to change as less as possible except converting cluster list implementation. If we don't delete the cluster from the free cluster list here and leave it to alloc_cluster(), does it work? If so, we can make the patch smaller and focused. If necessary, we can make the change in the later patch of the series.

This is the short term solutiolns "swap cluster order" listed in my "Swap Abstraction" discussion slice 8 in the recent LSF/MM conference.

When commit 845982eb264bc "mm: swap: allow storage of all mTHP orders" is introduced, it only allocates the mTHP swap entries from new empty cluster list. It has a fragmentation issue reported by Barry.

https://lore.kernel.org/all/CAGsJ_4zAcJkuW016Cfi6wicRr8N9X+GJJhgMQdSMp+Ah+NSgNQ@mail.gmail.com/

The reason is that all the empty cluster has been exhausted while there are planty of free swap entries to in the cluster that is not 100% free.

Remember the swap allocation order in the cluster.
Keep track of the per order non full cluster list for later allocation.

User impact: For users that allocate and free mix order mTHP swapping, It greatly improves the success rate of the mTHP swap allocation after the initial phase.

Barry provides a test program to show the effect:
https://lore.kernel.org/linux-mm/[email protected]/

Without:

$ mthp-swapout                                                          
Iteration 1: swpout inc: 222, swpout fallback inc: 0, Fallback percentage: 0.00%   
Iteration 2: swpout inc: 219, swpout fallback inc: 0, Fallback percentage: 0.00%                                                    
Iteration 3: swpout inc: 222, swpout fallback inc: 0, Fallback percentage: 0.00%   
Iteration 4: swpout inc: 219, swpout fallback inc: 0, Fallback percentage: 0.00%            
Iteration 5: swpout inc: 110, swpout fallback inc: 117, Fallback percentage: 51.54%                                                 
Iteration 6: swpout inc: 0, swpout fallback inc: 230, Fallback percentage: 100.00%          
Iteration 7: swpout inc: 0, swpout fallback inc: 229, Fallback percentage: 100.00% 
Iteration 8: swpout inc: 0, swpout fallback inc: 223, Fallback percentage: 100.00%                                                  
Iteration 9: swpout inc: 0, swpout fallback inc: 224, Fallback percentage: 100.00%                                                  
Iteration 10: swpout inc: 0, swpout fallback inc: 216, Fallback percentage: 100.00%                                                 
Iteration 11: swpout inc: 0, swpout fallback inc: 212, Fallback percentage: 100.00%                                                 
Iteration 12: swpout inc: 0, swpout fallback inc: 224, Fallback percentage: 100.00%                                                 
Iteration 13: swpout inc: 0, swpout fallback inc: 214, Fallback percentage: 100.00%        

$ mthp-swapout -s
Iteration 1: swpout inc: 222, swpout fallback inc: 0, Fallback percentage: 0.00%
Iteration 2: swpout inc: 227, swpout fallback inc: 0, Fallback percentage: 0.00%
Iteration 3: swpout inc: 222, swpout fallback inc: 0, Fallback percentage: 0.00%
Iteration 4: swpout inc: 224, swpout fallback inc: 0, Fallback percentage: 0.00%
Iteration 5: swpout inc: 33, swpout fallback inc: 197, Fallback percentage: 85.65%
Iteration 6: swpout inc: 0, swpout fallback inc: 229, Fallback percentage: 100.00%
Iteration 7: swpout inc: 0, swpout fallback inc: 223, Fallback percentage: 100.00%
Iteration 8: swpout inc: 0, swpout fallback inc: 219, Fallback percentage: 100.00%
Iteration 9: swpout inc: 0, swpout fallback inc: 212, Fallback percentage: 100.00%

With:

$ mthp-swapout       
Iteration 1: swpout inc: 222, swpout fallback inc: 0, Fallback percentage: 0.00%                                                    
Iteration 2: swpout inc: 219, swpout fallback inc: 0, Fallback percentage: 0.00%                                                    
Iteration 3: swpout inc: 222, swpout fallback inc: 0, Fallback percentage: 0.00%                                                    
Iteration 4: swpout inc: 219, swpout fallback inc: 0, Fallback percentage: 0.00%       
Iteration 5: swpout inc: 227, swpout fallback inc: 0, Fallback percentage: 0.00% 
Iteration 6: swpout inc: 230, swpout fallback inc: 0, Fallback percentage: 0.00%            
...
Iteration 94: swpout inc: 224, swpout fallback inc: 0, Fallback percentage: 0.00%
Iteration 95: swpout inc: 221, swpout fallback inc: 0, Fallback percentage: 0.00%
Iteration 96: swpout inc: 229, swpout fallback inc: 0, Fallback percentage: 0.00%
Iteration 97: swpout inc: 219, swpout fallback inc: 0, Fallback percentage: 0.00%
Iteration 98: swpout inc: 222, swpout fallback inc: 0, Fallback percentage: 0.00%
Iteration 99: swpout inc: 223, swpout fallback inc: 0, Fallback percentage: 0.00%
Iteration 100: swpout inc: 224, swpout fallback inc: 0, Fallback percentage: 0.00%

$ mthp-swapout -s
Iteration 1: swpout inc: 222, swpout fallback inc: 0, Fallback percentage: 0.00%
Iteration 2: swpout inc: 227, swpout fallback inc: 0, Fallback percentage: 0.00%
Iteration 3: swpout inc: 222, swpout fallback inc: 0, Fallback percentage: 0.00%
Iteration 4: swpout inc: 224, swpout fallback inc: 0, Fallback percentage: 0.00%
Iteration 5: swpout inc: 230, swpout fallback inc: 0, Fallback percentage: 0.00%
Iteration 6: swpout inc: 229, swpout fallback inc: 0, Fallback percentage: 0.00%
Iteration 7: swpout inc: 223, swpout fallback inc: 0, Fallback percentage: 0.00%
Iteration 8: swpout inc: 219, swpout fallback inc: 0, Fallback percentage: 0.00%

...
Iteration 94: swpout inc: 223, swpout fallback inc: 0, Fallback percentage: 0.00%
Iteration 95: swpout inc: 212, swpout fallback inc: 0, Fallback percentage: 0.00%
Iteration 96: swpout inc: 220, swpout fallback inc: 0, Fallback percentage: 0.00%
Iteration 97: swpout inc: 220, swpout fallback inc: 0, Fallback percentage: 0.00%
Iteration 98: swpout inc: 216, swpout fallback inc: 0, Fallback percentage: 0.00%
Iteration 99: swpout inc: 223, swpout fallback inc: 0, Fallback percentage: 0.00%
Iteration 100: swpout inc: 225, swpout fallback inc: 0, Fallback percentage: 0.00%

Reported-by Barry Song <[email protected]>

Signed-off-by Chris Li <[email protected]>

---
Changes in v3:
- Using V1 as base.
- Rename "next" to "list" for the list field, suggested by Ying.
- Update comment for the locking rules for cluster fields and list, suggested by Ying.
- Allocate from the nonfull list before attempting free list, suggested by Kairui.

- Link to v2: https://lore.kernel.org/r/[email protected]

Changes in v2:
- Abandoned.
- Link to v1: https://lore.kernel.org/r/[email protected]

---
Chris Li (2):
mm: swap: swap cluster switch to double link list
mm: swap: mTHP allocate swap entries from nonfull list

 include/linux/swap.h |  30 +++----
 mm/swapfile.c        | 248 +++++++++++++++++----------------------------------
 2 files changed, 95 insertions(+), 183 deletions(-)

---
base-commit: 19b8422c5bd56fb5e7085995801c6543a98bda1f
change-id: 20240523-swap-allocator-1534c480ece4

Best regards,

This is the short term solutiolns "swap cluster order" listed in my "Swap Abstraction" discussion slice 8 in the recent LSF/MM conference.

When commit 845982eb264bc "mm: swap: allow storage of all mTHP orders" is introduced, it only allocates the mTHP swap entries from new empty cluster list. It has a fragmentation issue reported by Barry.

https://lore.kernel.org/all/CAGsJ_4zAcJkuW016Cfi6wicRr8N9X+GJJhgMQdSMp+Ah+NSgNQ@mail.gmail.com/

The reason is that all the empty cluster has been exhausted while there are planty of free swap entries to in the cluster that is not 100% free.

Remember the swap allocation order in the cluster.
Keep track of the per order non full cluster list for later allocation.

User impact: For users that allocate and free mix order mTHP swapping, It greatly improves the success rate of the mTHP swap allocation after the initial phase.

Barry provides a test program to show the effect:
https://lore.kernel.org/linux-mm/[email protected]/

Without:

$ mthp-swapout                                                          
Iteration 1: swpout inc: 222, swpout fallback inc: 0, Fallback percentage: 0.00%   
Iteration 2: swpout inc: 219, swpout fallback inc: 0, Fallback percentage: 0.00%                                                    
Iteration 3: swpout inc: 222, swpout fallback inc: 0, Fallback percentage: 0.00%   
Iteration 4: swpout inc: 219, swpout fallback inc: 0, Fallback percentage: 0.00%            
Iteration 5: swpout inc: 110, swpout fallback inc: 117, Fallback percentage: 51.54%                                                 
Iteration 6: swpout inc: 0, swpout fallback inc: 230, Fallback percentage: 100.00%          
Iteration 7: swpout inc: 0, swpout fallback inc: 229, Fallback percentage: 100.00% 
Iteration 8: swpout inc: 0, swpout fallback inc: 223, Fallback percentage: 100.00%                                                  
Iteration 9: swpout inc: 0, swpout fallback inc: 224, Fallback percentage: 100.00%                                                  
Iteration 10: swpout inc: 0, swpout fallback inc: 216, Fallback percentage: 100.00%                                                 
Iteration 11: swpout inc: 0, swpout fallback inc: 212, Fallback percentage: 100.00%                                                 
Iteration 12: swpout inc: 0, swpout fallback inc: 224, Fallback percentage: 100.00%                                                 
Iteration 13: swpout inc: 0, swpout fallback inc: 214, Fallback percentage: 100.00%        

$ mthp-swapout -s
Iteration 1: swpout inc: 222, swpout fallback inc: 0, Fallback percentage: 0.00%
Iteration 2: swpout inc: 227, swpout fallback inc: 0, Fallback percentage: 0.00%
Iteration 3: swpout inc: 222, swpout fallback inc: 0, Fallback percentage: 0.00%
Iteration 4: swpout inc: 224, swpout fallback inc: 0, Fallback percentage: 0.00%
Iteration 5: swpout inc: 33, swpout fallback inc: 197, Fallback percentage: 85.65%
Iteration 6: swpout inc: 0, swpout fallback inc: 229, Fallback percentage: 100.00%
Iteration 7: swpout inc: 0, swpout fallback inc: 223, Fallback percentage: 100.00%
Iteration 8: swpout inc: 0, swpout fallback inc: 219, Fallback percentage: 100.00%
Iteration 9: swpout inc: 0, swpout fallback inc: 212, Fallback percentage: 100.00%

With:

$ mthp-swapout       
Iteration 1: swpout inc: 222, swpout fallback inc: 0, Fallback percentage: 0.00%                                                    
Iteration 2: swpout inc: 219, swpout fallback inc: 0, Fallback percentage: 0.00%                                                    
Iteration 3: swpout inc: 222, swpout fallback inc: 0, Fallback percentage: 0.00%                                                    
Iteration 4: swpout inc: 219, swpout fallback inc: 0, Fallback percentage: 0.00%       
Iteration 5: swpout inc: 227, swpout fallback inc: 0, Fallback percentage: 0.00% 
Iteration 6: swpout inc: 230, swpout fallback inc: 0, Fallback percentage: 0.00%            
...
Iteration 94: swpout inc: 224, swpout fallback inc: 0, Fallback percentage: 0.00%
Iteration 95: swpout inc: 221, swpout fallback inc: 0, Fallback percentage: 0.00%
Iteration 96: swpout inc: 229, swpout fallback inc: 0, Fallback percentage: 0.00%
Iteration 97: swpout inc: 219, swpout fallback inc: 0, Fallback percentage: 0.00%
Iteration 98: swpout inc: 222, swpout fallback inc: 0, Fallback percentage: 0.00%
Iteration 99: swpout inc: 223, swpout fallback inc: 0, Fallback percentage: 0.00%
Iteration 100: swpout inc: 224, swpout fallback inc: 0, Fallback percentage: 0.00%

$ mthp-swapout -s
Iteration 1: swpout inc: 222, swpout fallback inc: 0, Fallback percentage: 0.00%
Iteration 2: swpout inc: 227, swpout fallback inc: 0, Fallback percentage: 0.00%
Iteration 3: swpout inc: 222, swpout fallback inc: 0, Fallback percentage: 0.00%
Iteration 4: swpout inc: 224, swpout fallback inc: 0, Fallback percentage: 0.00%
Iteration 5: swpout inc: 230, swpout fallback inc: 0, Fallback percentage: 0.00%
Iteration 6: swpout inc: 229, swpout fallback inc: 0, Fallback percentage: 0.00%
Iteration 7: swpout inc: 223, swpout fallback inc: 0, Fallback percentage: 0.00%
Iteration 8: swpout inc: 219, swpout fallback inc: 0, Fallback percentage: 0.00%

...
Iteration 94: swpout inc: 223, swpout fallback inc: 0, Fallback percentage: 0.00%
Iteration 95: swpout inc: 212, swpout fallback inc: 0, Fallback percentage: 0.00%
Iteration 96: swpout inc: 220, swpout fallback inc: 0, Fallback percentage: 0.00%
Iteration 97: swpout inc: 220, swpout fallback inc: 0, Fallback percentage: 0.00%
Iteration 98: swpout inc: 216, swpout fallback inc: 0, Fallback percentage: 0.00%
Iteration 99: swpout inc: 223, swpout fallback inc: 0, Fallback percentage: 0.00%
Iteration 100: swpout inc: 225, swpout fallback inc: 0, Fallback percentage: 0.00%

Reported-by Barry Song <[email protected]>

Signed-off-by Chris Li <[email protected]>

---
Changes in v3:
- Using V1 as base.
- Rename "next" to "list" for the list field, suggested by Ying.
- Update comment for the locking rules for cluster fields and list, suggested by Ying.
- Allocate from the nonfull list before attempting free list, suggested by Kairui.

Quoted 78 lines · Chris Li

This is the short term solutiolns "swap cluster order" listed in my "Swap Abstraction" discussion slice 8 in the recent LSF/MM conference.

When commit 845982eb264bc "mm: swap: allow storage of all mTHP orders" is introduced, it only allocates the mTHP swap entries from new empty cluster list. It has a fragmentation issue reported by Barry.

https://lore.kernel.org/all/CAGsJ_4zAcJkuW016Cfi6wicRr8N9X+GJJhgMQdSMp+Ah+NSgNQ@mail.gmail.com/

The reason is that all the empty cluster has been exhausted while there are planty of free swap entries to in the cluster that is not 100% free.

Remember the swap allocation order in the cluster.
Keep track of the per order non full cluster list for later allocation.

User impact: For users that allocate and free mix order mTHP swapping, It greatly improves the success rate of the mTHP swap allocation after the initial phase.

Barry provides a test program to show the effect:
https://lore.kernel.org/linux-mm/[email protected]/

Without:

$ mthp-swapout
Iteration 1: swpout inc: 222, swpout fallback inc: 0, Fallback percentage: 0.00%
Iteration 2: swpout inc: 219, swpout fallback inc: 0, Fallback percentage: 0.00%
Iteration 3: swpout inc: 222, swpout fallback inc: 0, Fallback percentage: 0.00%
Iteration 4: swpout inc: 219, swpout fallback inc: 0, Fallback percentage: 0.00%
Iteration 5: swpout inc: 110, swpout fallback inc: 117, Fallback percentage: 51.54%
Iteration 6: swpout inc: 0, swpout fallback inc: 230, Fallback percentage: 100.00%
Iteration 7: swpout inc: 0, swpout fallback inc: 229, Fallback percentage: 100.00%
Iteration 8: swpout inc: 0, swpout fallback inc: 223, Fallback percentage: 100.00%
Iteration 9: swpout inc: 0, swpout fallback inc: 224, Fallback percentage: 100.00%
Iteration 10: swpout inc: 0, swpout fallback inc: 216, Fallback percentage: 100.00%
Iteration 11: swpout inc: 0, swpout fallback inc: 212, Fallback percentage: 100.00%
Iteration 12: swpout inc: 0, swpout fallback inc: 224, Fallback percentage: 100.00%
Iteration 13: swpout inc: 0, swpout fallback inc: 214, Fallback percentage: 100.00%

$ mthp-swapout -s
Iteration 1: swpout inc: 222, swpout fallback inc: 0, Fallback percentage: 0.00%
Iteration 2: swpout inc: 227, swpout fallback inc: 0, Fallback percentage: 0.00%
Iteration 3: swpout inc: 222, swpout fallback inc: 0, Fallback percentage: 0.00%
Iteration 4: swpout inc: 224, swpout fallback inc: 0, Fallback percentage: 0.00%
Iteration 5: swpout inc: 33, swpout fallback inc: 197, Fallback percentage: 85.65%
Iteration 6: swpout inc: 0, swpout fallback inc: 229, Fallback percentage: 100.00%
Iteration 7: swpout inc: 0, swpout fallback inc: 223, Fallback percentage: 100.00%
Iteration 8: swpout inc: 0, swpout fallback inc: 219, Fallback percentage: 100.00%
Iteration 9: swpout inc: 0, swpout fallback inc: 212, Fallback percentage: 100.00%

With:

$ mthp-swapout
Iteration 1: swpout inc: 222, swpout fallback inc: 0, Fallback percentage: 0.00%
Iteration 2: swpout inc: 219, swpout fallback inc: 0, Fallback percentage: 0.00%
Iteration 3: swpout inc: 222, swpout fallback inc: 0, Fallback percentage: 0.00%
Iteration 4: swpout inc: 219, swpout fallback inc: 0, Fallback percentage: 0.00%
Iteration 5: swpout inc: 227, swpout fallback inc: 0, Fallback percentage: 0.00%
Iteration 6: swpout inc: 230, swpout fallback inc: 0, Fallback percentage: 0.00%
...
Iteration 94: swpout inc: 224, swpout fallback inc: 0, Fallback percentage: 0.00%
Iteration 95: swpout inc: 221, swpout fallback inc: 0, Fallback percentage: 0.00%
Iteration 96: swpout inc: 229, swpout fallback inc: 0, Fallback percentage: 0.00%
Iteration 97: swpout inc: 219, swpout fallback inc: 0, Fallback percentage: 0.00%
Iteration 98: swpout inc: 222, swpout fallback inc: 0, Fallback percentage: 0.00%
Iteration 99: swpout inc: 223, swpout fallback inc: 0, Fallback percentage: 0.00%
Iteration 100: swpout inc: 224, swpout fallback inc: 0, Fallback percentage: 0.00%

$ mthp-swapout -s
Iteration 1: swpout inc: 222, swpout fallback inc: 0, Fallback percentage: 0.00%
Iteration 2: swpout inc: 227, swpout fallback inc: 0, Fallback percentage: 0.00%
Iteration 3: swpout inc: 222, swpout fallback inc: 0, Fallback percentage: 0.00%
Iteration 4: swpout inc: 224, swpout fallback inc: 0, Fallback percentage: 0.00%
Iteration 5: swpout inc: 230, swpout fallback inc: 0, Fallback percentage: 0.00%
Iteration 6: swpout inc: 229, swpout fallback inc: 0, Fallback percentage: 0.00%
Iteration 7: swpout inc: 223, swpout fallback inc: 0, Fallback percentage: 0.00%
Iteration 8: swpout inc: 219, swpout fallback inc: 0, Fallback percentage: 0.00%

Quoted 8 lines

...
Iteration 94: swpout inc: 223, swpout fallback inc: 0, Fallback percentage: 0.00%
Iteration 95: swpout inc: 212, swpout fallback inc: 0, Fallback percentage: 0.00%
Iteration 96: swpout inc: 220, swpout fallback inc: 0, Fallback percentage: 0.00%
Iteration 97: swpout inc: 220, swpout fallback inc: 0, Fallback percentage: 0.00%
Iteration 98: swpout inc: 216, swpout fallback inc: 0, Fallback percentage: 0.00%
Iteration 99: swpout inc: 223, swpout fallback inc: 0, Fallback percentage: 0.00%
Iteration 100: swpout inc: 225, swpout fallback inc: 0, Fallback percentage: 0.00%

Unfortunately, the data is gotten using a special designed test program which always swap-in pages with swapped-out size. I don't know whether such workloads exist in reality. Otherwise, you need to wait for mTHP

swap-in to be merged firstly, and people reach consensus that we should always swap-in pages with swapped-out size.

Alternately, we can make some design adjustment to make the patchset work in current situation (mTHP swap-out, normal page swap-in).

- One non-full cluster list for each order (same as current design)

- When one swap entry is freed, check whether one "order+1" swap entry becomes free, if so, move the cluster to "order+1" non-full cluster list.

- When allocate swap entry with "order", get cluster from free, "order", "order+1", ... non-full cluster list. If all are empty, fallback to

order 0.

Do you think that this works?

Quoted 10 lines

Reported-by Barry Song <[email protected]>

Signed-off-by Chris Li <[email protected]>

---
Changes in v3:
- Using V1 as base.
- Rename "next" to "list" for the list field, suggested by Ying.
- Update comment for the locking rules for cluster fields and list, suggested by Ying.
- Allocate from the nonfull list before attempting free list, suggested by Kairui.

Haven't looked into this. It appears that this breaks the original discard behavior which helps performance of some SSD, please refer to

commit 2a8f94493432 ("swap: change block allocation algorithm for SSD").

And as pointed out by Ryan, this may reduce the opportunity of the sequential block device writing during swap-out, which may hurt performance of SSD too.

Quoted 90 lines · Ying

Quoted 78 lines · Chris Li

This is the short term solutiolns "swap cluster order" listed in my "Swap Abstraction" discussion slice 8 in the recent LSF/MM conference.

When commit 845982eb264bc "mm: swap: allow storage of all mTHP orders" is introduced, it only allocates the mTHP swap entries from new empty cluster list. It has a fragmentation issue reported by Barry.

https://lore.kernel.org/all/CAGsJ_4zAcJkuW016Cfi6wicRr8N9X+GJJhgMQdSMp+Ah+NSgNQ@mail.gmail.com/

The reason is that all the empty cluster has been exhausted while there are planty of free swap entries to in the cluster that is not 100% free.

Remember the swap allocation order in the cluster.
Keep track of the per order non full cluster list for later allocation.

User impact: For users that allocate and free mix order mTHP swapping, It greatly improves the success rate of the mTHP swap allocation after the initial phase.

Barry provides a test program to show the effect:
https://lore.kernel.org/linux-mm/[email protected]/

Without:

$ mthp-swapout
Iteration 1: swpout inc: 222, swpout fallback inc: 0, Fallback percentage: 0.00%
Iteration 2: swpout inc: 219, swpout fallback inc: 0, Fallback percentage: 0.00%
Iteration 3: swpout inc: 222, swpout fallback inc: 0, Fallback percentage: 0.00%
Iteration 4: swpout inc: 219, swpout fallback inc: 0, Fallback percentage: 0.00%
Iteration 5: swpout inc: 110, swpout fallback inc: 117, Fallback percentage: 51.54%
Iteration 6: swpout inc: 0, swpout fallback inc: 230, Fallback percentage: 100.00%
Iteration 7: swpout inc: 0, swpout fallback inc: 229, Fallback percentage: 100.00%
Iteration 8: swpout inc: 0, swpout fallback inc: 223, Fallback percentage: 100.00%
Iteration 9: swpout inc: 0, swpout fallback inc: 224, Fallback percentage: 100.00%
Iteration 10: swpout inc: 0, swpout fallback inc: 216, Fallback percentage: 100.00%
Iteration 11: swpout inc: 0, swpout fallback inc: 212, Fallback percentage: 100.00%
Iteration 12: swpout inc: 0, swpout fallback inc: 224, Fallback percentage: 100.00%
Iteration 13: swpout inc: 0, swpout fallback inc: 214, Fallback percentage: 100.00%

$ mthp-swapout -s
Iteration 1: swpout inc: 222, swpout fallback inc: 0, Fallback percentage: 0.00%
Iteration 2: swpout inc: 227, swpout fallback inc: 0, Fallback percentage: 0.00%
Iteration 3: swpout inc: 222, swpout fallback inc: 0, Fallback percentage: 0.00%
Iteration 4: swpout inc: 224, swpout fallback inc: 0, Fallback percentage: 0.00%
Iteration 5: swpout inc: 33, swpout fallback inc: 197, Fallback percentage: 85.65%
Iteration 6: swpout inc: 0, swpout fallback inc: 229, Fallback percentage: 100.00%
Iteration 7: swpout inc: 0, swpout fallback inc: 223, Fallback percentage: 100.00%
Iteration 8: swpout inc: 0, swpout fallback inc: 219, Fallback percentage: 100.00%
Iteration 9: swpout inc: 0, swpout fallback inc: 212, Fallback percentage: 100.00%

With:

$ mthp-swapout
Iteration 1: swpout inc: 222, swpout fallback inc: 0, Fallback percentage: 0.00%
Iteration 2: swpout inc: 219, swpout fallback inc: 0, Fallback percentage: 0.00%
Iteration 3: swpout inc: 222, swpout fallback inc: 0, Fallback percentage: 0.00%
Iteration 4: swpout inc: 219, swpout fallback inc: 0, Fallback percentage: 0.00%
Iteration 5: swpout inc: 227, swpout fallback inc: 0, Fallback percentage: 0.00%
Iteration 6: swpout inc: 230, swpout fallback inc: 0, Fallback percentage: 0.00%
...
Iteration 94: swpout inc: 224, swpout fallback inc: 0, Fallback percentage: 0.00%
Iteration 95: swpout inc: 221, swpout fallback inc: 0, Fallback percentage: 0.00%
Iteration 96: swpout inc: 229, swpout fallback inc: 0, Fallback percentage: 0.00%
Iteration 97: swpout inc: 219, swpout fallback inc: 0, Fallback percentage: 0.00%
Iteration 98: swpout inc: 222, swpout fallback inc: 0, Fallback percentage: 0.00%
Iteration 99: swpout inc: 223, swpout fallback inc: 0, Fallback percentage: 0.00%
Iteration 100: swpout inc: 224, swpout fallback inc: 0, Fallback percentage: 0.00%

$ mthp-swapout -s
Iteration 1: swpout inc: 222, swpout fallback inc: 0, Fallback percentage: 0.00%
Iteration 2: swpout inc: 227, swpout fallback inc: 0, Fallback percentage: 0.00%
Iteration 3: swpout inc: 222, swpout fallback inc: 0, Fallback percentage: 0.00%
Iteration 4: swpout inc: 224, swpout fallback inc: 0, Fallback percentage: 0.00%
Iteration 5: swpout inc: 230, swpout fallback inc: 0, Fallback percentage: 0.00%
Iteration 6: swpout inc: 229, swpout fallback inc: 0, Fallback percentage: 0.00%
Iteration 7: swpout inc: 223, swpout fallback inc: 0, Fallback percentage: 0.00%
Iteration 8: swpout inc: 219, swpout fallback inc: 0, Fallback percentage: 0.00%

Quoted 8 lines

...
Iteration 94: swpout inc: 223, swpout fallback inc: 0, Fallback percentage: 0.00%
Iteration 95: swpout inc: 212, swpout fallback inc: 0, Fallback percentage: 0.00%
Iteration 96: swpout inc: 220, swpout fallback inc: 0, Fallback percentage: 0.00%
Iteration 97: swpout inc: 220, swpout fallback inc: 0, Fallback percentage: 0.00%
Iteration 98: swpout inc: 216, swpout fallback inc: 0, Fallback percentage: 0.00%
Iteration 99: swpout inc: 223, swpout fallback inc: 0, Fallback percentage: 0.00%
Iteration 100: swpout inc: 225, swpout fallback inc: 0, Fallback percentage: 0.00%

Quoted 3 lines

Unfortunately, the data is gotten using a special designed test program which always swap-in pages with swapped-out size. I don't know whether such workloads exist in reality. Otherwise, you need to wait for mTHP

The test program is designed to simulate mTHP swap behavior using zsmalloc and 64KB buffer.
If we insist on only designing for existing workloads, then zsmalloc using 64KB buffer usage will never be able to run, exactly due the kernel has high failure rate allocating swap entries for 64KB. There is a bit of a chick and egg problem there, such a usage can not exist because the kernel can't support it yet. Kernel can't add patches to support it because such simulation tests are not "real".

We need to break this cycle to support something new.

Quoted 2 lines

swap-in to be merged firstly, and people reach consensus that we should always swap-in pages with swapped-out size.

We don't have to be always. We can identify the situation that makes sense. For the zram/zsmalloc 64K buffer usage case, swap out as the same swap in size makes sense.
I think we have agreement on such zsmalloc 64K usage cases we do want to support.

Quoted 4 lines

Alternately, we can make some design adjustment to make the patchset work in current situation (mTHP swap-out, normal page swap-in).

Quoted 5 lines

- One non-full cluster list for each order (same as current design)

- When one swap entry is freed, check whether one "order+1" swap entry becomes free, if so, move the cluster to "order+1" non-full cluster list.

In the intended zsmalloc usage case, there is no order+1 swap entry request.

Moving the cluster to "order+1" will make less cluster available for "order". For that usage case it is negative gain.

Quoted 2 lines

- When allocate swap entry with "order", get cluster from free, "order", "order+1", ... non-full cluster list. If all are empty, fallback to

I don't see that it is useful for the zsmalloc 64K buffer usage case. There will be order 0 and order 4 and nothing else.

How about let's keep it simple for now. If we identify some workload this algorithm can help. We can do that as a follow up step.

Quoted 15 lines

order 0.

Do you think that this works?

Quoted 10 lines

Reported-by Barry Song <[email protected]>

Signed-off-by Chris Li <[email protected]>

---
Changes in v3:
- Using V1 as base.
- Rename "next" to "list" for the list field, suggested by Ying.
- Update comment for the locking rules for cluster fields and list, suggested by Ying.
- Allocate from the nonfull list before attempting free list, suggested by Kairui.

Quoted 2 lines

Haven't looked into this. It appears that this breaks the original discard behavior which helps performance of some SSD, please refer to

Can you clarify by "discard" you mean SSD discard command or just the way swap allocator recycles free clusters?

Quoted 1 line

commit 2a8f94493432 ("swap: change block allocation algorithm for SSD").

I did read that change log. Help me understand in more detail which discard behavior you have in mind. A lot of low end micro SD cards have proper FTL wear leveling now, ssd even better on that.

Quoted 3 lines

And as pointed out by Ryan, this may reduce the opportunity of the sequential block device writing during swap-out, which may hurt performance of SSD too.

Only at the initial phase. If the swap IO continues, after the first pass fills up the swap file, the write will be random on the swapfile anyway. Because the swapfile only issues 2M discards commands when all 512 4K pages are free. The discarded area will be much smaller than the free area on swapfile. That combined with the random write page on the whole swap file. It might produce a worse internal write amplification for SSD, compared to only writing a subset of the swapfile area. I would love to hear from someone who understands SSD internals to confirm or deny my theory.

Even let's assume the SSD wants a free block over a nonfull cluster first. Zswap and zram swap are not subject to SSD property. We might want to have a kernel option to select using nonfree clusters over the free one for zram and zswap (ghost swapfile). That will help contain the fragmented swap area.

Quoted 125 lines · Chris Li

Quoted 90 lines · Ying

Quoted 78 lines · Chris Li

This is the short term solutiolns "swap cluster order" listed in my "Swap Abstraction" discussion slice 8 in the recent LSF/MM conference.

When commit 845982eb264bc "mm: swap: allow storage of all mTHP orders" is introduced, it only allocates the mTHP swap entries from new empty cluster list. It has a fragmentation issue reported by Barry.

https://lore.kernel.org/all/CAGsJ_4zAcJkuW016Cfi6wicRr8N9X+GJJhgMQdSMp+Ah+NSgNQ@mail.gmail.com/

The reason is that all the empty cluster has been exhausted while there are planty of free swap entries to in the cluster that is not 100% free.

Remember the swap allocation order in the cluster.
Keep track of the per order non full cluster list for later allocation.

User impact: For users that allocate and free mix order mTHP swapping, It greatly improves the success rate of the mTHP swap allocation after the initial phase.

Barry provides a test program to show the effect:
https://lore.kernel.org/linux-mm/[email protected]/

Without:

$ mthp-swapout
Iteration 1: swpout inc: 222, swpout fallback inc: 0, Fallback percentage: 0.00%
Iteration 2: swpout inc: 219, swpout fallback inc: 0, Fallback percentage: 0.00%
Iteration 3: swpout inc: 222, swpout fallback inc: 0, Fallback percentage: 0.00%
Iteration 4: swpout inc: 219, swpout fallback inc: 0, Fallback percentage: 0.00%
Iteration 5: swpout inc: 110, swpout fallback inc: 117, Fallback percentage: 51.54%
Iteration 6: swpout inc: 0, swpout fallback inc: 230, Fallback percentage: 100.00%
Iteration 7: swpout inc: 0, swpout fallback inc: 229, Fallback percentage: 100.00%
Iteration 8: swpout inc: 0, swpout fallback inc: 223, Fallback percentage: 100.00%
Iteration 9: swpout inc: 0, swpout fallback inc: 224, Fallback percentage: 100.00%
Iteration 10: swpout inc: 0, swpout fallback inc: 216, Fallback percentage: 100.00%
Iteration 11: swpout inc: 0, swpout fallback inc: 212, Fallback percentage: 100.00%
Iteration 12: swpout inc: 0, swpout fallback inc: 224, Fallback percentage: 100.00%
Iteration 13: swpout inc: 0, swpout fallback inc: 214, Fallback percentage: 100.00%

$ mthp-swapout -s
Iteration 1: swpout inc: 222, swpout fallback inc: 0, Fallback percentage: 0.00%
Iteration 2: swpout inc: 227, swpout fallback inc: 0, Fallback percentage: 0.00%
Iteration 3: swpout inc: 222, swpout fallback inc: 0, Fallback percentage: 0.00%
Iteration 4: swpout inc: 224, swpout fallback inc: 0, Fallback percentage: 0.00%
Iteration 5: swpout inc: 33, swpout fallback inc: 197, Fallback percentage: 85.65%
Iteration 6: swpout inc: 0, swpout fallback inc: 229, Fallback percentage: 100.00%
Iteration 7: swpout inc: 0, swpout fallback inc: 223, Fallback percentage: 100.00%
Iteration 8: swpout inc: 0, swpout fallback inc: 219, Fallback percentage: 100.00%
Iteration 9: swpout inc: 0, swpout fallback inc: 212, Fallback percentage: 100.00%

With:

$ mthp-swapout
Iteration 1: swpout inc: 222, swpout fallback inc: 0, Fallback percentage: 0.00%
Iteration 2: swpout inc: 219, swpout fallback inc: 0, Fallback percentage: 0.00%
Iteration 3: swpout inc: 222, swpout fallback inc: 0, Fallback percentage: 0.00%
Iteration 4: swpout inc: 219, swpout fallback inc: 0, Fallback percentage: 0.00%
Iteration 5: swpout inc: 227, swpout fallback inc: 0, Fallback percentage: 0.00%
Iteration 6: swpout inc: 230, swpout fallback inc: 0, Fallback percentage: 0.00%
...
Iteration 94: swpout inc: 224, swpout fallback inc: 0, Fallback percentage: 0.00%
Iteration 95: swpout inc: 221, swpout fallback inc: 0, Fallback percentage: 0.00%
Iteration 96: swpout inc: 229, swpout fallback inc: 0, Fallback percentage: 0.00%
Iteration 97: swpout inc: 219, swpout fallback inc: 0, Fallback percentage: 0.00%
Iteration 98: swpout inc: 222, swpout fallback inc: 0, Fallback percentage: 0.00%
Iteration 99: swpout inc: 223, swpout fallback inc: 0, Fallback percentage: 0.00%
Iteration 100: swpout inc: 224, swpout fallback inc: 0, Fallback percentage: 0.00%

$ mthp-swapout -s
Iteration 1: swpout inc: 222, swpout fallback inc: 0, Fallback percentage: 0.00%
Iteration 2: swpout inc: 227, swpout fallback inc: 0, Fallback percentage: 0.00%
Iteration 3: swpout inc: 222, swpout fallback inc: 0, Fallback percentage: 0.00%
Iteration 4: swpout inc: 224, swpout fallback inc: 0, Fallback percentage: 0.00%
Iteration 5: swpout inc: 230, swpout fallback inc: 0, Fallback percentage: 0.00%
Iteration 6: swpout inc: 229, swpout fallback inc: 0, Fallback percentage: 0.00%
Iteration 7: swpout inc: 223, swpout fallback inc: 0, Fallback percentage: 0.00%
Iteration 8: swpout inc: 219, swpout fallback inc: 0, Fallback percentage: 0.00%

Quoted 8 lines

...
Iteration 94: swpout inc: 223, swpout fallback inc: 0, Fallback percentage: 0.00%
Iteration 95: swpout inc: 212, swpout fallback inc: 0, Fallback percentage: 0.00%
Iteration 96: swpout inc: 220, swpout fallback inc: 0, Fallback percentage: 0.00%
Iteration 97: swpout inc: 220, swpout fallback inc: 0, Fallback percentage: 0.00%
Iteration 98: swpout inc: 216, swpout fallback inc: 0, Fallback percentage: 0.00%
Iteration 99: swpout inc: 223, swpout fallback inc: 0, Fallback percentage: 0.00%
Iteration 100: swpout inc: 225, swpout fallback inc: 0, Fallback percentage: 0.00%

Quoted 3 lines

Unfortunately, the data is gotten using a special designed test program which always swap-in pages with swapped-out size. I don't know whether such workloads exist in reality. Otherwise, you need to wait for mTHP

The test program is designed to simulate mTHP swap behavior using zsmalloc and 64KB buffer.
If we insist on only designing for existing workloads, then zsmalloc using 64KB buffer usage will never be able to run, exactly due the kernel has high failure rate allocating swap entries for 64KB. There is a bit of a chick and egg problem there, such a usage can not exist because the kernel can't support it yet. Kernel can't add patches to support it because such simulation tests are not "real".

We need to break this cycle to support something new.

Quoted 2 lines

swap-in to be merged firstly, and people reach consensus that we should always swap-in pages with swapped-out size.

We don't have to be always. We can identify the situation that makes sense. For the zram/zsmalloc 64K buffer usage case, swap out as the same swap in size makes sense.
I think we have agreement on such zsmalloc 64K usage cases we do want to support.

Quoted 9 lines

Alternately, we can make some design adjustment to make the patchset work in current situation (mTHP swap-out, normal page swap-in).

- One non-full cluster list for each order (same as current design)

- When one swap entry is freed, check whether one "order+1" swap entry becomes free, if so, move the cluster to "order+1" non-full cluster list.

Quoted 2 lines

In the intended zsmalloc usage case, there is no order+1 swap entry request.

This my main concern about this series. Only the Android use cases are considered. The general use cases are just ignored. Is it hard to consider or test a normal swap partition on your development machine?

Quoted 2 lines

Moving the cluster to "order+1" will make less cluster available for "order". For that usage case it is negative gain.

The "order+1" cluster can be used to allocate "order" cluster when existing "order" cluster is used up.

And in this way, we can protect clusters with more free spaces so that they may become free.

Quoted 8 lines

Quoted 2 lines

- When allocate swap entry with "order", get cluster from free, "order", "order+1", ... non-full cluster list. If all are empty, fallback to

I don't see that it is useful for the zsmalloc 64K buffer usage case. There will be order 0 and order 4 and nothing else.

How about let's keep it simple for now. If we identify some workload this algorithm can help. We can do that as a follow up step.

The simple design isn't flexible enough for your workloads too. For example,

- Initially, almost only order-0 pages are swapped out, most non-full clusters are order-0.

- Later, quite some order-0 swap entries are freed so that there are quite some order-4 swap entries available.

- Order-4 pages need to be swapped out, but no enough order-4 non-full clusters available.

So, we need a way to migrate non-full clusters among orders to adjust to the situations automatically.

Quoted 19 lines

Quoted 18 lines

order 0.

Do you think that this works?

Quoted 10 lines

Reported-by Barry Song <[email protected]>

Signed-off-by Chris Li <[email protected]>

---
Changes in v3:
- Using V1 as base.
- Rename "next" to "list" for the list field, suggested by Ying.
- Update comment for the locking rules for cluster fields and list, suggested by Ying.
- Allocate from the nonfull list before attempting free list, suggested by Kairui.

Haven't looked into this. It appears that this breaks the original discard behavior which helps performance of some SSD, please refer to

Quoted 2 lines

Can you clarify by "discard" you mean SSD discard command or just the way swap allocator recycles free clusters?

The SSD discard command, like in the following URL,

https://en.wikipedia.org/wiki/Trim_(computing)

Quoted 5 lines

Quoted 1 line

commit 2a8f94493432 ("swap: change block allocation algorithm for SSD").

I did read that change log. Help me understand in more detail which discard behavior you have in mind. A lot of low end micro SD cards have proper FTL wear leveling now, ssd even better on that.

It's not FTL, it's discard/trim for SSD as above.

Quoted 5 lines

Quoted 4 lines

And as pointed out by Ryan, this may reduce the opportunity of the sequential block device writing during swap-out, which may hurt performance of SSD too.

Quoted 9 lines

Only at the initial phase. If the swap IO continues, after the first pass fills up the swap file, the write will be random on the swapfile anyway. Because the swapfile only issues 2M discards commands when all 512 4K pages are free. The discarded area will be much smaller than the free area on swapfile. That combined with the random write page on the whole swap file. It might produce a worse internal write amplification for SSD, compared to only writing a subset of the swapfile area. I would love to hear from someone who understands SSD internals to confirm or deny my theory.

It depends on workloads. Some workloads will have more severe fragmentation than others. For example, on quite some machines, the swap devices will be far from being full to avoid possible OOM.

Quoted 6 lines

Even let's assume the SSD wants a free block over a nonfull cluster first. Zswap and zram swap are not subject to SSD property. We might want to have a kernel option to select using nonfree clusters over the free one for zram and zswap (ghost swapfile). That will help contain the fragmented swap area.

I suspect that it will help fragmentation avoidance much. Please prove its effectiveness with data firstly. It can be a further optimization patch in the series.

Even if we really need it, we can try to do it without a kernel option. For example, detect whether we are using zram and enable it for zram automatically (through a general flag).

Quoted 128 lines · Ying

Quoted 125 lines · Chris Li

Quoted 90 lines · Ying

Quoted 78 lines · Chris Li

This is the short term solutiolns "swap cluster order" listed in my "Swap Abstraction" discussion slice 8 in the recent LSF/MM conference.

When commit 845982eb264bc "mm: swap: allow storage of all mTHP orders" is introduced, it only allocates the mTHP swap entries from new empty cluster list. It has a fragmentation issue reported by Barry.

https://lore.kernel.org/all/CAGsJ_4zAcJkuW016Cfi6wicRr8N9X+GJJhgMQdSMp+Ah+NSgNQ@mail.gmail.com/

The reason is that all the empty cluster has been exhausted while there are planty of free swap entries to in the cluster that is not 100% free.

Remember the swap allocation order in the cluster.
Keep track of the per order non full cluster list for later allocation.

User impact: For users that allocate and free mix order mTHP swapping, It greatly improves the success rate of the mTHP swap allocation after the initial phase.

Barry provides a test program to show the effect:
https://lore.kernel.org/linux-mm/[email protected]/

Without:

$ mthp-swapout
Iteration 1: swpout inc: 222, swpout fallback inc: 0, Fallback percentage: 0.00%
Iteration 2: swpout inc: 219, swpout fallback inc: 0, Fallback percentage: 0.00%
Iteration 3: swpout inc: 222, swpout fallback inc: 0, Fallback percentage: 0.00%
Iteration 4: swpout inc: 219, swpout fallback inc: 0, Fallback percentage: 0.00%
Iteration 5: swpout inc: 110, swpout fallback inc: 117, Fallback percentage: 51.54%
Iteration 6: swpout inc: 0, swpout fallback inc: 230, Fallback percentage: 100.00%
Iteration 7: swpout inc: 0, swpout fallback inc: 229, Fallback percentage: 100.00%
Iteration 8: swpout inc: 0, swpout fallback inc: 223, Fallback percentage: 100.00%
Iteration 9: swpout inc: 0, swpout fallback inc: 224, Fallback percentage: 100.00%
Iteration 10: swpout inc: 0, swpout fallback inc: 216, Fallback percentage: 100.00%
Iteration 11: swpout inc: 0, swpout fallback inc: 212, Fallback percentage: 100.00%
Iteration 12: swpout inc: 0, swpout fallback inc: 224, Fallback percentage: 100.00%
Iteration 13: swpout inc: 0, swpout fallback inc: 214, Fallback percentage: 100.00%

$ mthp-swapout -s
Iteration 1: swpout inc: 222, swpout fallback inc: 0, Fallback percentage: 0.00%
Iteration 2: swpout inc: 227, swpout fallback inc: 0, Fallback percentage: 0.00%
Iteration 3: swpout inc: 222, swpout fallback inc: 0, Fallback percentage: 0.00%
Iteration 4: swpout inc: 224, swpout fallback inc: 0, Fallback percentage: 0.00%
Iteration 5: swpout inc: 33, swpout fallback inc: 197, Fallback percentage: 85.65%
Iteration 6: swpout inc: 0, swpout fallback inc: 229, Fallback percentage: 100.00%
Iteration 7: swpout inc: 0, swpout fallback inc: 223, Fallback percentage: 100.00%
Iteration 8: swpout inc: 0, swpout fallback inc: 219, Fallback percentage: 100.00%
Iteration 9: swpout inc: 0, swpout fallback inc: 212, Fallback percentage: 100.00%

With:

$ mthp-swapout
Iteration 1: swpout inc: 222, swpout fallback inc: 0, Fallback percentage: 0.00%
Iteration 2: swpout inc: 219, swpout fallback inc: 0, Fallback percentage: 0.00%
Iteration 3: swpout inc: 222, swpout fallback inc: 0, Fallback percentage: 0.00%
Iteration 4: swpout inc: 219, swpout fallback inc: 0, Fallback percentage: 0.00%
Iteration 5: swpout inc: 227, swpout fallback inc: 0, Fallback percentage: 0.00%
Iteration 6: swpout inc: 230, swpout fallback inc: 0, Fallback percentage: 0.00%
...
Iteration 94: swpout inc: 224, swpout fallback inc: 0, Fallback percentage: 0.00%
Iteration 95: swpout inc: 221, swpout fallback inc: 0, Fallback percentage: 0.00%
Iteration 96: swpout inc: 229, swpout fallback inc: 0, Fallback percentage: 0.00%
Iteration 97: swpout inc: 219, swpout fallback inc: 0, Fallback percentage: 0.00%
Iteration 98: swpout inc: 222, swpout fallback inc: 0, Fallback percentage: 0.00%
Iteration 99: swpout inc: 223, swpout fallback inc: 0, Fallback percentage: 0.00%
Iteration 100: swpout inc: 224, swpout fallback inc: 0, Fallback percentage: 0.00%

$ mthp-swapout -s
Iteration 1: swpout inc: 222, swpout fallback inc: 0, Fallback percentage: 0.00%
Iteration 2: swpout inc: 227, swpout fallback inc: 0, Fallback percentage: 0.00%
Iteration 3: swpout inc: 222, swpout fallback inc: 0, Fallback percentage: 0.00%
Iteration 4: swpout inc: 224, swpout fallback inc: 0, Fallback percentage: 0.00%
Iteration 5: swpout inc: 230, swpout fallback inc: 0, Fallback percentage: 0.00%
Iteration 6: swpout inc: 229, swpout fallback inc: 0, Fallback percentage: 0.00%
Iteration 7: swpout inc: 223, swpout fallback inc: 0, Fallback percentage: 0.00%
Iteration 8: swpout inc: 219, swpout fallback inc: 0, Fallback percentage: 0.00%

Quoted 8 lines

...
Iteration 94: swpout inc: 223, swpout fallback inc: 0, Fallback percentage: 0.00%
Iteration 95: swpout inc: 212, swpout fallback inc: 0, Fallback percentage: 0.00%
Iteration 96: swpout inc: 220, swpout fallback inc: 0, Fallback percentage: 0.00%
Iteration 97: swpout inc: 220, swpout fallback inc: 0, Fallback percentage: 0.00%
Iteration 98: swpout inc: 216, swpout fallback inc: 0, Fallback percentage: 0.00%
Iteration 99: swpout inc: 223, swpout fallback inc: 0, Fallback percentage: 0.00%
Iteration 100: swpout inc: 225, swpout fallback inc: 0, Fallback percentage: 0.00%

Quoted 3 lines

Unfortunately, the data is gotten using a special designed test program which always swap-in pages with swapped-out size. I don't know whether such workloads exist in reality. Otherwise, you need to wait for mTHP

The test program is designed to simulate mTHP swap behavior using zsmalloc and 64KB buffer.
If we insist on only designing for existing workloads, then zsmalloc using 64KB buffer usage will never be able to run, exactly due the kernel has high failure rate allocating swap entries for 64KB. There is a bit of a chick and egg problem there, such a usage can not exist because the kernel can't support it yet. Kernel can't add patches to support it because such simulation tests are not "real".

We need to break this cycle to support something new.

Quoted 2 lines

swap-in to be merged firstly, and people reach consensus that we should always swap-in pages with swapped-out size.

We don't have to be always. We can identify the situation that makes sense. For the zram/zsmalloc 64K buffer usage case, swap out as the same swap in size makes sense.
I think we have agreement on such zsmalloc 64K usage cases we do want to support.

Quoted 9 lines

Alternately, we can make some design adjustment to make the patchset work in current situation (mTHP swap-out, normal page swap-in).

- One non-full cluster list for each order (same as current design)

- When one swap entry is freed, check whether one "order+1" swap entry becomes free, if so, move the cluster to "order+1" non-full cluster list.

Quoted 6 lines

Quoted 2 lines

In the intended zsmalloc usage case, there is no order+1 swap entry request.

This my main concern about this series. Only the Android use cases are considered. The general use cases are just ignored. Is it hard to consider or test a normal swap partition on your development machine?

Please see the V4 cover letter. The V4 already has the SSD, zram and HDD stress testing.
Of course I want to make sure the allocator works well with Barry's mthp test case as well.

Quoted 24 lines

Quoted 2 lines

Moving the cluster to "order+1" will make less cluster available for "order". For that usage case it is negative gain.

The "order+1" cluster can be used to allocate "order" cluster when existing "order" cluster is used up.

And in this way, we can protect clusters with more free spaces so that they may become free.

Quoted 8 lines

Quoted 2 lines

- When allocate swap entry with "order", get cluster from free, "order", "order+1", ... non-full cluster list. If all are empty, fallback to

I don't see that it is useful for the zsmalloc 64K buffer usage case. There will be order 0 and order 4 and nothing else.

How about let's keep it simple for now. If we identify some workload this algorithm can help. We can do that as a follow up step.

The simple design isn't flexible enough for your workloads too. For example,

- Initially, almost only order-0 pages are swapped out, most non-full clusters are order-0.

Quoted 8 lines

- Later, quite some order-0 swap entries are freed so that there are quite some order-4 swap entries available.

- Order-4 pages need to be swapped out, but no enough order-4 non-full clusters available.

So, we need a way to migrate non-full clusters among orders to adjust to the situations automatically.

Depends on how lucky it is to form the order-4 cluster naturally. The odds of forming the order-4 cluster naturally in random swap allocation/ free case is very low. I have the number in my other email thread.
Anyway, if we convince this payout for the complexity it introduces, we can do that as follow up steps. Try to keep things simple at first for the review benefit.

Quoted 19 lines

Quoted 19 lines

Quoted 18 lines

order 0.

Do you think that this works?

Quoted 10 lines

Reported-by Barry Song <[email protected]>

Signed-off-by Chris Li <[email protected]>

---
Changes in v3:
- Using V1 as base.
- Rename "next" to "list" for the list field, suggested by Ying.
- Update comment for the locking rules for cluster fields and list, suggested by Ying.
- Allocate from the nonfull list before attempting free list, suggested by Kairui.

Haven't looked into this. It appears that this breaks the original discard behavior which helps performance of some SSD, please refer to

Quoted 6 lines

Quoted 2 lines

Can you clarify by "discard" you mean SSD discard command or just the way swap allocator recycles free clusters?

The SSD discard command, like in the following URL,

https://en.wikipedia.org/wiki/Trim_(computing)

Thanks. I know what an SSD discard command is. Want to understand why that behavior is preferred.

So the reasoning to prefer a new free block rather than a recent particle free cluster is to let the previous written cluster have a higher chance to issue the discard command?

This preferred new block behavior is actually not friendly to SSD from a wearing point of view.
Take this example:
Let say the data need to allocate and free from swap. At any given time the swap usage is 1G. The swap SSD drive is 16G.
Let say the allocation and free are at random 4K page locations. There is totally 64G swap data needed to write to swap, but at any given time there is only 1G data occupite on swapfile.

a) If you always prefer new free blocks. Then the swap data will eventually write at all 16G drives then random write to full 16G. Chance of forming a free cluster so a discard command can be issued is very low. (15/16)**512 = 4.4E-15. From SSD point of view, it does not know most of the data written to 16G drive is not used. When a page is free on a swapfile, SSD drive doesn't know about it. It sees 4K random writes to all 16G of the drive, total 64G data written.

b) If you always prefer a non full cluster first over a new cluster. The 64G data will concentrate random writing to the first 1G of drive location. Total 64G data written.

I consider b) are more friendly to SSD than a). Because concentrate the write into the first 1G location. The SSD can know the data overwritten in those 1G has internally obsolete, so it can internally GC the those overwritten data without a discard command. Where a) random 4K writes to the whole drive without much discard at all. Full SSD doing random writes is a bad combination from a wearing point of view.

Just my 2 cents. Anyway I revert the V4 to use free cluster before nonfull cluster just to behave the same as previously.

Quoted 7 lines

Quoted 5 lines

Quoted 1 line

commit 2a8f94493432 ("swap: change block allocation algorithm for SSD").

I did read that change log. Help me understand in more detail which discard behavior you have in mind. A lot of low end micro SD cards have proper FTL wear leveling now, ssd even better on that.

It's not FTL, it's discard/trim for SSD as above.

Thanks for the clarification.

Quoted 15 lines

Quoted 5 lines

Quoted 4 lines

And as pointed out by Ryan, this may reduce the opportunity of the sequential block device writing during swap-out, which may hurt performance of SSD too.

Quoted 9 lines

Only at the initial phase. If the swap IO continues, after the first pass fills up the swap file, the write will be random on the swapfile anyway. Because the swapfile only issues 2M discards commands when all 512 4K pages are free. The discarded area will be much smaller than the free area on swapfile. That combined with the random write page on the whole swap file. It might produce a worse internal write amplification for SSD, compared to only writing a subset of the swapfile area. I would love to hear from someone who understands SSD internals to confirm or deny my theory.

Quoted 3 lines

It depends on workloads. Some workloads will have more severe fragmentation than others. For example, on quite some machines, the swap devices will be far from being full to avoid possible OOM.

I suspect most of the SSD swap on client devices nowadays are only as backup just in case it needs to be swapped.
There is not much SSD swap IO during normal use. The zram and zswap are more actively used in the data center and Android phone case, from swap IO ops point of view.

Quoted 10 lines

Quoted 6 lines

Even let's assume the SSD wants a free block over a nonfull cluster first. Zswap and zram swap are not subject to SSD property. We might want to have a kernel option to select using nonfree clusters over the free one for zram and zswap (ghost swapfile). That will help contain the fragmented swap area.

I suspect that it will help fragmentation avoidance much. Please prove its effectiveness with data firstly. It can be a further optimization patch in the series.

Take the above 1GB data written in a 16GB drive example. a) will fragment the whole 16GB drive.
b) will concentrate on the first 1GB location that was used.

Quoted 1 line

Quoted 3 lines

Even if we really need it, we can try to do it without a kernel option. For example, detect whether we are using zram and enable it for zram automatically (through a general flag).

zswap you need to have an option to choose from because it can write to the real swappfile as well.
Do you optimize the swap allocator for the zswap or physical swapfile.

Quoted 276 lines · Chris Li

Quoted 128 lines · Ying

Quoted 125 lines · Chris Li

Quoted 90 lines · Ying

Quoted 78 lines · Chris Li

This is the short term solutiolns "swap cluster order" listed in my "Swap Abstraction" discussion slice 8 in the recent LSF/MM conference.

When commit 845982eb264bc "mm: swap: allow storage of all mTHP orders" is introduced, it only allocates the mTHP swap entries from new empty cluster list. It has a fragmentation issue reported by Barry.

https://lore.kernel.org/all/CAGsJ_4zAcJkuW016Cfi6wicRr8N9X+GJJhgMQdSMp+Ah+NSgNQ@mail.gmail.com/

The reason is that all the empty cluster has been exhausted while there are planty of free swap entries to in the cluster that is not 100% free.

Remember the swap allocation order in the cluster.
Keep track of the per order non full cluster list for later allocation.

User impact: For users that allocate and free mix order mTHP swapping, It greatly improves the success rate of the mTHP swap allocation after the initial phase.

Barry provides a test program to show the effect:
https://lore.kernel.org/linux-mm/[email protected]/

Without:

$ mthp-swapout
Iteration 1: swpout inc: 222, swpout fallback inc: 0, Fallback percentage: 0.00%
Iteration 2: swpout inc: 219, swpout fallback inc: 0, Fallback percentage: 0.00%
Iteration 3: swpout inc: 222, swpout fallback inc: 0, Fallback percentage: 0.00%
Iteration 4: swpout inc: 219, swpout fallback inc: 0, Fallback percentage: 0.00%
Iteration 5: swpout inc: 110, swpout fallback inc: 117, Fallback percentage: 51.54%
Iteration 6: swpout inc: 0, swpout fallback inc: 230, Fallback percentage: 100.00%
Iteration 7: swpout inc: 0, swpout fallback inc: 229, Fallback percentage: 100.00%
Iteration 8: swpout inc: 0, swpout fallback inc: 223, Fallback percentage: 100.00%
Iteration 9: swpout inc: 0, swpout fallback inc: 224, Fallback percentage: 100.00%
Iteration 10: swpout inc: 0, swpout fallback inc: 216, Fallback percentage: 100.00%
Iteration 11: swpout inc: 0, swpout fallback inc: 212, Fallback percentage: 100.00%
Iteration 12: swpout inc: 0, swpout fallback inc: 224, Fallback percentage: 100.00%
Iteration 13: swpout inc: 0, swpout fallback inc: 214, Fallback percentage: 100.00%

$ mthp-swapout -s
Iteration 1: swpout inc: 222, swpout fallback inc: 0, Fallback percentage: 0.00%
Iteration 2: swpout inc: 227, swpout fallback inc: 0, Fallback percentage: 0.00%
Iteration 3: swpout inc: 222, swpout fallback inc: 0, Fallback percentage: 0.00%
Iteration 4: swpout inc: 224, swpout fallback inc: 0, Fallback percentage: 0.00%
Iteration 5: swpout inc: 33, swpout fallback inc: 197, Fallback percentage: 85.65%
Iteration 6: swpout inc: 0, swpout fallback inc: 229, Fallback percentage: 100.00%
Iteration 7: swpout inc: 0, swpout fallback inc: 223, Fallback percentage: 100.00%
Iteration 8: swpout inc: 0, swpout fallback inc: 219, Fallback percentage: 100.00%
Iteration 9: swpout inc: 0, swpout fallback inc: 212, Fallback percentage: 100.00%

With:

$ mthp-swapout
Iteration 1: swpout inc: 222, swpout fallback inc: 0, Fallback percentage: 0.00%
Iteration 2: swpout inc: 219, swpout fallback inc: 0, Fallback percentage: 0.00%
Iteration 3: swpout inc: 222, swpout fallback inc: 0, Fallback percentage: 0.00%
Iteration 4: swpout inc: 219, swpout fallback inc: 0, Fallback percentage: 0.00%
Iteration 5: swpout inc: 227, swpout fallback inc: 0, Fallback percentage: 0.00%
Iteration 6: swpout inc: 230, swpout fallback inc: 0, Fallback percentage: 0.00%
...
Iteration 94: swpout inc: 224, swpout fallback inc: 0, Fallback percentage: 0.00%
Iteration 95: swpout inc: 221, swpout fallback inc: 0, Fallback percentage: 0.00%
Iteration 96: swpout inc: 229, swpout fallback inc: 0, Fallback percentage: 0.00%
Iteration 97: swpout inc: 219, swpout fallback inc: 0, Fallback percentage: 0.00%
Iteration 98: swpout inc: 222, swpout fallback inc: 0, Fallback percentage: 0.00%
Iteration 99: swpout inc: 223, swpout fallback inc: 0, Fallback percentage: 0.00%
Iteration 100: swpout inc: 224, swpout fallback inc: 0, Fallback percentage: 0.00%

$ mthp-swapout -s
Iteration 1: swpout inc: 222, swpout fallback inc: 0, Fallback percentage: 0.00%
Iteration 2: swpout inc: 227, swpout fallback inc: 0, Fallback percentage: 0.00%
Iteration 3: swpout inc: 222, swpout fallback inc: 0, Fallback percentage: 0.00%
Iteration 4: swpout inc: 224, swpout fallback inc: 0, Fallback percentage: 0.00%
Iteration 5: swpout inc: 230, swpout fallback inc: 0, Fallback percentage: 0.00%
Iteration 6: swpout inc: 229, swpout fallback inc: 0, Fallback percentage: 0.00%
Iteration 7: swpout inc: 223, swpout fallback inc: 0, Fallback percentage: 0.00%
Iteration 8: swpout inc: 219, swpout fallback inc: 0, Fallback percentage: 0.00%

Quoted 8 lines

...
Iteration 94: swpout inc: 223, swpout fallback inc: 0, Fallback percentage: 0.00%
Iteration 95: swpout inc: 212, swpout fallback inc: 0, Fallback percentage: 0.00%
Iteration 96: swpout inc: 220, swpout fallback inc: 0, Fallback percentage: 0.00%
Iteration 97: swpout inc: 220, swpout fallback inc: 0, Fallback percentage: 0.00%
Iteration 98: swpout inc: 216, swpout fallback inc: 0, Fallback percentage: 0.00%
Iteration 99: swpout inc: 223, swpout fallback inc: 0, Fallback percentage: 0.00%
Iteration 100: swpout inc: 225, swpout fallback inc: 0, Fallback percentage: 0.00%

Quoted 3 lines

Unfortunately, the data is gotten using a special designed test program which always swap-in pages with swapped-out size. I don't know whether such workloads exist in reality. Otherwise, you need to wait for mTHP

The test program is designed to simulate mTHP swap behavior using zsmalloc and 64KB buffer.
If we insist on only designing for existing workloads, then zsmalloc using 64KB buffer usage will never be able to run, exactly due the kernel has high failure rate allocating swap entries for 64KB. There is a bit of a chick and egg problem there, such a usage can not exist because the kernel can't support it yet. Kernel can't add patches to support it because such simulation tests are not "real".

We need to break this cycle to support something new.

Quoted 2 lines

swap-in to be merged firstly, and people reach consensus that we should always swap-in pages with swapped-out size.

We don't have to be always. We can identify the situation that makes sense. For the zram/zsmalloc 64K buffer usage case, swap out as the same swap in size makes sense.
I think we have agreement on such zsmalloc 64K usage cases we do want to support.

Quoted 9 lines

Alternately, we can make some design adjustment to make the patchset work in current situation (mTHP swap-out, normal page swap-in).

- One non-full cluster list for each order (same as current design)

- When one swap entry is freed, check whether one "order+1" swap entry becomes free, if so, move the cluster to "order+1" non-full cluster list.

Quoted 6 lines

Quoted 2 lines

In the intended zsmalloc usage case, there is no order+1 swap entry request.

This my main concern about this series. Only the Android use cases are considered. The general use cases are just ignored. Is it hard to consider or test a normal swap partition on your development machine?

Please see the V4 cover letter. The V4 already has the SSD, zram and HDD stress testing.
Of course I want to make sure the allocator works well with Barry's mthp test case as well.

Quoted 24 lines

Quoted 2 lines

Moving the cluster to "order+1" will make less cluster available for "order". For that usage case it is negative gain.

The "order+1" cluster can be used to allocate "order" cluster when existing "order" cluster is used up.

And in this way, we can protect clusters with more free spaces so that they may become free.

Quoted 8 lines

Quoted 2 lines

- When allocate swap entry with "order", get cluster from free, "order", "order+1", ... non-full cluster list. If all are empty, fallback to

I don't see that it is useful for the zsmalloc 64K buffer usage case. There will be order 0 and order 4 and nothing else.

How about let's keep it simple for now. If we identify some workload this algorithm can help. We can do that as a follow up step.

The simple design isn't flexible enough for your workloads too. For example,

- Initially, almost only order-0 pages are swapped out, most non-full clusters are order-0.

Quoted 8 lines

- Later, quite some order-0 swap entries are freed so that there are quite some order-4 swap entries available.

- Order-4 pages need to be swapped out, but no enough order-4 non-full clusters available.

So, we need a way to migrate non-full clusters among orders to adjust to the situations automatically.

Depends on how lucky it is to form the order-4 cluster naturally. The odds of forming the order-4 cluster naturally in random swap allocation/ free case is very low. I have the number in my other email thread.
Anyway, if we convince this payout for the complexity it introduces, we can do that as follow up steps. Try to keep things simple at first for the review benefit.

Quoted 19 lines

Quoted 19 lines

Quoted 18 lines

order 0.

Do you think that this works?

Quoted 10 lines

Reported-by Barry Song <[email protected]>

Signed-off-by Chris Li <[email protected]>

---
Changes in v3:
- Using V1 as base.
- Rename "next" to "list" for the list field, suggested by Ying.
- Update comment for the locking rules for cluster fields and list, suggested by Ying.
- Allocate from the nonfull list before attempting free list, suggested by Kairui.

Haven't looked into this. It appears that this breaks the original discard behavior which helps performance of some SSD, please refer to

Quoted 6 lines

Quoted 2 lines

Can you clarify by "discard" you mean SSD discard command or just the way swap allocator recycles free clusters?

The SSD discard command, like in the following URL,

https://en.wikipedia.org/wiki/Trim_(computing)

Thanks. I know what an SSD discard command is. Want to understand why that behavior is preferred.

So the reasoning to prefer a new free block rather than a recent particle free cluster is to let the previous written cluster have a higher chance to issue the discard command?

This preferred new block behavior is actually not friendly to SSD from a wearing point of view.
Take this example:
Let say the data need to allocate and free from swap. At any given time the swap usage is 1G. The swap SSD drive is 16G.
Let say the allocation and free are at random 4K page locations. There is totally 64G swap data needed to write to swap, but at any given time there is only 1G data occupite on swapfile.

a) If you always prefer new free blocks. Then the swap data will eventually write at all 16G drives then random write to full 16G. Chance of forming a free cluster so a discard command can be issued is very low. (15/16)**512 = 4.4E-15. From SSD point of view, it does not know most of the data written to 16G drive is not used. When a page is free on a swapfile, SSD drive doesn't know about it. It sees 4K random writes to all 16G of the drive, total 64G data written.

b) If you always prefer a non full cluster first over a new cluster. The 64G data will concentrate random writing to the first 1G of drive location. Total 64G data written.

I consider b) are more friendly to SSD than a). Because concentrate the write into the first 1G location. The SSD can know the data overwritten in those 1G has internally obsolete, so it can internally GC the those overwritten data without a discard command. Where a) random 4K writes to the whole drive without much discard at all. Full SSD doing random writes is a bad combination from a wearing point of view.

Just my 2 cents. Anyway I revert the V4 to use free cluster before nonfull cluster just to behave the same as previously.

Quoted 7 lines

Quoted 5 lines

Quoted 1 line

commit 2a8f94493432 ("swap: change block allocation algorithm for SSD").

I did read that change log. Help me understand in more detail which discard behavior you have in mind. A lot of low end micro SD cards have proper FTL wear leveling now, ssd even better on that.

It's not FTL, it's discard/trim for SSD as above.

Thanks for the clarification.

Quoted 18 lines

Quoted 5 lines

Quoted 4 lines

And as pointed out by Ryan, this may reduce the opportunity of the sequential block device writing during swap-out, which may hurt performance of SSD too.

Quoted 9 lines

Only at the initial phase. If the swap IO continues, after the first pass fills up the swap file, the write will be random on the swapfile anyway. Because the swapfile only issues 2M discards commands when all 512 4K pages are free. The discarded area will be much smaller than the free area on swapfile. That combined with the random write page on the whole swap file. It might produce a worse internal write amplification for SSD, compared to only writing a subset of the swapfile area. I would love to hear from someone who understands SSD internals to confirm or deny my theory.

It depends on workloads. Some workloads will have more severe fragmentation than others. For example, on quite some machines, the swap devices will be far from being full to avoid possible OOM.

Quoted 5 lines

I suspect most of the SSD swap on client devices nowadays are only as backup just in case it needs to be swapped.
There is not much SSD swap IO during normal use. The zram and zswap are more actively used in the data center and Android phone case, from swap IO ops point of view.

I use a Linux laptop with 16GB DRAM for work. And I found that the swap space are almost always used.

Quoted 17 lines

Quoted 11 lines

Quoted 7 lines

Even let's assume the SSD wants a free block over a nonfull cluster first. Zswap and zram swap are not subject to SSD property. We might want to have a kernel option to select using nonfree clusters over the free one for zram and zswap (ghost swapfile). That will help contain the fragmented swap area.

I suspect that it will help fragmentation avoidance much. Please prove its effectiveness with data firstly. It can be a further optimization patch in the series.

Take the above 1GB data written in a 16GB drive example. a) will fragment the whole 16GB drive.
b) will concentrate on the first 1GB location that was used.

Quoted 1 line

Quoted 7 lines

Quoted 3 lines

Even if we really need it, we can try to do it without a kernel option. For example, detect whether we are using zram and enable it for zram automatically (through a general flag).

zswap you need to have an option to choose from because it can write to the real swappfile as well.
Do you optimize the swap allocator for the zswap or physical swapfile.

--
Best Regards,
Huang, Ying

Quoted 285 lines · Ying

Quoted 281 lines · Chris Li

Quoted 128 lines · Ying

Quoted 125 lines · Chris Li

Quoted 90 lines · Ying

Quoted 78 lines · Chris Li

This is the short term solutiolns "swap cluster order" listed in my "Swap Abstraction" discussion slice 8 in the recent LSF/MM conference.

When commit 845982eb264bc "mm: swap: allow storage of all mTHP orders" is introduced, it only allocates the mTHP swap entries from new empty cluster list. It has a fragmentation issue reported by Barry.

https://lore.kernel.org/all/CAGsJ_4zAcJkuW016Cfi6wicRr8N9X+GJJhgMQdSMp+Ah+NSgNQ@mail.gmail.com/

The reason is that all the empty cluster has been exhausted while there are planty of free swap entries to in the cluster that is not 100% free.

Remember the swap allocation order in the cluster.
Keep track of the per order non full cluster list for later allocation.

User impact: For users that allocate and free mix order mTHP swapping, It greatly improves the success rate of the mTHP swap allocation after the initial phase.

Barry provides a test program to show the effect:
https://lore.kernel.org/linux-mm/[email protected]/

Without:

$ mthp-swapout
Iteration 1: swpout inc: 222, swpout fallback inc: 0, Fallback percentage: 0.00%
Iteration 2: swpout inc: 219, swpout fallback inc: 0, Fallback percentage: 0.00%
Iteration 3: swpout inc: 222, swpout fallback inc: 0, Fallback percentage: 0.00%
Iteration 4: swpout inc: 219, swpout fallback inc: 0, Fallback percentage: 0.00%
Iteration 5: swpout inc: 110, swpout fallback inc: 117, Fallback percentage: 51.54%
Iteration 6: swpout inc: 0, swpout fallback inc: 230, Fallback percentage: 100.00%
Iteration 7: swpout inc: 0, swpout fallback inc: 229, Fallback percentage: 100.00%
Iteration 8: swpout inc: 0, swpout fallback inc: 223, Fallback percentage: 100.00%
Iteration 9: swpout inc: 0, swpout fallback inc: 224, Fallback percentage: 100.00%
Iteration 10: swpout inc: 0, swpout fallback inc: 216, Fallback percentage: 100.00%
Iteration 11: swpout inc: 0, swpout fallback inc: 212, Fallback percentage: 100.00%
Iteration 12: swpout inc: 0, swpout fallback inc: 224, Fallback percentage: 100.00%
Iteration 13: swpout inc: 0, swpout fallback inc: 214, Fallback percentage: 100.00%

$ mthp-swapout -s
Iteration 1: swpout inc: 222, swpout fallback inc: 0, Fallback percentage: 0.00%
Iteration 2: swpout inc: 227, swpout fallback inc: 0, Fallback percentage: 0.00%
Iteration 3: swpout inc: 222, swpout fallback inc: 0, Fallback percentage: 0.00%
Iteration 4: swpout inc: 224, swpout fallback inc: 0, Fallback percentage: 0.00%
Iteration 5: swpout inc: 33, swpout fallback inc: 197, Fallback percentage: 85.65%
Iteration 6: swpout inc: 0, swpout fallback inc: 229, Fallback percentage: 100.00%
Iteration 7: swpout inc: 0, swpout fallback inc: 223, Fallback percentage: 100.00%
Iteration 8: swpout inc: 0, swpout fallback inc: 219, Fallback percentage: 100.00%
Iteration 9: swpout inc: 0, swpout fallback inc: 212, Fallback percentage: 100.00%

With:

$ mthp-swapout
Iteration 1: swpout inc: 222, swpout fallback inc: 0, Fallback percentage: 0.00%
Iteration 2: swpout inc: 219, swpout fallback inc: 0, Fallback percentage: 0.00%
Iteration 3: swpout inc: 222, swpout fallback inc: 0, Fallback percentage: 0.00%
Iteration 4: swpout inc: 219, swpout fallback inc: 0, Fallback percentage: 0.00%
Iteration 5: swpout inc: 227, swpout fallback inc: 0, Fallback percentage: 0.00%
Iteration 6: swpout inc: 230, swpout fallback inc: 0, Fallback percentage: 0.00%
...
Iteration 94: swpout inc: 224, swpout fallback inc: 0, Fallback percentage: 0.00%
Iteration 95: swpout inc: 221, swpout fallback inc: 0, Fallback percentage: 0.00%
Iteration 96: swpout inc: 229, swpout fallback inc: 0, Fallback percentage: 0.00%
Iteration 97: swpout inc: 219, swpout fallback inc: 0, Fallback percentage: 0.00%
Iteration 98: swpout inc: 222, swpout fallback inc: 0, Fallback percentage: 0.00%
Iteration 99: swpout inc: 223, swpout fallback inc: 0, Fallback percentage: 0.00%
Iteration 100: swpout inc: 224, swpout fallback inc: 0, Fallback percentage: 0.00%

$ mthp-swapout -s
Iteration 1: swpout inc: 222, swpout fallback inc: 0, Fallback percentage: 0.00%
Iteration 2: swpout inc: 227, swpout fallback inc: 0, Fallback percentage: 0.00%
Iteration 3: swpout inc: 222, swpout fallback inc: 0, Fallback percentage: 0.00%
Iteration 4: swpout inc: 224, swpout fallback inc: 0, Fallback percentage: 0.00%
Iteration 5: swpout inc: 230, swpout fallback inc: 0, Fallback percentage: 0.00%
Iteration 6: swpout inc: 229, swpout fallback inc: 0, Fallback percentage: 0.00%
Iteration 7: swpout inc: 223, swpout fallback inc: 0, Fallback percentage: 0.00%
Iteration 8: swpout inc: 219, swpout fallback inc: 0, Fallback percentage: 0.00%

Quoted 8 lines

...
Iteration 94: swpout inc: 223, swpout fallback inc: 0, Fallback percentage: 0.00%
Iteration 95: swpout inc: 212, swpout fallback inc: 0, Fallback percentage: 0.00%
Iteration 96: swpout inc: 220, swpout fallback inc: 0, Fallback percentage: 0.00%
Iteration 97: swpout inc: 220, swpout fallback inc: 0, Fallback percentage: 0.00%
Iteration 98: swpout inc: 216, swpout fallback inc: 0, Fallback percentage: 0.00%
Iteration 99: swpout inc: 223, swpout fallback inc: 0, Fallback percentage: 0.00%
Iteration 100: swpout inc: 225, swpout fallback inc: 0, Fallback percentage: 0.00%

Quoted 3 lines

Unfortunately, the data is gotten using a special designed test program which always swap-in pages with swapped-out size. I don't know whether such workloads exist in reality. Otherwise, you need to wait for mTHP

The test program is designed to simulate mTHP swap behavior using zsmalloc and 64KB buffer.
If we insist on only designing for existing workloads, then zsmalloc using 64KB buffer usage will never be able to run, exactly due the kernel has high failure rate allocating swap entries for 64KB. There is a bit of a chick and egg problem there, such a usage can not exist because the kernel can't support it yet. Kernel can't add patches to support it because such simulation tests are not "real".

We need to break this cycle to support something new.

Quoted 2 lines

swap-in to be merged firstly, and people reach consensus that we should always swap-in pages with swapped-out size.

We don't have to be always. We can identify the situation that makes sense. For the zram/zsmalloc 64K buffer usage case, swap out as the same swap in size makes sense.
I think we have agreement on such zsmalloc 64K usage cases we do want to support.

Quoted 9 lines

Alternately, we can make some design adjustment to make the patchset work in current situation (mTHP swap-out, normal page swap-in).

- One non-full cluster list for each order (same as current design)

- When one swap entry is freed, check whether one "order+1" swap entry becomes free, if so, move the cluster to "order+1" non-full cluster list.

Quoted 6 lines

Quoted 2 lines

In the intended zsmalloc usage case, there is no order+1 swap entry request.

This my main concern about this series. Only the Android use cases are considered. The general use cases are just ignored. Is it hard to consider or test a normal swap partition on your development machine?

Please see the V4 cover letter. The V4 already has the SSD, zram and HDD stress testing.
Of course I want to make sure the allocator works well with Barry's mthp test case as well.

Quoted 24 lines

Quoted 2 lines

Moving the cluster to "order+1" will make less cluster available for "order". For that usage case it is negative gain.

The "order+1" cluster can be used to allocate "order" cluster when existing "order" cluster is used up.

And in this way, we can protect clusters with more free spaces so that they may become free.

Quoted 8 lines

Quoted 2 lines

- When allocate swap entry with "order", get cluster from free, "order", "order+1", ... non-full cluster list. If all are empty, fallback to

I don't see that it is useful for the zsmalloc 64K buffer usage case. There will be order 0 and order 4 and nothing else.

How about let's keep it simple for now. If we identify some workload this algorithm can help. We can do that as a follow up step.

The simple design isn't flexible enough for your workloads too. For example,

- Initially, almost only order-0 pages are swapped out, most non-full clusters are order-0.

Quoted 8 lines

- Later, quite some order-0 swap entries are freed so that there are quite some order-4 swap entries available.

- Order-4 pages need to be swapped out, but no enough order-4 non-full clusters available.

So, we need a way to migrate non-full clusters among orders to adjust to the situations automatically.

Depends on how lucky it is to form the order-4 cluster naturally. The odds of forming the order-4 cluster naturally in random swap allocation/ free case is very low. I have the number in my other email thread.
Anyway, if we convince this payout for the complexity it introduces, we can do that as follow up steps. Try to keep things simple at first for the review benefit.

Quoted 19 lines

Quoted 19 lines

Quoted 18 lines

order 0.

Do you think that this works?

Quoted 10 lines

Reported-by Barry Song <[email protected]>

Signed-off-by Chris Li <[email protected]>

---
Changes in v3:
- Using V1 as base.
- Rename "next" to "list" for the list field, suggested by Ying.
- Update comment for the locking rules for cluster fields and list, suggested by Ying.
- Allocate from the nonfull list before attempting free list, suggested by Kairui.

Haven't looked into this. It appears that this breaks the original discard behavior which helps performance of some SSD, please refer to

Quoted 6 lines

Quoted 2 lines

Can you clarify by "discard" you mean SSD discard command or just the way swap allocator recycles free clusters?

The SSD discard command, like in the following URL,

https://en.wikipedia.org/wiki/Trim_(computing)

Thanks. I know what an SSD discard command is. Want to understand why that behavior is preferred.

So the reasoning to prefer a new free block rather than a recent particle free cluster is to let the previous written cluster have a higher chance to issue the discard command?

This preferred new block behavior is actually not friendly to SSD from a wearing point of view.
Take this example:
Let say the data need to allocate and free from swap. At any given time the swap usage is 1G. The swap SSD drive is 16G.
Let say the allocation and free are at random 4K page locations. There is totally 64G swap data needed to write to swap, but at any given time there is only 1G data occupite on swapfile.

a) If you always prefer new free blocks. Then the swap data will eventually write at all 16G drives then random write to full 16G. Chance of forming a free cluster so a discard command can be issued is very low. (15/16)**512 = 4.4E-15. From SSD point of view, it does not know most of the data written to 16G drive is not used. When a page is free on a swapfile, SSD drive doesn't know about it. It sees 4K random writes to all 16G of the drive, total 64G data written.

b) If you always prefer a non full cluster first over a new cluster. The 64G data will concentrate random writing to the first 1G of drive location. Total 64G data written.

I consider b) are more friendly to SSD than a). Because concentrate the write into the first 1G location. The SSD can know the data overwritten in those 1G has internally obsolete, so it can internally GC the those overwritten data without a discard command. Where a) random 4K writes to the whole drive without much discard at all. Full SSD doing random writes is a bad combination from a wearing point of view.

Just my 2 cents. Anyway I revert the V4 to use free cluster before nonfull cluster just to behave the same as previously.

Quoted 7 lines

Quoted 5 lines

Quoted 1 line

commit 2a8f94493432 ("swap: change block allocation algorithm for SSD").

I did read that change log. Help me understand in more detail which discard behavior you have in mind. A lot of low end micro SD cards have proper FTL wear leveling now, ssd even better on that.

It's not FTL, it's discard/trim for SSD as above.

Thanks for the clarification.

Quoted 15 lines

Quoted 5 lines

Quoted 4 lines

And as pointed out by Ryan, this may reduce the opportunity of the sequential block device writing during swap-out, which may hurt performance of SSD too.

Quoted 9 lines

Only at the initial phase. If the swap IO continues, after the first pass fills up the swap file, the write will be random on the swapfile anyway. Because the swapfile only issues 2M discards commands when all 512 4K pages are free. The discarded area will be much smaller than the free area on swapfile. That combined with the random write page on the whole swap file. It might produce a worse internal write amplification for SSD, compared to only writing a subset of the swapfile area. I would love to hear from someone who understands SSD internals to confirm or deny my theory.

Quoted 3 lines

It depends on workloads. Some workloads will have more severe fragmentation than others. For example, on quite some machines, the swap devices will be far from being full to avoid possible OOM.

I suspect most of the SSD swap on client devices nowadays are only as backup just in case it needs to be swapped.
There is not much SSD swap IO during normal use. The zram and zswap are more actively used in the data center and Android phone case, from swap IO ops point of view.

Quoted 2 lines

I use a Linux laptop with 16GB DRAM for work. And I found that the swap space are almost always used.

Just curious how many swap OPS per second on average? I suspect it will be a very low number.

This is the short term solutiolns "swap cluster order" listed in my "Swap Abstraction" discussion slice 8 in the recent LSF/MM conference.

When commit 845982eb264bc "mm: swap: allow storage of all mTHP orders" is introduced, it only allocates the mTHP swap entries from new empty cluster list. It has a fragmentation issue reported by Barry.

https://lore.kernel.org/all/CAGsJ_4zAcJkuW016Cfi6wicRr8N9X+GJJhgMQdSMp+Ah+NSgNQ@mail.gmail.com/

The reason is that all the empty cluster has been exhausted while there are planty of free swap entries to in the cluster that is not 100% free.

Remember the swap allocation order in the cluster.
Keep track of the per order non full cluster list for later allocation.