Re: [PATCH v2] zswap: replace RB tree with xarray

[Chengming Zhou]

Hi Chris,

On 2024/2/29 16:46, Chris Li wrote:
> Very deep RB tree requires rebalance at times. That
> contributes to the zswap fault latencies. Xarray does not
> need to perform tree rebalance. Replacing RB tree to xarray
> can have some small performance gain.
> 
> One small difference is that xarray insert might fail with
> ENOMEM, while RB tree insert does not allocate additional
> memory.
> 
> The zswap_entry size will reduce a bit due to removing the
> RB node, which has two pointers and a color field. Xarray
> store the pointer in the xarray tree rather than the
> zswap_entry. Every entry has one pointer from the xarray
> tree. Overall, switching to xarray should save some memory,
> if the swap entries are densely packed.
> 
> Notice the zswap_rb_search and zswap_rb_insert always
> followed by zswap_rb_erase. Fold the entry erase into
> zswap_xa_search_and_erase and zswap_xa_insert. That saves
> one tree lookup as well.
> 
> Remove zswap_invalidate_entry due to no need to call
> zswap_rb_erase any more. Use zswap_free_entry instead.
> 
> The "struct zswap_tree" has been replaced by "struct xarray".
> The tree spin lock has transferred to the xarray lock.
> 
> Thanks to Chengming for providing the kernel build test number.
> 
> Run the kernel build testing 5 times for each version, averages:
> (memory.max=2GB, zswap shrinker and writeback enabled, one 50GB swapfile.)
> 
>                               mm-266f922c0b5e       zswap-xarray-test            
> real                          63.43                 63.12                        
> user                          1063.78               1062.59                      
> sys                           272.49                265.66
> 
> The sys time is about 2.5% faster.
> 
> Tested-by: Chengming Zhou <zhouchengming@xxxxxxxxxxxxx>
> ---
> 
> 
> Signed-off-by: Chris Li <chrisl@xxxxxxxxxx>
> ---
> Changes in v2:
> - Replace struct zswap_tree with struct xarray.
> - Remove zswap_tree spinlock, use xarray lock instead.
> - Fold zswap_rb_erase() into zswap_xa_search_and_delete() and zswap_xa_insert().
> - Delete zswap_invalidate_entry(), use zswap_free_entry() instead.
> - Link to v1: https://lore.kernel.org/r/20240117-zswap-xarray-v1-0-6daa86c08fae@xxxxxxxxxx
> ---
>  mm/zswap.c | 173 +++++++++++++++++++++++--------------------------------------
>  1 file changed, 64 insertions(+), 109 deletions(-)
> 
> diff --git a/mm/zswap.c b/mm/zswap.c
> index 011e068eb355..ac9ef14d88be 100644
> --- a/mm/zswap.c
> +++ b/mm/zswap.c
> @@ -20,7 +20,6 @@
>  #include <linux/spinlock.h>
>  #include <linux/types.h>
>  #include <linux/atomic.h>
> -#include <linux/rbtree.h>
>  #include <linux/swap.h>
>  #include <linux/crypto.h>
>  #include <linux/scatterlist.h>
> @@ -71,6 +70,8 @@ static u64 zswap_reject_compress_poor;
>  static u64 zswap_reject_alloc_fail;
>  /* Store failed because the entry metadata could not be allocated (rare) */
>  static u64 zswap_reject_kmemcache_fail;
> +/* Store failed because xarray can't insert the entry*/
> +static u64 zswap_reject_xarray_fail;
>  
>  /* Shrinker work queue */
>  static struct workqueue_struct *shrink_wq;
> @@ -196,7 +197,6 @@ static struct {
>   * This structure contains the metadata for tracking a single compressed
>   * page within zswap.
>   *
> - * rbnode - links the entry into red-black tree for the appropriate swap type
>   * swpentry - associated swap entry, the offset indexes into the red-black tree
>   * length - the length in bytes of the compressed page data.  Needed during
>   *          decompression. For a same value filled page length is 0, and both
> @@ -208,7 +208,6 @@ static struct {
>   * lru - handle to the pool's lru used to evict pages.
>   */
>  struct zswap_entry {
> -	struct rb_node rbnode;
>  	swp_entry_t swpentry;
>  	unsigned int length;
>  	struct zswap_pool *pool;
> @@ -220,12 +219,7 @@ struct zswap_entry {
>  	struct list_head lru;
>  };
>  
> -struct zswap_tree {
> -	struct rb_root rbroot;
> -	spinlock_t lock;
> -};
> -
> -static struct zswap_tree *zswap_trees[MAX_SWAPFILES];
> +static struct xarray *zswap_trees[MAX_SWAPFILES];
>  static unsigned int nr_zswap_trees[MAX_SWAPFILES];
>  
>  /* RCU-protected iteration */
> @@ -253,10 +247,10 @@ static bool zswap_has_pool;
>  * helpers and fwd declarations
>  **********************************/
>  
> -static inline struct zswap_tree *swap_zswap_tree(swp_entry_t swp)
> +static inline struct xarray *swap_zswap_tree(swp_entry_t swp)
>  {
> -	return &zswap_trees[swp_type(swp)][swp_offset(swp)
> -		>> SWAP_ADDRESS_SPACE_SHIFT];
> +	return zswap_trees[swp_type(swp)] + (swp_offset(swp)
> +		>> SWAP_ADDRESS_SPACE_SHIFT);
>  }
>  
>  #define zswap_pool_debug(msg, p)				\
> @@ -805,60 +799,38 @@ void zswap_memcg_offline_cleanup(struct mem_cgroup *memcg)
>  }
>  
>  /*********************************
> -* rbtree functions
> +* xarray functions
>  **********************************/
> -static struct zswap_entry *zswap_rb_search(struct rb_root *root, pgoff_t offset)
> +static struct zswap_entry *zswap_xa_search_and_erase(struct xarray *tree, pgoff_t offset)
>  {
> -	struct rb_node *node = root->rb_node;
> -	struct zswap_entry *entry;
> -	pgoff_t entry_offset;
> -
> -	while (node) {
> -		entry = rb_entry(node, struct zswap_entry, rbnode);
> -		entry_offset = swp_offset(entry->swpentry);
> -		if (entry_offset > offset)
> -			node = node->rb_left;
> -		else if (entry_offset < offset)
> -			node = node->rb_right;
> -		else
> -			return entry;
> -	}
> -	return NULL;
> +	return xa_erase(tree, offset);
>  }
>  
>  /*
> + * Expects xa_lock to be held on entry.
>   * In the case that a entry with the same offset is found, a pointer to
> - * the existing entry is stored in dupentry and the function returns -EEXIST
> + * the existing entry is stored in old and erased from the tree.
> + * Function return error on insert.
>   */
> -static int zswap_rb_insert(struct rb_root *root, struct zswap_entry *entry,
> -			struct zswap_entry **dupentry)
> +static int zswap_xa_insert(struct xarray *tree, struct zswap_entry *entry,
> +			   struct zswap_entry **old)
>  {
> -	struct rb_node **link = &root->rb_node, *parent = NULL;
> -	struct zswap_entry *myentry;
> -	pgoff_t myentry_offset, entry_offset = swp_offset(entry->swpentry);
> -
> -	while (*link) {
> -		parent = *link;
> -		myentry = rb_entry(parent, struct zswap_entry, rbnode);
> -		myentry_offset = swp_offset(myentry->swpentry);
> -		if (myentry_offset > entry_offset)
> -			link = &(*link)->rb_left;
> -		else if (myentry_offset < entry_offset)
> -			link = &(*link)->rb_right;
> -		else {
> -			*dupentry = myentry;
> -			return -EEXIST;
> -		}
> -	}
> -	rb_link_node(&entry->rbnode, parent, link);
> -	rb_insert_color(&entry->rbnode, root);
> -	return 0;
> -}
> +	int err;
> +	struct zswap_entry *e;
> +	pgoff_t offset = swp_offset(entry->swpentry);
>  
> -static void zswap_rb_erase(struct rb_root *root, struct zswap_entry *entry)
> -{
> -	rb_erase(&entry->rbnode, root);
> -	RB_CLEAR_NODE(&entry->rbnode);
> +	e = __xa_store(tree, offset, entry, GFP_KERNEL);
> +	err = xa_err(e);
> +
> +	if (err) {
> +		e = __xa_erase(tree, offset);
> +		if (err == -ENOMEM)
> +			zswap_reject_alloc_fail++;
> +		else
> +			zswap_reject_xarray_fail++;
> +	}
> +	*old = e;
> +	return err;
>  }
>  
>  /*********************************
> @@ -872,7 +844,6 @@ static struct zswap_entry *zswap_entry_cache_alloc(gfp_t gfp, int nid)
>  	entry = kmem_cache_alloc_node(zswap_entry_cache, gfp, nid);
>  	if (!entry)
>  		return NULL;
> -	RB_CLEAR_NODE(&entry->rbnode);
>  	return entry;
>  }
>  
> @@ -914,17 +885,6 @@ static void zswap_entry_free(struct zswap_entry *entry)
>  	zswap_update_total_size();
>  }
>  
> -/*
> - * The caller hold the tree lock and search the entry from the tree,
> - * so it must be on the tree, remove it from the tree and free it.
> - */
> -static void zswap_invalidate_entry(struct zswap_tree *tree,
> -				   struct zswap_entry *entry)
> -{
> -	zswap_rb_erase(&tree->rbroot, entry);
> -	zswap_entry_free(entry);
> -}
> -
>  /*********************************
>  * compressed storage functions
>  **********************************/
> @@ -1113,7 +1073,9 @@ static void zswap_decompress(struct zswap_entry *entry, struct page *page)
>  static int zswap_writeback_entry(struct zswap_entry *entry,
>  				 swp_entry_t swpentry)
>  {
> -	struct zswap_tree *tree;
> +	struct xarray *tree;
> +	pgoff_t offset = swp_offset(swpentry);
> +	struct zswap_entry *e;
>  	struct folio *folio;
>  	struct mempolicy *mpol;
>  	bool folio_was_allocated;
> @@ -1150,19 +1112,14 @@ static int zswap_writeback_entry(struct zswap_entry *entry,
>  	 * be dereferenced.
>  	 */
>  	tree = swap_zswap_tree(swpentry);
> -	spin_lock(&tree->lock);
> -	if (zswap_rb_search(&tree->rbroot, swp_offset(swpentry)) != entry) {
> -		spin_unlock(&tree->lock);
> +	e = zswap_xa_search_and_erase(tree, offset);
> +	if (e != entry) {

IIUC, here we should use xa_cmpxchg() instead of erasing it unconditionally.

>  		delete_from_swap_cache(folio);
>  		folio_unlock(folio);
>  		folio_put(folio);
>  		return -ENOMEM;
>  	}
>  
> -	/* Safe to deref entry after the entry is verified above. */
> -	zswap_rb_erase(&tree->rbroot, entry);
> -	spin_unlock(&tree->lock);
> -
>  	zswap_decompress(entry, &folio->page);
>  
>  	count_vm_event(ZSWPWB);
> @@ -1471,10 +1428,11 @@ bool zswap_store(struct folio *folio)
>  {
>  	swp_entry_t swp = folio->swap;
>  	pgoff_t offset = swp_offset(swp);
> -	struct zswap_tree *tree = swap_zswap_tree(swp);
> -	struct zswap_entry *entry, *dupentry;
> +	struct xarray *tree = swap_zswap_tree(swp);
> +	struct zswap_entry *entry, *old;
>  	struct obj_cgroup *objcg = NULL;
>  	struct mem_cgroup *memcg = NULL;
> +	int err;
>  
>  	VM_WARN_ON_ONCE(!folio_test_locked(folio));
>  	VM_WARN_ON_ONCE(!folio_test_swapcache(folio));
> @@ -1562,21 +1520,25 @@ bool zswap_store(struct folio *folio)
>  	}
>  
>  	/* map */
> -	spin_lock(&tree->lock);
> +	xa_lock(tree);
>  	/*
>  	 * The folio may have been dirtied again, invalidate the
>  	 * possibly stale entry before inserting the new entry.
>  	 */
> -	if (zswap_rb_insert(&tree->rbroot, entry, &dupentry) == -EEXIST) {
> -		zswap_invalidate_entry(tree, dupentry);
> -		WARN_ON(zswap_rb_insert(&tree->rbroot, entry, &dupentry));
> +	err = zswap_xa_insert(tree, entry, &old);
> +	if (old)
> +		zswap_entry_free(old);

Maybe it's safer to check old after !err, since "old" variable is not initialized
to NULL, and zswap_xa_insert() maybe won't overwrite "old" to NULL when err return?

> +	if (err) {
> +		xa_unlock(tree);
> +		goto free_zpool;
>  	}
> +
>  	if (entry->length) {
>  		INIT_LIST_HEAD(&entry->lru);
>  		zswap_lru_add(&zswap.list_lru, entry);
>  		atomic_inc(&zswap.nr_stored);
>  	}

It seems that we can put this part out of xarray lock section, then it's enough to
just use xa_insert().

Thanks.