All of lore.kernel.org
 help / color / mirror / Atom feed
From: Qu Wenruo <quwenruo@cn.fujitsu.com>
To: linux-btrfs@vger.kernel.org
Cc: Wang Xiaoguang <wangxg.fnst@cn.fujitsu.com>
Subject: [PATCH v5 03/19] btrfs: dedup: Introduce function to add hash into in-memory tree
Date: Tue,  2 Feb 2016 11:05:35 +0800	[thread overview]
Message-ID: <1454382351-31775-4-git-send-email-quwenruo@cn.fujitsu.com> (raw)
In-Reply-To: <1454382351-31775-1-git-send-email-quwenruo@cn.fujitsu.com>

From: Wang Xiaoguang <wangxg.fnst@cn.fujitsu.com>

Introduce static function inmem_add() to add hash into in-memory tree.
And now we can implement the btrfs_dedup_add() interface.

Signed-off-by: Qu Wenruo <quwenruo@cn.fujitsu.com>
Signed-off-by: Wang Xiaoguang <wangxg.fnst@cn.fujitsu.com>
---
 fs/btrfs/dedup.c | 157 +++++++++++++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 157 insertions(+)

diff --git a/fs/btrfs/dedup.c b/fs/btrfs/dedup.c
index b37db50..b6bff0a 100644
--- a/fs/btrfs/dedup.c
+++ b/fs/btrfs/dedup.c
@@ -21,6 +21,25 @@
 #include "transaction.h"
 #include "delayed-ref.h"
 
+struct inmem_hash {
+	struct rb_node hash_node;
+	struct rb_node bytenr_node;
+	struct list_head lru_list;
+
+	u64 bytenr;
+	u32 num_bytes;
+
+	u8 hash[];
+};
+
+static inline struct inmem_hash *inmem_alloc_hash(u16 type)
+{
+	if (WARN_ON(type >= ARRAY_SIZE(btrfs_dedup_sizes)))
+		return NULL;
+	return kzalloc(sizeof(struct inmem_hash) + btrfs_dedup_sizes[type],
+			GFP_NOFS);
+}
+
 int btrfs_dedup_enable(struct btrfs_fs_info *fs_info, u16 type, u16 backend,
 		       u64 blocksize, u64 limit_nr)
 {
@@ -98,3 +117,141 @@ out:
 		kfree(dedup_info);
 	return ret;
 }
+
+static int inmem_insert_hash(struct rb_root *root,
+			     struct inmem_hash *hash, int hash_len)
+{
+	struct rb_node **p = &root->rb_node;
+	struct rb_node *parent = NULL;
+	struct inmem_hash *entry = NULL;
+
+	while (*p) {
+		parent = *p;
+		entry = rb_entry(parent, struct inmem_hash, hash_node);
+		if (memcmp(hash->hash, entry->hash, hash_len) < 0)
+			p = &(*p)->rb_left;
+		else if (memcmp(hash->hash, entry->hash, hash_len) > 0)
+			p = &(*p)->rb_right;
+		else
+			return 1;
+	}
+	rb_link_node(&hash->hash_node, parent, p);
+	rb_insert_color(&hash->hash_node, root);
+	return 0;
+}
+
+static int inmem_insert_bytenr(struct rb_root *root,
+			       struct inmem_hash *hash)
+{
+	struct rb_node **p = &root->rb_node;
+	struct rb_node *parent = NULL;
+	struct inmem_hash *entry = NULL;
+
+	while (*p) {
+		parent = *p;
+		entry = rb_entry(parent, struct inmem_hash, bytenr_node);
+		if (hash->bytenr < entry->bytenr)
+			p = &(*p)->rb_left;
+		else if (hash->bytenr > entry->bytenr)
+			p = &(*p)->rb_right;
+		else
+			return 1;
+	}
+	rb_link_node(&hash->bytenr_node, parent, p);
+	rb_insert_color(&hash->bytenr_node, root);
+	return 0;
+}
+
+static void __inmem_del(struct btrfs_dedup_info *dedup_info,
+			struct inmem_hash *hash)
+{
+	list_del(&hash->lru_list);
+	rb_erase(&hash->hash_node, &dedup_info->hash_root);
+	rb_erase(&hash->bytenr_node, &dedup_info->bytenr_root);
+
+	if (!WARN_ON(dedup_info->current_nr == 0))
+		dedup_info->current_nr--;
+
+	kfree(hash);
+}
+
+/*
+ * Insert a hash into in-memory dedup tree
+ * Will remove exceeding last recent use hash.
+ *
+ * If the hash mathced with existing one, we won't insert it, to
+ * save memory
+ */
+static int inmem_add(struct btrfs_dedup_info *dedup_info,
+		     struct btrfs_dedup_hash *hash)
+{
+	int ret = 0;
+	u16 type = dedup_info->hash_type;
+	struct inmem_hash *ihash;
+
+	ihash = inmem_alloc_hash(type);
+
+	if (!ihash)
+		return -ENOMEM;
+
+	/* Copy the data out */
+	ihash->bytenr = hash->bytenr;
+	ihash->num_bytes = hash->num_bytes;
+	memcpy(ihash->hash, hash->hash, btrfs_dedup_sizes[type]);
+
+	mutex_lock(&dedup_info->lock);
+
+	ret = inmem_insert_bytenr(&dedup_info->bytenr_root, ihash);
+	if (ret > 0) {
+		kfree(ihash);
+		ret = 0;
+		goto out;
+	}
+
+	ret = inmem_insert_hash(&dedup_info->hash_root, ihash,
+				btrfs_dedup_sizes[type]);
+	if (ret > 0) {
+		/*
+		 * We only keep one hash in tree to save memory, so if
+		 * hash conflicts, free the one to insert.
+		 */
+		rb_erase(&ihash->bytenr_node, &dedup_info->bytenr_root);
+		kfree(ihash);
+		ret = 0;
+		goto out;
+	}
+
+	list_add(&ihash->lru_list, &dedup_info->lru_list);
+	dedup_info->current_nr++;
+
+	/* Remove the last dedup hash if we exceed limit */
+	while (dedup_info->current_nr > dedup_info->limit_nr) {
+		struct inmem_hash *last;
+
+		last = list_entry(dedup_info->lru_list.prev,
+				  struct inmem_hash, lru_list);
+		__inmem_del(dedup_info, last);
+	}
+out:
+	mutex_unlock(&dedup_info->lock);
+	return 0;
+}
+
+int btrfs_dedup_add(struct btrfs_trans_handle *trans,
+		    struct btrfs_dedup_info *dedup_info,
+		    struct btrfs_dedup_hash *hash)
+{
+	if (!dedup_info || !hash)
+		return 0;
+
+	/* ignore old hash */
+	if (dedup_info->blocksize != hash->num_bytes)
+		return 0;
+
+	if (WARN_ON(hash->bytenr == 0))
+		return -EINVAL;
+
+	if (dedup_info->backend == BTRFS_DEDUP_BACKEND_INMEMORY)
+		return inmem_add(dedup_info, hash);
+	return -EINVAL;
+}
-- 
2.7.0




  parent reply	other threads:[~2016-02-02  3:08 UTC|newest]

Thread overview: 20+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2016-02-02  3:05 [PATCH v5 00/19][For 4.6] Btrfs: Add inband (write time) de-duplication framework Qu Wenruo
2016-02-02  3:05 ` [PATCH v5 01/19] btrfs: dedup: Introduce dedup framework and its header Qu Wenruo
2016-02-02  3:05 ` [PATCH v5 02/19] btrfs: dedup: Introduce function to initialize dedup info Qu Wenruo
2016-02-02  3:05 ` Qu Wenruo [this message]
2016-02-02  3:05 ` [PATCH v5 04/19] btrfs: dedup: Introduce function to remove hash from in-memory tree Qu Wenruo
2016-02-02  3:05 ` [PATCH v5 05/19] btrfs: delayed-ref: Add support for increasing data ref under spinlock Qu Wenruo
2016-02-02  3:05 ` [PATCH v5 06/19] btrfs: dedup: Introduce function to search for an existing hash Qu Wenruo
2016-02-02  3:05 ` [PATCH v5 07/19] btrfs: dedup: Implement btrfs_dedup_calc_hash interface Qu Wenruo
2016-02-02  3:05 ` [PATCH v5 08/19] btrfs: ordered-extent: Add support for dedup Qu Wenruo
2016-02-02  3:05 ` [PATCH v5 09/19] btrfs: dedup: Inband in-memory only de-duplication implement Qu Wenruo
2016-02-02  3:05 ` [PATCH v5 10/19] btrfs: dedup: Add basic tree structure for on-disk dedup method Qu Wenruo
2016-02-02  3:05 ` [PATCH v5 11/19] btrfs: dedup: Introduce interfaces to resume and cleanup dedup info Qu Wenruo
2016-02-02  3:05 ` [PATCH v5 12/19] btrfs: dedup: Add support for on-disk hash search Qu Wenruo
2016-02-02  3:05 ` [PATCH v5 13/19] btrfs: dedup: Add support to delete hash for on-disk backend Qu Wenruo
2016-02-02  3:05 ` [PATCH v5 14/19] btrfs: dedup: Add support for adding " Qu Wenruo
2016-02-02  3:05 ` [PATCH v5 15/19] btrfs: dedup: Add ioctl for inband deduplication Qu Wenruo
2016-02-02  3:05 ` [PATCH v5 16/19] btrfs: dedup: add an inode nodedup flag Qu Wenruo
2016-02-02  3:05 ` [PATCH v5 17/19] btrfs: dedup: add a property handler for online dedup Qu Wenruo
2016-02-02  3:05 ` [PATCH v5 18/19] btrfs: dedup: add per-file online dedup control Qu Wenruo
2016-02-02  3:05 ` [PATCH v5 19/19] btrfs: try more times to alloc metadata reserve space Qu Wenruo

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=1454382351-31775-4-git-send-email-quwenruo@cn.fujitsu.com \
    --to=quwenruo@cn.fujitsu.com \
    --cc=linux-btrfs@vger.kernel.org \
    --cc=wangxg.fnst@cn.fujitsu.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.