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 v8 06/27] btrfs: dedupe: Introduce function to search for an existing hash
Date: Tue, 22 Mar 2016 09:35:31 +0800	[thread overview]
Message-ID: <1458610552-9845-7-git-send-email-quwenruo@cn.fujitsu.com> (raw)
In-Reply-To: <1458610552-9845-1-git-send-email-quwenruo@cn.fujitsu.com>

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

Introduce static function inmem_search() to handle the job for in-memory
hash tree.

The trick is, we must ensure the delayed ref head is not being run at
the time we search the for the hash.

With inmem_search(), we can implement the btrfs_dedupe_search()
interface.

Signed-off-by: Qu Wenruo <quwenruo@cn.fujitsu.com>
Signed-off-by: Wang Xiaoguang <wangxg.fnst@cn.fujitsu.com>
---
 fs/btrfs/dedupe.c | 184 ++++++++++++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 184 insertions(+)

diff --git a/fs/btrfs/dedupe.c b/fs/btrfs/dedupe.c
index e44993b..0196188 100644
--- a/fs/btrfs/dedupe.c
+++ b/fs/btrfs/dedupe.c
@@ -20,6 +20,7 @@
 #include "btrfs_inode.h"
 #include "transaction.h"
 #include "delayed-ref.h"
+#include "qgroup.h"
 
 struct inmem_hash {
 	struct rb_node hash_node;
@@ -362,3 +363,186 @@ int btrfs_dedupe_disable(struct btrfs_fs_info *fs_info)
 	kfree(dedupe_info);
 	return 0;
 }
+
+/*
+ * Caller must ensure the corresponding ref head is not being run.
+ */
+static struct inmem_hash *
+inmem_search_hash(struct btrfs_dedupe_info *dedupe_info, u8 *hash)
+{
+	struct rb_node **p = &dedupe_info->hash_root.rb_node;
+	struct rb_node *parent = NULL;
+	struct inmem_hash *entry = NULL;
+	u16 hash_type = dedupe_info->hash_type;
+	int hash_len = btrfs_dedupe_sizes[hash_type];
+
+	while (*p) {
+		parent = *p;
+		entry = rb_entry(parent, struct inmem_hash, hash_node);
+
+		if (memcmp(hash, entry->hash, hash_len) < 0) {
+			p = &(*p)->rb_left;
+		} else if (memcmp(hash, entry->hash, hash_len) > 0) {
+			p = &(*p)->rb_right;
+		} else {
+			/* Found, need to re-add it to LRU list head */
+			list_del(&entry->lru_list);
+			list_add(&entry->lru_list, &dedupe_info->lru_list);
+			return entry;
+		}
+	}
+	return NULL;
+}
+
+static int inmem_search(struct btrfs_dedupe_info *dedupe_info,
+			struct inode *inode, u64 file_pos,
+			struct btrfs_dedupe_hash *hash)
+{
+	int ret;
+	struct btrfs_root *root = BTRFS_I(inode)->root;
+	struct btrfs_trans_handle *trans;
+	struct btrfs_delayed_ref_root *delayed_refs;
+	struct btrfs_delayed_ref_head *head;
+	struct btrfs_delayed_ref_head *insert_head;
+	struct btrfs_delayed_data_ref *insert_dref;
+	struct btrfs_qgroup_extent_record *insert_qrecord = NULL;
+	struct inmem_hash *found_hash;
+	int free_insert = 1;
+	u64 bytenr;
+	u32 num_bytes;
+
+	insert_head = kmem_cache_alloc(btrfs_delayed_ref_head_cachep, GFP_NOFS);
+	if (!insert_head)
+		return -ENOMEM;
+	insert_head->extent_op = NULL;
+	insert_dref = kmem_cache_alloc(btrfs_delayed_data_ref_cachep, GFP_NOFS);
+	if (!insert_dref) {
+		kmem_cache_free(btrfs_delayed_ref_head_cachep, insert_head);
+		return -ENOMEM;
+	}
+	if (root->fs_info->quota_enabled &&
+	    is_fstree(root->root_key.objectid)) {
+		insert_qrecord = kmalloc(sizeof(*insert_qrecord), GFP_NOFS);
+		if (!insert_qrecord) {
+			kmem_cache_free(btrfs_delayed_ref_head_cachep,
+					insert_head);
+			kmem_cache_free(btrfs_delayed_data_ref_cachep,
+					insert_dref);
+			return -ENOMEM;
+		}
+	}
+
+	trans = btrfs_join_transaction(root);
+	if (IS_ERR(trans)) {
+		ret = PTR_ERR(trans);
+		goto free_mem;
+	}
+
+again:
+	mutex_lock(&dedupe_info->lock);
+	found_hash = inmem_search_hash(dedupe_info, hash->hash);
+	/* If we don't find a duplicated extent, just return. */
+	if (!found_hash) {
+		ret = 0;
+		goto out;
+	}
+	bytenr = found_hash->bytenr;
+	num_bytes = found_hash->num_bytes;
+
+	delayed_refs = &trans->transaction->delayed_refs;
+
+	spin_lock(&delayed_refs->lock);
+	head = btrfs_find_delayed_ref_head(trans, bytenr);
+	if (!head) {
+		/*
+		 * We can safely insert a new delayed_ref as long as we
+		 * hold delayed_refs->lock.
+		 * Only need to use atomic inc_extent_ref()
+		 */
+		btrfs_add_delayed_data_ref_locked(root->fs_info, trans,
+				insert_dref, insert_head, insert_qrecord,
+				bytenr, num_bytes, 0, root->root_key.objectid,
+				btrfs_ino(inode), file_pos, 0,
+				BTRFS_ADD_DELAYED_REF);
+		spin_unlock(&delayed_refs->lock);
+
+		/* add_delayed_data_ref_locked will free unused memory */
+		free_insert = 0;
+		hash->bytenr = bytenr;
+		hash->num_bytes = num_bytes;
+		ret = 1;
+		goto out;
+	}
+
+	/*
+	 * We can't lock ref head with dedupe_info->lock hold or we will cause
+	 * ABBA dead lock.
+	 */
+	mutex_unlock(&dedupe_info->lock);
+	ret = btrfs_delayed_ref_lock(trans, head);
+	spin_unlock(&delayed_refs->lock);
+	if (ret == -EAGAIN)
+		goto again;
+
+	mutex_lock(&dedupe_info->lock);
+	/* Search again to ensure the hash is still here */
+	found_hash = inmem_search_hash(dedupe_info, hash->hash);
+	if (!found_hash) {
+		ret = 0;
+		mutex_unlock(&head->mutex);
+		goto out;
+	}
+	hash->bytenr = bytenr;
+	hash->num_bytes = num_bytes;
+
+	/*
+	 * Increase the extent ref right now, to avoid delayed ref run
+	 * Or we may increase ref on non-exist extent.
+	 */
+	btrfs_inc_extent_ref(trans, root, bytenr, num_bytes, 0,
+			     root->root_key.objectid,
+			     btrfs_ino(inode), file_pos);
+	mutex_unlock(&head->mutex);
+out:
+	mutex_unlock(&dedupe_info->lock);
+	btrfs_end_transaction(trans, root);
+
+free_mem:
+	if (free_insert) {
+		kmem_cache_free(btrfs_delayed_ref_head_cachep, insert_head);
+		kmem_cache_free(btrfs_delayed_data_ref_cachep, insert_dref);
+		kfree(insert_qrecord);
+	}
+	return ret;
+}
+
+int btrfs_dedupe_search(struct btrfs_fs_info *fs_info,
+			struct inode *inode, u64 file_pos,
+			struct btrfs_dedupe_hash *hash)
+{
+	struct btrfs_dedupe_info *dedupe_info = fs_info->dedupe_info;
+	int ret = -EINVAL;
+
+	if (!hash)
+		return 0;
+
+	/*
+	 * This function doesn't follow fs_info->dedupe_enabled as it will need
+	 * to ensure any hashed extent to go through dedupe routine
+	 */
+	if (WARN_ON(dedupe_info == NULL))
+		return -EINVAL;
+
+	if (WARN_ON(btrfs_dedupe_hash_hit(hash)))
+		return -EINVAL;
+
+	if (dedupe_info->backend == BTRFS_DEDUPE_BACKEND_INMEMORY)
+		ret = inmem_search(dedupe_info, inode, file_pos, hash);
+
+	/* It's possible hash->bytenr/num_bytenr already changed */
+	if (ret == 0) {
+		hash->num_bytes = 0;
+		hash->bytenr = 0;
+	}
+	return ret;
+}
-- 
2.7.3




  parent reply	other threads:[~2016-03-22  1:38 UTC|newest]

Thread overview: 62+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2016-03-22  1:35 [PATCH v8 00/27][For 4.7] Btrfs: Add inband (write time) de-duplication framework Qu Wenruo
2016-03-22  1:35 ` [PATCH v8 01/27] btrfs: dedupe: Introduce dedupe framework and its header Qu Wenruo
2016-03-22  1:35 ` [PATCH v8 02/27] btrfs: dedupe: Introduce function to initialize dedupe info Qu Wenruo
2016-03-22  1:35 ` [PATCH v8 03/27] btrfs: dedupe: Introduce function to add hash into in-memory tree Qu Wenruo
2016-03-22  1:35 ` [PATCH v8 04/27] btrfs: dedupe: Introduce function to remove hash from " Qu Wenruo
2016-03-22  1:35 ` [PATCH v8 05/27] btrfs: delayed-ref: Add support for increasing data ref under spinlock Qu Wenruo
2016-03-22  1:35 ` Qu Wenruo [this message]
2016-03-22  1:35 ` [PATCH v8 07/27] btrfs: dedupe: Implement btrfs_dedupe_calc_hash interface Qu Wenruo
2016-03-22  1:35 ` [PATCH v8 08/27] btrfs: ordered-extent: Add support for dedupe Qu Wenruo
2016-03-22  1:35 ` [PATCH v8 09/27] btrfs: dedupe: Inband in-memory only de-duplication implement Qu Wenruo
2016-03-22  1:35 ` [PATCH v8 10/27] btrfs: dedupe: Add basic tree structure for on-disk dedupe method Qu Wenruo
2016-03-24 20:58   ` Chris Mason
2016-03-25  1:59     ` Qu Wenruo
2016-03-25 15:11       ` Chris Mason
2016-03-26 13:11         ` Qu Wenruo
2016-03-28 14:09           ` Chris Mason
2016-03-29  1:47             ` Qu Wenruo
2016-03-22  1:35 ` [PATCH v8 11/27] btrfs: dedupe: Introduce interfaces to resume and cleanup dedupe info Qu Wenruo
2016-03-29 17:31   ` Alex Lyakas
2016-03-30  0:26     ` Qu Wenruo
2016-03-22  1:35 ` [PATCH v8 12/27] btrfs: dedupe: Add support for on-disk hash search Qu Wenruo
2016-03-22  1:35 ` [PATCH v8 13/27] btrfs: dedupe: Add support to delete hash for on-disk backend Qu Wenruo
2016-03-22  1:35 ` [PATCH v8 14/27] btrfs: dedupe: Add support for adding " Qu Wenruo
2016-03-22  1:35 ` [PATCH v8 15/27] btrfs: dedupe: Add ioctl for inband dedupelication Qu Wenruo
2016-03-22  2:29   ` kbuild test robot
2016-03-22  2:48   ` kbuild test robot
2016-03-22  1:35 ` [PATCH v8 16/27] btrfs: dedupe: add an inode nodedupe flag Qu Wenruo
2016-03-22  1:35 ` [PATCH v8 17/27] btrfs: dedupe: add a property handler for online dedupe Qu Wenruo
2016-03-22  1:35 ` [PATCH v8 18/27] btrfs: dedupe: add per-file online dedupe control Qu Wenruo
2016-03-22  1:35 ` [PATCH v8 19/27] btrfs: try more times to alloc metadata reserve space Qu Wenruo
2016-04-22 18:06   ` Josef Bacik
2016-04-25  0:54     ` Qu Wenruo
2016-04-25 14:05       ` Josef Bacik
2016-04-26  0:50         ` Qu Wenruo
2016-03-22  1:35 ` [PATCH v8 20/27] btrfs: dedupe: Fix a bug when running inband dedupe with balance Qu Wenruo
2016-03-22  1:35 ` [PATCH v8 21/27] btrfs: Fix a memory leak in inband dedupe hash Qu Wenruo
2016-03-22  1:35 ` [PATCH v8 22/27] btrfs: dedupe: Fix metadata balance error when dedupe is enabled Qu Wenruo
2016-03-22  1:35 ` [PATCH v8 23/27] btrfs: dedupe: Avoid submit IO for hash hit extent Qu Wenruo
2016-03-22  1:35 ` [PATCH v8 24/27] btrfs: dedupe: Preparation for compress-dedupe co-work Qu Wenruo
2016-03-22  1:35 ` [PATCH v8 25/27] btrfs: dedupe: Add support for compression and dedpue Qu Wenruo
2016-03-24 20:35   ` Chris Mason
2016-03-25  1:44     ` Qu Wenruo
2016-03-25 15:12       ` Chris Mason
2016-03-22  1:35 ` [PATCH v8 26/27] btrfs: relocation: Enhance error handling to avoid BUG_ON Qu Wenruo
2016-03-22  1:35 ` [PATCH v8 27/27] btrfs: dedupe: Fix a space cache delalloc bytes underflow bug Qu Wenruo
2016-03-22 13:38 ` [PATCH v8 00/27][For 4.7] Btrfs: Add inband (write time) de-duplication framework David Sterba
2016-03-23  2:25   ` Qu Wenruo
2016-03-24 13:42     ` David Sterba
2016-03-25  1:38       ` Qu Wenruo
2016-04-04 16:55         ` David Sterba
2016-04-05  3:08           ` Qu Wenruo
2016-04-20  2:02             ` Qu Wenruo
2016-04-20 19:14               ` Chris Mason
2016-04-06  3:47           ` Nicholas D Steeves
2016-04-06  5:22             ` Qu Wenruo
2016-04-22 22:14               ` Nicholas D Steeves
2016-04-25  1:25                 ` Qu Wenruo
2016-03-29 17:22 ` Alex Lyakas
2016-03-30  0:34   ` Qu Wenruo
2016-03-30 10:36     ` Alex Lyakas
2016-04-03  8:22     ` Alex Lyakas
2016-04-05  3:51       ` 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=1458610552-9845-7-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.