linux-fsdevel.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Andiry Xu <jix024@eng.ucsd.edu>
To: linux-fsdevel@vger.kernel.org, linux-kernel@vger.kernel.org,
	linux-nvdimm@lists.01.org
Cc: dan.j.williams@intel.com, andy.rudoff@intel.com,
	coughlan@redhat.com, swanson@cs.ucsd.edu, david@fromorbit.com,
	jack@suse.com, swhiteho@redhat.com, miklos@szeredi.hu,
	andiry.xu@gmail.com, Andiry Xu <jix024@cs.ucsd.edu>
Subject: [RFC v2 46/83] Dir: Add Directory radix tree insert/remove methods.
Date: Sat, 10 Mar 2018 10:18:27 -0800	[thread overview]
Message-ID: <1520705944-6723-47-git-send-email-jix024@eng.ucsd.edu> (raw)
In-Reply-To: <1520705944-6723-1-git-send-email-jix024@eng.ucsd.edu>

From: Andiry Xu <jix024@cs.ucsd.edu>

NOVA uses Hash to quickly locate dentry in the directory inode log.
The key is the hash of the filename, the value is the dentry.

Currently hash collision is ignored, and the radix tree may occupy
large memory space with huge directories. Considering replacing
it in the future.

Signed-off-by: Andiry Xu <jix024@cs.ucsd.edu>
---
 fs/nova/Makefile |   2 +-
 fs/nova/dir.c    | 141 +++++++++++++++++++++++++++++++++++++++++++++++++++++++
 fs/nova/nova.h   |  26 ++++++++++
 3 files changed, 168 insertions(+), 1 deletion(-)
 create mode 100644 fs/nova/dir.c

diff --git a/fs/nova/Makefile b/fs/nova/Makefile
index 4aeadea..3a3243c 100644
--- a/fs/nova/Makefile
+++ b/fs/nova/Makefile
@@ -4,4 +4,4 @@
 
 obj-$(CONFIG_NOVA_FS) += nova.o
 
-nova-y := balloc.o bbuild.o inode.o journal.o log.o rebuild.o stats.o super.o
+nova-y := balloc.o bbuild.o dir.o inode.o journal.o log.o rebuild.o stats.o super.o
diff --git a/fs/nova/dir.c b/fs/nova/dir.c
new file mode 100644
index 0000000..5bea57a
--- /dev/null
+++ b/fs/nova/dir.c
@@ -0,0 +1,141 @@
+/*
+ * BRIEF DESCRIPTION
+ *
+ * File operations for directories.
+ *
+ * Copyright 2015-2016 Regents of the University of California,
+ * UCSD Non-Volatile Systems Lab, Andiry Xu <jix024@cs.ucsd.edu>
+ * Copyright 2012-2013 Intel Corporation
+ * Copyright 2009-2011 Marco Stornelli <marco.stornelli@gmail.com>
+ * Copyright 2003 Sony Corporation
+ * Copyright 2003 Matsushita Electric Industrial Co., Ltd.
+ * 2003-2004 (c) MontaVista Software, Inc. , Steve Longerbeam
+ * This file is licensed under the terms of the GNU General Public
+ * License version 2. This program is licensed "as is" without any
+ * warranty of any kind, whether express or implied.
+ */
+
+#include <linux/fs.h>
+#include <linux/pagemap.h>
+#include "nova.h"
+#include "inode.h"
+
+#define DT2IF(dt) (((dt) << 12) & S_IFMT)
+#define IF2DT(sif) (((sif) & S_IFMT) >> 12)
+
+struct nova_dentry *nova_find_dentry(struct super_block *sb,
+	struct nova_inode *pi, struct inode *inode, const char *name,
+	unsigned long name_len)
+{
+	struct nova_inode_info *si = NOVA_I(inode);
+	struct nova_inode_info_header *sih = &si->header;
+	struct nova_dentry *direntry;
+	unsigned long hash;
+
+	hash = BKDRHash(name, name_len);
+	direntry = radix_tree_lookup(&sih->tree, hash);
+
+	return direntry;
+}
+
+int nova_insert_dir_radix_tree(struct super_block *sb,
+	struct nova_inode_info_header *sih, const char *name,
+	int namelen, struct nova_dentry *direntry)
+{
+	unsigned long hash;
+	int ret;
+
+	hash = BKDRHash(name, namelen);
+	nova_dbgv("%s: insert %s hash %lu\n", __func__, name, hash);
+
+	/* FIXME: hash collision ignored here */
+	ret = radix_tree_insert(&sih->tree, hash, direntry);
+	if (ret)
+		nova_dbg("%s ERROR %d: %s\n", __func__, ret, name);
+
+	return ret;
+}
+
+static int nova_check_dentry_match(struct super_block *sb,
+	struct nova_dentry *dentry, const char *name, int namelen)
+{
+	if (dentry->name_len != namelen)
+		return -EINVAL;
+
+	return strncmp(dentry->name, name, namelen);
+}
+
+int nova_remove_dir_radix_tree(struct super_block *sb,
+	struct nova_inode_info_header *sih, const char *name, int namelen,
+	int replay, struct nova_dentry **create_dentry)
+{
+	struct nova_dentry *entry;
+	unsigned long hash;
+
+	hash = BKDRHash(name, namelen);
+	entry = radix_tree_delete(&sih->tree, hash);
+
+	if (replay == 0) {
+		if (!entry) {
+			nova_dbg("%s ERROR: %s, length %d, hash %lu\n",
+					__func__, name, namelen, hash);
+			return -EINVAL;
+		}
+
+		if (entry->ino == 0 || entry->invalid ||
+		    nova_check_dentry_match(sb, entry, name, namelen)) {
+			nova_dbg("%s dentry not match: %s, length %d, hash %lu\n",
+				 __func__, name, namelen, hash);
+			/* for debug information, still allow access to nvmm */
+			nova_dbg("dentry: type %d, inode %llu, name %s, namelen %u, rec len %u\n",
+				 entry->entry_type, le64_to_cpu(entry->ino),
+				 entry->name, entry->name_len,
+				 le16_to_cpu(entry->de_len));
+			return -EINVAL;
+		}
+
+		if (create_dentry)
+			*create_dentry = entry;
+	}
+
+	return 0;
+}
+
+void nova_delete_dir_tree(struct super_block *sb,
+	struct nova_inode_info_header *sih)
+{
+	struct nova_dentry *direntry;
+	unsigned long pos = 0;
+	struct nova_dentry *entries[FREE_BATCH];
+	timing_t delete_time;
+	int nr_entries;
+	int i;
+	void *ret;
+
+	NOVA_START_TIMING(delete_dir_tree_t, delete_time);
+
+	nova_dbgv("%s: delete dir %lu\n", __func__, sih->ino);
+	do {
+		nr_entries = radix_tree_gang_lookup(&sih->tree,
+					(void **)entries, pos, FREE_BATCH);
+		for (i = 0; i < nr_entries; i++) {
+			direntry = entries[i];
+
+			pos = BKDRHash(direntry->name, direntry->name_len);
+			ret = radix_tree_delete(&sih->tree, pos);
+			if (!ret || ret != direntry) {
+				nova_err(sb, "dentry: type %d, inode %llu, "
+					"name %s, namelen %u, rec len %u\n",
+					direntry->entry_type,
+					le64_to_cpu(direntry->ino),
+					direntry->name, direntry->name_len,
+					le16_to_cpu(direntry->de_len));
+				if (!ret)
+					nova_dbg("ret is NULL\n");
+			}
+		}
+		pos++;
+	} while (nr_entries == FREE_BATCH);
+
+	NOVA_END_TIMING(delete_dir_tree_t, delete_time);
+}
diff --git a/fs/nova/nova.h b/fs/nova/nova.h
index 8f085cf..3890479 100644
--- a/fs/nova/nova.h
+++ b/fs/nova/nova.h
@@ -340,6 +340,19 @@ static inline int old_entry_freeable(struct super_block *sb, u64 epoch_id)
 	return 0;
 }
 
+// BKDR String Hash Function
+static inline unsigned long BKDRHash(const char *str, int length)
+{
+	unsigned int seed = 131; // 31 131 1313 13131 131313 etc..
+	unsigned long hash = 0;
+	int i;
+
+	for (i = 0; i < length; i++)
+		hash = hash * seed + (*str++);
+
+	return hash;
+}
+
 #include "balloc.h"
 
 static inline struct nova_file_write_entry *
@@ -433,6 +446,19 @@ nova_get_blocknr(struct super_block *sb, u64 block, unsigned short btype)
 /* ==============  Function prototypes  ================= */
 /* ====================================================== */
 
+/* dir.c */
+int nova_insert_dir_radix_tree(struct super_block *sb,
+	struct nova_inode_info_header *sih, const char *name,
+	int namelen, struct nova_dentry *direntry);
+int nova_remove_dir_radix_tree(struct super_block *sb,
+	struct nova_inode_info_header *sih, const char *name, int namelen,
+	int replay, struct nova_dentry **create_dentry);
+void nova_delete_dir_tree(struct super_block *sb,
+	struct nova_inode_info_header *sih);
+struct nova_dentry *nova_find_dentry(struct super_block *sb,
+	struct nova_inode *pi, struct inode *inode, const char *name,
+	unsigned long name_len);
+
 /* rebuild.c */
 int nova_rebuild_inode(struct super_block *sb, struct nova_inode_info *si,
 	u64 ino, u64 pi_addr, int rebuild_dir);
-- 
2.7.4

  parent reply	other threads:[~2018-03-10 18:21 UTC|newest]

Thread overview: 119+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2018-03-10 18:17 [RFC v2 00/83] NOVA: a new file system for persistent memory Andiry Xu
2018-03-10 18:17 ` [RFC v2 01/83] Introduction and documentation of NOVA filesystem Andiry Xu
2018-03-19 20:43   ` Randy Dunlap
2018-03-19 23:00     ` Andiry Xu
2018-04-22  8:05   ` Pavel Machek
2018-03-10 18:17 ` [RFC v2 02/83] Add nova_def.h Andiry Xu
2018-03-10 18:17 ` [RFC v2 03/83] Add super.h Andiry Xu
2018-03-15  4:54   ` Darrick J. Wong
2018-03-15  6:11     ` Andiry Xu
2018-03-15  9:05       ` Arnd Bergmann
2018-03-15 17:51         ` Andiry Xu
2018-03-15 20:04           ` Andreas Dilger
2018-03-15 20:38           ` Arnd Bergmann
2018-03-16  2:59             ` Theodore Y. Ts'o
2018-03-16  6:17               ` Andiry Xu
2018-03-16  6:30                 ` Darrick J. Wong
2018-03-16  9:19               ` Arnd Bergmann
2018-03-10 18:17 ` [RFC v2 04/83] NOVA inode definition Andiry Xu
2018-03-15  5:06   ` Darrick J. Wong
2018-03-15  6:16     ` Andiry Xu
2018-03-10 18:17 ` [RFC v2 05/83] Add NOVA filesystem definitions and useful helper routines Andiry Xu
2018-03-11 12:00   ` Nikolay Borisov
2018-03-11 19:22     ` Eric Biggers
2018-03-11 21:45       ` Andiry Xu
2018-03-19 19:39       ` Andiry Xu
2018-03-19 20:30         ` Eric Biggers
2018-03-19 21:59           ` Andiry Xu
2018-03-10 18:17 ` [RFC v2 06/83] Add inode get/read methods Andiry Xu
2018-04-23  6:12   ` Darrick J. Wong
2018-04-23 15:55     ` Andiry Xu
2018-03-10 18:17 ` [RFC v2 07/83] Initialize inode_info and rebuild inode information in nova_iget() Andiry Xu
2018-03-10 18:17 ` [RFC v2 08/83] NOVA superblock operations Andiry Xu
2018-03-10 18:17 ` [RFC v2 09/83] Add Kconfig and Makefile Andiry Xu
2018-03-11 12:15   ` Nikolay Borisov
2018-03-11 21:32     ` Andiry Xu
2018-03-10 18:17 ` [RFC v2 10/83] Add superblock integrity check Andiry Xu
2018-03-10 18:17 ` [RFC v2 11/83] Add timing and I/O statistics for performance analysis and profiling Andiry Xu
2018-03-10 18:17 ` [RFC v2 12/83] Add timing for mount and init Andiry Xu
2018-03-10 18:17 ` [RFC v2 13/83] Add remount_fs and show_options methods Andiry Xu
2018-03-10 18:17 ` [RFC v2 14/83] Add range node kmem cache Andiry Xu
2018-03-11 11:55   ` Nikolay Borisov
2018-03-11 21:31     ` Andiry Xu
2018-03-10 18:17 ` [RFC v2 15/83] Add free list data structure Andiry Xu
2018-03-10 18:17 ` [RFC v2 16/83] Initialize block map and free lists in nova_init() Andiry Xu
2018-03-11 12:12   ` Nikolay Borisov
2018-03-11 21:30     ` Andiry Xu
2018-03-10 18:17 ` [RFC v2 17/83] Add statfs support Andiry Xu
2018-03-10 18:17 ` [RFC v2 18/83] Add freelist statistics printing Andiry Xu
2018-03-10 18:18 ` [RFC v2 19/83] Add pmem block free routines Andiry Xu
2018-03-10 18:18 ` [RFC v2 20/83] Pmem block allocation routines Andiry Xu
2018-03-10 18:18 ` [RFC v2 21/83] Add log structure Andiry Xu
2018-03-10 18:18 ` [RFC v2 22/83] Inode log pages allocation and reclaimation Andiry Xu
2018-03-10 18:18 ` [RFC v2 23/83] Save allocator to pmem in put_super Andiry Xu
2018-03-10 18:18 ` [RFC v2 24/83] Initialize and allocate inode table Andiry Xu
2018-03-10 18:18 ` [RFC v2 25/83] Support get normal inode address and inode table extentsion Andiry Xu
2018-03-10 18:18 ` [RFC v2 26/83] Add inode_map to track inuse inodes Andiry Xu
2018-03-10 18:18 ` [RFC v2 27/83] Save the inode inuse list to pmem upon umount Andiry Xu
2018-03-10 18:18 ` [RFC v2 28/83] Add NOVA address space operations Andiry Xu
2018-03-10 18:18 ` [RFC v2 29/83] Add write_inode and dirty_inode routines Andiry Xu
2018-03-10 18:18 ` [RFC v2 30/83] New NOVA inode allocation Andiry Xu
2018-03-10 18:18 ` [RFC v2 31/83] Add new vfs " Andiry Xu
2018-03-10 18:18 ` [RFC v2 32/83] Add log entry definitions Andiry Xu
2018-03-10 18:18 ` [RFC v2 33/83] Inode log and entry printing for debug purpose Andiry Xu
2018-03-10 18:18 ` [RFC v2 34/83] Journal: NOVA light weight journal definitions Andiry Xu
2018-03-10 18:18 ` [RFC v2 35/83] Journal: Lite journal helper routines Andiry Xu
2018-03-10 18:18 ` [RFC v2 36/83] Journal: Lite journal recovery Andiry Xu
2018-03-10 18:18 ` [RFC v2 37/83] Journal: Lite journal create and commit Andiry Xu
2018-03-10 18:18 ` [RFC v2 38/83] Journal: NOVA lite journal initialization Andiry Xu
2018-03-10 18:18 ` [RFC v2 39/83] Log operation: dentry append Andiry Xu
2018-03-10 18:18 ` [RFC v2 40/83] Log operation: file write entry append Andiry Xu
2018-03-10 18:18 ` [RFC v2 41/83] Log operation: setattr " Andiry Xu
2018-03-10 18:18 ` [RFC v2 42/83] Log operation: link change append Andiry Xu
2018-03-10 18:18 ` [RFC v2 43/83] Log operation: in-place update log entry Andiry Xu
2018-03-10 18:18 ` [RFC v2 44/83] Log operation: invalidate log entries Andiry Xu
2018-03-10 18:18 ` [RFC v2 45/83] Log operation: file inode log lookup and assign Andiry Xu
2018-03-10 18:18 ` Andiry Xu [this message]
2018-03-10 18:18 ` [RFC v2 47/83] Dir: Add initial dentries when initializing a directory inode log Andiry Xu
2018-03-10 18:18 ` [RFC v2 48/83] Dir: Readdir operation Andiry Xu
2018-03-10 18:18 ` [RFC v2 49/83] Dir: Append create/remove dentry Andiry Xu
2018-03-10 18:18 ` [RFC v2 50/83] Inode: Add nova_evict_inode Andiry Xu
2018-03-10 18:18 ` [RFC v2 51/83] Rebuild: directory inode Andiry Xu
2018-03-10 18:18 ` [RFC v2 52/83] Rebuild: file inode Andiry Xu
2018-03-10 18:18 ` [RFC v2 53/83] Namei: lookup Andiry Xu
2018-03-10 18:18 ` [RFC v2 54/83] Namei: create and mknod Andiry Xu
2018-03-10 18:18 ` [RFC v2 55/83] Namei: mkdir Andiry Xu
2018-03-10 18:18 ` [RFC v2 56/83] Namei: link and unlink Andiry Xu
2018-03-10 18:18 ` [RFC v2 57/83] Namei: rmdir Andiry Xu
2018-03-10 18:18 ` [RFC v2 58/83] Namei: rename Andiry Xu
2018-03-10 18:18 ` [RFC v2 59/83] Namei: setattr Andiry Xu
2018-03-10 18:18 ` [RFC v2 60/83] Add special inode operations Andiry Xu
2018-03-10 18:18 ` [RFC v2 61/83] Super: Add nova_export_ops Andiry Xu
2018-03-10 18:18 ` [RFC v2 62/83] File: getattr and file inode operations Andiry Xu
2018-03-10 18:18 ` [RFC v2 63/83] File operation: llseek Andiry Xu
2018-03-10 18:18 ` [RFC v2 64/83] File operation: open, fsync, flush Andiry Xu
2018-03-10 18:18 ` [RFC v2 65/83] File operation: read Andiry Xu
2018-03-10 18:18 ` [RFC v2 66/83] Super: Add file write item cache Andiry Xu
2018-03-10 18:18 ` [RFC v2 67/83] Dax: commit list of file write items to log Andiry Xu
2018-03-10 18:18 ` [RFC v2 68/83] File operation: copy-on-write write Andiry Xu
2018-03-10 18:18 ` [RFC v2 69/83] Super: Add module param inplace_data_updates Andiry Xu
2018-03-10 18:18 ` [RFC v2 70/83] File operation: Inplace write Andiry Xu
2018-03-10 18:18 ` [RFC v2 71/83] Symlink support Andiry Xu
2018-03-10 18:18 ` [RFC v2 72/83] File operation: fallocate Andiry Xu
2018-03-10 18:18 ` [RFC v2 73/83] Dax: Add iomap operations Andiry Xu
2018-03-10 18:18 ` [RFC v2 74/83] File operation: Mmap Andiry Xu
2018-03-10 18:18 ` [RFC v2 75/83] File operation: read/write iter Andiry Xu
2018-03-10 18:18 ` [RFC v2 76/83] Ioctl support Andiry Xu
2018-03-10 18:18 ` [RFC v2 77/83] GC: Fast garbage collection Andiry Xu
2018-03-10 18:18 ` [RFC v2 78/83] GC: Thorough " Andiry Xu
2018-03-10 18:19 ` [RFC v2 79/83] Normal recovery Andiry Xu
2018-03-10 18:19 ` [RFC v2 80/83] Failure recovery: bitmap operations Andiry Xu
2018-03-10 18:19 ` [RFC v2 81/83] Failure recovery: Inode pages recovery routines Andiry Xu
2018-03-10 18:19 ` [RFC v2 82/83] Failure recovery: Per-CPU recovery Andiry Xu
2018-03-10 18:19 ` [RFC v2 83/83] Sysfs support Andiry Xu
2018-03-15  0:33   ` Randy Dunlap
2018-03-15  6:07     ` Andiry Xu
2018-03-22 15:00   ` David Sterba
2018-03-23  0:31     ` Andiry Xu
2018-03-11  2:14 ` [RFC v2 00/83] NOVA: a new file system for persistent memory Theodore Y. Ts'o
2018-03-11  4:58   ` Andiry Xu

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=1520705944-6723-47-git-send-email-jix024@eng.ucsd.edu \
    --to=jix024@eng.ucsd.edu \
    --cc=andiry.xu@gmail.com \
    --cc=andy.rudoff@intel.com \
    --cc=coughlan@redhat.com \
    --cc=dan.j.williams@intel.com \
    --cc=david@fromorbit.com \
    --cc=jack@suse.com \
    --cc=jix024@cs.ucsd.edu \
    --cc=linux-fsdevel@vger.kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-nvdimm@lists.01.org \
    --cc=miklos@szeredi.hu \
    --cc=swanson@cs.ucsd.edu \
    --cc=swhiteho@redhat.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 a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).