Linux-Fsdevel Archive on lore.kernel.org
 help / color / 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 37/83] Journal: Lite journal create and commit.
Date: Sat, 10 Mar 2018 10:18:18 -0800
Message-ID: <1520705944-6723-38-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 lite journal to perform light weight transaction.
Instead of journaling metadata/data changes directly,
NOVA first append updates to each inode's log, and then
journal the log tail pointers to make sure all the logs
are updated atomically. For inode creation and deletion,
NOVA journals the inode's valid field.

Signed-off-by: Andiry Xu <jix024@cs.ucsd.edu>
---
 fs/nova/journal.c | 179 ++++++++++++++++++++++++++++++++++++++++++++++++++++++
 fs/nova/journal.h |  11 ++++
 2 files changed, 190 insertions(+)

diff --git a/fs/nova/journal.c b/fs/nova/journal.c
index f31de97..0e203fa 100644
--- a/fs/nova/journal.c
+++ b/fs/nova/journal.c
@@ -161,3 +161,182 @@ static int nova_recover_lite_journal(struct super_block *sb,
 
 	return 0;
 }
+
+/**************************** Create/commit ******************************/
+
+/* Create and append an undo entry for a small update to PMEM. */
+static u64 nova_append_entry_journal(struct super_block *sb,
+	u64 curr_p, void *field)
+{
+	struct nova_lite_journal_entry *entry;
+	struct nova_sb_info *sbi = NOVA_SB(sb);
+	u64 *aligned_field;
+	u64 addr;
+
+	entry = (struct nova_lite_journal_entry *)nova_get_block(sb,
+							curr_p);
+	entry->type = cpu_to_le64(JOURNAL_ENTRY);
+	entry->padding = 0;
+	/* Align to 8 bytes */
+	aligned_field = (u64 *)((unsigned long)field & ~7UL);
+	/* Store the offset from the start of Nova instead of the pointer */
+	addr = (u64)nova_get_addr_off(sbi, aligned_field);
+	entry->data1 = cpu_to_le64(addr);
+	entry->data2 = cpu_to_le64(*aligned_field);
+	nova_update_journal_entry_csum(sb, entry);
+
+	curr_p = next_lite_journal(curr_p);
+	return curr_p;
+}
+
+static u64 nova_journal_inode_tail(struct super_block *sb,
+	u64 curr_p, struct nova_inode *pi)
+{
+	curr_p = nova_append_entry_journal(sb, curr_p, &pi->log_tail);
+
+	return curr_p;
+}
+
+/* Create and append undo log entries for creating a new file or directory. */
+static u64 nova_append_inode_journal(struct super_block *sb,
+	u64 curr_p, struct inode *inode, int new_inode,
+	int invalidate, int is_dir)
+{
+	struct nova_inode *pi = nova_get_inode(sb, inode);
+
+	if (!pi) {
+		nova_err(sb, "%s: get inode failed\n", __func__);
+		return curr_p;
+	}
+
+	if (is_dir)
+		return nova_journal_inode_tail(sb, curr_p, pi);
+
+	if (new_inode) {
+		curr_p = nova_append_entry_journal(sb, curr_p,
+						&pi->valid);
+	} else {
+		curr_p = nova_journal_inode_tail(sb, curr_p, pi);
+		if (invalidate) {
+			curr_p = nova_append_entry_journal(sb, curr_p,
+						&pi->valid);
+			curr_p = nova_append_entry_journal(sb, curr_p,
+						&pi->delete_epoch_id);
+		}
+	}
+
+	return curr_p;
+}
+
+static u64 nova_append_dentry_journal(struct super_block *sb,
+	u64 curr_p, struct nova_dentry *dentry)
+{
+	curr_p = nova_append_entry_journal(sb, curr_p, &dentry->ino);
+	curr_p = nova_append_entry_journal(sb, curr_p, &dentry->csum);
+	return curr_p;
+}
+
+/* Journaled transactions for inode creation */
+u64 nova_create_inode_transaction(struct super_block *sb,
+	struct inode *inode, struct inode *dir, int cpu,
+	int new_inode, int invalidate)
+{
+	struct journal_ptr_pair *pair;
+	u64 temp;
+
+	pair = nova_get_journal_pointers(sb, cpu);
+
+	temp = pair->journal_head;
+
+	temp = nova_append_inode_journal(sb, temp, inode,
+					new_inode, invalidate, 0);
+
+	temp = nova_append_inode_journal(sb, temp, dir,
+					new_inode, invalidate, 1);
+
+	pair->journal_tail = temp;
+	nova_flush_buffer(&pair->journal_head, CACHELINE_SIZE, 1);
+
+	nova_dbgv("%s: head 0x%llx, tail 0x%llx\n",
+			__func__, pair->journal_head, pair->journal_tail);
+	return temp;
+}
+
+/* Journaled transactions for rename operations */
+u64 nova_create_rename_transaction(struct super_block *sb,
+	struct inode *old_inode, struct inode *old_dir, struct inode *new_inode,
+	struct inode *new_dir, struct nova_dentry *father_entry,
+	int invalidate_new_inode, int cpu)
+{
+	struct journal_ptr_pair *pair;
+	u64 temp;
+
+	pair = nova_get_journal_pointers(sb, cpu);
+
+	temp = pair->journal_head;
+
+	/* Journal tails for old inode */
+	temp = nova_append_inode_journal(sb, temp, old_inode, 0, 0, 0);
+
+	/* Journal tails for old dir */
+	temp = nova_append_inode_journal(sb, temp, old_dir, 0, 0, 1);
+
+	if (new_inode) {
+		/* New inode may be unlinked */
+		temp = nova_append_inode_journal(sb, temp, new_inode, 0,
+					invalidate_new_inode, 0);
+	}
+
+	if (new_dir)
+		temp = nova_append_inode_journal(sb, temp, new_dir, 0, 0, 1);
+
+	if (father_entry)
+		temp = nova_append_dentry_journal(sb, temp, father_entry);
+
+	pair->journal_tail = temp;
+	nova_flush_buffer(&pair->journal_head, CACHELINE_SIZE, 1);
+
+	nova_dbgv("%s: head 0x%llx, tail 0x%llx\n",
+			__func__, pair->journal_head, pair->journal_tail);
+	return temp;
+}
+
+/* For log entry inplace update */
+u64 nova_create_logentry_transaction(struct super_block *sb,
+	void *entry, enum nova_entry_type type, int cpu)
+{
+	struct journal_ptr_pair *pair;
+	size_t size = 0;
+	int i, count;
+	u64 temp;
+
+	pair = nova_get_journal_pointers(sb, cpu);
+
+	size = nova_get_log_entry_size(sb, type);
+
+	temp = pair->journal_head;
+
+	count = size / 8;
+	for (i = 0; i < count; i++) {
+		temp = nova_append_entry_journal(sb, temp,
+						(char *)entry + i * 8);
+	}
+
+	pair->journal_tail = temp;
+	nova_flush_buffer(&pair->journal_head, CACHELINE_SIZE, 1);
+
+	nova_dbgv("%s: head 0x%llx, tail 0x%llx\n",
+			__func__, pair->journal_head, pair->journal_tail);
+	return temp;
+}
+
+/* Commit the transactions by dropping the journal entries */
+void nova_commit_lite_transaction(struct super_block *sb, u64 tail, int cpu)
+{
+	struct journal_ptr_pair *pair;
+
+	pair = nova_get_journal_pointers(sb, cpu);
+
+	pair->journal_head = tail;
+	nova_flush_buffer(&pair->journal_head, CACHELINE_SIZE, 1);
+}
diff --git a/fs/nova/journal.h b/fs/nova/journal.h
index d1d0ffb..2259880 100644
--- a/fs/nova/journal.h
+++ b/fs/nova/journal.h
@@ -40,4 +40,15 @@ struct journal_ptr_pair *nova_get_journal_pointers(struct super_block *sb,
 }
 
 
+u64 nova_create_inode_transaction(struct super_block *sb,
+	struct inode *inode, struct inode *dir, int cpu,
+	int new_inode, int invalidate);
+u64 nova_create_rename_transaction(struct super_block *sb,
+	struct inode *old_inode, struct inode *old_dir, struct inode *new_inode,
+	struct inode *new_dir, struct nova_dentry *father_entry,
+	int invalidate_new_inode, int cpu);
+u64 nova_create_logentry_transaction(struct super_block *sb,
+	void *entry, enum nova_entry_type type, int cpu);
+void nova_commit_lite_transaction(struct super_block *sb, u64 tail, int cpu);
+
 #endif
-- 
2.7.4

  parent reply index

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 ` Andiry Xu [this message]
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 ` [RFC v2 46/83] Dir: Add Directory radix tree insert/remove methods Andiry Xu
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=1520705944-6723-38-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

Linux-Fsdevel Archive on lore.kernel.org

Archives are clonable:
	git clone --mirror https://lore.kernel.org/linux-fsdevel/0 linux-fsdevel/git/0.git

	# If you have public-inbox 1.1+ installed, you may
	# initialize and index your mirror using the following commands:
	public-inbox-init -V2 linux-fsdevel linux-fsdevel/ https://lore.kernel.org/linux-fsdevel \
		linux-fsdevel@vger.kernel.org
	public-inbox-index linux-fsdevel

Example config snippet for mirrors

Newsgroup available over NNTP:
	nntp://nntp.lore.kernel.org/org.kernel.vger.linux-fsdevel


AGPL code for this site: git clone https://public-inbox.org/public-inbox.git