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 23/83] Save allocator to pmem in put_super.
Date: Sat, 10 Mar 2018 10:18:04 -0800
Message-ID: <1520705944-6723-24-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>

We allocate log pages and append free range node to the log of the reserved blocknode inode.
We can recover the allocator status by reading the log upon normal recovery.

Signed-off-by: Andiry Xu <jix024@cs.ucsd.edu>
---
 fs/nova/bbuild.c | 114 +++++++++++++++++++++++++++++++++++++++++++++++++++++++
 fs/nova/bbuild.h |   1 +
 fs/nova/inode.h  |  13 +++++++
 fs/nova/nova.h   |   7 ++++
 fs/nova/super.c  |   2 +
 5 files changed, 137 insertions(+)

diff --git a/fs/nova/bbuild.c b/fs/nova/bbuild.c
index 8bc0545..12a2f11 100644
--- a/fs/nova/bbuild.c
+++ b/fs/nova/bbuild.c
@@ -51,3 +51,117 @@ void nova_init_header(struct super_block *sb,
 	init_rwsem(&sih->i_sem);
 }
 
+static u64 nova_append_range_node_entry(struct super_block *sb,
+	struct nova_range_node *curr, u64 tail, unsigned long cpuid)
+{
+	u64 curr_p;
+	size_t size = sizeof(struct nova_range_node_lowhigh);
+	struct nova_range_node_lowhigh *entry;
+
+	curr_p = tail;
+
+	if (curr_p == 0 || (is_last_entry(curr_p, size) &&
+				next_log_page(sb, curr_p) == 0)) {
+		nova_dbg("%s: inode log reaches end?\n", __func__);
+		goto out;
+	}
+
+	if (is_last_entry(curr_p, size))
+		curr_p = next_log_page(sb, curr_p);
+
+	entry = (struct nova_range_node_lowhigh *)nova_get_block(sb, curr_p);
+	entry->range_low = cpu_to_le64(curr->range_low);
+	if (cpuid)
+		entry->range_low |= cpu_to_le64(cpuid << 56);
+	entry->range_high = cpu_to_le64(curr->range_high);
+	nova_dbgv("append entry block low 0x%lx, high 0x%lx\n",
+			curr->range_low, curr->range_high);
+
+	nova_flush_buffer(entry, sizeof(struct nova_range_node_lowhigh), 0);
+out:
+	return curr_p;
+}
+
+static u64 nova_save_range_nodes_to_log(struct super_block *sb,
+	struct rb_root *tree, u64 temp_tail, unsigned long cpuid)
+{
+	struct nova_range_node *curr;
+	struct rb_node *temp;
+	size_t size = sizeof(struct nova_range_node_lowhigh);
+	u64 curr_entry = 0;
+
+	/* Save in increasing order */
+	temp = rb_first(tree);
+	while (temp) {
+		curr = container_of(temp, struct nova_range_node, node);
+		curr_entry = nova_append_range_node_entry(sb, curr,
+						temp_tail, cpuid);
+		temp_tail = curr_entry + size;
+		temp = rb_next(temp);
+		rb_erase(&curr->node, tree);
+		nova_free_range_node(curr);
+	}
+
+	return temp_tail;
+}
+
+static u64 nova_save_free_list_blocknodes(struct super_block *sb, int cpu,
+	u64 temp_tail)
+{
+	struct free_list *free_list;
+
+	free_list = nova_get_free_list(sb, cpu);
+	temp_tail = nova_save_range_nodes_to_log(sb,
+				&free_list->block_free_tree, temp_tail, 0);
+	return temp_tail;
+}
+
+void nova_save_blocknode_mappings_to_log(struct super_block *sb)
+{
+	struct nova_inode *pi = nova_get_inode_by_ino(sb, NOVA_BLOCKNODE_INO);
+	struct nova_inode_info_header sih;
+	struct nova_sb_info *sbi = NOVA_SB(sb);
+	struct free_list *free_list;
+	unsigned long num_blocknode = 0;
+	unsigned long num_pages;
+	int allocated;
+	u64 new_block = 0;
+	u64 temp_tail;
+	int i;
+
+	sih.ino = NOVA_BLOCKNODE_INO;
+	sih.i_blk_type = NOVA_DEFAULT_BLOCK_TYPE;
+
+	/* Allocate log pages before save blocknode mappings */
+	for (i = 0; i < sbi->cpus; i++) {
+		free_list = nova_get_free_list(sb, i);
+		num_blocknode += free_list->num_blocknode;
+		nova_dbgv("%s: free list %d: %lu nodes\n", __func__,
+				i, free_list->num_blocknode);
+	}
+
+	num_pages = num_blocknode / RANGENODE_PER_PAGE;
+	if (num_blocknode % RANGENODE_PER_PAGE)
+		num_pages++;
+
+	allocated = nova_allocate_inode_log_pages(sb, &sih, num_pages,
+						&new_block, ANY_CPU, 0);
+	if (allocated != num_pages) {
+		nova_dbg("Error saving blocknode mappings: %d\n", allocated);
+		return;
+	}
+
+	temp_tail = new_block;
+	for (i = 0; i < sbi->cpus; i++)
+		temp_tail = nova_save_free_list_blocknodes(sb, i, temp_tail);
+
+	/* Finally update log head and tail */
+	pi->log_head = new_block;
+	nova_update_tail(pi, temp_tail);
+	nova_flush_buffer(&pi->log_head, CACHELINE_SIZE, 0);
+
+	nova_dbg("%s: %lu blocknodes, %lu log pages, pi head 0x%llx, tail 0x%llx\n",
+		  __func__, num_blocknode, num_pages,
+		  pi->log_head, pi->log_tail);
+}
+
diff --git a/fs/nova/bbuild.h b/fs/nova/bbuild.h
index 162a832..59cc379 100644
--- a/fs/nova/bbuild.h
+++ b/fs/nova/bbuild.h
@@ -3,5 +3,6 @@
 
 void nova_init_header(struct super_block *sb,
 	struct nova_inode_info_header *sih, u16 i_mode);
+void nova_save_blocknode_mappings_to_log(struct super_block *sb);
 
 #endif
diff --git a/fs/nova/inode.h b/fs/nova/inode.h
index dbd5256..0594ef3 100644
--- a/fs/nova/inode.h
+++ b/fs/nova/inode.h
@@ -123,6 +123,19 @@ static inline void sih_unlock_shared(struct nova_inode_info_header *header)
 	up_read(&header->i_sem);
 }
 
+static inline void nova_update_tail(struct nova_inode *pi, u64 new_tail)
+{
+	timing_t update_time;
+
+	NOVA_START_TIMING(update_tail_t, update_time);
+
+	PERSISTENT_BARRIER();
+	pi->log_tail = new_tail;
+	nova_flush_buffer(&pi->log_tail, CACHELINE_SIZE, 1);
+
+	NOVA_END_TIMING(update_tail_t, update_time);
+}
+
 static inline unsigned int
 nova_inode_blk_shift(struct nova_inode_info_header *sih)
 {
diff --git a/fs/nova/nova.h b/fs/nova/nova.h
index f5b4ec8..aa88d9f 100644
--- a/fs/nova/nova.h
+++ b/fs/nova/nova.h
@@ -303,6 +303,13 @@ static inline u64 nova_get_epoch_id(struct super_block *sb)
 #include "inode.h"
 #include "log.h"
 
+struct nova_range_node_lowhigh {
+	__le64 range_low;
+	__le64 range_high;
+};
+
+#define	RANGENODE_PER_PAGE	254
+
 /* A node in the RB tree representing a range of pages */
 struct nova_range_node {
 	struct rb_node node;
diff --git a/fs/nova/super.c b/fs/nova/super.c
index 3500d19..7ee3f66 100644
--- a/fs/nova/super.c
+++ b/fs/nova/super.c
@@ -705,6 +705,8 @@ static void nova_put_super(struct super_block *sb)
 	struct nova_sb_info *sbi = NOVA_SB(sb);
 
 	if (sbi->virt_addr) {
+		/* Save everything before blocknode mapping! */
+		nova_save_blocknode_mappings_to_log(sb);
 		sbi->virt_addr = NULL;
 	}
 
-- 
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 ` Andiry Xu [this message]
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 ` [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=1520705944-6723-24-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