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 80/83] Failure recovery: bitmap operations.
Date: Sat, 10 Mar 2018 10:19:01 -0800
Message-ID: <1520705944-6723-81-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>

Upon system failure, NOVA needs to scan all the inode logs
to rebuild the allocator. During the scanning, NOVA stores allocated
log/data pages in a bitmap, and uses the bitmap to rebuild the allocator
once scan finishes.

Signed-off-by: Andiry Xu <jix024@cs.ucsd.edu>
---
 fs/nova/bbuild.c | 252 +++++++++++++++++++++++++++++++++++++++++++++++++++++++
 fs/nova/bbuild.h |  18 ++++
 2 files changed, 270 insertions(+)

diff --git a/fs/nova/bbuild.c b/fs/nova/bbuild.c
index ca51dca..35c661a 100644
--- a/fs/nova/bbuild.c
+++ b/fs/nova/bbuild.c
@@ -414,6 +414,258 @@ void nova_save_blocknode_mappings_to_log(struct super_block *sb)
 		  pi->log_head, pi->log_tail);
 }
 
+/************************** Bitmap operations ****************************/
+
+static inline void set_scan_bm(unsigned long bit,
+	struct single_scan_bm *scan_bm)
+{
+	set_bit(bit, scan_bm->bitmap);
+}
+
+inline void set_bm(unsigned long bit, struct scan_bitmap *bm,
+	enum bm_type type)
+{
+	switch (type) {
+	case BM_4K:
+		set_scan_bm(bit, &bm->scan_bm_4K);
+		break;
+	case BM_2M:
+		set_scan_bm(bit, &bm->scan_bm_2M);
+		break;
+	case BM_1G:
+		set_scan_bm(bit, &bm->scan_bm_1G);
+		break;
+	default:
+		break;
+	}
+}
+
+static int nova_insert_blocknode_map(struct super_block *sb,
+	int cpuid, unsigned long low, unsigned long high)
+{
+	struct nova_sb_info *sbi = NOVA_SB(sb);
+	struct free_list *free_list;
+	struct rb_root *tree;
+	struct nova_range_node *blknode = NULL;
+	unsigned long num_blocks = 0;
+	int ret;
+
+	num_blocks = high - low + 1;
+	nova_dbgv("%s: cpu %d, low %lu, high %lu, num %lu\n",
+		__func__, cpuid, low, high, num_blocks);
+	free_list = nova_get_free_list(sb, cpuid);
+	tree = &(free_list->block_free_tree);
+
+	blknode = nova_alloc_blocknode(sb);
+	if (blknode == NULL)
+		return -ENOMEM;
+	blknode->range_low = low;
+	blknode->range_high = high;
+	ret = nova_insert_blocktree(sbi, tree, blknode);
+	if (ret) {
+		nova_err(sb, "%s failed\n", __func__);
+		nova_free_blocknode(sb, blknode);
+		goto out;
+	}
+	if (!free_list->first_node)
+		free_list->first_node = blknode;
+	free_list->last_node = blknode;
+	free_list->num_blocknode++;
+	free_list->num_free_blocks += num_blocks;
+out:
+	return ret;
+}
+
+static int __nova_build_blocknode_map(struct super_block *sb,
+	unsigned long *bitmap, unsigned long bsize, unsigned long scale)
+{
+	struct nova_sb_info *sbi = NOVA_SB(sb);
+	struct free_list *free_list;
+	unsigned long next = 0;
+	unsigned long low = 0;
+	unsigned long start, end;
+	int cpuid = 0;
+
+	free_list = nova_get_free_list(sb, cpuid);
+	start = free_list->block_start;
+	end = free_list->block_end + 1;
+	while (1) {
+		next = find_next_zero_bit(bitmap, end, start);
+		if (next == bsize)
+			break;
+		if (next == end) {
+			if (cpuid == sbi->cpus - 1)
+				break;
+
+			cpuid++;
+			free_list = nova_get_free_list(sb, cpuid);
+			start = free_list->block_start;
+			end = free_list->block_end + 1;
+			continue;
+		}
+
+		low = next;
+		next = find_next_bit(bitmap, end, next);
+		if (nova_insert_blocknode_map(sb, cpuid,
+				low << scale, (next << scale) - 1)) {
+			nova_dbg("Error: could not insert %lu - %lu\n",
+				low << scale, ((next << scale) - 1));
+		}
+		start = next;
+		if (next == bsize)
+			break;
+		if (next == end) {
+			if (cpuid == sbi->cpus - 1)
+				break;
+
+			cpuid++;
+			free_list = nova_get_free_list(sb, cpuid);
+			start = free_list->block_start;
+			end = free_list->block_end + 1;
+		}
+	}
+	return 0;
+}
+
+static void nova_update_4K_map(struct super_block *sb,
+	struct scan_bitmap *bm,	unsigned long *bitmap,
+	unsigned long bsize, unsigned long scale)
+{
+	unsigned long next = 0;
+	unsigned long low = 0;
+	int i;
+
+	while (1) {
+		next = find_next_bit(bitmap, bsize, next);
+		if (next == bsize)
+			break;
+		low = next;
+		next = find_next_zero_bit(bitmap, bsize, next);
+		for (i = (low << scale); i < (next << scale); i++)
+			set_bm(i, bm, BM_4K);
+		if (next == bsize)
+			break;
+	}
+}
+
+struct scan_bitmap *global_bm[MAX_CPUS];
+
+static int nova_build_blocknode_map(struct super_block *sb,
+	unsigned long initsize)
+{
+	struct nova_sb_info *sbi = NOVA_SB(sb);
+	struct scan_bitmap *bm;
+	struct scan_bitmap *final_bm;
+	unsigned long *src, *dst;
+	int i, j;
+	int num;
+	int ret;
+
+	final_bm = kzalloc(sizeof(struct scan_bitmap), GFP_KERNEL);
+	if (!final_bm)
+		return -ENOMEM;
+
+	final_bm->scan_bm_4K.bitmap_size =
+				(initsize >> (PAGE_SHIFT + 0x3));
+
+	/* Alloc memory to hold the block alloc bitmap */
+	final_bm->scan_bm_4K.bitmap = kzalloc(final_bm->scan_bm_4K.bitmap_size,
+							GFP_KERNEL);
+
+	if (!final_bm->scan_bm_4K.bitmap) {
+		kfree(final_bm);
+		return -ENOMEM;
+	}
+
+	/*
+	 * We are using free lists. Set 2M and 1G blocks in 4K map,
+	 * and use 4K map to rebuild block map.
+	 */
+	for (i = 0; i < sbi->cpus; i++) {
+		bm = global_bm[i];
+		nova_update_4K_map(sb, bm, bm->scan_bm_2M.bitmap,
+			bm->scan_bm_2M.bitmap_size * 8, PAGE_SHIFT_2M - 12);
+		nova_update_4K_map(sb, bm, bm->scan_bm_1G.bitmap,
+			bm->scan_bm_1G.bitmap_size * 8, PAGE_SHIFT_1G - 12);
+	}
+
+	/* Merge per-CPU bms to the final single bm */
+	num = final_bm->scan_bm_4K.bitmap_size / sizeof(unsigned long);
+	if (final_bm->scan_bm_4K.bitmap_size % sizeof(unsigned long))
+		num++;
+
+	for (i = 0; i < sbi->cpus; i++) {
+		bm = global_bm[i];
+		src = (unsigned long *)bm->scan_bm_4K.bitmap;
+		dst = (unsigned long *)final_bm->scan_bm_4K.bitmap;
+
+		for (j = 0; j < num; j++)
+			dst[j] |= src[j];
+	}
+
+	ret = __nova_build_blocknode_map(sb, final_bm->scan_bm_4K.bitmap,
+			final_bm->scan_bm_4K.bitmap_size * 8, PAGE_SHIFT - 12);
+
+	kfree(final_bm->scan_bm_4K.bitmap);
+	kfree(final_bm);
+
+	return ret;
+}
+
+static void free_bm(struct super_block *sb)
+{
+	struct nova_sb_info *sbi = NOVA_SB(sb);
+	struct scan_bitmap *bm;
+	int i;
+
+	for (i = 0; i < sbi->cpus; i++) {
+		bm = global_bm[i];
+		if (bm) {
+			kfree(bm->scan_bm_4K.bitmap);
+			kfree(bm->scan_bm_2M.bitmap);
+			kfree(bm->scan_bm_1G.bitmap);
+			kfree(bm);
+		}
+	}
+}
+
+static int alloc_bm(struct super_block *sb, unsigned long initsize)
+{
+	struct nova_sb_info *sbi = NOVA_SB(sb);
+	struct scan_bitmap *bm;
+	int i;
+
+	for (i = 0; i < sbi->cpus; i++) {
+		bm = kzalloc(sizeof(struct scan_bitmap), GFP_KERNEL);
+		if (!bm)
+			return -ENOMEM;
+
+		global_bm[i] = bm;
+
+		bm->scan_bm_4K.bitmap_size =
+				(initsize >> (PAGE_SHIFT + 0x3));
+		bm->scan_bm_2M.bitmap_size =
+				(initsize >> (PAGE_SHIFT_2M + 0x3));
+		bm->scan_bm_1G.bitmap_size =
+				(initsize >> (PAGE_SHIFT_1G + 0x3));
+
+		/* Alloc memory to hold the block alloc bitmap */
+		bm->scan_bm_4K.bitmap = kzalloc(bm->scan_bm_4K.bitmap_size,
+							GFP_KERNEL);
+		bm->scan_bm_2M.bitmap = kzalloc(bm->scan_bm_2M.bitmap_size,
+							GFP_KERNEL);
+		bm->scan_bm_1G.bitmap = kzalloc(bm->scan_bm_1G.bitmap_size,
+							GFP_KERNEL);
+
+		if (!bm->scan_bm_4K.bitmap || !bm->scan_bm_2M.bitmap ||
+				!bm->scan_bm_1G.bitmap)
+			return -ENOMEM;
+	}
+
+	return 0;
+}
+
+
 /*********************** Recovery entrance *************************/
 
 /* Return TRUE if we can do a normal unmount recovery */
diff --git a/fs/nova/bbuild.h b/fs/nova/bbuild.h
index 2c3deb0..b093e05 100644
--- a/fs/nova/bbuild.h
+++ b/fs/nova/bbuild.h
@@ -1,6 +1,24 @@
 #ifndef __BBUILD_H
 #define __BBUILD_H
 
+enum bm_type {
+	BM_4K = 0,
+	BM_2M,
+	BM_1G,
+};
+
+struct single_scan_bm {
+	unsigned long bitmap_size;
+	unsigned long *bitmap;
+};
+
+struct scan_bitmap {
+	struct single_scan_bm scan_bm_4K;
+	struct single_scan_bm scan_bm_2M;
+	struct single_scan_bm scan_bm_1G;
+};
+
+
 void nova_init_header(struct super_block *sb,
 	struct nova_inode_info_header *sih, u16 i_mode);
 void nova_save_inode_list_to_log(struct super_block *sb);
-- 
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 ` [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 ` Andiry Xu [this message]
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=1520705944-6723-81-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