From 306e16ce13c0f3d4fc071b45803b5b83c2606011 Mon Sep 17 00:00:00 2001 From: David Sterba Date: Tue, 19 Apr 2011 14:29:38 +0200 Subject: btrfs: rename variables clashing with global function names reported by gcc -Wshadow: page_index, page_offset, new_inode, dev_name Signed-off-by: David Sterba --- fs/btrfs/super.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'fs/btrfs/super.c') diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c index 0ac712efcdf2..3e28521643fb 100644 --- a/fs/btrfs/super.c +++ b/fs/btrfs/super.c @@ -739,7 +739,7 @@ static int btrfs_set_super(struct super_block *s, void *data) * for multiple device setup. Make sure to keep it in sync. */ static struct dentry *btrfs_mount(struct file_system_type *fs_type, int flags, - const char *dev_name, void *data) + const char *device_name, void *data) { struct block_device *bdev = NULL; struct super_block *s; @@ -762,7 +762,7 @@ static struct dentry *btrfs_mount(struct file_system_type *fs_type, int flags, if (error) return ERR_PTR(error); - error = btrfs_scan_one_device(dev_name, mode, fs_type, &fs_devices); + error = btrfs_scan_one_device(device_name, mode, fs_type, &fs_devices); if (error) goto error_free_subvol_name; -- cgit v1.2.3 From bcd53741cc2af4342ac3ff6983bddc4a1b63b9b4 Mon Sep 17 00:00:00 2001 From: Arne Jansen Date: Tue, 12 Apr 2011 10:43:21 +0200 Subject: btrfs: move btrfs_cmp_device_free_bytes to super.c this function won't be used here anymore, so move it super.c where it is used for df-calculation --- fs/btrfs/super.c | 26 ++++++++++++++++++++++++++ 1 file changed, 26 insertions(+) (limited to 'fs/btrfs/super.c') diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c index 0ac712efcdf2..32fe8b33cc1c 100644 --- a/fs/btrfs/super.c +++ b/fs/btrfs/super.c @@ -913,6 +913,32 @@ static int btrfs_remount(struct super_block *sb, int *flags, char *data) return 0; } +/* Used to sort the devices by max_avail(descending sort) */ +static int btrfs_cmp_device_free_bytes(const void *dev_info1, + const void *dev_info2) +{ + if (((struct btrfs_device_info *)dev_info1)->max_avail > + ((struct btrfs_device_info *)dev_info2)->max_avail) + return -1; + else if (((struct btrfs_device_info *)dev_info1)->max_avail < + ((struct btrfs_device_info *)dev_info2)->max_avail) + return 1; + else + return 0; +} + +/* + * sort the devices by max_avail, in which max free extent size of each device + * is stored.(Descending Sort) + */ +static inline void btrfs_descending_sort_devices( + struct btrfs_device_info *devices, + size_t nr_devices) +{ + sort(devices, nr_devices, sizeof(struct btrfs_device_info), + btrfs_cmp_device_free_bytes, NULL); +} + /* * The helper to calc the free space on the devices that can be used to store * file data. -- cgit v1.2.3 From 16cdcec736cd214350cdb591bf1091f8beedefa0 Mon Sep 17 00:00:00 2001 From: Miao Xie Date: Fri, 22 Apr 2011 18:12:22 +0800 Subject: btrfs: implement delayed inode items operation Changelog V5 -> V6: - Fix oom when the memory load is high, by storing the delayed nodes into the root's radix tree, and letting btrfs inodes go. Changelog V4 -> V5: - Fix the race on adding the delayed node to the inode, which is spotted by Chris Mason. - Merge Chris Mason's incremental patch into this patch. - Fix deadlock between readdir() and memory fault, which is reported by Itaru Kitayama. Changelog V3 -> V4: - Fix nested lock, which is reported by Itaru Kitayama, by updating space cache inode in time. Changelog V2 -> V3: - Fix the race between the delayed worker and the task which does delayed items balance, which is reported by Tsutomu Itoh. - Modify the patch address David Sterba's comment. - Fix the bug of the cpu recursion spinlock, reported by Chris Mason Changelog V1 -> V2: - break up the global rb-tree, use a list to manage the delayed nodes, which is created for every directory and file, and used to manage the delayed directory name index items and the delayed inode item. - introduce a worker to deal with the delayed nodes. Compare with Ext3/4, the performance of file creation and deletion on btrfs is very poor. the reason is that btrfs must do a lot of b+ tree insertions, such as inode item, directory name item, directory name index and so on. If we can do some delayed b+ tree insertion or deletion, we can improve the performance, so we made this patch which implemented delayed directory name index insertion/deletion and delayed inode update. Implementation: - introduce a delayed root object into the filesystem, that use two lists to manage the delayed nodes which are created for every file/directory. One is used to manage all the delayed nodes that have delayed items. And the other is used to manage the delayed nodes which is waiting to be dealt with by the work thread. - Every delayed node has two rb-tree, one is used to manage the directory name index which is going to be inserted into b+ tree, and the other is used to manage the directory name index which is going to be deleted from b+ tree. - introduce a worker to deal with the delayed operation. This worker is used to deal with the works of the delayed directory name index items insertion and deletion and the delayed inode update. When the delayed items is beyond the lower limit, we create works for some delayed nodes and insert them into the work queue of the worker, and then go back. When the delayed items is beyond the upper bound, we create works for all the delayed nodes that haven't been dealt with, and insert them into the work queue of the worker, and then wait for that the untreated items is below some threshold value. - When we want to insert a directory name index into b+ tree, we just add the information into the delayed inserting rb-tree. And then we check the number of the delayed items and do delayed items balance. (The balance policy is above.) - When we want to delete a directory name index from the b+ tree, we search it in the inserting rb-tree at first. If we look it up, just drop it. If not, add the key of it into the delayed deleting rb-tree. Similar to the delayed inserting rb-tree, we also check the number of the delayed items and do delayed items balance. (The same to inserting manipulation) - When we want to update the metadata of some inode, we cached the data of the inode into the delayed node. the worker will flush it into the b+ tree after dealing with the delayed insertion and deletion. - We will move the delayed node to the tail of the list after we access the delayed node, By this way, we can cache more delayed items and merge more inode updates. - If we want to commit transaction, we will deal with all the delayed node. - the delayed node will be freed when we free the btrfs inode. - Before we log the inode items, we commit all the directory name index items and the delayed inode update. I did a quick test by the benchmark tool[1] and found we can improve the performance of file creation by ~15%, and file deletion by ~20%. Before applying this patch: Create files: Total files: 50000 Total time: 1.096108 Average time: 0.000022 Delete files: Total files: 50000 Total time: 1.510403 Average time: 0.000030 After applying this patch: Create files: Total files: 50000 Total time: 0.932899 Average time: 0.000019 Delete files: Total files: 50000 Total time: 1.215732 Average time: 0.000024 [1] http://marc.info/?l=linux-btrfs&m=128212635122920&q=p3 Many thanks for Kitayama-san's help! Signed-off-by: Miao Xie Reviewed-by: David Sterba Tested-by: Tsutomu Itoh Tested-by: Itaru Kitayama Signed-off-by: Chris Mason --- fs/btrfs/super.c | 10 +++++++++- 1 file changed, 9 insertions(+), 1 deletion(-) (limited to 'fs/btrfs/super.c') diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c index 0ac712efcdf2..cc5a2a8a5acb 100644 --- a/fs/btrfs/super.c +++ b/fs/btrfs/super.c @@ -40,6 +40,7 @@ #include #include #include "compat.h" +#include "delayed-inode.h" #include "ctree.h" #include "disk-io.h" #include "transaction.h" @@ -1206,10 +1207,14 @@ static int __init init_btrfs_fs(void) if (err) goto free_extent_io; - err = btrfs_interface_init(); + err = btrfs_delayed_inode_init(); if (err) goto free_extent_map; + err = btrfs_interface_init(); + if (err) + goto free_delayed_inode; + err = register_filesystem(&btrfs_fs_type); if (err) goto unregister_ioctl; @@ -1219,6 +1224,8 @@ static int __init init_btrfs_fs(void) unregister_ioctl: btrfs_interface_exit(); +free_delayed_inode: + btrfs_delayed_inode_exit(); free_extent_map: extent_map_exit(); free_extent_io: @@ -1235,6 +1242,7 @@ free_sysfs: static void __exit exit_btrfs_fs(void) { btrfs_destroy_cachep(); + btrfs_delayed_inode_exit(); extent_map_exit(); extent_io_exit(); btrfs_interface_exit(); -- cgit v1.2.3 From b083916638eee513be501f53b42a4be0b9851db0 Mon Sep 17 00:00:00 2001 From: Julia Lawall Date: Sat, 14 May 2011 07:10:51 +0000 Subject: fs/btrfs: Add missing btrfs_free_path Btrfs_alloc_path should be matched with btrfs_free_path in error-handling code. A simplified version of the semantic match that finds this problem is as follows: (http://coccinelle.lip6.fr/) // @r exists@ local idexpression struct btrfs_path * x; expression ra,rb; position p1,p2; @@ x = btrfs_alloc_path@p1(...) ... when != btrfs_free_path(x,...) when != if (...) { ... btrfs_free_path(x,...) ...} when != x = ra if(...) { ... when != x = rb when forall when != btrfs_free_path(x,...) \(return <+...x...+>; \| return@p2...; \) } @script:python@ p1 << r.p1; p2 << r.p2; @@ cocci.print_main("alloc",p1) cocci.print_secs("return",p2) // Signed-off-by: Julia Lawall Signed-off-by: Chris Mason --- fs/btrfs/super.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'fs/btrfs/super.c') diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c index 0ac712efcdf2..46d7eed7e965 100644 --- a/fs/btrfs/super.c +++ b/fs/btrfs/super.c @@ -506,8 +506,10 @@ static struct dentry *get_default_root(struct super_block *sb, */ dir_id = btrfs_super_root_dir(&root->fs_info->super_copy); di = btrfs_lookup_dir_item(NULL, root, path, dir_id, "default", 7, 0); - if (IS_ERR(di)) + if (IS_ERR(di)) { + btrfs_free_path(path); return ERR_CAST(di); + } if (!di) { /* * Ok the default dir item isn't there. This is weird since -- cgit v1.2.3 From 90a887c9a2e25bcb1fc658fad59dfbc6fb792734 Mon Sep 17 00:00:00 2001 From: Dan Magenheimer Date: Thu, 26 May 2011 10:01:56 -0600 Subject: btrfs: add cleancache support This sixth patch of eight in this cleancache series "opts-in" cleancache for btrfs. Filesystems must explicitly enable cleancache by calling cleancache_init_fs anytime an instance of the filesystem is mounted. Btrfs uses its own readpage which must be hooked, but all other cleancache hooks are in the VFS layer including the matching cleancache_flush_fs hook which must be called on unmount. Details and a FAQ can be found in Documentation/vm/cleancache.txt [v6-v8: no changes] [v5: jeremy@goop.org: simplify init hook and any future fs init changes] Signed-off-by: Dan Magenheimer Signed-off-by: Chris Mason Reviewed-by: Jeremy Fitzhardinge Reviewed-by: Konrad Rzeszutek Wilk Cc: Andrew Morton Cc: Al Viro Cc: Matthew Wilcox Cc: Nick Piggin Cc: Mel Gorman Cc: Rik Van Riel Cc: Jan Beulich Cc: Andreas Dilger Cc: Ted Ts'o Cc: Mark Fasheh Cc: Joel Becker Cc: Nitin Gupta --- fs/btrfs/super.c | 2 ++ 1 file changed, 2 insertions(+) (limited to 'fs/btrfs/super.c') diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c index 0ac712efcdf2..be4ffa12f3ef 100644 --- a/fs/btrfs/super.c +++ b/fs/btrfs/super.c @@ -39,6 +39,7 @@ #include #include #include +#include #include "compat.h" #include "ctree.h" #include "disk-io.h" @@ -624,6 +625,7 @@ static int btrfs_fill_super(struct super_block *sb, sb->s_root = root_dentry; save_mount_options(sb, data); + cleancache_init_fs(sb); return 0; fail_close: -- cgit v1.2.3 From 4cb5300bc839b8a943eb19c9f27f25470e22d0ca Mon Sep 17 00:00:00 2001 From: Chris Mason Date: Tue, 24 May 2011 15:35:30 -0400 Subject: Btrfs: add mount -o auto_defrag This will detect small random writes into files and queue the up for an auto defrag process. It isn't well suited to database workloads yet, but works for smaller files such as rpm, sqlite or bdb databases. Signed-off-by: Chris Mason --- fs/btrfs/super.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) (limited to 'fs/btrfs/super.c') diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c index cd0c7cd2c8fb..28e3cb2607ff 100644 --- a/fs/btrfs/super.c +++ b/fs/btrfs/super.c @@ -160,7 +160,7 @@ enum { Opt_compress_type, Opt_compress_force, Opt_compress_force_type, Opt_notreelog, Opt_ratio, Opt_flushoncommit, Opt_discard, Opt_space_cache, Opt_clear_cache, Opt_user_subvol_rm_allowed, - Opt_enospc_debug, Opt_subvolrootid, Opt_err, + Opt_enospc_debug, Opt_subvolrootid, Opt_defrag, Opt_err, }; static match_table_t tokens = { @@ -191,6 +191,7 @@ static match_table_t tokens = { {Opt_user_subvol_rm_allowed, "user_subvol_rm_allowed"}, {Opt_enospc_debug, "enospc_debug"}, {Opt_subvolrootid, "subvolrootid=%d"}, + {Opt_defrag, "autodefrag"}, {Opt_err, NULL}, }; @@ -369,6 +370,10 @@ int btrfs_parse_options(struct btrfs_root *root, char *options) case Opt_enospc_debug: btrfs_set_opt(info->mount_opt, ENOSPC_DEBUG); break; + case Opt_defrag: + printk(KERN_INFO "btrfs: enabling auto defrag"); + btrfs_set_opt(info->mount_opt, AUTO_DEFRAG); + break; case Opt_err: printk(KERN_INFO "btrfs: unrecognized mount option " "'%s'\n", p); -- cgit v1.2.3 From 9e1f1de02c2275d7172e18dc4e7c2065777611bf Mon Sep 17 00:00:00 2001 From: Al Viro Date: Fri, 3 Jun 2011 18:24:58 -0400 Subject: more conservative S_NOSEC handling Caching "we have already removed suid/caps" was overenthusiastic as merged. On network filesystems we might have had suid/caps set on another client, silently picked by this client on revalidate, all of that *without* clearing the S_NOSEC flag. AFAICS, the only reasonably sane way to deal with that is * new superblock flag; unless set, S_NOSEC is not going to be set. * local block filesystems set it in their ->mount() (more accurately, mount_bdev() does, so does btrfs ->mount(), users of mount_bdev() other than local block ones clear it) * if any network filesystem (or a cluster one) wants to use S_NOSEC, it'll need to set MS_NOSEC in sb->s_flags *AND* take care to clear S_NOSEC when inode attribute changes are picked from other clients. It's not an earth-shattering hole (anybody that can set suid on another client will almost certainly be able to write to the file before doing that anyway), but it's a bug that needs fixing. Signed-off-by: Al Viro --- fs/btrfs/super.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'fs/btrfs/super.c') diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c index 9b2e7e5bc3ef..d158b672a2d2 100644 --- a/fs/btrfs/super.c +++ b/fs/btrfs/super.c @@ -819,7 +819,7 @@ static struct dentry *btrfs_mount(struct file_system_type *fs_type, int flags, } else { char b[BDEVNAME_SIZE]; - s->s_flags = flags; + s->s_flags = flags | MS_NOSEC; strlcpy(s->s_id, bdevname(bdev, b), sizeof(s->s_id)); error = btrfs_fill_super(s, fs_devices, data, flags & MS_SILENT ? 1 : 0); -- cgit v1.2.3 From 4b9465cb9e3859186eefa1ca3b990a5849386320 Mon Sep 17 00:00:00 2001 From: Chris Mason Date: Fri, 3 Jun 2011 09:36:29 -0400 Subject: Btrfs: add mount -o inode_cache This makes the inode map cache default to off until we fix the overflow problem when the free space crcs don't fit inside a single page. Signed-off-by: Chris Mason --- fs/btrfs/super.c | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) (limited to 'fs/btrfs/super.c') diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c index 28e3cb2607ff..3559d0b3518a 100644 --- a/fs/btrfs/super.c +++ b/fs/btrfs/super.c @@ -160,7 +160,8 @@ enum { Opt_compress_type, Opt_compress_force, Opt_compress_force_type, Opt_notreelog, Opt_ratio, Opt_flushoncommit, Opt_discard, Opt_space_cache, Opt_clear_cache, Opt_user_subvol_rm_allowed, - Opt_enospc_debug, Opt_subvolrootid, Opt_defrag, Opt_err, + Opt_enospc_debug, Opt_subvolrootid, Opt_defrag, + Opt_inode_cache, Opt_err, }; static match_table_t tokens = { @@ -192,6 +193,7 @@ static match_table_t tokens = { {Opt_enospc_debug, "enospc_debug"}, {Opt_subvolrootid, "subvolrootid=%d"}, {Opt_defrag, "autodefrag"}, + {Opt_inode_cache, "inode_cache"}, {Opt_err, NULL}, }; @@ -360,6 +362,10 @@ int btrfs_parse_options(struct btrfs_root *root, char *options) printk(KERN_INFO "btrfs: enabling disk space caching\n"); btrfs_set_opt(info->mount_opt, SPACE_CACHE); break; + case Opt_inode_cache: + printk(KERN_INFO "btrfs: enabling inode map caching\n"); + btrfs_set_opt(info->mount_opt, INODE_MAP_CACHE); + break; case Opt_clear_cache: printk(KERN_INFO "btrfs: force clearing of disk cache\n"); btrfs_set_opt(info->mount_opt, CLEAR_CACHE); -- cgit v1.2.3