[RFC] ext4: Add pollable sysfs entry for block threshold events
From: Beata Michalska
Date: Wed Mar 11 2015 - 06:17:03 EST
Add support for pollable sysfs entry for logical blocks
threshold, allowing the userspace to wait for
the notification whenever the threshold is reached
instead of periodically calling the statfs.
This is supposed to work as a single-shot notifiaction
to reduce the number of triggered events.
Signed-off-by: Beata Michalska <b.michalska@xxxxxxxxxxx>
---
fs/ext4/balloc.c | 17 ++++-------------
fs/ext4/ext4.h | 12 ++++++++++++
fs/ext4/ialloc.c | 5 +----
fs/ext4/inode.c | 2 +-
fs/ext4/mballoc.c | 14 ++++----------
fs/ext4/resize.c | 3 ++-
fs/ext4/super.c | 52 ++++++++++++++++++++++++++++++++++++++++++++++++++--
7 files changed, 74 insertions(+), 31 deletions(-)
diff --git a/fs/ext4/balloc.c b/fs/ext4/balloc.c
index 83a6f49..bf4a669 100644
--- a/fs/ext4/balloc.c
+++ b/fs/ext4/balloc.c
@@ -193,10 +193,7 @@ static int ext4_init_block_bitmap(struct super_block *sb,
* essentially implementing a per-group read-only flag. */
if (!ext4_group_desc_csum_verify(sb, block_group, gdp)) {
grp = ext4_get_group_info(sb, block_group);
- if (!EXT4_MB_GRP_BBITMAP_CORRUPT(grp))
- percpu_counter_sub(&sbi->s_freeclusters_counter,
- grp->bb_free);
- set_bit(EXT4_GROUP_INFO_BBITMAP_CORRUPT_BIT, &grp->bb_state);
+ ext4_mark_group_tainted(sbi, grp);
if (!EXT4_MB_GRP_IBITMAP_CORRUPT(grp)) {
int count;
count = ext4_free_inodes_count(sb, gdp);
@@ -252,7 +249,7 @@ unsigned ext4_free_clusters_after_init(struct super_block *sb,
ext4_group_t block_group,
struct ext4_group_desc *gdp)
{
- return num_clusters_in_group(sb, block_group) -
+ return num_clusters_in_group(sb, block_group) -
ext4_num_overhead_clusters(sb, block_group, gdp);
}
@@ -379,20 +376,14 @@ static void ext4_validate_block_bitmap(struct super_block *sb,
ext4_unlock_group(sb, block_group);
ext4_error(sb, "bg %u: block %llu: invalid block bitmap",
block_group, blk);
- if (!EXT4_MB_GRP_BBITMAP_CORRUPT(grp))
- percpu_counter_sub(&sbi->s_freeclusters_counter,
- grp->bb_free);
- set_bit(EXT4_GROUP_INFO_BBITMAP_CORRUPT_BIT, &grp->bb_state);
+ ext4_mark_group_tainted(sbi, grp);
return;
}
if (unlikely(!ext4_block_bitmap_csum_verify(sb, block_group,
desc, bh))) {
ext4_unlock_group(sb, block_group);
ext4_error(sb, "bg %u: bad block bitmap checksum", block_group);
- if (!EXT4_MB_GRP_BBITMAP_CORRUPT(grp))
- percpu_counter_sub(&sbi->s_freeclusters_counter,
- grp->bb_free);
- set_bit(EXT4_GROUP_INFO_BBITMAP_CORRUPT_BIT, &grp->bb_state);
+ ext4_mark_group_tainted(sbi, grp);
return;
}
set_buffer_verified(bh);
diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h
index f63c3d5..ee911b7 100644
--- a/fs/ext4/ext4.h
+++ b/fs/ext4/ext4.h
@@ -1309,6 +1309,7 @@ struct ext4_sb_info {
unsigned long s_sectors_written_start;
u64 s_kbytes_written;
+ atomic64_t block_thres_event;
/* the size of zero-out chunk */
unsigned int s_extent_max_zeroout_kb;
@@ -2207,6 +2208,7 @@ extern int ext4_alloc_flex_bg_array(struct super_block *sb,
ext4_group_t ngroup);
extern const char *ext4_decode_error(struct super_block *sb, int errno,
char nbuf[16]);
+extern void ext4_block_thres_notify(struct ext4_sb_info *sbi);
extern __printf(4, 5)
void __ext4_error(struct super_block *, const char *, unsigned int,
@@ -2535,6 +2537,16 @@ static inline spinlock_t *ext4_group_lock_ptr(struct super_block *sb,
return bgl_lock_ptr(EXT4_SB(sb)->s_blockgroup_lock, group);
}
+static inline
+void ext4_mark_group_tainted(struct ext4_sb_info *sbi,
+ struct ext4_group_info *grp)
+{
+ if (!EXT4_MB_GRP_BBITMAP_CORRUPT(grp))
+ percpu_counter_sub(&sbi->s_freeclusters_counter, grp->bb_free);
+ set_bit(EXT4_GROUP_INFO_BBITMAP_CORRUPT_BIT, &grp->bb_state);
+ ext4_block_thres_notify(sbi);
+}
+
/*
* Returns true if the filesystem is busy enough that attempts to
* access the block group locks has run into contention.
diff --git a/fs/ext4/ialloc.c b/fs/ext4/ialloc.c
index ac644c3..65336b3 100644
--- a/fs/ext4/ialloc.c
+++ b/fs/ext4/ialloc.c
@@ -79,10 +79,7 @@ static unsigned ext4_init_inode_bitmap(struct super_block *sb,
if (!ext4_group_desc_csum_verify(sb, block_group, gdp)) {
ext4_error(sb, "Checksum bad for group %u", block_group);
grp = ext4_get_group_info(sb, block_group);
- if (!EXT4_MB_GRP_BBITMAP_CORRUPT(grp))
- percpu_counter_sub(&sbi->s_freeclusters_counter,
- grp->bb_free);
- set_bit(EXT4_GROUP_INFO_BBITMAP_CORRUPT_BIT, &grp->bb_state);
+ ext4_mark_group_tainted(sbi, grp);
if (!EXT4_MB_GRP_IBITMAP_CORRUPT(grp)) {
int count;
count = ext4_free_inodes_count(sb, gdp);
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index 5cb9a21..0dfe147 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -1203,7 +1203,7 @@ static int ext4_da_reserve_space(struct inode *inode, ext4_lblk_t lblock)
}
ei->i_reserved_data_blocks++;
spin_unlock(&ei->i_block_reservation_lock);
-
+ ext4_block_thres_notify(sbi);
return 0; /* success */
}
diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c
index 8d1e602..94bef9b 100644
--- a/fs/ext4/mballoc.c
+++ b/fs/ext4/mballoc.c
@@ -760,10 +760,7 @@ void ext4_mb_generate_buddy(struct super_block *sb,
* corrupt and update bb_free using bitmap value
*/
grp->bb_free = free;
- if (!EXT4_MB_GRP_BBITMAP_CORRUPT(grp))
- percpu_counter_sub(&sbi->s_freeclusters_counter,
- grp->bb_free);
- set_bit(EXT4_GROUP_INFO_BBITMAP_CORRUPT_BIT, &grp->bb_state);
+ ext4_mark_group_tainted(sbi, grp);
}
mb_set_largest_free_order(sb, grp);
@@ -1448,9 +1445,7 @@ static void mb_free_blocks(struct inode *inode, struct ext4_buddy *e4b,
"freeing already freed block "
"(bit %u); block bitmap corrupt.",
block);
- if (!EXT4_MB_GRP_BBITMAP_CORRUPT(e4b->bd_info))
- percpu_counter_sub(&sbi->s_freeclusters_counter,
- e4b->bd_info->bb_free);
+ ext4_mark_group_tainted(sbi, e4b->bd_info);
/* Mark the block group as corrupt. */
set_bit(EXT4_GROUP_INFO_BBITMAP_CORRUPT_BIT,
&e4b->bd_info->bb_state);
@@ -2362,7 +2357,7 @@ int ext4_mb_alloc_groupinfo(struct super_block *sb, ext4_group_t ngroups)
}
sbi->s_group_info = new_groupinfo;
sbi->s_group_info_size = size / sizeof(*sbi->s_group_info);
- ext4_debug("allocated s_groupinfo array for %d meta_bg's\n",
+ ext4_debug("allocated s_groupinfo array for %d meta_bg's\n",
sbi->s_group_info_size);
return 0;
}
@@ -2967,7 +2962,6 @@ ext4_mb_mark_diskspace_used(struct ext4_allocation_context *ac,
if (err)
goto out_err;
err = ext4_handle_dirty_metadata(handle, NULL, gdp_bh);
-
out_err:
brelse(bitmap_bh);
return err;
@@ -4525,8 +4519,8 @@ out:
reserv_clstrs);
}
+ ext4_block_thres_notify(sbi);
trace_ext4_allocate_blocks(ar, (unsigned long long)block);
-
return block;
}
diff --git a/fs/ext4/resize.c b/fs/ext4/resize.c
index 8a8ec62..7ae308b 100644
--- a/fs/ext4/resize.c
+++ b/fs/ext4/resize.c
@@ -1244,7 +1244,7 @@ static int ext4_setup_new_descs(handle_t *handle, struct super_block *sb,
ext4_group_t group;
__u16 *bg_flags = flex_gd->bg_flags;
int i, gdb_off, gdb_num, err = 0;
-
+
for (i = 0; i < flex_gd->count; i++, group_data++, bg_flags++) {
group = group_data->group;
@@ -1397,6 +1397,7 @@ static void ext4_update_super(struct super_block *sb,
*/
ext4_calculate_overhead(sb);
+ ext4_block_thres_notify(sbi);
if (test_opt(sb, DEBUG))
printk(KERN_DEBUG "EXT4-fs: added group %u:"
"%llu blocks(%llu free %llu reserved)\n", flex_gd->count,
diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index e061e66..36f00f3 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -2558,10 +2558,56 @@ static ssize_t reserved_clusters_store(struct ext4_attr *a,
if (parse_strtoull(buf, -1ULL, &val))
return -EINVAL;
ret = ext4_reserve_clusters(sbi, val);
-
+ ext4_block_thres_notify(sbi);
return ret ? ret : count;
}
+void ext4_block_thres_notify(struct ext4_sb_info *sbi)
+{
+ struct ext4_super_block *es = sbi->s_es;
+ unsigned long long bcount, bfree;
+
+ if (!atomic64_read(&sbi->block_thres_event))
+ /* No limit set -> no notification needed */
+ return;
+ /* Verify the limit has not been reached. If so notify the watchers */
+ bcount = ext4_blocks_count(es) - EXT4_C2B(sbi, sbi->s_overhead);
+ bfree = percpu_counter_sum_positive(&sbi->s_freeclusters_counter) -
+ percpu_counter_sum_positive(&sbi->s_dirtyclusters_counter);
+ bfree = EXT4_C2B(sbi, max_t(s64, bfree, 0));
+
+ if (bcount - bfree > atomic64_read(&sbi->block_thres_event)) {
+ sysfs_notify(&sbi->s_kobj, NULL, "block_thres_event");
+ /* Prevent flooding notifications */
+ atomic64_set(&sbi->block_thres_event, 0);
+ }
+}
+
+static ssize_t block_thres_event_show(struct ext4_attr *a,
+ struct ext4_sb_info *sbi, char *buf)
+{
+ return snprintf(buf, PAGE_SIZE, "%llu\n",
+ atomic64_read(&sbi->block_thres_event));
+
+}
+
+static ssize_t block_thres_event_store(struct ext4_attr *a,
+ struct ext4_sb_info *sbi,
+ const char *buf, size_t count)
+{
+ struct ext4_super_block *es = sbi->s_es;
+ unsigned long long bcount, val;
+
+ bcount = ext4_blocks_count(es) - EXT4_C2B(sbi, sbi->s_overhead);
+ if (parse_strtoull(buf, bcount, &val))
+ return -EINVAL;
+ if (val != atomic64_read(&sbi->block_thres_event)) {
+ atomic64_set(&sbi->block_thres_event, val);
+ ext4_block_thres_notify(sbi);
+ }
+ return count;
+}
+
static ssize_t trigger_test_error(struct ext4_attr *a,
struct ext4_sb_info *sbi,
const char *buf, size_t count)
@@ -2631,6 +2677,7 @@ EXT4_RO_ATTR(delayed_allocation_blocks);
EXT4_RO_ATTR(session_write_kbytes);
EXT4_RO_ATTR(lifetime_write_kbytes);
EXT4_RW_ATTR(reserved_clusters);
+EXT4_RW_ATTR(block_thres_event);
EXT4_ATTR_OFFSET(inode_readahead_blks, 0644, sbi_ui_show,
inode_readahead_blks_store, s_inode_readahead_blks);
EXT4_RW_ATTR_SBI_UI(inode_goal, s_inode_goal);
@@ -2658,6 +2705,7 @@ static struct attribute *ext4_attrs[] = {
ATTR_LIST(session_write_kbytes),
ATTR_LIST(lifetime_write_kbytes),
ATTR_LIST(reserved_clusters),
+ ATTR_LIST(block_thres_event),
ATTR_LIST(inode_readahead_blks),
ATTR_LIST(inode_goal),
ATTR_LIST(mb_stats),
@@ -4153,7 +4201,7 @@ no_journal:
}
block = ext4_count_free_clusters(sb);
- ext4_free_blocks_count_set(sbi->s_es,
+ ext4_free_blocks_count_set(sbi->s_es,
EXT4_C2B(sbi, block));
err = percpu_counter_init(&sbi->s_freeclusters_counter, block,
GFP_KERNEL);
--
1.7.9.5
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/