Re: [RFC 3/4] ext4: Add support for generic FS events

[Beata Michalska]

On 04/15/2015 09:18 PM, Darrick J. Wong wrote:
> On Wed, Apr 15, 2015 at 09:15:46AM +0200, Beata Michalska wrote:
>> Add support for generic FS events including threshold
>> notifications, ENOSPC and remount as read-only warnings,
>> along with generic internal warnings/errors.
>>
>> Signed-off-by: Beata Michalska <b.michalska@xxxxxxxxxxx>
>> ---
>>  fs/ext4/balloc.c  |   11 +++++++++--
>>  fs/ext4/ext4.h    |    1 +
>>  fs/ext4/inode.c   |    2 +-
>>  fs/ext4/mballoc.c |    6 +++++-
>>  fs/ext4/resize.c  |    1 +
>>  fs/ext4/super.c   |   43 +++++++++++++++++++++++++++++++++++++++++++
>>  6 files changed, 60 insertions(+), 4 deletions(-)
>>
>> diff --git a/fs/ext4/balloc.c b/fs/ext4/balloc.c
>> index e95b27a..49d2ace 100644
>> --- a/fs/ext4/balloc.c
>> +++ b/fs/ext4/balloc.c
>> @@ -569,6 +569,7 @@ int ext4_claim_free_clusters(struct ext4_sb_info *sbi,
>>  {
>>  	if (ext4_has_free_clusters(sbi, nclusters, flags)) {
>>  		percpu_counter_add(&sbi->s_dirtyclusters_counter, nclusters);
>> +		fs_event_alloc_space(sbi->s_sb, EXT4_C2B(sbi, nclusters));
>>  		return 0;
>>  	} else
>>  		return -ENOSPC;
>> @@ -590,9 +591,10 @@ int ext4_should_retry_alloc(struct super_block *sb, int *retries)
>>  {
>>  	if (!ext4_has_free_clusters(EXT4_SB(sb), 1, 0) ||
>>  	    (*retries)++ > 3 ||
>> -	    !EXT4_SB(sb)->s_journal)
>> +	    !EXT4_SB(sb)->s_journal) {
>> +		fs_event_notify(sb, FS_EVENT_WARN, FS_WARN_ENOSPC);
>>  		return 0;
>> -
>> +	}
>>  	jbd_debug(1, "%s: retrying operation after ENOSPC\n", sb->s_id);
>>  
>>  	return jbd2_journal_force_commit_nested(EXT4_SB(sb)->s_journal);
>> @@ -637,6 +639,11 @@ ext4_fsblk_t ext4_new_meta_blocks(handle_t *handle, struct inode *inode,
>>  		dquot_alloc_block_nofail(inode,
>>  				EXT4_C2B(EXT4_SB(inode->i_sb), ar.len));
>>  	}
>> +
>> +	if (*errp == -ENOSPC)
>> +		fs_event_notify(inode->i_sb, FS_EVENT_WARN,
>> +				FS_WANR_ENOSPC_META);
>> +
>>  	return ret;
>>  }
>>  
>> diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h
>> index 163afe2..7d75ff9 100644
>> --- a/fs/ext4/ext4.h
>> +++ b/fs/ext4/ext4.h
>> @@ -2542,6 +2542,7 @@ void ext4_mark_group_corrupted(struct ext4_sb_info *sbi,
>>  	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);
>> +	fs_event_alloc_space(sbi->s_sb, EXT4_C2B(sbi, grp->bb_free));
> 
> While we're adding fs netlink notifications, could we add a message that means
> "This FS is corrupt, go run fsck"?  A monitoring app could possibly figure
> this out by a sudden drop in free space accompanied by EIO errors hitting
> userland apps, but we might as well be explicit about the flaming death. :)
> 
> --D
> 

The notifications sent through this interface can be extended to whatever is needed.
The are very few basic event codes - among them are FS_ERR_UNKNOWN and FS_ERR_ITERNAL.
So one can assume that whenever one of those is being triggered - smth wrong is going on.
So at this point running fsck would be a good idea. If this is not enough, new event
codes might be introduced. Note that it is also possible for the file systems
to send their own messages placing within the payload whatever they like.
This is an early version, so it can definitely be adjusted.

BR
Beata

>>  }
>>  
>>  /*
>> diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
>> index 5cb9a21..2a7af0f 100644
>> --- a/fs/ext4/inode.c
>> +++ b/fs/ext4/inode.c
>> @@ -1238,7 +1238,7 @@ static void ext4_da_release_space(struct inode *inode, int to_free)
>>  	percpu_counter_sub(&sbi->s_dirtyclusters_counter, to_free);
>>  
>>  	spin_unlock(&EXT4_I(inode)->i_block_reservation_lock);
>> -
>> +	fs_event_free_space(sbi->s_sb, to_free);
>>  	dquot_release_reservation_block(inode, EXT4_C2B(sbi, to_free));
>>  }
>>  
>> diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c
>> index 24a4b6d..e6cbbd6 100644
>> --- a/fs/ext4/mballoc.c
>> +++ b/fs/ext4/mballoc.c
>> @@ -4511,6 +4511,9 @@ out:
>>  		kmem_cache_free(ext4_ac_cachep, ac);
>>  	if (inquota && ar->len < inquota)
>>  		dquot_free_block(ar->inode, EXT4_C2B(sbi, inquota - ar->len));
>> +	if (reserv_clstrs && ar->len < reserv_clstrs)
>> +		 fs_event_free_space(sbi->s_sb,
>> +		 	EXT4_C2B(sbi, reserv_clstrs - ar->len));
>>  	if (!ar->len) {
>>  		if ((ar->flags & EXT4_MB_DELALLOC_RESERVED) == 0)
>>  			/* release all the reserved blocks if non delalloc */
>> @@ -4848,7 +4851,7 @@ do_more:
>>  	if (!(flags & EXT4_FREE_BLOCKS_NO_QUOT_UPDATE))
>>  		dquot_free_block(inode, EXT4_C2B(sbi, count_clusters));
>>  	percpu_counter_add(&sbi->s_freeclusters_counter, count_clusters);
>> -
>> +	fs_event_free_space(sb, EXT4_C2B(sbi, count_clusters));
>>  	ext4_mb_unload_buddy(&e4b);
>>  
>>  	/* We dirtied the bitmap block */
>> @@ -4982,6 +4985,7 @@ int ext4_group_add_blocks(handle_t *handle, struct super_block *sb,
>>  	ext4_unlock_group(sb, block_group);
>>  	percpu_counter_add(&sbi->s_freeclusters_counter,
>>  			   EXT4_NUM_B2C(sbi, blocks_freed));
>> +	fs_event_free_space(sb, blocks_freed);
>>  
>>  	if (sbi->s_log_groups_per_flex) {
>>  		ext4_group_t flex_group = ext4_flex_group(sbi, block_group);
>> diff --git a/fs/ext4/resize.c b/fs/ext4/resize.c
>> index 8a8ec62..dbf08d6 100644
>> --- a/fs/ext4/resize.c
>> +++ b/fs/ext4/resize.c
>> @@ -1378,6 +1378,7 @@ static void ext4_update_super(struct super_block *sb,
>>  			   EXT4_NUM_B2C(sbi, free_blocks));
>>  	percpu_counter_add(&sbi->s_freeinodes_counter,
>>  			   EXT4_INODES_PER_GROUP(sb) * flex_gd->count);
>> +	fs_event_free_space(sb, free_blocks - reserved_blocks);
>>  
>>  	ext4_debug("free blocks count %llu",
>>  		   percpu_counter_read(&sbi->s_freeclusters_counter));
>> diff --git a/fs/ext4/super.c b/fs/ext4/super.c
>> index e061e66..52091da 100644
>> --- a/fs/ext4/super.c
>> +++ b/fs/ext4/super.c
>> @@ -398,6 +398,7 @@ static void ext4_handle_error(struct super_block *sb)
>>  	if (test_opt(sb, ERRORS_PANIC))
>>  		panic("EXT4-fs (device %s): panic forced after error\n",
>>  			sb->s_id);
>> +	fs_event_notify(sb, FS_EVENT_ERR, FS_ERR_UNKNOWN);
>>  }
>>  
>>  #define ext4_error_ratelimit(sb)					\
>> @@ -585,6 +586,8 @@ void __ext4_abort(struct super_block *sb, const char *function,
>>  		if (EXT4_SB(sb)->s_journal)
>>  			jbd2_journal_abort(EXT4_SB(sb)->s_journal, -EIO);
>>  		save_error_info(sb, function, line);
>> +		fs_event_notify(sb, FS_EVENT_ERR, FS_ERR_RO_REMOUT);
>> +
>>  	}
>>  	if (test_opt(sb, ERRORS_PANIC))
>>  		panic("EXT4-fs panic from previous error\n");
>> @@ -612,6 +615,8 @@ void __ext4_warning(struct super_block *sb, const char *function,
>>  	struct va_format vaf;
>>  	va_list args;
>>  
>> +	fs_event_notify(sb, FS_EVENT_WARN, FS_WARN_UNKNOWN);
>> +
>>  	if (!___ratelimit(&(EXT4_SB(sb)->s_warning_ratelimit_state),
>>  			  "EXT4-fs warning"))
>>  		return;
>> @@ -1083,6 +1088,13 @@ static const struct quotactl_ops ext4_qctl_operations = {
>>  };
>>  #endif
>>  
>> +static int ext4_trace_query(struct super_block *sb,
>> +			    struct fs_trace_sdata *data);
>> +
>> +static const struct fs_trace_operations ext4_trace_ops = {
>> +	.fs_trace_query	= ext4_trace_query,
>> +};
>> +
>>  static const struct super_operations ext4_sops = {
>>  	.alloc_inode	= ext4_alloc_inode,
>>  	.destroy_inode	= ext4_destroy_inode,
>> @@ -3398,11 +3410,20 @@ static int ext4_reserve_clusters(struct ext4_sb_info *sbi, ext4_fsblk_t count)
>>  {
>>  	ext4_fsblk_t clusters = ext4_blocks_count(sbi->s_es) >>
>>  				sbi->s_cluster_bits;
>> +	ext4_fsblk_t current_resv;
>>  
>>  	if (count >= clusters)
>>  		return -EINVAL;
>>  
>> +	current_resv = atomic64_read(&sbi->s_resv_clusters);
>>  	atomic64_set(&sbi->s_resv_clusters, count);
>> +
>> +	if (count > current_resv)
>> +		fs_event_alloc_space(sbi->s_sb,
>> +			EXT4_C2B(sbi, count - current_resv));
>> +	else
>> +		fs_event_free_space(sbi->s_sb,
>> +			EXT4_C2B(sbi, current_resv - count));
>>  	return 0;
>>  }
>>  
>> @@ -3966,6 +3987,8 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
>>  		sb->s_qcop = &ext4_qctl_operations;
>>  	sb->s_quota_types = QTYPE_MASK_USR | QTYPE_MASK_GRP;
>>  #endif
>> +	sb->s_trace_ops = &ext4_trace_ops;
>> +
>>  	memcpy(sb->s_uuid, es->s_uuid, sizeof(es->s_uuid));
>>  
>>  	INIT_LIST_HEAD(&sbi->s_orphan); /* unlinked but open files */
>> @@ -5438,6 +5461,26 @@ out:
>>  
>>  #endif
>>  
>> +static int ext4_trace_query(struct super_block *sb, struct fs_trace_sdata *data)
>> +{
>> +	struct ext4_sb_info *sbi = EXT4_SB(sb);
>> +	struct ext4_super_block *es = sbi->s_es;
>> +	ext4_fsblk_t rsv_blocks;
>> +
>> +	data->available_blks =
>> +		percpu_counter_sum_positive(&sbi->s_freeclusters_counter) -
>> +		percpu_counter_sum_positive(&sbi->s_dirtyclusters_counter);
>> +	data->available_blks = EXT4_C2B(sbi, data->available_blks);
>> +	rsv_blocks = ext4_r_blocks_count(es) +
>> +		     EXT4_C2B(sbi, atomic64_read(&sbi->s_resv_clusters));
>> +	if (data->available_blks < rsv_blocks)
>> +		data->available_blks = 0;
>> +	else
>> +		data->available_blks -= rsv_blocks;
>> +	data->events_cap_mask = FS_EVENTS_ALL;
>> +	return 0;
>> +}
>> +
>>  static struct dentry *ext4_mount(struct file_system_type *fs_type, int flags,
>>  		       const char *dev_name, void *data)
>>  {
>> -- 
>> 1.7.9.5
>>
>> --
>> To unsubscribe from this list: send the line "unsubscribe linux-ext4" in
>> the body of a message to majordomo@xxxxxxxxxxxxxxx
>> More majordomo info at  http://vger.kernel.org/majordomo-info.html
> 

--
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/