Re: [PATCH v3 4/4] btrfs: Refactor find_free_extent() loops update into find_free_extent_update_loop()

[Qu Wenruo <wqu@suse.de>]

[-- Attachment #1.1: Type: text/plain, Size: 5682 bytes --]



On 2018/10/12 下午9:52, Josef Bacik wrote:
> On Fri, Oct 12, 2018 at 02:18:19PM +0800, Qu Wenruo wrote:
>> We have a complex loop design for find_free_extent(), that has different
>> behavior for each loop, some even includes new chunk allocation.
>>
>> Instead of putting such a long code into find_free_extent() and makes it
>> harder to read, just extract them into find_free_extent_update_loop().
>>
>> With all the cleanups, the main find_free_extent() should be pretty
>> barebone:
>>
>> find_free_extent()
>> |- Iterate through all block groups
>> |  |- Get a valid block group
>> |  |- Try to do clustered allocation in that block group
>> |  |- Try to do unclustered allocation in that block group
>> |  |- Check if the result is valid
>> |  |  |- If valid, then exit
>> |  |- Jump to next block group
>> |
>> |- Push harder to find free extents
>>    |- If not found, re-iterate all block groups
>>
>> Signed-off-by: Qu Wenruo <wqu@suse.com>
>> Reviewed-by: Su Yue <suy.fnst@cn.fujitsu.com>
>> ---
>>  fs/btrfs/extent-tree.c | 217 ++++++++++++++++++++++-------------------
>>  1 file changed, 117 insertions(+), 100 deletions(-)
>>
>> diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
>> index e6bfa91af41c..938569d2c583 100644
>> --- a/fs/btrfs/extent-tree.c
>> +++ b/fs/btrfs/extent-tree.c
>> @@ -7236,7 +7236,9 @@ struct find_free_extent_ctl {
>>  	/* RAID index, converted from flags */
>>  	int index;
>>  
>> -	/* Current loop number */
>> +	/*
>> +	 * Current loop number, check find_free_extent_update_loop() for details
>> +	 */
>>  	int loop;
>>  
>>  	/*
>> @@ -7433,6 +7435,117 @@ static int find_free_extent_unclustered(struct btrfs_block_group_cache *bg,
>>  	return 0;
>>  }
>>  
>> +/*
>> + * Return >0 means caller needs to re-search for free extent
>> + * Return 0 means we have the needed free extent.
>> + * Return <0 means we failed to locate any free extent.
>> + */
>> +static int find_free_extent_update_loop(struct btrfs_fs_info *fs_info,
>> +					struct btrfs_free_cluster *last_ptr,
>> +					struct btrfs_key *ins,
>> +					struct find_free_extent_ctl *ffe_ctl,
>> +					int full_search, bool use_cluster)
>> +{
>> +	struct btrfs_root *root = fs_info->extent_root;
>> +	int ret;
>> +
>> +	if ((ffe_ctl->loop == LOOP_CACHING_NOWAIT) &&
>> +	    ffe_ctl->have_caching_bg && !ffe_ctl->orig_have_caching_bg)
>> +		ffe_ctl->orig_have_caching_bg = true;
>> +
>> +	if (!ins->objectid && ffe_ctl->loop >= LOOP_CACHING_WAIT &&
>> +	     ffe_ctl->have_caching_bg)
>> +		return 1;
>> +
>> +	if (!ins->objectid && ++(ffe_ctl->index) < BTRFS_NR_RAID_TYPES)
>> +		return 1;
>> +
>> +	/*
>> +	 * LOOP_CACHING_NOWAIT, search partially cached block groups, kicking
>> +	 *			caching kthreads as we move along
>> +	 * LOOP_CACHING_WAIT, search everything, and wait if our bg is caching
>> +	 * LOOP_ALLOC_CHUNK, force a chunk allocation and try again
>> +	 * LOOP_NO_EMPTY_SIZE, set empty_size and empty_cluster to 0 and try
>> +	 *			again
>> +	 */
>> +	if (!ins->objectid && ffe_ctl->loop < LOOP_NO_EMPTY_SIZE) {
>> +		ffe_ctl->index = 0;
>> +		if (ffe_ctl->loop == LOOP_CACHING_NOWAIT) {
>> +			/*
>> +			 * We want to skip the LOOP_CACHING_WAIT step if we
>> +			 * don't have any uncached bgs and we've already done a
>> +			 * full search through.
>> +			 */
>> +			if (ffe_ctl->orig_have_caching_bg || !full_search)
>> +				ffe_ctl->loop = LOOP_CACHING_WAIT;
>> +			else
>> +				ffe_ctl->loop = LOOP_ALLOC_CHUNK;
>> +		} else {
>> +			ffe_ctl->loop++;
>> +		}
>> +
>> +		if (ffe_ctl->loop == LOOP_ALLOC_CHUNK) {
>> +			struct btrfs_trans_handle *trans;
>> +			int exist = 0;
>> +
>> +			trans = current->journal_info;
>> +			if (trans)
>> +				exist = 1;
>> +			else
>> +				trans = btrfs_join_transaction(root);
>> +
>> +			if (IS_ERR(trans)) {
>> +				ret = PTR_ERR(trans);
>> +				return ret;
>> +			}
>> +
>> +			ret = do_chunk_alloc(trans, ffe_ctl->flags,
>> +					     CHUNK_ALLOC_FORCE);
>> +
>> +			/*
>> +			 * If we can't allocate a new chunk we've already looped
>> +			 * through at least once, move on to the NO_EMPTY_SIZE
>> +			 * case.
>> +			 */
>> +			if (ret == -ENOSPC)
>> +				ffe_ctl->loop = LOOP_NO_EMPTY_SIZE;
>> +
>> +			/* Do not bail out on ENOSPC since we can do more. */
>> +			if (ret < 0 && ret != -ENOSPC)
>> +				btrfs_abort_transaction(trans, ret);
>> +			else
>> +				ret = 0;
>> +			if (!exist)
>> +				btrfs_end_transaction(trans);
>> +			if (ret)
>> +				return ret;
>> +		}
>> +
>> +		if (ffe_ctl->loop == LOOP_NO_EMPTY_SIZE) {
>> +			/*
>> +			 * Don't loop again if we already have no empty_size and
>> +			 * no empty_cluster.
>> +			 */
>> +			if (ffe_ctl->empty_size == 0 &&
>> +			    ffe_ctl->empty_cluster == 0)
>> +				return -ENOSPC;
>> +			ffe_ctl->empty_size = 0;
>> +			ffe_ctl->empty_cluster = 0;
>> +		}
>> +		return 1;
>> +	} else if (!ins->objectid) {
>> +		ret = -ENOSPC;
>> +	} else if (ins->objectid) {
>> +		if (!use_cluster && last_ptr) {
>> +			spin_lock(&last_ptr->lock);
>> +			last_ptr->window_start = ins->objectid;
>> +			spin_unlock(&last_ptr->lock);
>> +		}
>> +		ret = 0;
>> +	}
>> +	return ret;
>> +}
> 
> Rework this so the
> 
> if (ins->objectid)
> 	blah
> 
> is the first thing, that way you don't have to do the
> 
> if (!ins->objectid && <other things>)
> 
> for all the other if statements here.  The fast path should be the first thing,
> then we can deal with all of the other crap last.  Thanks,

Indeed, the ENOSPC should be in the last else branch.

Thanks,
Qu

> 
> Josef
> 


[-- Attachment #2: OpenPGP digital signature --]
[-- Type: application/pgp-signature, Size: 488 bytes --]