Re: [PATCH] Btrfs: incremental send, apply asynchronous page cache readahead

[peterh <peterh@synology.com>]

Hi Pasi

Sorry for missing the word.
9 and 15 percent performance gain on HDD and SSD after
the patch is applied.

Kuanling

Pasi Kärkkäinen 於 2017-09-13 17:33 寫到:
> Hi,
> 
> On Wed, Sep 13, 2017 at 02:38:49PM +0800, peterh wrote:
>> From: Kuanling Huang <peterh@synology.com>
>> 
>> By analyzing the perf on btrfs send, we found it take large
>> amount of cpu time on page_cache_sync_readahead. This effort
>> can be reduced after switching to asynchronous one. Overall
>> performance gain on HDD and SSD were 9 and 15 respectively if
>> simply send a large file.
>> 
> 
> hmm, 9 and 15 what?
> 
> 
> -- Pasi
> 
>> Signed-off-by: Kuanling Huang <peterh@synology.com>
>> ---
>>  fs/btrfs/send.c | 21 ++++++++++++++++-----
>>  1 file changed, 16 insertions(+), 5 deletions(-)
>> 
>> diff --git a/fs/btrfs/send.c b/fs/btrfs/send.c
>> index 63a6152..ac67ff6 100644
>> --- a/fs/btrfs/send.c
>> +++ b/fs/btrfs/send.c
>> @@ -4475,16 +4475,27 @@ static ssize_t fill_read_buf(struct send_ctx 
>> *sctx, u64 offset, u32 len)
>>  	/* initial readahead */
>>  	memset(&sctx->ra, 0, sizeof(struct file_ra_state));
>>  	file_ra_state_init(&sctx->ra, inode->i_mapping);
>> -	btrfs_force_ra(inode->i_mapping, &sctx->ra, NULL, index,
>> -		       last_index - index + 1);
>> 
>>  	while (index <= last_index) {
>>  		unsigned cur_len = min_t(unsigned, len,
>>  					 PAGE_CACHE_SIZE - pg_offset);
>> -		page = find_or_create_page(inode->i_mapping, index, GFP_NOFS);
>> +		page = find_lock_page(inode->i_mapping, index);
>>  		if (!page) {
>> -			ret = -ENOMEM;
>> -			break;
>> +			page_cache_sync_readahead(inode->i_mapping,
>> +				&sctx->ra, NULL, index,
>> +				last_index + 1 - index);
>> +
>> +			page = find_or_create_page(inode->i_mapping, index, GFP_NOFS);
>> +			if (unlikely(!page)) {
>> +				ret = -ENOMEM;
>> +				break;
>> +			}
>> +		}
>> +
>> +		if (PageReadahead(page)) {
>> +			page_cache_async_readahead(inode->i_mapping,
>> +				&sctx->ra, NULL, page, index,
>> +				last_index + 1 - index);
>>  		}
>> 
>>  		if (!PageUptodate(page)) {
>> --
>> 1.9.1
>>