f2fs: produce more nids and reduce readahead nats

The readahead nat pages are more likely to be reclaimed quickly, so it'd better
to gather more free nids in advance.

And, let's keep some free nids as much as possible.

Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
This commit is contained in:
Jaegeuk Kim
2016-06-16 16:41:49 -07:00
parent 52763a4b7a
commit ad4edb8314
6 changed files with 18 additions and 8 deletions

View File

@@ -371,7 +371,9 @@ void f2fs_balance_fs_bg(struct f2fs_sb_info *sbi)
try_to_free_nats(sbi, NAT_ENTRY_PER_BLOCK);
if (!available_free_memory(sbi, FREE_NIDS))
try_to_free_nids(sbi, NAT_ENTRY_PER_BLOCK * FREE_NID_PAGES);
try_to_free_nids(sbi, MAX_FREE_NIDS);
else
build_free_nids(sbi);
/* checkpoint is the only way to shrink partial cached entries */
if (!available_free_memory(sbi, NAT_ENTRIES) ||