p71924506
/
linux_old1
1
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

f2fs: avoid high cpu usage in discard thread 

We take very long time to finish generic/476, this is because we will
check consistence of all discard entries in global rb tree while
traversing all different granularity pending lists, even when the list
is empty, in order to avoid that unneeded overhead, we have to skip
the check when coming up an empty list.

generic/476 time consumption:
					cost
Before patch & w/o consistence check	57s
Before patch & w/ consistence check	1426s
After patch				78s

Signed-off-by: Chao Yu <yuchao0@huawei.com>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
This commit is contained in:
Chao Yu 2018-01-08 18:48:33 +08:00 committed by Jaegeuk Kim
parent 94b1e10e74
commit 49c60c67d2
1 changed files with 3 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

3
fs/f2fs/segment.c
View File

@ -1204,6 +1204,8 @@ static int __issue_discard_cmd(struct f2fs_sb_info *sbi,
pend_list = &dcc->pend_list[i]; pend_list = &dcc->pend_list[i];
mutex_lock(&dcc->cmd_lock); mutex_lock(&dcc->cmd_lock);
if (list_empty(pend_list))
goto next;
f2fs_bug_on(sbi, !__check_rb_tree_consistence(sbi, &dcc->root)); f2fs_bug_on(sbi, !__check_rb_tree_consistence(sbi, &dcc->root));
blk_start_plug(&plug); blk_start_plug(&plug);
list_for_each_entry_safe(dc, tmp, pend_list, list) { list_for_each_entry_safe(dc, tmp, pend_list, list) {
@ -1222,6 +1224,7 @@ static int __issue_discard_cmd(struct f2fs_sb_info *sbi,
break; break;
} }
blk_finish_plug(&plug); blk_finish_plug(&plug);
next:
mutex_unlock(&dcc->cmd_lock); mutex_unlock(&dcc->cmd_lock);
if (iter >= dpolicy->max_requests) if (iter >= dpolicy->max_requests)