Commit 49c60c67 authored Jan 08, 2018 by Chao Yu Committed by Jaegeuk Kim Jan 16, 2018

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>

parent 94b1e10e

fs/f2fs/segment.c

+3 −0

Original line number	Diff line number	Diff line
		@@ -1204,6 +1204,8 @@ static int __issue_discard_cmd(struct f2fs_sb_info *sbi,
		pend_list = &dcc->pend_list[i];

		mutex_lock(&dcc->cmd_lock);
		if (list_empty(pend_list))
		goto next;
		f2fs_bug_on(sbi, !__check_rb_tree_consistence(sbi, &dcc->root));
		blk_start_plug(&plug);
		list_for_each_entry_safe(dc, tmp, pend_list, list) {
		@@ -1222,6 +1224,7 @@ skip:
		break;
		}
		blk_finish_plug(&plug);
		next:
		mutex_unlock(&dcc->cmd_lock);

		if (iter >= dpolicy->max_requests)

Admin message