All of lore.kernel.org
 help / color / mirror / Atom feed
From: chengming.zhou@linux.dev
To: axboe@kernel.dk, osandov@fb.com, ming.lei@redhat.com,
	kbusch@kernel.org, krisman@suse.de
Cc: linux-block@vger.kernel.org, linux-kernel@vger.kernel.org,
	zhouchengming@bytedance.com
Subject: [PATCH v2 2/3] sbitmap: fix strict round-robin non-wrap with hint > 0
Date: Thu, 27 Jul 2023 23:20:19 +0800	[thread overview]
Message-ID: <20230727152020.3633009-2-chengming.zhou@linux.dev> (raw)
In-Reply-To: <20230727152020.3633009-1-chengming.zhou@linux.dev>

From: Chengming Zhou <zhouchengming@bytedance.com>

If we have alloc_hint > 0 and don't wrap, we need to recheck
sb->map[index] with hint == 0 to exhaust the map.

For example: we have 8 words to search, index == 4, hint > 0

In sb->map[4] word, we only search [hint, 63] bits in the first
word search. Then we search left 7 words, the sb->map[4] [0, hint-1]
bits aren't searched.

This patch fix it by searching 9 words in this case, so we will
search sb->map[4] the second time at last with hint == 0.

Signed-off-by: Chengming Zhou <zhouchengming@bytedance.com>
---
 lib/sbitmap.c | 10 +++++++++-
 1 file changed, 9 insertions(+), 1 deletion(-)

diff --git a/lib/sbitmap.c b/lib/sbitmap.c
index ac4027884765..6e098a46be26 100644
--- a/lib/sbitmap.c
+++ b/lib/sbitmap.c
@@ -199,10 +199,18 @@ static int sbitmap_find_bit(struct sbitmap *sb,
 			    unsigned int alloc_hint,
 			    bool wrap)
 {
+	unsigned int map_nr = sb->map_nr;
 	unsigned int i;
 	int nr = -1;
 
-	for (i = 0; i < sb->map_nr; i++) {
+	/*
+	 * If we have alloc_hint > 0 and don't wrap, we need to
+	 * recheck sb->map[index] with hint == 0 to exhaust the map.
+	 */
+	if (alloc_hint && !wrap)
+		map_nr += 1;
+
+	for (i = 0; i < map_nr; i++) {
 		nr = sbitmap_find_bit_in_word(&sb->map[index],
 					      min_t(unsigned int,
 						    __map_depth(sb, index),
-- 
2.41.0


  reply	other threads:[~2023-07-27 15:21 UTC|newest]

Thread overview: 3+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2023-07-27 15:20 [PATCH v2 1/3] sbitmap: fix hint wrap in the failure case chengming.zhou
2023-07-27 15:20 ` chengming.zhou [this message]
2023-07-27 15:20 ` [PATCH v2 3/3] sbitmap: drop wrap logic in __sbitmap_get_word() chengming.zhou

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20230727152020.3633009-2-chengming.zhou@linux.dev \
    --to=chengming.zhou@linux.dev \
    --cc=axboe@kernel.dk \
    --cc=kbusch@kernel.org \
    --cc=krisman@suse.de \
    --cc=linux-block@vger.kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=ming.lei@redhat.com \
    --cc=osandov@fb.com \
    --cc=zhouchengming@bytedance.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.