[Ocfs2-devel] [PATCH] ocfs2: submit another bio if current bio is full

From: Changwei Ge <ge.changwei@h3c.com>
To: ocfs2-devel@oss.oracle.com
Subject: [Ocfs2-devel] [PATCH] ocfs2: submit another bio if current bio is full
Date: Fri, 13 Apr 2018 13:51:07 +0800	[thread overview]
Message-ID: <1523598667-29401-1-git-send-email-ge.changwei@h3c.com> (raw)

If cluster scale exceeds 16 nodes, bio will be full and bio_add_page()
returns 0 when adding pages to bio. Returning -EIO to o2hb_read_slots()
from o2hb_setup_one_bio() will lead to losing chance to allocate more
bios to present all heartbeat region.

So o2hb_read_slots() fails.

In my test, making fs fails in starting o2cb service.

Attach error log:
(mkfs.ocfs2,27479,2):o2hb_setup_one_bio:463 page 0, vec_len = 4096, vec_start = 0
(mkfs.ocfs2,27479,2):o2hb_setup_one_bio:463 page 1, vec_len = 4096, vec_start = 0
(mkfs.ocfs2,27479,2):o2hb_setup_one_bio:463 page 2, vec_len = 4096, vec_start = 0
(mkfs.ocfs2,27479,2):o2hb_setup_one_bio:463 page 3, vec_len = 4096, vec_start = 0
(mkfs.ocfs2,27479,2):o2hb_setup_one_bio:463 page 4, vec_len = 4096, vec_start = 0
(mkfs.ocfs2,27479,2):o2hb_setup_one_bio:463 page 5, vec_len = 4096, vec_start = 0
(mkfs.ocfs2,27479,2):o2hb_setup_one_bio:463 page 6, vec_len = 4096, vec_start = 0
(mkfs.ocfs2,27479,2):o2hb_setup_one_bio:463 page 7, vec_len = 4096, vec_start = 0
(mkfs.ocfs2,27479,2):o2hb_setup_one_bio:463 page 8, vec_len = 4096, vec_start = 0
(mkfs.ocfs2,27479,2):o2hb_setup_one_bio:463 page 9, vec_len = 4096, vec_start = 0
(mkfs.ocfs2,27479,2):o2hb_setup_one_bio:463 page 10, vec_len = 4096, vec_start = 0
(mkfs.ocfs2,27479,2):o2hb_setup_one_bio:463 page 11, vec_len = 4096, vec_start = 0
(mkfs.ocfs2,27479,2):o2hb_setup_one_bio:463 page 12, vec_len = 4096, vec_start = 0
(mkfs.ocfs2,27479,2):o2hb_setup_one_bio:463 page 13, vec_len = 4096, vec_start = 0
(mkfs.ocfs2,27479,2):o2hb_setup_one_bio:463 page 14, vec_len = 4096, vec_start = 0
(mkfs.ocfs2,27479,2):o2hb_setup_one_bio:463 page 15, vec_len = 4096, vec_start = 0
(mkfs.ocfs2,27479,2):o2hb_setup_one_bio:463 page 16, vec_len = 4096, vec_start = 0
(mkfs.ocfs2,27479,2):o2hb_setup_one_bio:471 ERROR: Adding page[16] to bio failed, page ffffea0002d7ed40, len 0, vec_len 4096, vec_start 0, bi_sector 8192
(mkfs.ocfs2,27479,2):o2hb_read_slots:500 ERROR: status = -5
(mkfs.ocfs2,27479,2):o2hb_populate_slot_data:1911 ERROR: status = -5
(mkfs.ocfs2,27479,2):o2hb_region_dev_write:2012 ERROR: status = -5

Fixes: ba16ddfbeb9d ("ocfs2/o2hb: check len for bio_add_page() to avoid getting incorrect bio"

Signed-off-by: Changwei Ge <ge.changwei@h3c.com>
---
 fs/ocfs2/cluster/heartbeat.c | 8 ++++++--
 1 file changed, 6 insertions(+), 2 deletions(-)

diff --git a/fs/ocfs2/cluster/heartbeat.c b/fs/ocfs2/cluster/heartbeat.c
index 91a8889abf9b..2809e29d612d 100644
--- a/fs/ocfs2/cluster/heartbeat.c
+++ b/fs/ocfs2/cluster/heartbeat.c
@@ -540,11 +540,12 @@ static struct bio *o2hb_setup_one_bio(struct o2hb_region *reg,
 	struct bio *bio;
 	struct page *page;
 
+#define O2HB_BIO_VECS 16
 	/* Testing has shown this allocation to take long enough under
 	 * GFP_KERNEL that the local node can get fenced. It would be
 	 * nicest if we could pre-allocate these bios and avoid this
 	 * all together. */
-	bio = bio_alloc(GFP_ATOMIC, 16);
+	bio = bio_alloc(GFP_ATOMIC, O2HB_BIO_VECS);
 	if (!bio) {
 		mlog(ML_ERROR, "Could not alloc slots BIO!\n");
 		bio = ERR_PTR(-ENOMEM);
@@ -570,7 +571,10 @@ static struct bio *o2hb_setup_one_bio(struct o2hb_region *reg,
 		     current_page, vec_len, vec_start);
 
 		len = bio_add_page(bio, page, vec_len, vec_start);
-		if (len != vec_len) {
+		if (len == 0 && current_page == O2HB_BIO_VECS) {
+			/* bio is full now. */
+			goto bail;
+		} else if (len != vec_len) {
 			mlog(ML_ERROR, "Adding page[%d] to bio failed, "
 			     "page %p, len %d, vec_len %u, vec_start %u, "
 			     "bi_sector %llu\n", current_page, page, len,
-- 
2.7.4
