Skip to contentSkip to conversation

gfs2: Abort gfs2_freeze if io error is seen

PATCH Superseded Bob Peterson 2 participants 2 messages Nov 14, 2019 1 message not in the archive GFS2 file system

v1 of 2 Superseded Latest is v2 →

lore
Share & tools
lore

A message that is not in the archive (sent off-list or not yet received): [email protected]

#1 lore raw

PATCH 1/1 gfs2: Abort gfs2_freeze if io error is seen

Hi,

Before this patch, an io error, such as -EIO writing to the journal would cause function gfs2_freeze to go into an infinite loop, continuously retrying the freeze operation. But nothing ever clears the -EIO except unmount after withdraw, which is impossible if the freeze operation never ends (fails). Instead you get:

[ 6499.767994] gfs2: fsid=dm-32.0: error freezing FS: -5
[ 6499.773058] gfs2: fsid=dm-32.0: retrying...
[ 6500.791957] gfs2: fsid=dm-32.0: error freezing FS: -5
[ 6500.797015] gfs2: fsid=dm-32.0: retrying...

This patch adds a check for -EIO in gfs2_freeze, and if seen, it dequeues the freeze glock, aborts the loop and returns the error. Also, there's no need to pass the freeze holder to function gfs2_lock_fs_check_clean since it's only called in one place and it's a well-known superblock pointer, so this simplifies that.

---
 fs/gfs2/super.c | 18 +++++++++++-------
 1 file changed, 11 insertions(+), 7 deletions(-)
fs/gfs2/super.c +11 -7
index 8154c38e488b..eb1fbd533e6d 100644
@@ -399,8 +399,7 @@ struct lfcc {
  * Returns: errno
  */
 
-static int gfs2_lock_fs_check_clean(struct gfs2_sbd *sdp,
-				    struct gfs2_holder *freeze_gh)
+static int gfs2_lock_fs_check_clean(struct gfs2_sbd *sdp)
 {
 	struct gfs2_inode *ip;
 	struct gfs2_jdesc *jd;
@@ -425,7 +424,7 @@ static int gfs2_lock_fs_check_clean(struct gfs2_sbd *sdp,
 	}
 
 	error = gfs2_glock_nq_init(sdp->sd_freeze_gl, LM_ST_EXCLUSIVE,
-				   GL_NOCACHE, freeze_gh);
+				   GL_NOCACHE, &sdp->sd_freeze_gh);
 
 	list_for_each_entry(jd, &sdp->sd_jindex_list, jd_list) {
 		error = gfs2_jdesc_check(jd);
@@ -441,7 +440,7 @@ static int gfs2_lock_fs_check_clean(struct gfs2_sbd *sdp,
 	}
 
 	if (error)
-		gfs2_glock_dq_uninit(freeze_gh);
+		gfs2_glock_dq_uninit(&sdp->sd_freeze_gh);
 
 out:
 	while (!list_empty(&list)) {
@@ -767,15 +766,20 @@ static int gfs2_freeze(struct super_block *sb)
 			goto out;
 		}
 
-		error = gfs2_lock_fs_check_clean(sdp, &sdp->sd_freeze_gh);
+		error = gfs2_lock_fs_check_clean(sdp);
 		if (!error)
 			break;
 
 		if (error == -EBUSY)
 			fs_err(sdp, "waiting for recovery before freeze\n");
-		else
+		else if (error == -EIO) {
+			fs_err(sdp, "Fatal IO error: cannot freeze gfs2 due "
+			       "to recovery error.\n");
+			gfs2_glock_dq_uninit(&sdp->sd_freeze_gh);
+			goto out;
+		} else {
 			fs_err(sdp, "error freezing FS: %d\n", error);
-
+		}
 		fs_err(sdp, "retrying...\n");
 		msleep(1000);
 	}
#2 lore raw

PATCH 1/1 gfs2: Abort gfs2_freeze if io error is seen

Quoted 37 lines · Bob Peterson

Before this patch, an io error, such as -EIO writing to the journal would cause function gfs2_freeze to go into an infinite loop, continuously retrying the freeze operation. But nothing ever clears the -EIO except unmount after withdraw, which is impossible if the freeze operation never ends (fails). Instead you get:

[ 6499.767994] gfs2: fsid=dm-32.0: error freezing FS: -5
[ 6499.773058] gfs2: fsid=dm-32.0: retrying...
[ 6500.791957] gfs2: fsid=dm-32.0: error freezing FS: -5
[ 6500.797015] gfs2: fsid=dm-32.0: retrying...

This patch adds a check for -EIO in gfs2_freeze, and if seen, it dequeues the freeze glock, aborts the loop and returns the error. Also, there's no need to pass the freeze holder to function gfs2_lock_fs_check_clean since it's only called in one place and it's a well-known superblock pointer, so this simplifies that.

---
 fs/gfs2/super.c | 18 +++++++++++-------
 1 file changed, 11 insertions(+), 7 deletions(-)
fs/gfs2/super.c +1 -2
index 8154c38e488b..eb1fbd533e6d 100644
@@ -399,8 +399,7 @@ struct lfcc {
  * Returns: errno
  */
 
-static int gfs2_lock_fs_check_clean(struct gfs2_sbd *sdp,
-                                   struct gfs2_holder *freeze_gh)
+static int gfs2_lock_fs_check_clean(struct gfs2_sbd *sdp)
 {
        struct gfs2_inode *ip;
        struct gfs2_jdesc *jd;

fs/gfs2/super.c static int gfs2_lock_fs_check_clean(struct gfs2_sbd *sdp, · line 427

Quoted 5 lines
fs/gfs2/super.c +1 -1
@@ -425,7 +424,7 @@ static int gfs2_lock_fs_check_clean(struct gfs2_sbd *sdp,
        }
 
        error = gfs2_glock_nq_init(sdp->sd_freeze_gl, LM_ST_EXCLUSIVE,
-                                  GL_NOCACHE, freeze_gh);
+                                  GL_NOCACHE, &sdp->sd_freeze_gh);

Missing here:

        if (error)
              goto out;
Quoted 17 lines
fs/gfs2/super.c +2 -2
        list_for_each_entry(jd, &sdp->sd_jindex_list, jd_list) {
                error = gfs2_jdesc_check(jd);
@@ -441,7 +440,7 @@ static int gfs2_lock_fs_check_clean(struct gfs2_sbd *sdp,
        }
 
        if (error)
-               gfs2_glock_dq_uninit(freeze_gh);
+               gfs2_glock_dq_uninit(&sdp->sd_freeze_gh);
 
 out:
        while (!list_empty(&list)) {
@@ -767,15 +766,20 @@ static int gfs2_freeze(struct super_block *sb)
                        goto out;
                }
 
-               error = gfs2_lock_fs_check_clean(sdp, &sdp->sd_freeze_gh);
+               error = gfs2_lock_fs_check_clean(sdp);

fs/gfs2/super.c static int gfs2_freeze(struct super_block *sb) · line 778

Quoted 10 lines
fs/gfs2/super.c +4 -1
                if (!error)
                        break;
 
                if (error == -EBUSY)
                        fs_err(sdp, "waiting for recovery before freeze\n");
-               else
+               else if (error == -EIO) {
+                       fs_err(sdp, "Fatal IO error: cannot freeze gfs2 due "
+                              "to recovery error.\n");
+                       gfs2_glock_dq_uninit(&sdp->sd_freeze_gh);

Instead of this, gfs2_lock_fs_check_clean should make sure it doesn't keep sd_freeze_ghl held when it fails.

fs/gfs2/super.c static int gfs2_freeze(struct super_block *sb) · line 785

Quoted 9 lines
fs/gfs2/super.c +3 -1
+                       goto out;
+               } else {
                        fs_err(sdp, "error freezing FS: %d\n", error);
-
+               }
                fs_err(sdp, "retrying...\n");
                msleep(1000);
        }

Thanks,
Andreas