GFS2: Withdraw for IO errors writing to the journal or statfs

Before this patch, if GFS2 encountered IO errors while writing to
the journal, it would not report the problem, so they would go
unnoticed, sometimes for many hours. Sometimes this would only be
noticed later, when recovery tried to do journal replay and failed
due to invalid metadata at the blocks that resulted in IO errors.

This patch makes GFS2's log daemon check for IO errors. If it
encounters one, it withdraws from the file system and reports
why in dmesg. A similar action is taken when IO errors occur when
writing to the system statfs file.

These errors are also reported back to any callers of fsync, since
that requires the journal to be flushed. Therefore, any IO errors
that would previously go unnoticed are now noticed and the file
system is withdrawn as early as possible, thus preventing further
file system damage.

Also note that this reintroduces superblock variable sd_log_error,
which Christoph removed with commit f729b66fca.

Signed-off-by: Bob Peterson <rpeterso@redhat.com>

diff --git a/fs/gfs2/incore.h b/fs/gfs2/incore.h
index a7b0331c549da73895f9c5ab79e2444588dc2397..0ce0b334f412dc0bd408596a658a683b6d8f3141 100644 (file)
--- a/fs/gfs2/incore.h
+++ b/fs/gfs2/incore.h
@@ -817,6 +817,7 @@ struct gfs2_sbd {
        atomic_t sd_log_in_flight;
        struct bio *sd_log_bio;
        wait_queue_head_t sd_log_flush_wait;
+       int sd_log_error;
 
        atomic_t sd_reserving_log;
        wait_queue_head_t sd_reserving_log_wait;

diff --git a/fs/gfs2/log.c b/fs/gfs2/log.c
index 31585c2d22feaaa0ca7b6bab6e8eaa52cdb46eb7..f72c442314062c4835ecaa3e0b92b538522f759a 100644 (file)
--- a/fs/gfs2/log.c
+++ b/fs/gfs2/log.c
@@ -923,6 +923,15 @@ int gfs2_logd(void *data)
 
        while (!kthread_should_stop()) {
 
+               /* Check for errors writing to the journal */
+               if (sdp->sd_log_error) {
+                       gfs2_lm_withdraw(sdp,
+                                        "GFS2: fsid=%s: error %d: "
+                                        "withdrawing the file system to "
+                                        "prevent further damage.\n",
+                                        sdp->sd_fsname, sdp->sd_log_error);
+               }
+
                did_flush = false;
                if (gfs2_jrnl_flush_reqd(sdp) || t == 0) {
                        gfs2_ail1_empty(sdp);

diff --git a/fs/gfs2/lops.c b/fs/gfs2/lops.c
index 3010f9edd177dffeb3e270515a15e643e37bdd22..7dabbe721dba089a2562e792bae49abf2f393ca2 100644 (file)
--- a/fs/gfs2/lops.c
+++ b/fs/gfs2/lops.c
@@ -207,8 +207,11 @@ static void gfs2_end_log_write(struct bio *bio)
        struct page *page;
        int i;
 
-       if (bio->bi_status)
-               fs_err(sdp, "Error %d writing to log\n", bio->bi_status);
+       if (bio->bi_status) {
+               fs_err(sdp, "Error %d writing to journal, jid=%u\n",
+                      bio->bi_status, sdp->sd_jdesc->jd_jid);
+               wake_up(&sdp->sd_logd_waitq);
+       }
 
        bio_for_each_segment_all(bvec, bio, i) {
                page = bvec->bv_page;

diff --git a/fs/gfs2/quota.c b/fs/gfs2/quota.c
index 739adf105d7f0409649c53bd2248dea5f907bf2d..e647938432bdde6610022e98dadf5e8ad0319f93 100644 (file)
--- a/fs/gfs2/quota.c
+++ b/fs/gfs2/quota.c
@@ -1474,8 +1474,11 @@ static void quotad_error(struct gfs2_sbd *sdp, const char *msg, int error)
 {
        if (error == 0 || error == -EROFS)
                return;
-       if (!test_bit(SDF_SHUTDOWN, &sdp->sd_flags))
+       if (!test_bit(SDF_SHUTDOWN, &sdp->sd_flags)) {
                fs_err(sdp, "gfs2_quotad: %s error %d\n", msg, error);
+               sdp->sd_log_error = error;
+               wake_up(&sdp->sd_logd_waitq);
+       }
 }
 
 static void quotad_check_timeo(struct gfs2_sbd *sdp, const char *msg,

diff --git a/fs/gfs2/super.c b/fs/gfs2/super.c
index a83fe8260d2e2bf4e563ad334da2cd9a3be663f6..769841185ce52f0df9e1c017aa94698d01e84d61 100644 (file)
--- a/fs/gfs2/super.c
+++ b/fs/gfs2/super.c
@@ -944,9 +944,9 @@ static int gfs2_sync_fs(struct super_block *sb, int wait)
        struct gfs2_sbd *sdp = sb->s_fs_info;
 
        gfs2_quota_sync(sb, -1);
-       if (wait && sdp)
+       if (wait)
                gfs2_log_flush(sdp, NULL, NORMAL_FLUSH);
-       return 0;
+       return sdp->sd_log_error;
 }
 
 void gfs2_freeze_func(struct work_struct *work)