diff --git a/drivers/md/md.c b/drivers/md/md.c
index 26ba42a..498b68c 100644
--- a/drivers/md/md.c
+++ b/drivers/md/md.c
@@ -68,6 +68,11 @@ static DECLARE_WAIT_QUEUE_HEAD(resync_wait);
#define MD_BUG(x...) { printk("md: bug in file %s, line %d\n", __FILE__, __LINE__); md_print_devices(); }
/*
+ * Default number of read corrections we'll attempt on an rdev
+ * before ejecting it from the array.
+ */
+#define MD_DEFAULT_MAX_CORRECTED_READ_ERRORS 50
+/*
* Current RAID-1,4,5 parallel reconstruction 'guaranteed speed limit'
* is 1000 KB/sec, so the extra system load does not show up that much.
* Increase it if you want to have more _guaranteed_ speed. Note that@@ -2195,6 +2200,27 @@ static struct rdev_sysfs_entry rdev_errors =
__ATTR(errors, S_IRUGO|S_IWUSR, errors_show, errors_store);
static ssize_t
+read_errors_show(mdk_rdev_t *rdev, char *page)
+{
+ return sprintf(page, "%d\n", atomic_read(&rdev->read_errors));
+}
+
+static ssize_t
+read_errors_store(mdk_rdev_t *rdev, const char *buf, size_t len)
+{
+ char *e;
+ unsigned long n = simple_strtoul(buf, &e, 10);
+ if (*buf && (*e == 0 || *e == '\n')) {
+ atomic_set(&rdev->read_errors, n);
+ return len;
+ }
+ return -EINVAL;
+}
+
+static struct rdev_sysfs_entry rdev_read_errors =
+__ATTR(read_errors, S_IRUGO, read_errors_show, read_errors_store);
+
+static ssize_t
slot_show(mdk_rdev_t *rdev, char *page)
{
if (rdev->raid_disk < 0)@@ -2427,6 +2453,7 @@ static struct attribute *rdev_default_attrs[] = {
&rdev_slot.attr,
&rdev_offset.attr,
&rdev_size.attr,
+ &rdev_read_errors.attr,
NULL,
};
static ssize_t@@ -3144,6 +3171,27 @@ array_state_store(mddev_t *mddev, const char *buf, size_t len)
static struct md_sysfs_entry md_array_state =
__ATTR(array_state, S_IRUGO|S_IWUSR, array_state_show, array_state_store);
+static ssize_t
+max_corrected_read_errors_show(mddev_t *mddev, char *page){
+ return sprintf(page, "%d\n", atomic_read(&mddev->max_corrected_read_errors));
+}
+
+static ssize_t
+max_corrected_read_errors_store(mddev_t *mddev, const char *buf, size_t len)
+{
+ char *e;
+ unsigned long n = simple_strtoul(buf, &e, 10);
+ if (*buf && (*e == 0 || *e == '\n')) {
+ atomic_set(&mddev->max_corrected_read_errors, n);
+ return len;
+ }
+ return -EINVAL;
+}
+
+static struct md_sysfs_entry max_corr_read_errors =
+__ATTR(max_read_errors, S_IRUGO|S_IWUSR, max_corrected_read_errors_show,
+ max_corrected_read_errors_store);
+
static ssize_t
null_show(mddev_t *mddev, char *page)
{@@ -3769,6 +3817,7 @@ static struct attribute *md_default_attrs[] = {
&md_array_state.attr,
&md_reshape_position.attr,
&md_array_size.attr,
+ &max_corr_read_errors.attr,
NULL,
};
@@ -4185,6 +4234,8 @@ static int do_md_run(mddev_t * mddev)
mddev->ro = 0;
atomic_set(&mddev->writes_pending,0);
+ atomic_set(&mddev->max_corrected_read_errors,
+ MD_DEFAULT_MAX_CORRECTED_READ_ERRORS);
mddev->safemode = 0;
mddev->safemode_timer.function = md_safemode_timeout;
mddev->safemode_timer.data = (unsigned long) mddev;
diff --git a/drivers/md/md.h b/drivers/md/md.h
index f184b69..526d1d9 100644
--- a/drivers/md/md.h
+++ b/drivers/md/md.h
@@ -290,6 +290,10 @@ struct mddev_s
* eventually be settable by sysfs.
*/
+ atomic_t max_corrected_read_errors; /* per md device value
+ indicating the maximum number of
+ read retries on an rd */
+
struct list_head all_mddevs;
};
diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c
index 51c4c5c..471b161 100644
--- a/drivers/md/raid10.c
+++ b/drivers/md/raid10.c
@@ -1444,6 +1444,38 @@ static void fix_read_error(conf_t *conf, mddev_t *mddev, r10bio_t *r10_bio)
int sect = 0; /* Offset from r10_bio->sector */
int sectors = r10_bio->sectors;
mdk_rdev_t*rdev;
+ int max_read_errors = atomic_read(&mddev->max_corrected_read_errors);
+
+ rcu_read_lock();
+ {
+ int d = r10_bio->devs[r10_bio->read_slot].devnum;
+ unsigned int cur_read_error_count = 0;
+ char b[BDEVNAME_SIZE];
+
+ rdev = rcu_dereference(conf->mirrors[d].rdev);
+ atomic_inc(&rdev->read_errors);
+ bdevname(rdev->bdev, b);
+
+ cur_read_error_count = atomic_read(&rdev->read_errors);
+ if (test_bit(Faulty, &rdev->flags)) {
+ rcu_read_unlock();
+ /* drive has already been failed, just ignore any
+ more fix_read_error() attempts */
+ return;
+ }
+
+ if (cur_read_error_count > max_read_errors) {
+ rcu_read_unlock();
+ printk (KERN_NOTICE "raid10:%s: Raid device exceeded read_error threshold [cur %d:max %d]\n",
+ b, cur_read_error_count, max_read_errors);
+ printk (KERN_NOTICE "raid10:%s: Failing raid device\n", b);
+ md_error(mddev, conf->mirrors[d].rdev);
+ return;
+ }
+
+ }
+ rcu_read_unlock();
+
while(sectors) {
int s = sectors;
int sl = r10_bio->read_slot;@@ -1488,6 +1520,7 @@ static void fix_read_error(conf_t *conf, mddev_t *mddev, r10bio_t *r10_bio)
/* write it back and re-read */
rcu_read_lock();
while (sl != r10_bio->read_slot) {
+ char b[BDEVNAME_SIZE];
int d;
if (sl==0)
sl = conf->copies;@@ -1503,9 +1536,19 @@ static void fix_read_error(conf_t *conf, mddev_t *mddev, r10bio_t *r10_bio)
r10_bio->devs[sl].addr +
sect + rdev->data_offset,
s<<9, conf->tmppage, WRITE)
- == 0)
+ == 0) {
/* Well, this device is dead */
+ printk(KERN_NOTICE
+ "raid10:%s: read correction write failed"
+ " (%d sectors at %llu on %s)\n",
+ mdname(mddev), s,
+ (unsigned long long)(sect+
+ rdev->data_offset),
+ bdevname(rdev->bdev, b));
+ printk(KERN_NOTICE "raid10:%s: failing drive\n",
+ bdevname(rdev->bdev, b));
md_error(mddev, rdev);
+ }
rdev_dec_pending(rdev, mddev);
rcu_read_lock();
}@@ -1526,10 +1569,20 @@ static void fix_read_error(conf_t *conf, mddev_t *mddev, r10bio_t *r10_bio)
if (sync_page_io(rdev->bdev,
r10_bio->devs[sl].addr +
sect + rdev->data_offset,
- s<<9, conf->tmppage, READ) == 0)
+ s<<9, conf->tmppage, READ) == 0) {
/* Well, this device is dead */
+ printk(KERN_NOTICE
+ "raid10:%s: unable to read back corrected sectors"
+ " (%d sectors at %llu on %s)\n",
+ mdname(mddev), s,
+ (unsigned long long)(sect+
+ rdev->data_offset),
+ bdevname(rdev->bdev, b));
+ printk(KERN_NOTICE "raid10:%s: failing drive\n",
+ bdevname(rdev->bdev, b));
+
md_error(mddev, rdev);
- else
+ } else {
printk(KERN_INFO
"raid10:%s: read error corrected"
" (%d sectors at %llu on %s)\n",@@ -1537,6 +1590,7 @@ static void fix_read_error(conf_t *conf, mddev_t *mddev, r10bio_t *r10_bio)
(unsigned long long)(sect+
rdev->data_offset),
bdevname(rdev->bdev, b));
+ }
rdev_dec_pending(rdev, mddev);
rcu_read_lock();
--
1.5.6.1