From: NeilBrown <neilb@suse.de>
To: Andrew Morton <akpm@osdl.org>
Cc: linux-raid@vger.kernel.org
Subject: [PATCH md 013 of 20] Count corrected read errors per drive.
Date: Mon, 12 Dec 2005 14:15:19 +1100 [thread overview]
Message-ID: <1051212031519.5128@suse.de> (raw)
In-Reply-To: 20051212135705.4561.patches@notabene
Store this total in superblock (As appropriate),
and make it available to userspace via sysfs.
Signed-off-by: Neil Brown <neilb@suse.de>
### Diffstat output
./Documentation/md.txt | 11 +++++++++++
./drivers/md/md.c | 27 ++++++++++++++++++++++++++-
./drivers/md/raid1.c | 2 ++
./drivers/md/raid10.c | 11 ++++++++---
./drivers/md/raid5.c | 3 +++
./drivers/md/raid6main.c | 3 +++
./include/linux/raid/md_k.h | 4 ++++
7 files changed, 57 insertions(+), 4 deletions(-)
diff ./Documentation/md.txt~current~ ./Documentation/md.txt
--- ./Documentation/md.txt~current~ 2005-12-12 11:33:35.000000000 +1100
+++ ./Documentation/md.txt 2005-12-12 11:34:21.000000000 +1100
@@ -222,6 +222,17 @@ Each directory contains:
of being recoverred to
This list make grow in future.
+ errors
+ An approximate count of read errors that have been detected on
+ this device but have not caused the device to be evicted from
+ the array (either because they were corrected or because they
+ happened while the array was read-only). When using version-1
+ metadata, this value persists across restarts of the array.
+
+ This value can be written while assembling an array thus
+ providing an ongoing count for arrays with metadata managed by
+ userspace.
+
An active md device will also contain and entry for each active device
in the array. These are named
diff ./drivers/md/md.c~current~ ./drivers/md/md.c
--- ./drivers/md/md.c~current~ 2005-12-12 11:33:56.000000000 +1100
+++ ./drivers/md/md.c 2005-12-12 11:34:37.000000000 +1100
@@ -1000,6 +1000,7 @@ static int super_1_load(mdk_rdev_t *rdev
}
rdev->preferred_minor = 0xffff;
rdev->data_offset = le64_to_cpu(sb->data_offset);
+ atomic_set(&rdev->corrected_errors, le32_to_cpu(sb->cnt_corrected_read));
rdev->sb_size = le32_to_cpu(sb->max_dev) * 2 + 256;
bmask = queue_hardsect_size(rdev->bdev->bd_disk->queue)-1;
@@ -1139,6 +1140,8 @@ static void super_1_sync(mddev_t *mddev,
else
sb->resync_offset = cpu_to_le64(0);
+ sb->cnt_corrected_read = atomic_read(&rdev->corrected_errors);
+
if (mddev->bitmap && mddev->bitmap_file == NULL) {
sb->bitmap_offset = cpu_to_le32((__u32)mddev->bitmap_offset);
sb->feature_map = cpu_to_le32(MD_FEATURE_BITMAP_OFFSET);
@@ -1592,9 +1595,30 @@ super_show(mdk_rdev_t *rdev, char *page)
}
static struct rdev_sysfs_entry rdev_super = __ATTR_RO(super);
+static ssize_t
+errors_show(mdk_rdev_t *rdev, char *page)
+{
+ return sprintf(page, "%d\n", atomic_read(&rdev->corrected_errors));
+}
+
+static ssize_t
+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->corrected_errors, n);
+ return len;
+ }
+ return -EINVAL;
+}
+static struct rdev_sysfs_entry rdev_errors =
+__ATTR(errors, 0644, errors_show, errors_store);
+
static struct attribute *rdev_default_attrs[] = {
&rdev_state.attr,
&rdev_super.attr,
+ &rdev_errors.attr,
NULL,
};
static ssize_t
@@ -1674,6 +1698,7 @@ static mdk_rdev_t *md_import_device(dev_
rdev->data_offset = 0;
atomic_set(&rdev->nr_pending, 0);
atomic_set(&rdev->read_errors, 0);
+ atomic_set(&rdev->corrected_errors, 0);
size = rdev->bdev->bd_inode->i_size >> BLOCK_SIZE_BITS;
if (!size) {
@@ -4721,7 +4746,7 @@ static int set_ro(const char *val, struc
int num = simple_strtoul(val, &e, 10);
if (*val && (*e == '\0' || *e == '\n')) {
start_readonly = num;
- return 0;;
+ return 0;
}
return -EINVAL;
}
diff ./drivers/md/raid1.c~current~ ./drivers/md/raid1.c
--- ./drivers/md/raid1.c~current~ 2005-12-12 11:33:35.000000000 +1100
+++ ./drivers/md/raid1.c 2005-12-12 11:34:21.000000000 +1100
@@ -1265,6 +1265,7 @@ static void sync_request_write(mddev_t *
if (r1_bio->bios[d]->bi_end_io != end_sync_read)
continue;
rdev = conf->mirrors[d].rdev;
+ atomic_add(s, &rdev->corrected_errors);
if (sync_page_io(rdev->bdev,
sect + rdev->data_offset,
s<<9,
@@ -1463,6 +1464,7 @@ static void raid1d(mddev_t *mddev)
d = conf->raid_disks;
d--;
rdev = conf->mirrors[d].rdev;
+ atomic_add(s, &rdev->corrected_errors);
if (rdev &&
test_bit(In_sync, &rdev->flags)) {
if (sync_page_io(rdev->bdev,
diff ./drivers/md/raid10.c~current~ ./drivers/md/raid10.c
--- ./drivers/md/raid10.c~current~ 2005-12-12 11:33:35.000000000 +1100
+++ ./drivers/md/raid10.c 2005-12-12 11:34:21.000000000 +1100
@@ -1122,9 +1122,13 @@ static int end_sync_read(struct bio *bio
if (test_bit(BIO_UPTODATE, &bio->bi_flags))
set_bit(R10BIO_Uptodate, &r10_bio->state);
- else if (!test_bit(MD_RECOVERY_SYNC, &conf->mddev->recovery))
- md_error(r10_bio->mddev,
- conf->mirrors[d].rdev);
+ else {
+ atomic_add(r10_bio->sectors,
+ &conf->mirrors[d].rdev->corrected_errors);
+ if (!test_bit(MD_RECOVERY_SYNC, &conf->mddev->recovery))
+ md_error(r10_bio->mddev,
+ conf->mirrors[d].rdev);
+ }
/* for reconstruct, we always reschedule after a read.
* for resync, only after all reads
@@ -1430,6 +1434,7 @@ static void raid10d(mddev_t *mddev)
sl--;
d = r10_bio->devs[sl].devnum;
rdev = conf->mirrors[d].rdev;
+ atomic_add(s, &rdev->corrected_errors);
if (rdev &&
test_bit(In_sync, &rdev->flags)) {
if (sync_page_io(rdev->bdev,
diff ./drivers/md/raid5.c~current~ ./drivers/md/raid5.c
--- ./drivers/md/raid5.c~current~ 2005-12-12 11:33:35.000000000 +1100
+++ ./drivers/md/raid5.c 2005-12-12 11:34:21.000000000 +1100
@@ -1400,6 +1400,9 @@ static void handle_stripe(struct stripe_
bi->bi_io_vec[0].bv_offset = 0;
bi->bi_size = STRIPE_SIZE;
bi->bi_next = NULL;
+ if (rw == WRITE &&
+ test_bit(R5_ReWrite, &sh->dev[i].flags))
+ atomic_add(STRIPE_SECTORS, &rdev->corrected_errors);
generic_make_request(bi);
} else {
if (rw == 1)
diff ./drivers/md/raid6main.c~current~ ./drivers/md/raid6main.c
--- ./drivers/md/raid6main.c~current~ 2005-12-12 11:33:35.000000000 +1100
+++ ./drivers/md/raid6main.c 2005-12-12 11:34:21.000000000 +1100
@@ -1562,6 +1562,9 @@ static void handle_stripe(struct stripe_
bi->bi_io_vec[0].bv_offset = 0;
bi->bi_size = STRIPE_SIZE;
bi->bi_next = NULL;
+ if (rw == WRITE &&
+ test_bit(R5_ReWrite, &sh->dev[i].flags))
+ atomic_add(STRIPE_SECTORS, &rdev->corrected_errors);
generic_make_request(bi);
} else {
if (rw == 1)
diff ./include/linux/raid/md_k.h~current~ ./include/linux/raid/md_k.h
--- ./include/linux/raid/md_k.h~current~ 2005-12-12 11:33:35.000000000 +1100
+++ ./include/linux/raid/md_k.h 2005-12-12 11:34:21.000000000 +1100
@@ -95,6 +95,10 @@ struct mdk_rdev_s
atomic_t read_errors; /* number of consecutive read errors that
* we have tried to ignore.
*/
+ atomic_t corrected_errors; /* number of corrected read errors,
+ * for reporting to userspace and storing
+ * in superblock.
+ */
};
struct mddev_s
next prev parent reply other threads:[~2005-12-12 3:15 UTC|newest]
Thread overview: 23+ messages / expand[flat|nested] mbox.gz Atom feed top
2005-12-12 3:10 [PATCH md 000 of 20] Introduction NeilBrown
2005-12-12 3:10 ` [PATCH md 001 of 20] Fix a use-after-free bug in raid1 NeilBrown
2005-12-12 3:10 ` [PATCH md 003 of 20] Define and use safe_put_page for md NeilBrown
2005-12-12 3:10 ` [PATCH md 002 of 20] Use correct size of raid5 stripe cache when measuring how full it is NeilBrown
2005-12-12 3:13 ` [PATCH md 004 of 20] Helper function to match commands written to sysfs files NeilBrown
2005-12-12 3:14 ` [PATCH md 005 of 20] Fix typo in comment NeilBrown
2005-12-12 3:14 ` [PATCH md 006 of 20] Make a couple of names in md.c static NeilBrown
2005-12-12 3:14 ` [PATCH md 007 of 20] Make sure bitmap updates are visible through filesystem NeilBrown
2005-12-12 3:14 ` [PATCH md 008 of 20] Fix rdev->pending counts in raid1 NeilBrown
2005-12-12 3:14 ` [PATCH md 009 of 20] Allow chunk_size to be settable through sysfs NeilBrown
2005-12-12 3:15 ` [PATCH md 010 of 20] Allow md array component size to be accessed and set via sysfs NeilBrown
2005-12-12 3:15 ` [PATCH md 011 of 20] Expose md metadata format in sysfs NeilBrown
2005-12-12 3:15 ` [PATCH md 012 of 20] Allow array level to be set textually via sysfs NeilBrown
2005-12-12 3:15 ` NeilBrown [this message]
2005-12-12 10:07 ` [PATCH md 013 of 20] Count corrected read errors per drive Andrew Morton
2005-12-12 3:15 ` [PATCH md 014 of 20] Allow md/raid_disks to be settable NeilBrown
2005-12-12 3:15 ` [PATCH md 015 of 20] Keep better track of dev/array size when assembling md arrays NeilBrown
2005-12-12 3:15 ` [PATCH md 016 of 20] Expose device slot information via sysfs NeilBrown
2005-12-12 3:15 ` [PATCH md 017 of 20] Export rdev->data_offset " NeilBrown
2005-12-12 3:15 ` [PATCH md 018 of 20] Allow available size of component devices to be set " NeilBrown
2005-12-12 3:15 ` [PATCH md 019 of 20] Support adding new devices to md arrays " NeilBrown
2005-12-12 3:15 ` [PATCH md 020 of 20] Allow sync-speed to be controlled per-device NeilBrown
2005-12-12 11:30 ` Jeff Breidenbach
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=1051212031519.5128@suse.de \
--to=neilb@suse.de \
--cc=akpm@osdl.org \
--cc=linux-raid@vger.kernel.org \
/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.