/* to submit async io_units, to fulfill ordering of flush */
struct work_struct deferred_io_work;
+ /* to disable write back during in degraded mode */
+ struct work_struct disable_writeback_work;
};
/*
r5l_do_submit_io(log, io);
}
+static void r5c_disable_writeback_async(struct work_struct *work)
+{
+ struct r5l_log *log = container_of(work, struct r5l_log,
+ disable_writeback_work);
+ struct mddev *mddev = log->rdev->mddev;
+
+ if (log->r5c_journal_mode == R5C_JOURNAL_MODE_WRITE_THROUGH)
+ return;
+ pr_info("md/raid:%s: Disabling writeback cache for degraded array.\n",
+ mdname(mddev));
+ mddev_suspend(mddev);
+ log->r5c_journal_mode = R5C_JOURNAL_MODE_WRITE_THROUGH;
+ mddev_resume(mddev);
+}
+
static void r5l_submit_current_io(struct r5l_log *log)
{
struct r5l_io_unit *io = log->current_io;
next_checkpoint = r5c_calculate_new_cp(conf);
spin_unlock_irq(&log->io_list_lock);
- BUG_ON(reclaimable < 0);
-
if (reclaimable == 0 || !write_super)
return;
r5c_recovery_rewrite_data_only_stripes(struct r5l_log *log,
struct r5l_recovery_ctx *ctx)
{
- struct stripe_head *sh, *next;
+ struct stripe_head *sh;
struct mddev *mddev = log->rdev->mddev;
struct page *page;
sector_t next_checkpoint = MaxSector;
WARN_ON(list_empty(&ctx->cached_list));
- list_for_each_entry_safe(sh, next, &ctx->cached_list, lru) {
+ list_for_each_entry(sh, &ctx->cached_list, lru) {
struct r5l_meta_block *mb;
int i;
int offset;
ctx->pos = write_pos;
ctx->seq += 1;
next_checkpoint = sh->log_start;
- list_del_init(&sh->lru);
- raid5_release_stripe(sh);
}
log->next_checkpoint = next_checkpoint;
__free_page(page);
return 0;
}
+static void r5c_recovery_flush_data_only_stripes(struct r5l_log *log,
+ struct r5l_recovery_ctx *ctx)
+{
+ struct mddev *mddev = log->rdev->mddev;
+ struct r5conf *conf = mddev->private;
+ struct stripe_head *sh, *next;
+
+ if (ctx->data_only_stripes == 0)
+ return;
+
+ log->r5c_journal_mode = R5C_JOURNAL_MODE_WRITE_BACK;
+
+ list_for_each_entry_safe(sh, next, &ctx->cached_list, lru) {
+ r5c_make_stripe_write_out(sh);
+ set_bit(STRIPE_HANDLE, &sh->state);
+ list_del_init(&sh->lru);
+ raid5_release_stripe(sh);
+ }
+
+ md_wakeup_thread(conf->mddev->thread);
+ /* reuse conf->wait_for_quiescent in recovery */
+ wait_event(conf->wait_for_quiescent,
+ atomic_read(&conf->active_stripes) == 0);
+
+ log->r5c_journal_mode = R5C_JOURNAL_MODE_WRITE_THROUGH;
+}
+
static int r5l_recovery_log(struct r5l_log *log)
{
struct mddev *mddev = log->rdev->mddev;
pos = ctx.pos;
ctx.seq += 10000;
- if (ctx.data_only_stripes == 0) {
- log->next_checkpoint = ctx.pos;
- r5l_log_write_empty_meta_block(log, ctx.pos, ctx.seq++);
- ctx.pos = r5l_ring_add(log, ctx.pos, BLOCK_SECTORS);
- }
if ((ctx.data_only_stripes == 0) && (ctx.data_parity_stripes == 0))
pr_debug("md/raid:%s: starting from clean shutdown\n",
mdname(mddev));
- else {
+ else
pr_debug("md/raid:%s: recovering %d data-only stripes and %d data-parity stripes\n",
mdname(mddev), ctx.data_only_stripes,
ctx.data_parity_stripes);
- if (ctx.data_only_stripes > 0)
- if (r5c_recovery_rewrite_data_only_stripes(log, &ctx)) {
- pr_err("md/raid:%s: failed to rewrite stripes to journal\n",
- mdname(mddev));
- return -EIO;
- }
+ if (ctx.data_only_stripes == 0) {
+ log->next_checkpoint = ctx.pos;
+ r5l_log_write_empty_meta_block(log, ctx.pos, ctx.seq++);
+ ctx.pos = r5l_ring_add(log, ctx.pos, BLOCK_SECTORS);
+ } else if (r5c_recovery_rewrite_data_only_stripes(log, &ctx)) {
+ pr_err("md/raid:%s: failed to rewrite stripes to journal\n",
+ mdname(mddev));
+ return -EIO;
}
log->log_start = ctx.pos;
log->seq = ctx.seq;
log->last_checkpoint = pos;
r5l_write_super(log, pos);
+
+ r5c_recovery_flush_data_only_stripes(log, &ctx);
return 0;
}
val > R5C_JOURNAL_MODE_WRITE_BACK)
return -EINVAL;
+ if (raid5_calc_degraded(conf) > 0 &&
+ val == R5C_JOURNAL_MODE_WRITE_BACK)
+ return -EINVAL;
+
mddev_suspend(mddev);
conf->log->r5c_journal_mode = val;
mddev_resume(mddev);
set_bit(STRIPE_R5C_CACHING, &sh->state);
}
+ /*
+ * When run in degraded mode, array is set to write-through mode.
+ * This check helps drain pending write safely in the transition to
+ * write-through mode.
+ */
+ if (s->failed) {
+ r5c_make_stripe_write_out(sh);
+ return -EAGAIN;
+ }
+
for (i = disks; i--; ) {
dev = &sh->dev[i];
/* if non-overwrite, use writing-out phase */
struct page *p = sh->dev[i].orig_page;
sh->dev[i].orig_page = sh->dev[i].page;
+ clear_bit(R5_OrigPageUPTDODATE, &sh->dev[i].flags);
+
if (!using_disk_info_extra_page)
put_page(p);
}
return ret;
}
+void r5c_update_on_rdev_error(struct mddev *mddev)
+{
+ struct r5conf *conf = mddev->private;
+ struct r5l_log *log = conf->log;
+
+ if (!log)
+ return;
+
+ if (raid5_calc_degraded(conf) > 0 &&
+ conf->log->r5c_journal_mode == R5C_JOURNAL_MODE_WRITE_BACK)
+ schedule_work(&log->disable_writeback_work);
+}
+
int r5l_init_log(struct r5conf *conf, struct md_rdev *rdev)
{
struct request_queue *q = bdev_get_queue(rdev->bdev);
spin_lock_init(&log->no_space_stripes_lock);
INIT_WORK(&log->deferred_io_work, r5l_submit_io_async);
+ INIT_WORK(&log->disable_writeback_work, r5c_disable_writeback_async);
log->r5c_journal_mode = R5C_JOURNAL_MODE_WRITE_THROUGH;
INIT_LIST_HEAD(&log->stripe_in_journal_list);
void r5l_exit_log(struct r5l_log *log)
{
+ flush_work(&log->disable_writeback_work);
md_unregister_thread(&log->reclaim_thread);
mempool_destroy(log->meta_pool);
bioset_free(log->bs);
* of the two sections, and some non-in_sync devices may
* be insync in the section most affected by failed devices.
*/
-static int calc_degraded(struct r5conf *conf)
+int raid5_calc_degraded(struct r5conf *conf)
{
int degraded, degraded2;
int i;
if (conf->mddev->reshape_position == MaxSector)
return conf->mddev->degraded > conf->max_degraded;
- degraded = calc_degraded(conf);
+ degraded = raid5_calc_degraded(conf);
if (degraded > conf->max_degraded)
return 1;
return 0;
if (test_bit(R5_SkipCopy, &sh->dev[i].flags))
WARN_ON(test_bit(R5_UPTODATE, &sh->dev[i].flags));
- sh->dev[i].vec.bv_page = sh->dev[i].page;
+
+ if (!op_is_write(op) &&
+ test_bit(R5_InJournal, &sh->dev[i].flags))
+ /*
+ * issuing read for a page in journal, this
+ * must be preparing for prexor in rmw; read
+ * the data into orig_page
+ */
+ sh->dev[i].vec.bv_page = sh->dev[i].orig_page;
+ else
+ sh->dev[i].vec.bv_page = sh->dev[i].page;
bi->bi_vcnt = 1;
bi->bi_io_vec[0].bv_len = STRIPE_SIZE;
bi->bi_io_vec[0].bv_offset = 0;
} else if (test_bit(R5_ReadNoMerge, &sh->dev[i].flags))
clear_bit(R5_ReadNoMerge, &sh->dev[i].flags);
+ if (test_bit(R5_InJournal, &sh->dev[i].flags))
+ /*
+ * end read for a page in journal, this
+ * must be preparing for prexor in rmw
+ */
+ set_bit(R5_OrigPageUPTDODATE, &sh->dev[i].flags);
+
if (atomic_read(&rdev->read_errors))
atomic_set(&rdev->read_errors, 0);
} else {
spin_lock_irqsave(&conf->device_lock, flags);
clear_bit(In_sync, &rdev->flags);
- mddev->degraded = calc_degraded(conf);
+ mddev->degraded = raid5_calc_degraded(conf);
spin_unlock_irqrestore(&conf->device_lock, flags);
set_bit(MD_RECOVERY_INTR, &mddev->recovery);
bdevname(rdev->bdev, b),
mdname(mddev),
conf->raid_disks - mddev->degraded);
+ r5c_update_on_rdev_error(mddev);
}
/*
return r_sector;
}
+/*
+ * There are cases where we want handle_stripe_dirtying() and
+ * schedule_reconstruction() to delay towrite to some dev of a stripe.
+ *
+ * This function checks whether we want to delay the towrite. Specifically,
+ * we delay the towrite when:
+ *
+ * 1. degraded stripe has a non-overwrite to the missing dev, AND this
+ * stripe has data in journal (for other devices).
+ *
+ * In this case, when reading data for the non-overwrite dev, it is
+ * necessary to handle complex rmw of write back cache (prexor with
+ * orig_page, and xor with page). To keep read path simple, we would
+ * like to flush data in journal to RAID disks first, so complex rmw
+ * is handled in the write patch (handle_stripe_dirtying).
+ *
+ */
+static inline bool delay_towrite(struct r5dev *dev,
+ struct stripe_head_state *s)
+{
+ return !test_bit(R5_OVERWRITE, &dev->flags) &&
+ !test_bit(R5_Insync, &dev->flags) && s->injournal;
+}
+
static void
schedule_reconstruction(struct stripe_head *sh, struct stripe_head_state *s,
int rcw, int expand)
for (i = disks; i--; ) {
struct r5dev *dev = &sh->dev[i];
- if (dev->towrite) {
+ if (dev->towrite && !delay_towrite(dev, s)) {
set_bit(R5_LOCKED, &dev->flags);
set_bit(R5_Wantdrain, &dev->flags);
if (!expand)
return rv;
}
-/* fetch_block - checks the given member device to see if its data needs
- * to be read or computed to satisfy a request.
- *
- * Returns 1 when no more member devices need to be checked, otherwise returns
- * 0 to tell the loop in handle_stripe_fill to continue
- */
-
static int need_this_block(struct stripe_head *sh, struct stripe_head_state *s,
int disk_idx, int disks)
{
return 0;
}
+/* fetch_block - checks the given member device to see if its data needs
+ * to be read or computed to satisfy a request.
+ *
+ * Returns 1 when no more member devices need to be checked, otherwise returns
+ * 0 to tell the loop in handle_stripe_fill to continue
+ */
static int fetch_block(struct stripe_head *sh, struct stripe_head_state *s,
int disk_idx, int disks)
{
* midst of changing due to a write
*/
if (!test_bit(STRIPE_COMPUTE_RUN, &sh->state) && !sh->check_state &&
- !sh->reconstruct_state)
+ !sh->reconstruct_state) {
+
+ /*
+ * For degraded stripe with data in journal, do not handle
+ * read requests yet, instead, flush the stripe to raid
+ * disks first, this avoids handling complex rmw of write
+ * back cache (prexor with orig_page, and then xor with
+ * page) in the read path
+ */
+ if (s->injournal && s->failed) {
+ if (test_bit(STRIPE_R5C_CACHING, &sh->state))
+ r5c_make_stripe_write_out(sh);
+ goto out;
+ }
+
for (i = disks; i--; )
if (fetch_block(sh, s, i, disks))
break;
+ }
+out:
set_bit(STRIPE_HANDLE, &sh->state);
}
break_stripe_batch_list(head_sh, STRIPE_EXPAND_SYNC_FLAGS);
}
+/*
+ * For RMW in write back cache, we need extra page in prexor to store the
+ * old data. This page is stored in dev->orig_page.
+ *
+ * This function checks whether we have data for prexor. The exact logic
+ * is:
+ * R5_UPTODATE && (!R5_InJournal || R5_OrigPageUPTDODATE)
+ */
+static inline bool uptodate_for_rmw(struct r5dev *dev)
+{
+ return (test_bit(R5_UPTODATE, &dev->flags)) &&
+ (!test_bit(R5_InJournal, &dev->flags) ||
+ test_bit(R5_OrigPageUPTDODATE, &dev->flags));
+}
+
static int handle_stripe_dirtying(struct r5conf *conf,
struct stripe_head *sh,
struct stripe_head_state *s,
} else for (i = disks; i--; ) {
/* would I have to read this buffer for read_modify_write */
struct r5dev *dev = &sh->dev[i];
- if ((dev->towrite || i == sh->pd_idx || i == sh->qd_idx ||
+ if (((dev->towrite && !delay_towrite(dev, s)) ||
+ i == sh->pd_idx || i == sh->qd_idx ||
test_bit(R5_InJournal, &dev->flags)) &&
!test_bit(R5_LOCKED, &dev->flags) &&
- !((test_bit(R5_UPTODATE, &dev->flags) &&
- (!test_bit(R5_InJournal, &dev->flags) ||
- dev->page != dev->orig_page)) ||
+ !(uptodate_for_rmw(dev) ||
test_bit(R5_Wantcompute, &dev->flags))) {
if (test_bit(R5_Insync, &dev->flags))
rmw++;
i != sh->pd_idx && i != sh->qd_idx &&
!test_bit(R5_LOCKED, &dev->flags) &&
!(test_bit(R5_UPTODATE, &dev->flags) ||
- test_bit(R5_InJournal, &dev->flags) ||
test_bit(R5_Wantcompute, &dev->flags))) {
if (test_bit(R5_Insync, &dev->flags))
rcw++;
for (i = disks; i--; ) {
struct r5dev *dev = &sh->dev[i];
- if ((dev->towrite ||
+ if (((dev->towrite && !delay_towrite(dev, s)) ||
i == sh->pd_idx || i == sh->qd_idx ||
test_bit(R5_InJournal, &dev->flags)) &&
!test_bit(R5_LOCKED, &dev->flags) &&
- !((test_bit(R5_UPTODATE, &dev->flags) &&
- (!test_bit(R5_InJournal, &dev->flags) ||
- dev->page != dev->orig_page)) ||
+ !(uptodate_for_rmw(dev) ||
test_bit(R5_Wantcompute, &dev->flags)) &&
test_bit(R5_Insync, &dev->flags)) {
if (test_bit(STRIPE_PREREAD_ACTIVE,
i != sh->pd_idx && i != sh->qd_idx &&
!test_bit(R5_LOCKED, &dev->flags) &&
!(test_bit(R5_UPTODATE, &dev->flags) ||
- test_bit(R5_InJournal, &dev->flags) ||
test_bit(R5_Wantcompute, &dev->flags))) {
rcw++;
if (test_bit(R5_Insync, &dev->flags) &&
/*
* 0 for a fully functional array, 1 or 2 for a degraded array.
*/
- mddev->degraded = calc_degraded(conf);
+ mddev->degraded = raid5_calc_degraded(conf);
if (has_failed(conf)) {
pr_crit("md/raid:%s: not enough operational devices (%d/%d failed)\n",
}
}
spin_lock_irqsave(&conf->device_lock, flags);
- mddev->degraded = calc_degraded(conf);
+ mddev->degraded = raid5_calc_degraded(conf);
spin_unlock_irqrestore(&conf->device_lock, flags);
print_raid5_conf(conf);
return count;
* pre and post number of devices.
*/
spin_lock_irqsave(&conf->device_lock, flags);
- mddev->degraded = calc_degraded(conf);
+ mddev->degraded = raid5_calc_degraded(conf);
spin_unlock_irqrestore(&conf->device_lock, flags);
}
mddev->raid_disks = conf->raid_disks;
} else {
int d;
spin_lock_irq(&conf->device_lock);
- mddev->degraded = calc_degraded(conf);
+ mddev->degraded = raid5_calc_degraded(conf);
spin_unlock_irq(&conf->device_lock);
for (d = conf->raid_disks ;
d < conf->raid_disks - mddev->delta_disks;
projects / mirror_ubuntu-zesty-kernel.git / commitdiff