X-Git-Url: http://pilppa.org/gitweb/gitweb.cgi?a=blobdiff_plain;f=drivers%2Fmd%2Fraid10.c;h=a9401c017e3588f076411d83046c84b27495eab8;hb=f30c53a873d0d227493197064b8886af2d57bbd6;hp=7f636283a1ba3dfcb78aa52f925fbc65fc9525a7;hpb=71bc7bf045262e82c645cad48fd56dd17e75344e;p=linux-2.6-omap-h63xx.git diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c index 7f636283a1b..a9401c017e3 100644 --- a/drivers/md/raid10.c +++ b/drivers/md/raid10.c @@ -648,6 +648,26 @@ static int raid10_issue_flush(request_queue_t *q, struct gendisk *disk, return ret; } +static int raid10_congested(void *data, int bits) +{ + mddev_t *mddev = data; + conf_t *conf = mddev_to_conf(mddev); + int i, ret = 0; + + rcu_read_lock(); + for (i = 0; i < mddev->raid_disks && ret == 0; i++) { + mdk_rdev_t *rdev = rcu_dereference(conf->mirrors[i].rdev); + if (rdev && !test_bit(Faulty, &rdev->flags)) { + request_queue_t *q = bdev_get_queue(rdev->bdev); + + ret |= bdi_congested(&q->backing_dev_info, bits); + } + } + rcu_read_unlock(); + return ret; +} + + /* Barriers.... * Sometimes we need to suspend IO while we do something else, * either some resync/recovery, or reconfigure the array. @@ -762,6 +782,7 @@ static int make_request(request_queue_t *q, struct bio * bio) int i; int chunk_sects = conf->chunk_mask + 1; const int rw = bio_data_dir(bio); + const int do_sync = bio_sync(bio); struct bio_list bl; unsigned long flags; @@ -843,7 +864,7 @@ static int make_request(request_queue_t *q, struct bio * bio) mirror->rdev->data_offset; read_bio->bi_bdev = mirror->rdev->bdev; read_bio->bi_end_io = raid10_end_read_request; - read_bio->bi_rw = READ; + read_bio->bi_rw = READ | do_sync; read_bio->bi_private = r10_bio; generic_make_request(read_bio); @@ -889,7 +910,7 @@ static int make_request(request_queue_t *q, struct bio * bio) conf->mirrors[d].rdev->data_offset; mbio->bi_bdev = conf->mirrors[d].rdev->bdev; mbio->bi_end_io = raid10_end_write_request; - mbio->bi_rw = WRITE; + mbio->bi_rw = WRITE | do_sync; mbio->bi_private = r10_bio; atomic_inc(&r10_bio->remaining); @@ -902,6 +923,9 @@ static int make_request(request_queue_t *q, struct bio * bio) blk_plug_device(mddev->queue); spin_unlock_irqrestore(&conf->device_lock, flags); + if (do_sync) + md_wakeup_thread(mddev->thread); + return 0; } @@ -921,7 +945,7 @@ static void status(struct seq_file *seq, mddev_t *mddev) seq_printf(seq, " %d far-copies", conf->far_copies); } seq_printf(seq, " [%d/%d] [", conf->raid_disks, - conf->working_disks); + conf->raid_disks - mddev->degraded); for (i = 0; i < conf->raid_disks; i++) seq_printf(seq, "%s", conf->mirrors[i].rdev && @@ -941,7 +965,7 @@ static void error(mddev_t *mddev, mdk_rdev_t *rdev) * else mark the drive as failed */ if (test_bit(In_sync, &rdev->flags) - && conf->working_disks == 1) + && conf->raid_disks-mddev->degraded == 1) /* * Don't fail the drive, just return an IO error. * The test should really be more sophisticated than @@ -950,20 +974,21 @@ static void error(mddev_t *mddev, mdk_rdev_t *rdev) * really dead" tests... */ return; - if (test_bit(In_sync, &rdev->flags)) { + if (test_and_clear_bit(In_sync, &rdev->flags)) { + unsigned long flags; + spin_lock_irqsave(&conf->device_lock, flags); mddev->degraded++; - conf->working_disks--; + spin_unlock_irqrestore(&conf->device_lock, flags); /* * if recovery is running, make sure it aborts. */ set_bit(MD_RECOVERY_ERR, &mddev->recovery); } - clear_bit(In_sync, &rdev->flags); set_bit(Faulty, &rdev->flags); - mddev->sb_dirty = 1; + set_bit(MD_CHANGE_DEVS, &mddev->flags); printk(KERN_ALERT "raid10: Disk failure on %s, disabling device. \n" " Operation continuing on %d devices\n", - bdevname(rdev->bdev,b), conf->working_disks); + bdevname(rdev->bdev,b), conf->raid_disks - mddev->degraded); } static void print_conf(conf_t *conf) @@ -976,7 +1001,7 @@ static void print_conf(conf_t *conf) printk("(!conf)\n"); return; } - printk(" --- wd:%d rd:%d\n", conf->working_disks, + printk(" --- wd:%d rd:%d\n", conf->raid_disks - conf->mddev->degraded, conf->raid_disks); for (i = 0; i < conf->raid_disks; i++) { @@ -1034,10 +1059,11 @@ static int raid10_spare_active(mddev_t *mddev) tmp = conf->mirrors + i; if (tmp->rdev && !test_bit(Faulty, &tmp->rdev->flags) - && !test_bit(In_sync, &tmp->rdev->flags)) { - conf->working_disks++; + && !test_and_set_bit(In_sync, &tmp->rdev->flags)) { + unsigned long flags; + spin_lock_irqsave(&conf->device_lock, flags); mddev->degraded--; - set_bit(In_sync, &tmp->rdev->flags); + spin_unlock_irqrestore(&conf->device_lock, flags); } } @@ -1350,9 +1376,119 @@ static void recovery_request_write(mddev_t *mddev, r10bio_t *r10_bio) * * 1. Retries failed read operations on working mirrors. * 2. Updates the raid superblock when problems encounter. - * 3. Performs writes following reads for array syncronising. + * 3. Performs writes following reads for array synchronising. */ +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; + while(sectors) { + int s = sectors; + int sl = r10_bio->read_slot; + int success = 0; + int start; + + if (s > (PAGE_SIZE>>9)) + s = PAGE_SIZE >> 9; + + rcu_read_lock(); + do { + int d = r10_bio->devs[sl].devnum; + rdev = rcu_dereference(conf->mirrors[d].rdev); + if (rdev && + test_bit(In_sync, &rdev->flags)) { + atomic_inc(&rdev->nr_pending); + rcu_read_unlock(); + success = sync_page_io(rdev->bdev, + r10_bio->devs[sl].addr + + sect + rdev->data_offset, + s<<9, + conf->tmppage, READ); + rdev_dec_pending(rdev, mddev); + rcu_read_lock(); + if (success) + break; + } + sl++; + if (sl == conf->copies) + sl = 0; + } while (!success && sl != r10_bio->read_slot); + rcu_read_unlock(); + + if (!success) { + /* Cannot read from anywhere -- bye bye array */ + int dn = r10_bio->devs[r10_bio->read_slot].devnum; + md_error(mddev, conf->mirrors[dn].rdev); + break; + } + + start = sl; + /* write it back and re-read */ + rcu_read_lock(); + while (sl != r10_bio->read_slot) { + int d; + if (sl==0) + sl = conf->copies; + sl--; + d = r10_bio->devs[sl].devnum; + rdev = rcu_dereference(conf->mirrors[d].rdev); + if (rdev && + test_bit(In_sync, &rdev->flags)) { + atomic_inc(&rdev->nr_pending); + rcu_read_unlock(); + atomic_add(s, &rdev->corrected_errors); + if (sync_page_io(rdev->bdev, + r10_bio->devs[sl].addr + + sect + rdev->data_offset, + s<<9, conf->tmppage, WRITE) + == 0) + /* Well, this device is dead */ + md_error(mddev, rdev); + rdev_dec_pending(rdev, mddev); + rcu_read_lock(); + } + } + sl = start; + while (sl != r10_bio->read_slot) { + int d; + if (sl==0) + sl = conf->copies; + sl--; + d = r10_bio->devs[sl].devnum; + rdev = rcu_dereference(conf->mirrors[d].rdev); + if (rdev && + test_bit(In_sync, &rdev->flags)) { + char b[BDEVNAME_SIZE]; + atomic_inc(&rdev->nr_pending); + rcu_read_unlock(); + if (sync_page_io(rdev->bdev, + r10_bio->devs[sl].addr + + sect + rdev->data_offset, + s<<9, conf->tmppage, READ) == 0) + /* Well, this device is dead */ + md_error(mddev, rdev); + else + printk(KERN_INFO + "raid10:%s: read error corrected" + " (%d sectors at %llu on %s)\n", + mdname(mddev), s, + (unsigned long long)(sect+ + rdev->data_offset), + bdevname(rdev->bdev, b)); + + rdev_dec_pending(rdev, mddev); + rcu_read_lock(); + } + } + rcu_read_unlock(); + + sectors -= s; + sect += s; + } +} + static void raid10d(mddev_t *mddev) { r10bio_t *r10_bio; @@ -1413,101 +1549,12 @@ static void raid10d(mddev_t *mddev) * This is all done synchronously while the array is * frozen. */ - int sect = 0; /* Offset from r10_bio->sector */ - int sectors = r10_bio->sectors; - freeze_array(conf); - if (mddev->ro == 0) while(sectors) { - int s = sectors; - int sl = r10_bio->read_slot; - int success = 0; - - if (s > (PAGE_SIZE>>9)) - s = PAGE_SIZE >> 9; - - rcu_read_lock(); - do { - int d = r10_bio->devs[sl].devnum; - rdev = rcu_dereference(conf->mirrors[d].rdev); - if (rdev && - test_bit(In_sync, &rdev->flags)) { - atomic_inc(&rdev->nr_pending); - rcu_read_unlock(); - success = sync_page_io(rdev->bdev, - r10_bio->devs[sl].addr + - sect + rdev->data_offset, - s<<9, - conf->tmppage, READ); - rdev_dec_pending(rdev, mddev); - rcu_read_lock(); - if (success) - break; - } - sl++; - if (sl == conf->copies) - sl = 0; - } while (!success && sl != r10_bio->read_slot); - rcu_read_unlock(); - - if (success) { - int start = sl; - /* write it back and re-read */ - rcu_read_lock(); - while (sl != r10_bio->read_slot) { - int d; - if (sl==0) - sl = conf->copies; - sl--; - d = r10_bio->devs[sl].devnum; - rdev = rcu_dereference(conf->mirrors[d].rdev); - if (rdev && - test_bit(In_sync, &rdev->flags)) { - atomic_inc(&rdev->nr_pending); - rcu_read_unlock(); - atomic_add(s, &rdev->corrected_errors); - if (sync_page_io(rdev->bdev, - r10_bio->devs[sl].addr + - sect + rdev->data_offset, - s<<9, conf->tmppage, WRITE) == 0) - /* Well, this device is dead */ - md_error(mddev, rdev); - rdev_dec_pending(rdev, mddev); - rcu_read_lock(); - } - } - sl = start; - while (sl != r10_bio->read_slot) { - int d; - if (sl==0) - sl = conf->copies; - sl--; - d = r10_bio->devs[sl].devnum; - rdev = rcu_dereference(conf->mirrors[d].rdev); - if (rdev && - test_bit(In_sync, &rdev->flags)) { - atomic_inc(&rdev->nr_pending); - rcu_read_unlock(); - if (sync_page_io(rdev->bdev, - r10_bio->devs[sl].addr + - sect + rdev->data_offset, - s<<9, conf->tmppage, READ) == 0) - /* Well, this device is dead */ - md_error(mddev, rdev); - rdev_dec_pending(rdev, mddev); - rcu_read_lock(); - } - } - rcu_read_unlock(); - } else { - /* Cannot read from anywhere -- bye bye array */ - md_error(mddev, conf->mirrors[r10_bio->devs[r10_bio->read_slot].devnum].rdev); - break; - } - sectors -= s; - sect += s; + if (mddev->ro == 0) { + freeze_array(conf); + fix_read_error(conf, mddev, r10_bio); + unfreeze_array(conf); } - unfreeze_array(conf); - bio = r10_bio->devs[r10_bio->read_slot].bio; r10_bio->devs[r10_bio->read_slot].bio = mddev->ro ? IO_BLOCKED : NULL; @@ -1520,6 +1567,7 @@ static void raid10d(mddev_t *mddev) (unsigned long long)r10_bio->sector); raid_end_bio_io(r10_bio); } else { + const int do_sync = bio_sync(r10_bio->master_bio); rdev = conf->mirrors[mirror].rdev; if (printk_ratelimit()) printk(KERN_ERR "raid10: %s: redirecting sector %llu to" @@ -1531,7 +1579,7 @@ static void raid10d(mddev_t *mddev) bio->bi_sector = r10_bio->devs[r10_bio->read_slot].addr + rdev->data_offset; bio->bi_bdev = rdev->bdev; - bio->bi_rw = READ; + bio->bi_rw = READ | do_sync; bio->bi_private = r10_bio; bio->bi_end_io = raid10_end_read_request; unplug = 1; @@ -1742,7 +1790,7 @@ static sector_t sync_request(mddev_t *mddev, sector_t sector_nr, int *skipped, i biolist = bio; bio->bi_private = r10_bio; bio->bi_end_io = end_sync_read; - bio->bi_rw = 0; + bio->bi_rw = READ; bio->bi_sector = r10_bio->devs[j].addr + conf->mirrors[d].rdev->data_offset; bio->bi_bdev = conf->mirrors[d].rdev->bdev; @@ -1758,7 +1806,7 @@ static sector_t sync_request(mddev_t *mddev, sector_t sector_nr, int *skipped, i biolist = bio; bio->bi_private = r10_bio; bio->bi_end_io = end_sync_write; - bio->bi_rw = 1; + bio->bi_rw = WRITE; bio->bi_sector = r10_bio->devs[k].addr + conf->mirrors[i].rdev->data_offset; bio->bi_bdev = conf->mirrors[i].rdev->bdev; @@ -1827,7 +1875,7 @@ static sector_t sync_request(mddev_t *mddev, sector_t sector_nr, int *skipped, i biolist = bio; bio->bi_private = r10_bio; bio->bi_end_io = end_sync_read; - bio->bi_rw = 0; + bio->bi_rw = READ; bio->bi_sector = r10_bio->devs[i].addr + conf->mirrors[d].rdev->data_offset; bio->bi_bdev = conf->mirrors[d].rdev->bdev; @@ -2014,8 +2062,6 @@ static int run(mddev_t *mddev) mddev->queue->max_sectors = (PAGE_SIZE>>9); disk->head_position = 0; - if (!test_bit(Faulty, &rdev->flags) && test_bit(In_sync, &rdev->flags)) - conf->working_disks++; } conf->raid_disks = mddev->raid_disks; conf->mddev = mddev; @@ -2038,7 +2084,7 @@ static int run(mddev_t *mddev) disk = conf->mirrors + i; if (!disk->rdev || - !test_bit(In_sync, &rdev->flags)) { + !test_bit(In_sync, &disk->rdev->flags)) { disk->head_position = 0; mddev->degraded++; } @@ -2073,6 +2119,8 @@ static int run(mddev_t *mddev) mddev->queue->unplug_fn = raid10_unplug; mddev->queue->issue_flush_fn = raid10_issue_flush; + mddev->queue->backing_dev_info.congested_fn = raid10_congested; + mddev->queue->backing_dev_info.congested_data = mddev; /* Calculate max read-ahead size. * We need to readahead at least twice a whole stripe....