From ba22dcbf106338a5c46d6979f9b19564faae3d49 Mon Sep 17 00:00:00 2001 From: NeilBrown Date: Tue, 8 Nov 2005 21:39:31 -0800 Subject: [PATCH] md: improvements to raid5 handling of read errors Two refinements to the 'attempt-overwrite-on-read-error' mechanism. 1/ If the array is read-only, don't attempt an over-write. 2/ If there are more than max_nr_stripes read errors on a device with no success, fail the drive. This will make sure a dead drive will be eventually kicked even when we aren't trying to rewrite (which would normally kick a dead drive more quickly. Signed-off-by: Neil Brown Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- drivers/md/raid5.c | 25 +++++++++++++++++-------- 1 file changed, 17 insertions(+), 8 deletions(-) (limited to 'drivers/md/raid5.c') diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c index 08a1620b9f8c..77610b98d4e0 100644 --- a/drivers/md/raid5.c +++ b/drivers/md/raid5.c @@ -420,21 +420,29 @@ static int raid5_end_read_request(struct bio * bi, unsigned int bytes_done, clear_bit(R5_ReadError, &sh->dev[i].flags); clear_bit(R5_ReWrite, &sh->dev[i].flags); } + if (atomic_read(&conf->disks[i].rdev->read_errors)) + atomic_set(&conf->disks[i].rdev->read_errors, 0); } else { + int retry = 0; clear_bit(R5_UPTODATE, &sh->dev[i].flags); - if (conf->mddev->degraded) { + atomic_inc(&conf->disks[i].rdev->read_errors); + if (conf->mddev->degraded) printk("R5: read error not correctable.\n"); - clear_bit(R5_ReadError, &sh->dev[i].flags); - clear_bit(R5_ReWrite, &sh->dev[i].flags); - md_error(conf->mddev, conf->disks[i].rdev); - } else if (test_bit(R5_ReWrite, &sh->dev[i].flags)) { + else if (test_bit(R5_ReWrite, &sh->dev[i].flags)) /* Oh, no!!! */ printk("R5: read error NOT corrected!!\n"); + else if (atomic_read(&conf->disks[i].rdev->read_errors) + > conf->max_nr_stripes) + printk("raid5: Too many read errors, failing device.\n"); + else + retry = 1; + if (retry) + set_bit(R5_ReadError, &sh->dev[i].flags); + else { clear_bit(R5_ReadError, &sh->dev[i].flags); clear_bit(R5_ReWrite, &sh->dev[i].flags); md_error(conf->mddev, conf->disks[i].rdev); - } else - set_bit(R5_ReadError, &sh->dev[i].flags); + } } rdev_dec_pending(conf->disks[i].rdev, conf->mddev); #if 0 @@ -1328,7 +1336,8 @@ static void handle_stripe(struct stripe_head *sh) /* If the failed drive is just a ReadError, then we might need to progress * the repair/check process */ - if (failed == 1 && test_bit(R5_ReadError, &sh->dev[failed_num].flags) + if (failed == 1 && ! conf->mddev->ro && + test_bit(R5_ReadError, &sh->dev[failed_num].flags) && !test_bit(R5_LOCKED, &sh->dev[failed_num].flags) && test_bit(R5_UPTODATE, &sh->dev[failed_num].flags) ) { -- cgit v1.2.2