[PATCH 11/12] md: raid5 io requests to raid5_run_ops

From: Dan Williams
Date: Thu Nov 30 2006 - 15:13:25 EST


From: Dan Williams <dan.j.williams@xxxxxxxxx>

generic_make_request may sleep, moving io to raid5_run_ops allows raid5d to
run freely. Since raid5_run_ops is a workqueue other cpus can make forward
progress on other stripes.

Signed-off-by: Dan Williams <dan.j.williams@xxxxxxxxx>
---

drivers/md/raid5.c | 68 ++++++++--------------------------------------------
1 files changed, 10 insertions(+), 58 deletions(-)

diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c
index 8b36611..7d75fbe 100644
--- a/drivers/md/raid5.c
+++ b/drivers/md/raid5.c
@@ -2431,6 +2431,8 @@ #endif
PRINTK("Read_old block %d for r-m-w\n", i);
set_bit(R5_LOCKED, &dev->flags);
set_bit(R5_Wantread, &dev->flags);
+ if (!test_and_set_bit(STRIPE_OP_IO, &sh->ops.pending))
+ sh->ops.count++;
locked++;
} else {
set_bit(STRIPE_DELAYED, &sh->state);
@@ -2451,6 +2453,8 @@ #endif
PRINTK("Read_old block %d for Reconstruct\n", i);
set_bit(R5_LOCKED, &dev->flags);
set_bit(R5_Wantread, &dev->flags);
+ if (!test_and_set_bit(STRIPE_OP_IO, &sh->ops.pending))
+ sh->ops.count++;
locked++;
} else {
set_bit(STRIPE_DELAYED, &sh->state);
@@ -2550,6 +2554,8 @@ #endif

set_bit(R5_LOCKED, &dev->flags);
set_bit(R5_Wantwrite, &dev->flags);
+ if (!test_and_set_bit(STRIPE_OP_IO, &sh->ops.pending))
+ sh->ops.count++;
clear_bit(STRIPE_DEGRADED, &sh->state);
locked++;
set_bit(STRIPE_INSYNC, &sh->state);
@@ -2571,12 +2577,16 @@ #endif
dev = &sh->dev[failed_num];
if (!test_bit(R5_ReWrite, &dev->flags)) {
set_bit(R5_Wantwrite, &dev->flags);
+ if (!test_and_set_bit(STRIPE_OP_IO, &sh->ops.pending))
+ sh->ops.count++;
set_bit(R5_ReWrite, &dev->flags);
set_bit(R5_LOCKED, &dev->flags);
locked++;
} else {
/* let's read it back */
set_bit(R5_Wantread, &dev->flags);
+ if (!test_and_set_bit(STRIPE_OP_IO, &sh->ops.pending))
+ sh->ops.count++;
set_bit(R5_LOCKED, &dev->flags);
locked++;
}
@@ -2682,64 +2692,6 @@ #endif
bi->bi_size = 0;
bi->bi_end_io(bi, bytes, 0);
}
- for (i=disks; i-- ;) {
- int rw;
- struct bio *bi;
- mdk_rdev_t *rdev;
- if (test_and_clear_bit(R5_Wantwrite, &sh->dev[i].flags))
- rw = 1;
- else if (test_and_clear_bit(R5_Wantread, &sh->dev[i].flags))
- rw = 0;
- else
- continue;
-
- bi = &sh->dev[i].req;
-
- bi->bi_rw = rw;
- if (rw)
- bi->bi_end_io = raid5_end_write_request;
- else
- bi->bi_end_io = raid5_end_read_request;
-
- rcu_read_lock();
- rdev = rcu_dereference(conf->disks[i].rdev);
- if (rdev && test_bit(Faulty, &rdev->flags))
- rdev = NULL;
- if (rdev)
- atomic_inc(&rdev->nr_pending);
- rcu_read_unlock();
-
- if (rdev) {
- if (syncing || expanding || expanded)
- md_sync_acct(rdev->bdev, STRIPE_SECTORS);
-
- bi->bi_bdev = rdev->bdev;
- PRINTK("for %llu schedule op %ld on disc %d\n",
- (unsigned long long)sh->sector, bi->bi_rw, i);
- atomic_inc(&sh->count);
- bi->bi_sector = sh->sector + rdev->data_offset;
- bi->bi_flags = 1 << BIO_UPTODATE;
- bi->bi_vcnt = 1;
- bi->bi_max_vecs = 1;
- bi->bi_idx = 0;
- bi->bi_io_vec = &sh->dev[i].vec;
- bi->bi_io_vec[0].bv_len = STRIPE_SIZE;
- 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)
- set_bit(STRIPE_DEGRADED, &sh->state);
- PRINTK("skip op %ld on disc %d for sector %llu\n",
- bi->bi_rw, i, (unsigned long long)sh->sector);
- clear_bit(R5_LOCKED, &sh->dev[i].flags);
- set_bit(STRIPE_HANDLE, &sh->state);
- }
- }
}

static void handle_stripe6(struct stripe_head *sh, struct page *tmp_page)
-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/