md/raid6: asynchronous handle_stripe_fill6

Modify handle_stripe_fill6 to work asynchronously by introducing
fetch_block6 as the raid6 analog of fetch_block5 (schedule compute
operations for missing/out-of-sync disks).

[dan.j.williams@intel.com: compute D+Q in one pass]
Signed-off-by: Yuri Tikhonov <yur@emcraft.com>
Signed-off-by: Ilya Yanok <yanok@emcraft.com>
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
This commit is contained in:
Yuri Tikhonov 2009-08-29 19:13:12 -07:00 committed by Dan Williams
parent c0f7bddbe6
commit 5599becca4

View File

@ -2520,61 +2520,104 @@ static void handle_stripe_fill5(struct stripe_head *sh,
set_bit(STRIPE_HANDLE, &sh->state);
}
/* fetch_block6 - 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_fill6 to continue
*/
static int fetch_block6(struct stripe_head *sh, struct stripe_head_state *s,
struct r6_state *r6s, int disk_idx, int disks)
{
struct r5dev *dev = &sh->dev[disk_idx];
struct r5dev *fdev[2] = { &sh->dev[r6s->failed_num[0]],
&sh->dev[r6s->failed_num[1]] };
if (!test_bit(R5_LOCKED, &dev->flags) &&
!test_bit(R5_UPTODATE, &dev->flags) &&
(dev->toread ||
(dev->towrite && !test_bit(R5_OVERWRITE, &dev->flags)) ||
s->syncing || s->expanding ||
(s->failed >= 1 &&
(fdev[0]->toread || s->to_write)) ||
(s->failed >= 2 &&
(fdev[1]->toread || s->to_write)))) {
/* we would like to get this block, possibly by computing it,
* otherwise read it if the backing disk is insync
*/
BUG_ON(test_bit(R5_Wantcompute, &dev->flags));
BUG_ON(test_bit(R5_Wantread, &dev->flags));
if ((s->uptodate == disks - 1) &&
(s->failed && (disk_idx == r6s->failed_num[0] ||
disk_idx == r6s->failed_num[1]))) {
/* have disk failed, and we're requested to fetch it;
* do compute it
*/
pr_debug("Computing stripe %llu block %d\n",
(unsigned long long)sh->sector, disk_idx);
set_bit(STRIPE_COMPUTE_RUN, &sh->state);
set_bit(STRIPE_OP_COMPUTE_BLK, &s->ops_request);
set_bit(R5_Wantcompute, &dev->flags);
sh->ops.target = disk_idx;
sh->ops.target2 = -1; /* no 2nd target */
s->req_compute = 1;
s->uptodate++;
return 1;
} else if (s->uptodate == disks-2 && s->failed >= 2) {
/* Computing 2-failure is *very* expensive; only
* do it if failed >= 2
*/
int other;
for (other = disks; other--; ) {
if (other == disk_idx)
continue;
if (!test_bit(R5_UPTODATE,
&sh->dev[other].flags))
break;
}
BUG_ON(other < 0);
pr_debug("Computing stripe %llu blocks %d,%d\n",
(unsigned long long)sh->sector,
disk_idx, other);
set_bit(STRIPE_COMPUTE_RUN, &sh->state);
set_bit(STRIPE_OP_COMPUTE_BLK, &s->ops_request);
set_bit(R5_Wantcompute, &sh->dev[disk_idx].flags);
set_bit(R5_Wantcompute, &sh->dev[other].flags);
sh->ops.target = disk_idx;
sh->ops.target2 = other;
s->uptodate += 2;
s->req_compute = 1;
return 1;
} else if (test_bit(R5_Insync, &dev->flags)) {
set_bit(R5_LOCKED, &dev->flags);
set_bit(R5_Wantread, &dev->flags);
s->locked++;
pr_debug("Reading block %d (sync=%d)\n",
disk_idx, s->syncing);
}
}
return 0;
}
/**
* handle_stripe_fill6 - read or compute data to satisfy pending requests.
*/
static void handle_stripe_fill6(struct stripe_head *sh,
struct stripe_head_state *s, struct r6_state *r6s,
int disks)
{
int i;
for (i = disks; i--; ) {
struct r5dev *dev = &sh->dev[i];
if (!test_bit(R5_LOCKED, &dev->flags) &&
!test_bit(R5_UPTODATE, &dev->flags) &&
(dev->toread || (dev->towrite &&
!test_bit(R5_OVERWRITE, &dev->flags)) ||
s->syncing || s->expanding ||
(s->failed >= 1 &&
(sh->dev[r6s->failed_num[0]].toread ||
s->to_write)) ||
(s->failed >= 2 &&
(sh->dev[r6s->failed_num[1]].toread ||
s->to_write)))) {
/* we would like to get this block, possibly
* by computing it, but we might not be able to
*/
if ((s->uptodate == disks - 1) &&
(s->failed && (i == r6s->failed_num[0] ||
i == r6s->failed_num[1]))) {
pr_debug("Computing stripe %llu block %d\n",
(unsigned long long)sh->sector, i);
compute_block_1(sh, i, 0);
s->uptodate++;
} else if ( s->uptodate == disks-2 && s->failed >= 2 ) {
/* Computing 2-failure is *very* expensive; only
* do it if failed >= 2
*/
int other;
for (other = disks; other--; ) {
if (other == i)
continue;
if (!test_bit(R5_UPTODATE,
&sh->dev[other].flags))
break;
}
BUG_ON(other < 0);
pr_debug("Computing stripe %llu blocks %d,%d\n",
(unsigned long long)sh->sector,
i, other);
compute_block_2(sh, i, other);
s->uptodate += 2;
} else if (test_bit(R5_Insync, &dev->flags)) {
set_bit(R5_LOCKED, &dev->flags);
set_bit(R5_Wantread, &dev->flags);
s->locked++;
pr_debug("Reading block %d (sync=%d)\n",
i, s->syncing);
}
}
}
/* look for blocks to read/compute, skip this if a compute
* is already in flight, or if the stripe contents are in the
* midst of changing due to a write
*/
if (!test_bit(STRIPE_COMPUTE_RUN, &sh->state) && !sh->check_state &&
!sh->reconstruct_state)
for (i = disks; i--; )
if (fetch_block6(sh, s, r6s, i, disks))
break;
set_bit(STRIPE_HANDLE, &sh->state);
}