md: add proper merge_bvec handling to RAID0 and Linear.

These personalities currently set a max request size of one page
when any member device has a merge_bvec_fn because they don't
bother to call that function.

This causes extra works in splitting and combining requests.

So make the extra effort to call the merge_bvec_fn when it exists
so that we end up with larger requests out the bottom.

Signed-off-by: NeilBrown <neilb@suse.de>

diff --git a/drivers/md/linear.c b/drivers/md/linear.c
index 67940741b19d5f7f2ec9c438cb058580d0437406..b0fcc7d02adb49b37275ccf9caa2c48465e886ad 100644 (file)
--- a/drivers/md/linear.c
+++ b/drivers/md/linear.c
@@ -68,10 +68,19 @@ static int linear_mergeable_bvec(struct request_queue *q,
        struct dev_info *dev0;
        unsigned long maxsectors, bio_sectors = bvm->bi_size >> 9;
        sector_t sector = bvm->bi_sector + get_start_sect(bvm->bi_bdev);
+       int maxbytes = biovec->bv_len;
+       struct request_queue *subq;
 
        rcu_read_lock();
        dev0 = which_dev(mddev, sector);
        maxsectors = dev0->end_sector - sector;
+       subq = bdev_get_queue(dev0->rdev->bdev);
+       if (subq->merge_bvec_fn) {
+               bvm->bi_bdev = dev0->rdev->bdev;
+               bvm->bi_sector -= dev0->end_sector - dev0->rdev->sectors;
+               maxbytes = min(maxbytes, subq->merge_bvec_fn(subq, bvm,
+                                                            biovec));
+       }
        rcu_read_unlock();
 
        if (maxsectors < bio_sectors)
@@ -80,12 +89,12 @@ static int linear_mergeable_bvec(struct request_queue *q,
                maxsectors -= bio_sectors;
 
        if (maxsectors <= (PAGE_SIZE >> 9 ) && bio_sectors == 0)
-               return biovec->bv_len;
-       /* The bytes available at this offset could be really big,
-        * so we cap at 2^31 to avoid overflow */
-       if (maxsectors > (1 << (31-9)))
-               return 1<<31;
-       return maxsectors << 9;
+               return maxbytes;
+
+       if (maxsectors > (maxbytes >> 9))
+               return maxbytes;
+       else
+               return maxsectors << 9;
 }
 
 static int linear_congested(void *data, int bits)
@@ -158,15 +167,6 @@ static struct linear_conf *linear_conf(struct mddev *mddev, int raid_disks)
 
                disk_stack_limits(mddev->gendisk, rdev->bdev,
                                  rdev->data_offset << 9);
-               /* as we don't honour merge_bvec_fn, we must never risk
-                * violating it, so limit max_segments to 1 lying within
-                * a single page.
-                */
-               if (rdev->bdev->bd_disk->queue->merge_bvec_fn) {
-                       blk_queue_max_segments(mddev->queue, 1);
-                       blk_queue_segment_boundary(mddev->queue,
-                                                  PAGE_CACHE_SIZE - 1);
-               }
 
                conf->array_sectors += rdev->sectors;
                cnt++;

diff --git a/drivers/md/raid0.c b/drivers/md/raid0.c
index 7ef5cbf31bb1a5dfc7b7f11593988aaef38d7cf3..6f31f5596e01e0d032f50db71077e07d3af5c3e4 100644 (file)
--- a/drivers/md/raid0.c
+++ b/drivers/md/raid0.c
@@ -188,16 +188,10 @@ static int create_strip_zones(struct mddev *mddev, struct r0conf **private_conf)
 
                disk_stack_limits(mddev->gendisk, rdev1->bdev,
                                  rdev1->data_offset << 9);
-               /* as we don't honour merge_bvec_fn, we must never risk
-                * violating it, so limit ->max_segments to 1, lying within
-                * a single page.
-                */
 
-               if (rdev1->bdev->bd_disk->queue->merge_bvec_fn) {
-                       blk_queue_max_segments(mddev->queue, 1);
-                       blk_queue_segment_boundary(mddev->queue,
-                                                  PAGE_CACHE_SIZE - 1);
-               }
+               if (rdev1->bdev->bd_disk->queue->merge_bvec_fn)
+                       conf->has_merge_bvec = 1;
+
                if (!smallest || (rdev1->sectors < smallest->sectors))
                        smallest = rdev1;
                cnt++;
@@ -290,8 +284,64 @@ abort:
        return err;
 }
 
+/* Find the zone which holds a particular offset
+ * Update *sectorp to be an offset in that zone
+ */
+static struct strip_zone *find_zone(struct r0conf *conf,
+                                   sector_t *sectorp)
+{
+       int i;
+       struct strip_zone *z = conf->strip_zone;
+       sector_t sector = *sectorp;
+
+       for (i = 0; i < conf->nr_strip_zones; i++)
+               if (sector < z[i].zone_end) {
+                       if (i)
+                               *sectorp = sector - z[i-1].zone_end;
+                       return z + i;
+               }
+       BUG();
+}
+
+/*
+ * remaps the bio to the target device. we separate two flows.
+ * power 2 flow and a general flow for the sake of perfromance
+*/
+static struct md_rdev *map_sector(struct mddev *mddev, struct strip_zone *zone,
+                               sector_t sector, sector_t *sector_offset)
+{
+       unsigned int sect_in_chunk;
+       sector_t chunk;
+       struct r0conf *conf = mddev->private;
+       int raid_disks = conf->strip_zone[0].nb_dev;
+       unsigned int chunk_sects = mddev->chunk_sectors;
+
+       if (is_power_of_2(chunk_sects)) {
+               int chunksect_bits = ffz(~chunk_sects);
+               /* find the sector offset inside the chunk */
+               sect_in_chunk  = sector & (chunk_sects - 1);
+               sector >>= chunksect_bits;
+               /* chunk in zone */
+               chunk = *sector_offset;
+               /* quotient is the chunk in real device*/
+               sector_div(chunk, zone->nb_dev << chunksect_bits);
+       } else{
+               sect_in_chunk = sector_div(sector, chunk_sects);
+               chunk = *sector_offset;
+               sector_div(chunk, chunk_sects * zone->nb_dev);
+       }
+       /*
+       *  position the bio over the real device
+       *  real sector = chunk in device + starting of zone
+       *       + the position in the chunk
+       */
+       *sector_offset = (chunk * chunk_sects) + sect_in_chunk;
+       return conf->devlist[(zone - conf->strip_zone)*raid_disks
+                            + sector_div(sector, zone->nb_dev)];
+}
+
 /**
- *     raid0_mergeable_bvec -- tell bio layer if a two requests can be merged
+ *     raid0_mergeable_bvec -- tell bio layer if two requests can be merged
  *     @q: request queue
  *     @bvm: properties of new bio
  *     @biovec: the request that could be merged to it.
@@ -303,10 +353,15 @@ static int raid0_mergeable_bvec(struct request_queue *q,
                                struct bio_vec *biovec)
 {
        struct mddev *mddev = q->queuedata;
+       struct r0conf *conf = mddev->private;
        sector_t sector = bvm->bi_sector + get_start_sect(bvm->bi_bdev);
+       sector_t sector_offset = sector;
        int max;
        unsigned int chunk_sectors = mddev->chunk_sectors;
        unsigned int bio_sectors = bvm->bi_size >> 9;
+       struct strip_zone *zone;
+       struct md_rdev *rdev;
+       struct request_queue *subq;
 
        if (is_power_of_2(chunk_sectors))
                max =  (chunk_sectors - ((sector & (chunk_sectors-1))
@@ -314,10 +369,27 @@ static int raid0_mergeable_bvec(struct request_queue *q,
        else
                max =  (chunk_sectors - (sector_div(sector, chunk_sectors)
                                                + bio_sectors)) << 9;
-       if (max < 0) max = 0; /* bio_add cannot handle a negative return */
+       if (max < 0)
+               max = 0; /* bio_add cannot handle a negative return */
        if (max <= biovec->bv_len && bio_sectors == 0)
                return biovec->bv_len;
-       else 
+       if (max < biovec->bv_len)
+               /* too small already, no need to check further */
+               return max;
+       if (!conf->has_merge_bvec)
+               return max;
+
+       /* May need to check subordinate device */
+       sector = sector_offset;
+       zone = find_zone(mddev->private, &sector_offset);
+       rdev = map_sector(mddev, zone, sector, &sector_offset);
+       subq = bdev_get_queue(rdev->bdev);
+       if (subq->merge_bvec_fn) {
+               bvm->bi_bdev = rdev->bdev;
+               bvm->bi_sector = sector_offset + zone->dev_start +
+                       rdev->data_offset;
+               return min(max, subq->merge_bvec_fn(subq, bvm, biovec));
+       } else
                return max;
 }
 
@@ -397,62 +469,6 @@ static int raid0_stop(struct mddev *mddev)
        return 0;
 }
 
-/* Find the zone which holds a particular offset
- * Update *sectorp to be an offset in that zone
- */
-static struct strip_zone *find_zone(struct r0conf *conf,
-                                   sector_t *sectorp)
-{
-       int i;
-       struct strip_zone *z = conf->strip_zone;
-       sector_t sector = *sectorp;
-
-       for (i = 0; i < conf->nr_strip_zones; i++)
-               if (sector < z[i].zone_end) {
-                       if (i)
-                               *sectorp = sector - z[i-1].zone_end;
-                       return z + i;
-               }
-       BUG();
-}
-
-/*
- * remaps the bio to the target device. we separate two flows.
- * power 2 flow and a general flow for the sake of perfromance
-*/
-static struct md_rdev *map_sector(struct mddev *mddev, struct strip_zone *zone,
-                               sector_t sector, sector_t *sector_offset)
-{
-       unsigned int sect_in_chunk;
-       sector_t chunk;
-       struct r0conf *conf = mddev->private;
-       int raid_disks = conf->strip_zone[0].nb_dev;
-       unsigned int chunk_sects = mddev->chunk_sectors;
-
-       if (is_power_of_2(chunk_sects)) {
-               int chunksect_bits = ffz(~chunk_sects);
-               /* find the sector offset inside the chunk */
-               sect_in_chunk  = sector & (chunk_sects - 1);
-               sector >>= chunksect_bits;
-               /* chunk in zone */
-               chunk = *sector_offset;
-               /* quotient is the chunk in real device*/
-               sector_div(chunk, zone->nb_dev << chunksect_bits);
-       } else{
-               sect_in_chunk = sector_div(sector, chunk_sects);
-               chunk = *sector_offset;
-               sector_div(chunk, chunk_sects * zone->nb_dev);
-       }
-       /*
-       *  position the bio over the real device
-       *  real sector = chunk in device + starting of zone
-       *       + the position in the chunk
-       */
-       *sector_offset = (chunk * chunk_sects) + sect_in_chunk;
-       return conf->devlist[(zone - conf->strip_zone)*raid_disks
-                            + sector_div(sector, zone->nb_dev)];
-}
-
 /*
  * Is io distribute over 1 or more chunks ?
 */
@@ -505,7 +521,7 @@ static void raid0_make_request(struct mddev *mddev, struct bio *bio)
        }
 
        sector_offset = bio->bi_sector;
-       zone =  find_zone(mddev->private, &sector_offset);
+       zone = find_zone(mddev->private, &sector_offset);
        tmp_dev = map_sector(mddev, zone, bio->bi_sector,
                             &sector_offset);
        bio->bi_bdev = tmp_dev->bdev;

diff --git a/drivers/md/raid0.h b/drivers/md/raid0.h
index 0884bba8df4ca90b36ef307b28f759e4455245a7..05539d9c97f06212ad3f436585e6574557c5f962 100644 (file)
--- a/drivers/md/raid0.h
+++ b/drivers/md/raid0.h
@@ -4,13 +4,16 @@
 struct strip_zone {
        sector_t zone_end;      /* Start of the next zone (in sectors) */
        sector_t dev_start;     /* Zone offset in real dev (in sectors) */
-       int nb_dev;             /* # of devices attached to the zone */
+       int      nb_dev;        /* # of devices attached to the zone */
 };
 
 struct r0conf {
-       struct strip_zone *strip_zone;
-       struct md_rdev **devlist; /* lists of rdevs, pointed to by strip_zone->dev */
-       int nr_strip_zones;
+       struct strip_zone       *strip_zone;
+       struct md_rdev          **devlist; /* lists of rdevs, pointed to
+                                           * by strip_zone->dev */
+       int                     nr_strip_zones;
+       int                     has_merge_bvec; /* at least one member has
+                                                * a merge_bvec_fn */
 };
 
 #endif