mdk_rdev_t **devlist = conf->devlist;
int i, ret = 0;
+ if (mddev_congested(mddev, bits))
+ return 1;
+
for (i = 0; i < mddev->raid_disks && !ret ; i++) {
struct request_queue *q = bdev_get_queue(devlist[i]->bdev);
return ret;
}
+/*
+ * inform the user of the raid configuration
+*/
+static void dump_zones(mddev_t *mddev)
+{
+ int j, k, h;
+ sector_t zone_size = 0;
+ sector_t zone_start = 0;
+ char b[BDEVNAME_SIZE];
+ raid0_conf_t *conf = mddev->private;
+ printk(KERN_INFO "******* %s configuration *********\n",
+ mdname(mddev));
+ h = 0;
+ for (j = 0; j < conf->nr_strip_zones; j++) {
+ printk(KERN_INFO "zone%d=[", j);
+ for (k = 0; k < conf->strip_zone[j].nb_dev; k++)
+ printk("%s/",
+ bdevname(conf->devlist[j*mddev->raid_disks
+ + k]->bdev, b));
+ printk("]\n");
+
+ zone_size = conf->strip_zone[j].zone_end - zone_start;
+ printk(KERN_INFO " zone offset=%llukb "
+ "device offset=%llukb size=%llukb\n",
+ (unsigned long long)zone_start>>1,
+ (unsigned long long)conf->strip_zone[j].dev_start>>1,
+ (unsigned long long)zone_size>>1);
+ zone_start = conf->strip_zone[j].zone_end;
+ }
+ printk(KERN_INFO "**********************************\n\n");
+}
+
static int create_strip_zones(mddev_t *mddev)
{
- int i, c, j, err;
+ int i, c, err;
sector_t curr_zone_end, sectors;
mdk_rdev_t *smallest, *rdev1, *rdev2, *rdev, **dev;
struct strip_zone *zone;
printk(KERN_INFO "raid0: looking at %s\n",
bdevname(rdev1->bdev,b));
c = 0;
+
+ /* round size to chunk_size */
+ sectors = rdev1->sectors;
+ sector_div(sectors, mddev->chunk_sectors);
+ rdev1->sectors = sectors * mddev->chunk_sectors;
+
list_for_each_entry(rdev2, &mddev->disks, same_set) {
printk(KERN_INFO "raid0: comparing %s(%llu)",
bdevname(rdev1->bdev,b),
}
dev[j] = rdev1;
- blk_queue_stack_limits(mddev->queue,
- rdev1->bdev->bd_disk->queue);
+ 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_sector to one PAGE, as
* a one page request is never in violation.
/* now do the other zones */
for (i = 1; i < conf->nr_strip_zones; i++)
{
+ int j;
+
zone = conf->strip_zone + i;
dev = conf->devlist + i * mddev->raid_disks;
c = 0;
for (j=0; j<cnt; j++) {
- char b[BDEVNAME_SIZE];
rdev = conf->devlist[j];
printk(KERN_INFO "raid0: checking %s ...",
bdevname(rdev->bdev, b));
mddev->queue->backing_dev_info.congested_fn = raid0_congested;
mddev->queue->backing_dev_info.congested_data = mddev;
+ /*
+ * now since we have the hard sector sizes, we can make sure
+ * chunk size is a multiple of that sector size
+ */
+ if ((mddev->chunk_sectors << 9) % queue_logical_block_size(mddev->queue)) {
+ printk(KERN_ERR "%s chunk_size of %d not valid\n",
+ mdname(mddev),
+ mddev->chunk_sectors << 9);
+ goto abort;
+ }
+
+ blk_queue_io_min(mddev->queue, mddev->chunk_sectors << 9);
+ blk_queue_io_opt(mddev->queue,
+ (mddev->chunk_sectors << 9) * mddev->raid_disks);
+
printk(KERN_INFO "raid0: done.\n");
mddev->private = conf;
return 0;
mddev_t *mddev = q->queuedata;
sector_t sector = bvm->bi_sector + get_start_sect(bvm->bi_bdev);
int max;
- unsigned int chunk_sectors = mddev->chunk_size >> 9;
+ unsigned int chunk_sectors = mddev->chunk_sectors;
unsigned int bio_sectors = bvm->bi_size >> 9;
- max = (chunk_sectors - ((sector & (chunk_sectors - 1)) + bio_sectors)) << 9;
+ if (is_power_of_2(chunk_sectors))
+ max = (chunk_sectors - ((sector & (chunk_sectors-1))
+ + bio_sectors)) << 9;
+ 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 <= biovec->bv_len && bio_sectors == 0)
return biovec->bv_len;
{
int ret;
- if (mddev->chunk_size == 0) {
- printk(KERN_ERR "md/raid0: non-zero chunk size required.\n");
+ if (mddev->chunk_sectors == 0) {
+ printk(KERN_ERR "md/raid0: chunk size must be set.\n");
return -EINVAL;
}
- blk_queue_max_sectors(mddev->queue, mddev->chunk_size >> 9);
+ if (md_check_no_bitmap(mddev))
+ return -EINVAL;
+ blk_queue_max_sectors(mddev->queue, mddev->chunk_sectors);
mddev->queue->queue_lock = &mddev->queue->__queue_lock;
ret = create_strip_zones(mddev);
* chunksize should be used in that case.
*/
{
- int stripe = mddev->raid_disks * mddev->chunk_size / PAGE_SIZE;
+ int stripe = mddev->raid_disks *
+ (mddev->chunk_sectors << 9) / PAGE_SIZE;
if (mddev->queue->backing_dev_info.ra_pages < 2* stripe)
mddev->queue->backing_dev_info.ra_pages = 2* stripe;
}
blk_queue_merge_bvec(mddev->queue, raid0_mergeable_bvec);
+ dump_zones(mddev);
+ md_integrity_register(mddev);
return 0;
}
BUG();
}
-static int raid0_make_request (struct request_queue *q, struct bio *bio)
+/*
+ * remaps the bio to the target device. we separate two flows.
+ * power 2 flow and a general flow for the sake of perfromance
+*/
+static mdk_rdev_t *map_sector(mddev_t *mddev, struct strip_zone *zone,
+ sector_t sector, sector_t *sector_offset)
{
- mddev_t *mddev = q->queuedata;
- unsigned int sect_in_chunk, chunksect_bits, chunk_sects;
+ unsigned int sect_in_chunk;
+ sector_t chunk;
raid0_conf_t *conf = mddev->private;
+ 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)*mddev->raid_disks
+ + sector_div(sector, zone->nb_dev)];
+}
+
+/*
+ * Is io distribute over 1 or more chunks ?
+*/
+static inline int is_io_in_chunk_boundary(mddev_t *mddev,
+ unsigned int chunk_sects, struct bio *bio)
+{
+ if (likely(is_power_of_2(chunk_sects))) {
+ return chunk_sects >= ((bio->bi_sector & (chunk_sects-1))
+ + (bio->bi_size >> 9));
+ } else{
+ sector_t sector = bio->bi_sector;
+ return chunk_sects >= (sector_div(sector, chunk_sects)
+ + (bio->bi_size >> 9));
+ }
+}
+
+static int raid0_make_request(struct request_queue *q, struct bio *bio)
+{
+ mddev_t *mddev = q->queuedata;
+ unsigned int chunk_sects;
+ sector_t sector_offset;
struct strip_zone *zone;
mdk_rdev_t *tmp_dev;
- sector_t chunk;
- sector_t sector, rsect, sector_offset;
const int rw = bio_data_dir(bio);
int cpu;
- if (unlikely(bio_barrier(bio))) {
- bio_endio(bio, -EOPNOTSUPP);
+ if (unlikely(bio_rw_flagged(bio, BIO_RW_BARRIER))) {
+ md_barrier_request(mddev, bio);
return 0;
}
bio_sectors(bio));
part_stat_unlock();
- chunk_sects = mddev->chunk_size >> 9;
- chunksect_bits = ffz(~chunk_sects);
- sector = bio->bi_sector;
-
- if (unlikely(chunk_sects < (bio->bi_sector & (chunk_sects - 1)) + (bio->bi_size >> 9))) {
+ chunk_sects = mddev->chunk_sectors;
+ if (unlikely(!is_io_in_chunk_boundary(mddev, chunk_sects, bio))) {
+ sector_t sector = bio->bi_sector;
struct bio_pair *bp;
/* Sanity check -- queue functions should prevent this happening */
if (bio->bi_vcnt != 1 ||
/* This is a one page bio that upper layers
* refuse to split for us, so we need to split it.
*/
- bp = bio_split(bio, chunk_sects - (bio->bi_sector & (chunk_sects - 1)));
+ if (likely(is_power_of_2(chunk_sects)))
+ bp = bio_split(bio, chunk_sects - (sector &
+ (chunk_sects-1)));
+ else
+ bp = bio_split(bio, chunk_sects -
+ sector_div(sector, chunk_sects));
if (raid0_make_request(q, &bp->bio1))
generic_make_request(&bp->bio1);
if (raid0_make_request(q, &bp->bio2))
bio_pair_release(bp);
return 0;
}
- sector_offset = sector;
- zone = find_zone(conf, §or_offset);
- sect_in_chunk = bio->bi_sector & (chunk_sects - 1);
- {
- sector_t x = sector_offset >> chunksect_bits;
- sector_div(x, zone->nb_dev);
- chunk = x;
-
- x = sector >> chunksect_bits;
- tmp_dev = conf->devlist[(zone - conf->strip_zone)*mddev->raid_disks
- + sector_div(x, zone->nb_dev)];
- }
- rsect = (chunk << chunksect_bits) + zone->dev_start + sect_in_chunk;
-
+ sector_offset = bio->bi_sector;
+ zone = find_zone(mddev->private, §or_offset);
+ tmp_dev = map_sector(mddev, zone, bio->bi_sector,
+ §or_offset);
bio->bi_bdev = tmp_dev->bdev;
- bio->bi_sector = rsect + tmp_dev->data_offset;
-
+ bio->bi_sector = sector_offset + zone->dev_start +
+ tmp_dev->data_offset;
/*
* Let the main block layer submit the IO and resolve recursion:
*/
zone_start = conf->strip_zone[j].zone_end;
}
#endif
- seq_printf(seq, " %dk chunks", mddev->chunk_size/1024);
+ seq_printf(seq, " %dk chunks", mddev->chunk_sectors / 2);
return;
}
module_init(raid0_init);
module_exit(raid0_exit);
MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("RAID0 (striping) personality for MD");
MODULE_ALIAS("md-personality-2"); /* RAID0 */
MODULE_ALIAS("md-raid0");
MODULE_ALIAS("md-level-0");