On Wed, 2020-05-27 at 08:22 +0200, Hannes Reinecke wrote:
> Random and sequential zones should be part of the respective
> device structure to make arbitration between devices possible.
>
> Signed-off-by: Hannes Reinecke <[email protected]>
> ---
> drivers/md/dm-zoned-metadata.c | 139
> +++++++++++++++++++++++------------------
> drivers/md/dm-zoned-reclaim.c | 15 +++--
> drivers/md/dm-zoned-target.c | 25 ++++++--
> drivers/md/dm-zoned.h | 18 ++++--
> 4 files changed, 119 insertions(+), 78 deletions(-)
>
> diff --git a/drivers/md/dm-zoned-metadata.c b/drivers/md/dm-zoned-metadata.c
> index 445760730d10..f309219a5457 100644
> --- a/drivers/md/dm-zoned-metadata.c
> +++ b/drivers/md/dm-zoned-metadata.c
> @@ -192,21 +192,12 @@ struct dmz_metadata {
> /* Zone allocation management */
> struct mutex map_lock;
> struct dmz_mblock **map_mblk;
> - unsigned int nr_rnd;
> - atomic_t unmap_nr_rnd;
> - struct list_head unmap_rnd_list;
> - struct list_head map_rnd_list;
>
> unsigned int nr_cache;
> atomic_t unmap_nr_cache;
> struct list_head unmap_cache_list;
> struct list_head map_cache_list;
>
> - unsigned int nr_seq;
> - atomic_t unmap_nr_seq;
> - struct list_head unmap_seq_list;
> - struct list_head map_seq_list;
> -
> atomic_t nr_reserved_seq_zones;
> struct list_head reserved_seq_zones_list;
>
> @@ -279,14 +270,14 @@ unsigned int dmz_nr_chunks(struct dmz_metadata *zmd)
> return zmd->nr_chunks;
> }
>
> -unsigned int dmz_nr_rnd_zones(struct dmz_metadata *zmd)
> +unsigned int dmz_nr_rnd_zones(struct dmz_metadata *zmd, int idx)
> {
> - return zmd->nr_rnd;
> + return zmd->dev[idx].nr_rnd;
> }
>
> -unsigned int dmz_nr_unmap_rnd_zones(struct dmz_metadata *zmd)
> +unsigned int dmz_nr_unmap_rnd_zones(struct dmz_metadata *zmd, int idx)
> {
> - return atomic_read(&zmd->unmap_nr_rnd);
> + return atomic_read(&zmd->dev[idx].unmap_nr_rnd);
> }
>
> unsigned int dmz_nr_cache_zones(struct dmz_metadata *zmd)
> @@ -299,14 +290,14 @@ unsigned int dmz_nr_unmap_cache_zones(struct
> dmz_metadata *zmd)
> return atomic_read(&zmd->unmap_nr_cache);
> }
>
> -unsigned int dmz_nr_seq_zones(struct dmz_metadata *zmd)
> +unsigned int dmz_nr_seq_zones(struct dmz_metadata *zmd, int idx)
> {
> - return zmd->nr_seq;
> + return zmd->dev[idx].nr_seq;
> }
>
> -unsigned int dmz_nr_unmap_seq_zones(struct dmz_metadata *zmd)
> +unsigned int dmz_nr_unmap_seq_zones(struct dmz_metadata *zmd, int idx)
> {
> - return atomic_read(&zmd->unmap_nr_seq);
> + return atomic_read(&zmd->dev[idx].unmap_nr_seq);
> }
>
> static struct dm_zone *dmz_get(struct dmz_metadata *zmd, unsigned int
> zone_id)
> @@ -1495,6 +1486,14 @@ static int dmz_init_zones(struct dmz_metadata *zmd)
>
> dev->metadata = zmd;
> zmd->nr_zones += dev->nr_zones;
> +
> + atomic_set(&dev->unmap_nr_rnd, 0);
> + INIT_LIST_HEAD(&dev->unmap_rnd_list);
> + INIT_LIST_HEAD(&dev->map_rnd_list);
> +
> + atomic_set(&dev->unmap_nr_seq, 0);
> + INIT_LIST_HEAD(&dev->unmap_seq_list);
> + INIT_LIST_HEAD(&dev->map_seq_list);
> }
>
> if (!zmd->nr_zones) {
> @@ -1715,9 +1714,9 @@ static int dmz_load_mapping(struct dmz_metadata *zmd)
> if (dmz_is_cache(dzone))
> list_add_tail(&dzone->link, &zmd->map_cache_list);
> else if (dmz_is_rnd(dzone))
> - list_add_tail(&dzone->link, &zmd->map_rnd_list);
> + list_add_tail(&dzone->link, &dzone->dev->map_rnd_list);
> else
> - list_add_tail(&dzone->link, &zmd->map_seq_list);
> + list_add_tail(&dzone->link, &dzone->dev->map_seq_list);
>
> /* Check buffer zone */
> bzone_id = le32_to_cpu(dmap[e].bzone_id);
> @@ -1751,7 +1750,7 @@ static int dmz_load_mapping(struct dmz_metadata *zmd)
> if (dmz_is_cache(bzone))
> list_add_tail(&bzone->link, &zmd->map_cache_list);
> else
> - list_add_tail(&bzone->link, &zmd->map_rnd_list);
> + list_add_tail(&bzone->link, &bzone->dev->map_rnd_list);
> next:
> chunk++;
> e++;
> @@ -1776,9 +1775,9 @@ static int dmz_load_mapping(struct dmz_metadata *zmd)
> if (dmz_is_cache(dzone))
> zmd->nr_cache++;
> else if (dmz_is_rnd(dzone))
> - zmd->nr_rnd++;
> + dzone->dev->nr_rnd++;
> else
> - zmd->nr_seq++;
> + dzone->dev->nr_seq++;
>
> if (dmz_is_data(dzone)) {
> /* Already initialized */
> @@ -1792,16 +1791,18 @@ static int dmz_load_mapping(struct dmz_metadata *zmd)
> list_add_tail(&dzone->link, &zmd->unmap_cache_list);
> atomic_inc(&zmd->unmap_nr_cache);
> } else if (dmz_is_rnd(dzone)) {
> - list_add_tail(&dzone->link, &zmd->unmap_rnd_list);
> - atomic_inc(&zmd->unmap_nr_rnd);
> + list_add_tail(&dzone->link,
> + &dzone->dev->unmap_rnd_list);
> + atomic_inc(&dzone->dev->unmap_nr_rnd);
> } else if (atomic_read(&zmd->nr_reserved_seq_zones) <
> zmd->nr_reserved_seq) {
> list_add_tail(&dzone->link,
> &zmd->reserved_seq_zones_list);
> set_bit(DMZ_RESERVED, &dzone->flags);
> atomic_inc(&zmd->nr_reserved_seq_zones);
> - zmd->nr_seq--;
> + dzone->dev->nr_seq--;
> } else {
> - list_add_tail(&dzone->link, &zmd->unmap_seq_list);
> - atomic_inc(&zmd->unmap_nr_seq);
> + list_add_tail(&dzone->link,
> + &dzone->dev->unmap_seq_list);
> + atomic_inc(&dzone->dev->unmap_nr_seq);
> }
> }
>
> @@ -1835,13 +1836,13 @@ static void __dmz_lru_zone(struct dmz_metadata *zmd,
> struct dm_zone *zone)
> list_del_init(&zone->link);
> if (dmz_is_seq(zone)) {
> /* LRU rotate sequential zone */
> - list_add_tail(&zone->link, &zmd->map_seq_list);
> + list_add_tail(&zone->link, &zone->dev->map_seq_list);
> } else if (dmz_is_cache(zone)) {
> /* LRU rotate cache zone */
> list_add_tail(&zone->link, &zmd->map_cache_list);
> } else {
> /* LRU rotate random zone */
> - list_add_tail(&zone->link, &zmd->map_rnd_list);
> + list_add_tail(&zone->link, &zone->dev->map_rnd_list);
> }
> }
>
> @@ -1923,14 +1924,24 @@ static struct dm_zone
> *dmz_get_rnd_zone_for_reclaim(struct dmz_metadata *zmd,
> {
> struct dm_zone *dzone = NULL;
> struct dm_zone *zone;
> - struct list_head *zone_list = &zmd->map_rnd_list;
> + struct list_head *zone_list;
>
> /* If we have cache zones select from the cache zone list */
> if (zmd->nr_cache) {
> zone_list = &zmd->map_cache_list;
> /* Try to relaim random zones, too, when idle */
> - if (idle && list_empty(zone_list))
> - zone_list = &zmd->map_rnd_list;
> + if (idle && list_empty(zone_list)) {
> + int i;
> +
> + for (i = 1; i < zmd->nr_devs; i++) {
> + zone_list = &zmd->dev[i].map_rnd_list;
> + if (!list_empty(zone_list))
> + break;
> + }
> + }
> + } else {
> + /* Otherwise the random zones are on the first disk */
> + zone_list = &zmd->dev[0].map_rnd_list;
> }
>
> list_for_each_entry(zone, zone_list, link) {
> @@ -1951,12 +1962,17 @@ static struct dm_zone
> *dmz_get_rnd_zone_for_reclaim(struct dmz_metadata *zmd,
> static struct dm_zone *dmz_get_seq_zone_for_reclaim(struct dmz_metadata *zmd)
> {
> struct dm_zone *zone;
> + int i;
>
> - list_for_each_entry(zone, &zmd->map_seq_list, link) {
> - if (!zone->bzone)
> - continue;
> - if (dmz_lock_zone_reclaim(zone))
> - return zone;
> + for (i = 0; i < zmd->nr_devs; i++) {
> + struct dmz_dev *dev = &zmd->dev[i];
> +
> + list_for_each_entry(zone, &dev->map_seq_list, link) {
> + if (!zone->bzone)
> + continue;
> + if (dmz_lock_zone_reclaim(zone))
> + return zone;
> + }
> }
>
> return NULL;
> @@ -2142,7 +2158,7 @@ struct dm_zone *dmz_get_chunk_buffer(struct
> dmz_metadata *zmd,
> if (dmz_is_cache(bzone))
> list_add_tail(&bzone->link, &zmd->map_cache_list);
> else
> - list_add_tail(&bzone->link, &zmd->map_rnd_list);
> + list_add_tail(&bzone->link, &bzone->dev->map_rnd_list);
> out:
> dmz_unlock_map(zmd);
>
> @@ -2157,21 +2173,27 @@ struct dm_zone *dmz_alloc_zone(struct dmz_metadata
> *zmd, unsigned long flags)
> {
> struct list_head *list;
> struct dm_zone *zone;
> + unsigned int dev_idx = 0;
>
> +again:
> if (flags & DMZ_ALLOC_CACHE)
> list = &zmd->unmap_cache_list;
> else if (flags & DMZ_ALLOC_RND)
> - list = &zmd->unmap_rnd_list;
> + list = &zmd->dev[dev_idx].unmap_rnd_list;
> else
> - list = &zmd->unmap_seq_list;
> + list = &zmd->dev[dev_idx].unmap_seq_list;
>
> -again:
> if (list_empty(list)) {
> /*
> * No free zone: return NULL if this is for not reclaim.
> */
> if (!(flags & DMZ_ALLOC_RECLAIM))
> return NULL;
> + if (dev_idx < zmd->nr_devs) {
> + dev_idx++;
> + goto again;
> + }
> +
> /*
> * Fallback to the reserved sequential zones
> */
> @@ -2190,9 +2212,9 @@ struct dm_zone *dmz_alloc_zone(struct dmz_metadata
> *zmd, unsigned long flags)
> if (dmz_is_cache(zone))
> atomic_dec(&zmd->unmap_nr_cache);
> else if (dmz_is_rnd(zone))
> - atomic_dec(&zmd->unmap_nr_rnd);
> + atomic_dec(&zone->dev->unmap_nr_rnd);
> else
> - atomic_dec(&zmd->unmap_nr_seq);
> + atomic_dec(&zone->dev->unmap_nr_seq);
>
> if (dmz_is_offline(zone)) {
> dmz_zmd_warn(zmd, "Zone %u is offline", zone->id);
> @@ -2222,14 +2244,14 @@ void dmz_free_zone(struct dmz_metadata *zmd, struct
> dm_zone *zone)
> list_add_tail(&zone->link, &zmd->unmap_cache_list);
> atomic_inc(&zmd->unmap_nr_cache);
> } else if (dmz_is_rnd(zone)) {
> - list_add_tail(&zone->link, &zmd->unmap_rnd_list);
> - atomic_inc(&zmd->unmap_nr_rnd);
> + list_add_tail(&zone->link, &zone->dev->unmap_rnd_list);
> + atomic_inc(&zone->dev->unmap_nr_rnd);
> } else if (dmz_is_reserved(zone)) {
> list_add_tail(&zone->link, &zmd->reserved_seq_zones_list);
> atomic_inc(&zmd->nr_reserved_seq_zones);
> } else {
> - list_add_tail(&zone->link, &zmd->unmap_seq_list);
> - atomic_inc(&zmd->unmap_nr_seq);
> + list_add_tail(&zone->link, &zone->dev->unmap_seq_list);
> + atomic_inc(&zone->dev->unmap_nr_seq);
> }
>
> wake_up_all(&zmd->free_wq);
> @@ -2249,9 +2271,9 @@ void dmz_map_zone(struct dmz_metadata *zmd, struct
> dm_zone *dzone,
> if (dmz_is_cache(dzone))
> list_add_tail(&dzone->link, &zmd->map_cache_list);
> else if (dmz_is_rnd(dzone))
> - list_add_tail(&dzone->link, &zmd->map_rnd_list);
> + list_add_tail(&dzone->link, &dzone->dev->map_rnd_list);
> else
> - list_add_tail(&dzone->link, &zmd->map_seq_list);
> + list_add_tail(&dzone->link, &dzone->dev->map_seq_list);
> }
>
> /*
> @@ -2819,18 +2841,11 @@ int dmz_ctr_metadata(struct dmz_dev *dev, int num_dev,
> INIT_LIST_HEAD(&zmd->mblk_dirty_list);
>
> mutex_init(&zmd->map_lock);
> - atomic_set(&zmd->unmap_nr_rnd, 0);
> - INIT_LIST_HEAD(&zmd->unmap_rnd_list);
> - INIT_LIST_HEAD(&zmd->map_rnd_list);
>
> atomic_set(&zmd->unmap_nr_cache, 0);
> INIT_LIST_HEAD(&zmd->unmap_cache_list);
> INIT_LIST_HEAD(&zmd->map_cache_list);
>
> - atomic_set(&zmd->unmap_nr_seq, 0);
> - INIT_LIST_HEAD(&zmd->unmap_seq_list);
> - INIT_LIST_HEAD(&zmd->map_seq_list);
> -
> atomic_set(&zmd->nr_reserved_seq_zones, 0);
> INIT_LIST_HEAD(&zmd->reserved_seq_zones_list);
>
> @@ -2899,10 +2914,14 @@ int dmz_ctr_metadata(struct dmz_dev *dev, int num_dev,
> zmd->nr_data_zones, zmd->nr_chunks);
> dmz_zmd_debug(zmd, " %u cache zones (%u unmapped)",
> zmd->nr_cache, atomic_read(&zmd->unmap_nr_cache));
> - dmz_zmd_debug(zmd, " %u random zones (%u unmapped)",
> - zmd->nr_rnd, atomic_read(&zmd->unmap_nr_rnd));
> - dmz_zmd_debug(zmd, " %u sequential zones (%u unmapped)",
> - zmd->nr_seq, atomic_read(&zmd->unmap_nr_seq));
> + for (i = 0; i < zmd->nr_devs; i++) {
> + dmz_zmd_debug(zmd, " %u random zones (%u unmapped)",
> + dmz_nr_rnd_zones(zmd, i),
> + dmz_nr_unmap_rnd_zones(zmd, i));
> + dmz_zmd_debug(zmd, " %u sequential zones (%u unmapped)",
> + dmz_nr_seq_zones(zmd, i),
> + dmz_nr_unmap_seq_zones(zmd, i));
> + }
> dmz_zmd_debug(zmd, " %u reserved sequential data zones",
> zmd->nr_reserved_seq);
> dmz_zmd_debug(zmd, "Format:");
> diff --git a/drivers/md/dm-zoned-reclaim.c b/drivers/md/dm-zoned-reclaim.c
> index 09843645248a..18edf1b9bf52 100644
> --- a/drivers/md/dm-zoned-reclaim.c
> +++ b/drivers/md/dm-zoned-reclaim.c
> @@ -447,15 +447,14 @@ static unsigned int dmz_reclaim_percentage(struct
> dmz_reclaim *zrc)
> {
> struct dmz_metadata *zmd = zrc->metadata;
> unsigned int nr_cache = dmz_nr_cache_zones(zmd);
> - unsigned int nr_rnd = dmz_nr_rnd_zones(zmd);
> unsigned int nr_unmap, nr_zones;
>
> if (nr_cache) {
> nr_zones = nr_cache;
> nr_unmap = dmz_nr_unmap_cache_zones(zmd);
> } else {
> - nr_zones = nr_rnd;
> - nr_unmap = dmz_nr_unmap_rnd_zones(zmd);
> + nr_zones = dmz_nr_rnd_zones(zmd, zrc->dev_idx);
> + nr_unmap = dmz_nr_unmap_rnd_zones(zmd, zrc->dev_idx);
> }
> return nr_unmap * 100 / nr_zones;
> }
> @@ -467,7 +466,7 @@ static bool dmz_should_reclaim(struct dmz_reclaim *zrc,
> unsigned int p_unmap)
> {
> unsigned int nr_reclaim;
>
> - nr_reclaim = dmz_nr_rnd_zones(zrc->metadata);
> + nr_reclaim = dmz_nr_rnd_zones(zrc->metadata, zrc->dev_idx);
>
> if (dmz_nr_cache_zones(zrc->metadata)) {
> /*
> @@ -528,8 +527,8 @@ static void dmz_reclaim_work(struct work_struct *work)
> zrc->kc_throttle.throttle = min(75U, 100U - p_unmap / 2);
> }
>
> - nr_unmap_rnd = dmz_nr_unmap_rnd_zones(zmd);
> - nr_rnd = dmz_nr_rnd_zones(zmd);
> + nr_unmap_rnd = dmz_nr_unmap_rnd_zones(zmd, zrc->dev_idx);
> + nr_rnd = dmz_nr_rnd_zones(zmd, zrc->dev_idx);
>
> DMDEBUG("(%s/%u): Reclaim (%u): %s, %u%% free zones (%u/%u cache %u/%u
> random)",
> dmz_metadata_label(zmd), zrc->dev_idx,
> @@ -537,8 +536,8 @@ static void dmz_reclaim_work(struct work_struct *work)
> (dmz_target_idle(zrc) ? "Idle" : "Busy"),
> p_unmap, dmz_nr_unmap_cache_zones(zmd),
> dmz_nr_cache_zones(zmd),
> - dmz_nr_unmap_rnd_zones(zmd),
> - dmz_nr_rnd_zones(zmd));
> + dmz_nr_unmap_rnd_zones(zmd, zrc->dev_idx),
> + dmz_nr_rnd_zones(zmd, zrc->dev_idx));
>
> ret = dmz_do_reclaim(zrc);
> if (ret && ret != -EINTR) {
> diff --git a/drivers/md/dm-zoned-target.c b/drivers/md/dm-zoned-target.c
> index fc1df9714f63..f6f00a363903 100644
> --- a/drivers/md/dm-zoned-target.c
> +++ b/drivers/md/dm-zoned-target.c
> @@ -1082,17 +1082,30 @@ static void dmz_status(struct dm_target *ti,
> status_type_t type,
> ssize_t sz = 0;
> char buf[BDEVNAME_SIZE];
> struct dmz_dev *dev;
> + int i;
>
> switch (type) {
> case STATUSTYPE_INFO:
> - DMEMIT("%u zones %u/%u cache %u/%u random %u/%u sequential",
> + DMEMIT("%u zones %u/%u cache",
> dmz_nr_zones(dmz->metadata),
> dmz_nr_unmap_cache_zones(dmz->metadata),
> - dmz_nr_cache_zones(dmz->metadata),
> - dmz_nr_unmap_rnd_zones(dmz->metadata),
> - dmz_nr_rnd_zones(dmz->metadata),
> - dmz_nr_unmap_seq_zones(dmz->metadata),
> - dmz_nr_seq_zones(dmz->metadata));
> + dmz_nr_cache_zones(dmz->metadata));
> + for (i = 0; i < DMZ_MAX_DEVS; i++) {
i < zmd->nr_devs ? Since now only what is needed is allocated.
> + if (!dmz->ddev[i])
> + continue;
> + /*
> + * For a multi-device setup the first device
> + * contains only cache zones.
> + */
> + if ((i == 0) &&
> + (dmz_nr_cache_zones(dmz->metadata) > 0))
> + continue;
> + DMEMIT(" %u/%u random %u/%u sequential",
> + dmz_nr_unmap_rnd_zones(dmz->metadata, i),
> + dmz_nr_rnd_zones(dmz->metadata, i),
> + dmz_nr_unmap_seq_zones(dmz->metadata, i),
> + dmz_nr_seq_zones(dmz->metadata, i));
> + }
> break;
> case STATUSTYPE_TABLE:
> dev = &dmz->dev[0];
> diff --git a/drivers/md/dm-zoned.h b/drivers/md/dm-zoned.h
> index 0cc3459f78ce..f2a760f62db5 100644
> --- a/drivers/md/dm-zoned.h
> +++ b/drivers/md/dm-zoned.h
> @@ -67,6 +67,16 @@ struct dmz_dev {
> unsigned int flags;
>
> sector_t zone_nr_sectors;
> +
> + unsigned int nr_rnd;
> + atomic_t unmap_nr_rnd;
> + struct list_head unmap_rnd_list;
> + struct list_head map_rnd_list;
> +
> + unsigned int nr_seq;
> + atomic_t unmap_nr_seq;
> + struct list_head unmap_seq_list;
> + struct list_head map_seq_list;
> };
>
> #define dmz_bio_chunk(zmd, bio) ((bio)->bi_iter.bi_sector >> \
> @@ -213,10 +223,10 @@ void dmz_unmap_zone(struct dmz_metadata *zmd, struct
> dm_zone *zone);
> unsigned int dmz_nr_zones(struct dmz_metadata *zmd);
> unsigned int dmz_nr_cache_zones(struct dmz_metadata *zmd);
> unsigned int dmz_nr_unmap_cache_zones(struct dmz_metadata *zmd);
> -unsigned int dmz_nr_rnd_zones(struct dmz_metadata *zmd);
> -unsigned int dmz_nr_unmap_rnd_zones(struct dmz_metadata *zmd);
> -unsigned int dmz_nr_seq_zones(struct dmz_metadata *zmd);
> -unsigned int dmz_nr_unmap_seq_zones(struct dmz_metadata *zmd);
> +unsigned int dmz_nr_rnd_zones(struct dmz_metadata *zmd, int idx);
> +unsigned int dmz_nr_unmap_rnd_zones(struct dmz_metadata *zmd, int idx);
> +unsigned int dmz_nr_seq_zones(struct dmz_metadata *zmd, int idx);
> +unsigned int dmz_nr_unmap_seq_zones(struct dmz_metadata *zmd, int idx);
> unsigned int dmz_zone_nr_blocks(struct dmz_metadata *zmd);
> unsigned int dmz_zone_nr_blocks_shift(struct dmz_metadata *zmd);
> unsigned int dmz_zone_nr_sectors(struct dmz_metadata *zmd);
--
Damien Le Moal
Western Digital Research
--
dm-devel mailing list
[email protected]
https://www.redhat.com/mailman/listinfo/dm-devel
