unsigned int nr_meta_blocks;
unsigned int nr_meta_zones;
unsigned int nr_data_zones;
+ unsigned int nr_cache_zones;
unsigned int nr_rnd_zones;
unsigned int nr_reserved_seq;
unsigned int nr_chunks;
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;
return atomic_read(&zmd->unmap_nr_rnd);
}
+unsigned int dmz_nr_cache_zones(struct dmz_metadata *zmd)
+{
+ return zmd->nr_cache;
+}
+
+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)
{
return zmd->nr_seq;
atomic_set(&zone->refcount, 0);
zone->id = idx;
zone->chunk = DMZ_MAP_UNMAPPED;
- set_bit(DMZ_RND, &zone->flags);
+ set_bit(DMZ_CACHE, &zone->flags);
zone->wp_block = 0;
- zmd->nr_rnd_zones++;
+ zmd->nr_cache_zones++;
zmd->nr_useable_zones++;
if (dev->capacity - zone_offset < zmd->zone_nr_sectors) {
/* Disable runt zone */
dzone->chunk = chunk;
dmz_get_zone_weight(zmd, dzone);
- if (dmz_is_rnd(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);
else
list_add_tail(&dzone->link, &zmd->map_seq_list);
}
bzone = dmz_get(zmd, bzone_id);
- if (!dmz_is_rnd(bzone)) {
+ if (!dmz_is_rnd(bzone) && !dmz_is_cache(bzone)) {
dmz_zmd_err(zmd, "Chunk %u mapping: invalid buffer zone %u",
chunk, bzone_id);
return -EIO;
bzone->bzone = dzone;
dzone->bzone = bzone;
dmz_get_zone_weight(zmd, bzone);
- list_add_tail(&bzone->link, &zmd->map_rnd_list);
+ if (dmz_is_cache(bzone))
+ list_add_tail(&bzone->link, &zmd->map_cache_list);
+ else
+ list_add_tail(&bzone->link, &zmd->map_rnd_list);
next:
chunk++;
e++;
dzone = dmz_get(zmd, i);
if (dmz_is_meta(dzone))
continue;
+ if (dmz_is_offline(dzone))
+ continue;
- if (dmz_is_rnd(dzone))
+ if (dmz_is_cache(dzone))
+ zmd->nr_cache++;
+ else if (dmz_is_rnd(dzone))
zmd->nr_rnd++;
else
zmd->nr_seq++;
/* Unmapped data zone */
set_bit(DMZ_DATA, &dzone->flags);
dzone->chunk = DMZ_MAP_UNMAPPED;
- if (dmz_is_rnd(dzone)) {
+ if (dmz_is_cache(dzone)) {
+ 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);
} else if (atomic_read(&zmd->nr_reserved_seq_zones) < zmd->nr_reserved_seq) {
if (dmz_is_seq(zone)) {
/* LRU rotate sequential zone */
list_add_tail(&zone->link, &zmd->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);
}
/*
- * Select a random write zone for reclaim.
+ * Select a cache or random write zone for reclaim.
*/
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;
- if (list_empty(&zmd->map_rnd_list))
- return ERR_PTR(-EBUSY);
+ /* If we have cache zones select from the cache zone list */
+ if (zmd->nr_cache)
+ zone_list = &zmd->map_cache_list;
- list_for_each_entry(zone, &zmd->map_rnd_list, link) {
+ list_for_each_entry(zone, zone_list, link) {
if (dmz_is_buf(zone))
dzone = zone->bzone;
else
{
struct dm_zone *zone;
- if (list_empty(&zmd->map_seq_list))
- return ERR_PTR(-EBUSY);
-
list_for_each_entry(zone, &zmd->map_seq_list, link) {
if (!zone->bzone)
continue;
unsigned int dzone_id;
struct dm_zone *dzone = NULL;
int ret = 0;
+ int alloc_flags = zmd->nr_cache ? DMZ_ALLOC_CACHE : DMZ_ALLOC_RND;
dmz_lock_map(zmd);
again:
goto out;
/* Allocate a random zone */
- dzone = dmz_alloc_zone(zmd, DMZ_ALLOC_RND);
+ dzone = dmz_alloc_zone(zmd, alloc_flags);
if (!dzone) {
if (dmz_dev_is_dying(zmd)) {
dzone = ERR_PTR(-EIO);
struct dm_zone *dzone)
{
struct dm_zone *bzone;
+ int alloc_flags = zmd->nr_cache ? DMZ_ALLOC_CACHE : DMZ_ALLOC_RND;
dmz_lock_map(zmd);
again:
goto out;
/* Allocate a random zone */
- bzone = dmz_alloc_zone(zmd, DMZ_ALLOC_RND);
+ bzone = dmz_alloc_zone(zmd, alloc_flags);
if (!bzone) {
if (dmz_dev_is_dying(zmd)) {
bzone = ERR_PTR(-EIO);
bzone->chunk = dzone->chunk;
bzone->bzone = dzone;
dzone->bzone = bzone;
- list_add_tail(&bzone->link, &zmd->map_rnd_list);
+ if (dmz_is_cache(bzone))
+ list_add_tail(&bzone->link, &zmd->map_cache_list);
+ else
+ list_add_tail(&bzone->link, &zmd->map_rnd_list);
out:
dmz_unlock_map(zmd);
struct list_head *list;
struct dm_zone *zone;
- if (flags & DMZ_ALLOC_RND)
+ if (flags & DMZ_ALLOC_CACHE)
+ list = &zmd->unmap_cache_list;
+ else if (flags & DMZ_ALLOC_RND)
list = &zmd->unmap_rnd_list;
else
list = &zmd->unmap_seq_list;
+
again:
if (list_empty(list)) {
/*
- * No free zone: if this is for reclaim, allow using the
- * reserved sequential zones.
+ * No free zone: return NULL if this is for not reclaim.
*/
- if (!(flags & DMZ_ALLOC_RECLAIM) ||
- list_empty(&zmd->reserved_seq_zones_list))
+ if (!(flags & DMZ_ALLOC_RECLAIM))
return NULL;
-
- zone = list_first_entry(&zmd->reserved_seq_zones_list,
- struct dm_zone, link);
- list_del_init(&zone->link);
- atomic_dec(&zmd->nr_reserved_seq_zones);
+ /*
+ * Use sequential write zones if we started off with random
+ * zones and the list is empty
+ */
+ if (list == &zmd->unmap_rnd_list) {
+ list = &zmd->unmap_seq_list;
+ goto again;
+ }
+ /*
+ * Fallback to the reserved sequential zones
+ */
+ zone = list_first_entry_or_null(&zmd->reserved_seq_zones_list,
+ struct dm_zone, link);
+ if (zone) {
+ list_del_init(&zone->link);
+ atomic_dec(&zmd->nr_reserved_seq_zones);
+ }
return zone;
}
zone = list_first_entry(list, struct dm_zone, link);
list_del_init(&zone->link);
- if (dmz_is_rnd(zone))
+ if (dmz_is_cache(zone))
+ atomic_dec(&zmd->unmap_nr_cache);
+ else if (dmz_is_rnd(zone))
atomic_dec(&zmd->unmap_nr_rnd);
else
atomic_dec(&zmd->unmap_nr_seq);
dmz_reset_zone(zmd, zone);
/* Return the zone to its type unmap list */
- if (dmz_is_rnd(zone)) {
+ if (dmz_is_cache(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);
} else if (atomic_read(&zmd->nr_reserved_seq_zones) <
dmz_set_chunk_mapping(zmd, chunk, dzone->id,
DMZ_MAP_UNMAPPED);
dzone->chunk = chunk;
- if (dmz_is_rnd(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);
else
list_add_tail(&dzone->link, &zmd->map_seq_list);
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);
/* Set metadata zones starting from sb_zone */
for (i = 0; i < zmd->nr_meta_zones << 1; i++) {
zone = dmz_get(zmd, zmd->sb[0].zone->id + i);
- if (!dmz_is_rnd(zone)) {
+ if (!dmz_is_rnd(zone) && !dmz_is_cache(zone)) {
dmz_zmd_err(zmd,
"metadata zone %d is not random", i);
ret = -ENXIO;
zmd->nr_meta_zones * 2);
dmz_zmd_debug(zmd, " %u data zones for %u chunks",
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)",
* Percentage of unmapped (free) random zones below which reclaim starts
* even if the target is busy.
*/
-#define DMZ_RECLAIM_LOW_UNMAP_RND 30
+#define DMZ_RECLAIM_LOW_UNMAP_ZONES 30
/*
* Percentage of unmapped (free) random zones above which reclaim will
* stop if the target is busy.
*/
-#define DMZ_RECLAIM_HIGH_UNMAP_RND 50
+#define DMZ_RECLAIM_HIGH_UNMAP_ZONES 50
/*
* Align a sequential zone write pointer to chunk_block.
struct dm_zone *szone = NULL;
struct dmz_metadata *zmd = zrc->metadata;
int ret;
+ int alloc_flags = dmz_nr_cache_zones(zmd) ?
+ DMZ_ALLOC_RND : DMZ_ALLOC_SEQ;
/* Get a free sequential zone */
dmz_lock_map(zmd);
- szone = dmz_alloc_zone(zmd, DMZ_ALLOC_RECLAIM);
+ szone = dmz_alloc_zone(zmd, alloc_flags | DMZ_ALLOC_RECLAIM);
dmz_unlock_map(zmd);
if (!szone)
return -ENOSPC;
- DMDEBUG("(%s): Chunk %u, move rnd zone %u (weight %u) to seq zone %u",
- dmz_metadata_label(zmd),
- chunk, dzone->id, dmz_weight(dzone), szone->id);
+ DMDEBUG("(%s): Chunk %u, move %s zone %u (weight %u) to %s zone %u",
+ dmz_metadata_label(zmd), chunk,
+ dmz_is_cache(dzone) ? "cache" : "rnd",
+ dzone->id, dmz_weight(dzone),
+ dmz_is_rnd(szone) ? "rnd" : "seq", szone->id);
/* Flush the random data zone into the sequential zone */
ret = dmz_reclaim_copy(zrc, dzone, szone);
return -EBUSY;
start = jiffies;
- if (dmz_is_rnd(dzone)) {
+ if (dmz_is_cache(dzone) || dmz_is_rnd(dzone)) {
if (!dmz_weight(dzone)) {
/* Empty zone */
dmz_reclaim_empty(zrc, dzone);
return time_is_before_jiffies(zrc->atime + DMZ_IDLE_PERIOD);
}
-/*
- * Test if reclaim is necessary.
- */
-static bool dmz_should_reclaim(struct dmz_reclaim *zrc)
+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_rnd = dmz_nr_unmap_rnd_zones(zmd);
- unsigned int p_unmap_rnd = nr_unmap_rnd * 100 / nr_rnd;
+ 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);
+ }
+ return nr_unmap * 100 / nr_zones;
+}
+
+/*
+ * Test if reclaim is necessary.
+ */
+static bool dmz_should_reclaim(struct dmz_reclaim *zrc, unsigned int p_unmap)
+{
/* Reclaim when idle */
- if (dmz_target_idle(zrc) && nr_unmap_rnd < nr_rnd)
+ if (dmz_target_idle(zrc) && p_unmap < 100)
return true;
- /* If there are still plenty of random zones, do not reclaim */
- if (p_unmap_rnd >= DMZ_RECLAIM_HIGH_UNMAP_RND)
+ /* If there are still plenty of cache zones, do not reclaim */
+ if (p_unmap >= DMZ_RECLAIM_HIGH_UNMAP_ZONES)
return false;
/*
- * If the percentage of unmapped random zones is low,
+ * If the percentage of unmapped cache zones is low,
* reclaim even if the target is busy.
*/
- return p_unmap_rnd <= DMZ_RECLAIM_LOW_UNMAP_RND;
+ return p_unmap <= DMZ_RECLAIM_LOW_UNMAP_ZONES;
}
/*
{
struct dmz_reclaim *zrc = container_of(work, struct dmz_reclaim, work.work);
struct dmz_metadata *zmd = zrc->metadata;
- unsigned int nr_rnd, nr_unmap_rnd;
- unsigned int p_unmap_rnd;
+ unsigned int p_unmap;
int ret;
if (dmz_dev_is_dying(zmd))
return;
- if (!dmz_should_reclaim(zrc)) {
+ p_unmap = dmz_reclaim_percentage(zrc);
+ if (!dmz_should_reclaim(zrc, p_unmap)) {
mod_delayed_work(zrc->wq, &zrc->work, DMZ_IDLE_PERIOD);
return;
}
* and slower if there are still some free random zones to avoid
* as much as possible to negatively impact the user workload.
*/
- nr_rnd = dmz_nr_rnd_zones(zmd);
- nr_unmap_rnd = dmz_nr_unmap_rnd_zones(zmd);
- p_unmap_rnd = nr_unmap_rnd * 100 / nr_rnd;
- if (dmz_target_idle(zrc) || p_unmap_rnd < DMZ_RECLAIM_LOW_UNMAP_RND / 2) {
+ if (dmz_target_idle(zrc) || p_unmap < DMZ_RECLAIM_LOW_UNMAP_ZONES / 2) {
/* Idle or very low percentage: go fast */
zrc->kc_throttle.throttle = 100;
} else {
/* Busy but we still have some random zone: throttle */
- zrc->kc_throttle.throttle = min(75U, 100U - p_unmap_rnd / 2);
+ zrc->kc_throttle.throttle = min(75U, 100U - p_unmap / 2);
}
- DMDEBUG("(%s): Reclaim (%u): %s, %u%% free rnd zones (%u/%u)",
+ DMDEBUG("(%s): Reclaim (%u): %s, %u%% free zones (%u/%u cache %u/%u random)",
dmz_metadata_label(zmd),
zrc->kc_throttle.throttle,
(dmz_target_idle(zrc) ? "Idle" : "Busy"),
- p_unmap_rnd, nr_unmap_rnd, nr_rnd);
+ p_unmap, dmz_nr_unmap_cache_zones(zmd),
+ dmz_nr_cache_zones(zmd),
+ dmz_nr_unmap_rnd_zones(zmd),
+ dmz_nr_rnd_zones(zmd));
ret = dmz_do_reclaim(zrc);
if (ret) {
*/
void dmz_schedule_reclaim(struct dmz_reclaim *zrc)
{
- if (dmz_should_reclaim(zrc))
+ unsigned int p_unmap = dmz_reclaim_percentage(zrc);
+
+ if (dmz_should_reclaim(zrc, p_unmap))
mod_delayed_work(zrc->wq, &zrc->work, 0);
}
DMDEBUG("(%s): READ chunk %llu -> %s zone %u, block %llu, %u blocks",
dmz_metadata_label(zmd),
(unsigned long long)dmz_bio_chunk(zmd, bio),
- (dmz_is_rnd(zone) ? "RND" : "SEQ"),
+ (dmz_is_rnd(zone) ? "RND" :
+ (dmz_is_cache(zone) ? "CACHE" : "SEQ")),
zone->id,
(unsigned long long)chunk_block, nr_blocks);
bzone = zone->bzone;
while (chunk_block < end_block) {
nr_blocks = 0;
- if (dmz_is_rnd(zone) || chunk_block < zone->wp_block) {
+ if (dmz_is_rnd(zone) || dmz_is_cache(zone) ||
+ chunk_block < zone->wp_block) {
/* Test block validity in the data zone */
ret = dmz_block_valid(zmd, zone, chunk_block);
if (ret < 0)
DMDEBUG("(%s): WRITE chunk %llu -> %s zone %u, block %llu, %u blocks",
dmz_metadata_label(zmd),
(unsigned long long)dmz_bio_chunk(zmd, bio),
- (dmz_is_rnd(zone) ? "RND" : "SEQ"),
+ (dmz_is_rnd(zone) ? "RND" :
+ (dmz_is_cache(zone) ? "CACHE" : "SEQ")),
zone->id,
(unsigned long long)chunk_block, nr_blocks);
- if (dmz_is_rnd(zone) || chunk_block == zone->wp_block) {
+ if (dmz_is_rnd(zone) || dmz_is_cache(zone) ||
+ chunk_block == zone->wp_block) {
/*
* zone is a random zone or it is a sequential zone
* and the BIO is aligned to the zone write pointer:
* Invalidate blocks in the data zone and its
* buffer zone if one is mapped.
*/
- if (dmz_is_rnd(zone) || chunk_block < zone->wp_block)
+ if (dmz_is_rnd(zone) || dmz_is_cache(zone) ||
+ chunk_block < zone->wp_block)
ret = dmz_invalidate_blocks(zmd, zone, chunk_block, nr_blocks);
if (ret == 0 && zone->bzone)
ret = dmz_invalidate_blocks(zmd, zone->bzone,
switch (type) {
case STATUSTYPE_INFO:
- DMEMIT("%u zones %u/%u random %u/%u sequential",
+ DMEMIT("%u zones %u/%u cache %u/%u random %u/%u sequential",
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),
*/
enum {
/* Zone write type */
+ DMZ_CACHE,
DMZ_RND,
DMZ_SEQ,
/*
* Zone data accessors.
*/
+#define dmz_is_cache(z) test_bit(DMZ_CACHE, &(z)->flags)
#define dmz_is_rnd(z) test_bit(DMZ_RND, &(z)->flags)
#define dmz_is_seq(z) test_bit(DMZ_SEQ, &(z)->flags)
#define dmz_is_empty(z) ((z)->wp_block == 0)
bool dmz_dev_is_dying(struct dmz_metadata *zmd);
#define DMZ_ALLOC_RND 0x01
-#define DMZ_ALLOC_RECLAIM 0x02
+#define DMZ_ALLOC_CACHE 0x02
+#define DMZ_ALLOC_SEQ 0x04
+#define DMZ_ALLOC_RECLAIM 0x10
struct dm_zone *dmz_alloc_zone(struct dmz_metadata *zmd, unsigned long flags);
void dmz_free_zone(struct dmz_metadata *zmd, struct dm_zone *zone);
unsigned int chunk);
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);
projects / users / jedix / linux-maple.git / commitdiff