X-Git-Url: https://git.kernel.dk/?a=blobdiff_plain;f=zbd.c;h=70afdd825f7d6b59d5f6de02645fd7e0a7352c48;hb=b5a0f7ce303d5fa5cca51af0652b7f7cf9bc5d61;hp=6a26fe108a68acf55c7ad2b7e59e8fccb97f0dc8;hpb=2ef3c1b02473a14bf7b8b52e28d0cdded9c5cc9a;p=fio.git

diff --git a/zbd.c b/zbd.c
index 6a26fe10..70afdd82 100644
--- a/zbd.c
+++ b/zbd.c
@@ -22,16 +22,133 @@
 #include "pshared.h"
 #include "zbd.h"
 
+static bool is_valid_offset(const struct fio_file *f, uint64_t offset)
+{
+	return (uint64_t)(offset - f->file_offset) < f->io_size;
+}
+
+static inline unsigned int zbd_zone_nr(const struct fio_file *f,
+				       struct fio_zone_info *zone)
+{
+	return zone - f->zbd_info->zone_info;
+}
+
+/**
+ * zbd_zone_idx - convert an offset into a zone number
+ * @f: file pointer.
+ * @offset: offset in bytes. If this offset is in the first zone_size bytes
+ *	    past the disk size then the index of the sentinel is returned.
+ */
+static uint32_t zbd_zone_idx(const struct fio_file *f, uint64_t offset)
+{
+	uint32_t zone_idx;
+
+	if (f->zbd_info->zone_size_log2 > 0)
+		zone_idx = offset >> f->zbd_info->zone_size_log2;
+	else
+		zone_idx = offset / f->zbd_info->zone_size;
+
+	return min(zone_idx, f->zbd_info->nr_zones);
+}
+
+/**
+ * zbd_zone_end - Return zone end location
+ * @z: zone info pointer.
+ */
+static inline uint64_t zbd_zone_end(const struct fio_zone_info *z)
+{
+	return (z+1)->start;
+}
+
+/**
+ * zbd_zone_capacity_end - Return zone capacity limit end location
+ * @z: zone info pointer.
+ */
+static inline uint64_t zbd_zone_capacity_end(const struct fio_zone_info *z)
+{
+	return z->start + z->capacity;
+}
+
+/**
+ * zbd_zone_full - verify whether a minimum number of bytes remain in a zone
+ * @f: file pointer.
+ * @z: zone info pointer.
+ * @required: minimum number of bytes that must remain in a zone.
+ *
+ * The caller must hold z->mutex.
+ */
+static bool zbd_zone_full(const struct fio_file *f, struct fio_zone_info *z,
+			  uint64_t required)
+{
+	assert((required & 511) == 0);
+
+	return z->has_wp &&
+		z->wp + required > zbd_zone_capacity_end(z);
+}
+
+static void zone_lock(struct thread_data *td, const struct fio_file *f,
+		      struct fio_zone_info *z)
+{
+	struct zoned_block_device_info *zbd = f->zbd_info;
+	uint32_t nz = z - zbd->zone_info;
+
+	/* A thread should never lock zones outside its working area. */
+	assert(f->min_zone <= nz && nz < f->max_zone);
+
+	assert(z->has_wp);
+
+	/*
+	 * Lock the io_u target zone. The zone will be unlocked if io_u offset
+	 * is changed or when io_u completes and zbd_put_io() executed.
+	 * To avoid multiple jobs doing asynchronous I/Os from deadlocking each
+	 * other waiting for zone locks when building an io_u batch, first
+	 * only trylock the zone. If the zone is already locked by another job,
+	 * process the currently queued I/Os so that I/O progress is made and
+	 * zones unlocked.
+	 */
+	if (pthread_mutex_trylock(&z->mutex) != 0) {
+		if (!td_ioengine_flagged(td, FIO_SYNCIO))
+			io_u_quiesce(td);
+		pthread_mutex_lock(&z->mutex);
+	}
+}
+
+static inline void zone_unlock(struct fio_zone_info *z)
+{
+	int ret;
+
+	assert(z->has_wp);
+	ret = pthread_mutex_unlock(&z->mutex);
+	assert(!ret);
+}
+
+static inline struct fio_zone_info *get_zone(const struct fio_file *f,
+					     unsigned int zone_nr)
+{
+	return &f->zbd_info->zone_info[zone_nr];
+}
+
 /**
  * zbd_get_zoned_model - Get a device zoned model
  * @td: FIO thread data
  * @f: FIO file for which to get model information
  */
-int zbd_get_zoned_model(struct thread_data *td, struct fio_file *f,
-			enum zbd_zoned_model *model)
+static int zbd_get_zoned_model(struct thread_data *td, struct fio_file *f,
+			       enum zbd_zoned_model *model)
 {
 	int ret;
 
+	if (f->filetype == FIO_TYPE_PIPE) {
+		log_err("zonemode=zbd does not support pipes\n");
+		return -EINVAL;
+	}
+
+	/* If regular file, always emulate zones inside the file. */
+	if (f->filetype == FIO_TYPE_FILE) {
+		*model = ZBD_NONE;
+		return 0;
+	}
+
 	if (td->io_ops && td->io_ops->get_zoned_model)
 		ret = td->io_ops->get_zoned_model(td, f, model);
 	else
@@ -60,9 +177,9 @@ int zbd_get_zoned_model(struct thread_data *td, struct fio_file *f,
  * upon failure. If the zone report is empty, always assume an error (device
  * problem) and return -EIO.
  */
-int zbd_report_zones(struct thread_data *td, struct fio_file *f,
-		     uint64_t offset, struct zbd_zone *zones,
-		     unsigned int nr_zones)
+static int zbd_report_zones(struct thread_data *td, struct fio_file *f,
+			    uint64_t offset, struct zbd_zone *zones,
+			    unsigned int nr_zones)
 {
 	int ret;
 
@@ -72,12 +189,12 @@ int zbd_report_zones(struct thread_data *td, struct fio_file *f,
 		ret = blkzoned_report_zones(td, f, offset, zones, nr_zones);
 	if (ret < 0) {
 		td_verror(td, errno, "report zones failed");
-		log_err("%s: report zones from sector %llu failed (%d).\n",
-			f->file_name, (unsigned long long)offset >> 9, errno);
+		log_err("%s: report zones from sector %"PRIu64" failed (%d).\n",
+			f->file_name, offset >> 9, errno);
 	} else if (ret == 0) {
 		td_verror(td, errno, "Empty zone report");
-		log_err("%s: report zones from sector %llu is empty.\n",
-			f->file_name, (unsigned long long)offset >> 9);
+		log_err("%s: report zones from sector %"PRIu64" is empty.\n",
+			f->file_name, offset >> 9);
 		ret = -EIO;
 	}
 
@@ -94,8 +211,8 @@ int zbd_report_zones(struct thread_data *td, struct fio_file *f,
  * Reset the write pointer of all zones in the range @offset...@offset+@length.
  * Returns 0 upon success and a negative error code upon failure.
  */
-int zbd_reset_wp(struct thread_data *td, struct fio_file *f,
-		 uint64_t offset, uint64_t length)
+static int zbd_reset_wp(struct thread_data *td, struct fio_file *f,
+			uint64_t offset, uint64_t length)
 {
 	int ret;
 
@@ -105,112 +222,227 @@ int zbd_reset_wp(struct thread_data *td, struct fio_file *f,
 		ret = blkzoned_reset_wp(td, f, offset, length);
 	if (ret < 0) {
 		td_verror(td, errno, "resetting wp failed");
-		log_err("%s: resetting wp for %llu sectors at sector %llu failed (%d).\n",
-			f->file_name, (unsigned long long)length >> 9,
-			(unsigned long long)offset >> 9, errno);
+		log_err("%s: resetting wp for %"PRIu64" sectors at sector %"PRIu64" failed (%d).\n",
+			f->file_name, length >> 9, offset >> 9, errno);
 	}
 
 	return ret;
 }
 
 /**
- * zbd_zone_idx - convert an offset into a zone number
- * @f: file pointer.
- * @offset: offset in bytes. If this offset is in the first zone_size bytes
- *	    past the disk size then the index of the sentinel is returned.
+ * zbd_reset_zone - reset the write pointer of a single zone
+ * @td: FIO thread data.
+ * @f: FIO file associated with the disk for which to reset a write pointer.
+ * @z: Zone to reset.
+ *
+ * Returns 0 upon success and a negative error code upon failure.
+ *
+ * The caller must hold z->mutex.
  */
-static uint32_t zbd_zone_idx(const struct fio_file *f, uint64_t offset)
+static int zbd_reset_zone(struct thread_data *td, struct fio_file *f,
+			  struct fio_zone_info *z)
 {
-	uint32_t zone_idx;
+	uint64_t offset = z->start;
+	uint64_t length = (z+1)->start - offset;
+	uint64_t data_in_zone = z->wp - z->start;
+	int ret = 0;
 
-	if (f->zbd_info->zone_size_log2 > 0)
-		zone_idx = offset >> f->zbd_info->zone_size_log2;
-	else
-		zone_idx = offset / f->zbd_info->zone_size;
+	if (!data_in_zone)
+		return 0;
 
-	return min(zone_idx, f->zbd_info->nr_zones);
+	assert(is_valid_offset(f, offset + length - 1));
+
+	dprint(FD_ZBD, "%s: resetting wp of zone %u.\n", f->file_name,
+		zbd_zone_nr(f, z));
+	switch (f->zbd_info->model) {
+	case ZBD_HOST_AWARE:
+	case ZBD_HOST_MANAGED:
+		ret = zbd_reset_wp(td, f, offset, length);
+		if (ret < 0)
+			return ret;
+		break;
+	default:
+		break;
+	}
+
+	pthread_mutex_lock(&f->zbd_info->mutex);
+	f->zbd_info->sectors_with_data -= data_in_zone;
+	f->zbd_info->wp_sectors_with_data -= data_in_zone;
+	pthread_mutex_unlock(&f->zbd_info->mutex);
+	z->wp = z->start;
+	z->verify_block = 0;
+
+	td->ts.nr_zone_resets++;
+
+	return ret;
 }
 
 /**
- * zbd_zone_end - Return zone end location
- * @z: zone info pointer.
+ * zbd_close_zone - Remove a zone from the open zones array.
+ * @td: FIO thread data.
+ * @f: FIO file associated with the disk for which to reset a write pointer.
+ * @zone_idx: Index of the zone to remove.
+ *
+ * The caller must hold f->zbd_info->mutex.
  */
-static inline uint64_t zbd_zone_end(const struct fio_zone_info *z)
+static void zbd_close_zone(struct thread_data *td, const struct fio_file *f,
+			   unsigned int zone_idx)
 {
-	return (z+1)->start;
+	uint32_t open_zone_idx = 0;
+
+	for (; open_zone_idx < f->zbd_info->num_open_zones; open_zone_idx++) {
+		if (f->zbd_info->open_zones[open_zone_idx] == zone_idx)
+			break;
+	}
+	if (open_zone_idx == f->zbd_info->num_open_zones)
+		return;
+
+	dprint(FD_ZBD, "%s: closing zone %d\n", f->file_name, zone_idx);
+	memmove(f->zbd_info->open_zones + open_zone_idx,
+		f->zbd_info->open_zones + open_zone_idx + 1,
+		(ZBD_MAX_OPEN_ZONES - (open_zone_idx + 1)) *
+		sizeof(f->zbd_info->open_zones[0]));
+	f->zbd_info->num_open_zones--;
+	td->num_open_zones--;
+	get_zone(f, zone_idx)->open = 0;
 }
 
 /**
- * zbd_zone_capacity_end - Return zone capacity limit end location
- * @z: zone info pointer.
+ * zbd_reset_zones - Reset a range of zones.
+ * @td: fio thread data.
+ * @f: fio file for which to reset zones
+ * @zb: first zone to reset.
+ * @ze: first zone not to reset.
+ *
+ * Returns 0 upon success and 1 upon failure.
  */
-static inline uint64_t zbd_zone_capacity_end(const struct fio_zone_info *z)
+static int zbd_reset_zones(struct thread_data *td, struct fio_file *f,
+			   struct fio_zone_info *const zb,
+			   struct fio_zone_info *const ze)
 {
-	return z->start + z->capacity;
+	struct fio_zone_info *z;
+	const uint64_t min_bs = td->o.min_bs[DDIR_WRITE];
+	int res = 0;
+
+	assert(min_bs);
+
+	dprint(FD_ZBD, "%s: examining zones %u .. %u\n", f->file_name,
+		zbd_zone_nr(f, zb), zbd_zone_nr(f, ze));
+	for (z = zb; z < ze; z++) {
+		uint32_t nz = zbd_zone_nr(f, z);
+
+		if (!z->has_wp)
+			continue;
+		zone_lock(td, f, z);
+		pthread_mutex_lock(&f->zbd_info->mutex);
+		zbd_close_zone(td, f, nz);
+		pthread_mutex_unlock(&f->zbd_info->mutex);
+		if (z->wp != z->start) {
+			dprint(FD_ZBD, "%s: resetting zone %u\n",
+			       f->file_name, zbd_zone_nr(f, z));
+			if (zbd_reset_zone(td, f, z) < 0)
+				res = 1;
+		}
+		zone_unlock(z);
+	}
+
+	return res;
 }
 
 /**
- * zbd_zone_full - verify whether a minimum number of bytes remain in a zone
- * @f: file pointer.
- * @z: zone info pointer.
- * @required: minimum number of bytes that must remain in a zone.
+ * zbd_get_max_open_zones - Get the maximum number of open zones
+ * @td: FIO thread data
+ * @f: FIO file for which to get max open zones
+ * @max_open_zones: Upon success, result will be stored here.
  *
- * The caller must hold z->mutex.
+ * A @max_open_zones value set to zero means no limit.
+ *
+ * Returns 0 upon success and a negative error code upon failure.
  */
-static bool zbd_zone_full(const struct fio_file *f, struct fio_zone_info *z,
-			  uint64_t required)
+static int zbd_get_max_open_zones(struct thread_data *td, struct fio_file *f,
+				  unsigned int *max_open_zones)
 {
-	assert((required & 511) == 0);
+	int ret;
 
-	return z->has_wp &&
-		z->wp + required > zbd_zone_capacity_end(z);
+	if (td->io_ops && td->io_ops->get_max_open_zones)
+		ret = td->io_ops->get_max_open_zones(td, f, max_open_zones);
+	else
+		ret = blkzoned_get_max_open_zones(td, f, max_open_zones);
+	if (ret < 0) {
+		td_verror(td, errno, "get max open zones failed");
+		log_err("%s: get max open zones failed (%d).\n",
+			f->file_name, errno);
+	}
+
+	return ret;
 }
 
-static void zone_lock(struct thread_data *td, const struct fio_file *f,
-		      struct fio_zone_info *z)
+/**
+ * zbd_open_zone - Add a zone to the array of open zones.
+ * @td: fio thread data.
+ * @f: fio file that has the open zones to add.
+ * @zone_idx: Index of the zone to add.
+ *
+ * Open a ZBD zone if it is not already open. Returns true if either the zone
+ * was already open or if the zone was successfully added to the array of open
+ * zones without exceeding the maximum number of open zones. Returns false if
+ * the zone was not already open and opening the zone would cause the zone limit
+ * to be exceeded.
+ */
+static bool zbd_open_zone(struct thread_data *td, const struct fio_file *f,
+			  uint32_t zone_idx)
 {
-	struct zoned_block_device_info *zbd = f->zbd_info;
-	uint32_t nz = z - zbd->zone_info;
-
-	/* A thread should never lock zones outside its working area. */
-	assert(f->min_zone <= nz && nz < f->max_zone);
+	const uint64_t min_bs = td->o.min_bs[DDIR_WRITE];
+	struct zoned_block_device_info *zbdi = f->zbd_info;
+	struct fio_zone_info *z = get_zone(f, zone_idx);
+	bool res = true;
 
-	assert(z->has_wp);
+	if (z->cond == ZBD_ZONE_COND_OFFLINE)
+		return false;
 
 	/*
-	 * Lock the io_u target zone. The zone will be unlocked if io_u offset
-	 * is changed or when io_u completes and zbd_put_io() executed.
-	 * To avoid multiple jobs doing asynchronous I/Os from deadlocking each
-	 * other waiting for zone locks when building an io_u batch, first
-	 * only trylock the zone. If the zone is already locked by another job,
-	 * process the currently queued I/Os so that I/O progress is made and
-	 * zones unlocked.
+	 * Skip full zones with data verification enabled because resetting a
+	 * zone causes data loss and hence causes verification to fail.
 	 */
-	if (pthread_mutex_trylock(&z->mutex) != 0) {
-		if (!td_ioengine_flagged(td, FIO_SYNCIO))
-			io_u_quiesce(td);
-		pthread_mutex_lock(&z->mutex);
-	}
-}
+	if (td->o.verify != VERIFY_NONE && zbd_zone_full(f, z, min_bs))
+		return false;
 
-static inline void zone_unlock(struct fio_zone_info *z)
-{
-	int ret;
+	/*
+	 * zbdi->max_open_zones == 0 means that there is no limit on the maximum
+	 * number of open zones. In this case, do no track open zones in
+	 * zbdi->open_zones array.
+	 */
+	if (!zbdi->max_open_zones)
+		return true;
 
-	assert(z->has_wp);
-	ret = pthread_mutex_unlock(&z->mutex);
-	assert(!ret);
-}
+	pthread_mutex_lock(&zbdi->mutex);
 
-static bool is_valid_offset(const struct fio_file *f, uint64_t offset)
-{
-	return (uint64_t)(offset - f->file_offset) < f->io_size;
-}
+	if (z->open) {
+		/*
+		 * If the zone is going to be completely filled by writes
+		 * already in-flight, handle it as a full zone instead of an
+		 * open zone.
+		 */
+		if (z->wp >= zbd_zone_capacity_end(z))
+			res = false;
+		goto out;
+	}
+	res = false;
+	/* Zero means no limit */
+	if (td->o.job_max_open_zones > 0 &&
+	    td->num_open_zones >= td->o.job_max_open_zones)
+		goto out;
+	if (zbdi->num_open_zones >= zbdi->max_open_zones)
+		goto out;
+	dprint(FD_ZBD, "%s: opening zone %d\n", f->file_name, zone_idx);
+	zbdi->open_zones[zbdi->num_open_zones++] = zone_idx;
+	td->num_open_zones++;
+	z->open = 1;
+	res = true;
 
-static inline struct fio_zone_info *get_zone(const struct fio_file *f,
-					     unsigned int zone_nr)
-{
-	return &f->zbd_info->zone_info[zone_nr];
+out:
+	pthread_mutex_unlock(&zbdi->mutex);
+	return res;
 }
 
 /* Verify whether direct I/O is used for all host-managed zoned drives. */
@@ -279,18 +511,16 @@ static bool zbd_verify_sizes(void)
 					return false;
 				}
 			} else if (td->o.zone_size != f->zbd_info->zone_size) {
-				log_err("%s: job parameter zonesize %llu does not match disk zone size %llu.\n",
-					f->file_name, (unsigned long long) td->o.zone_size,
-					(unsigned long long) f->zbd_info->zone_size);
+				log_err("%s: job parameter zonesize %llu does not match disk zone size %"PRIu64".\n",
+					f->file_name, td->o.zone_size,
+					f->zbd_info->zone_size);
 				return false;
 			}
 
-			if (td->o.zone_skip &&
-			    (td->o.zone_skip < td->o.zone_size ||
-			     td->o.zone_skip % td->o.zone_size)) {
+			if (td->o.zone_skip % td->o.zone_size) {
 				log_err("%s: zoneskip %llu is not a multiple of the device zone size %llu.\n",
-					f->file_name, (unsigned long long) td->o.zone_skip,
-					(unsigned long long) td->o.zone_size);
+					f->file_name, td->o.zone_skip,
+					td->o.zone_size);
 				return false;
 			}
 
@@ -304,9 +534,9 @@ static bool zbd_verify_sizes(void)
 						 f->file_name);
 					return false;
 				}
-				log_info("%s: rounded up offset from %llu to %llu\n",
-					 f->file_name, (unsigned long long) f->file_offset,
-					 (unsigned long long) new_offset);
+				log_info("%s: rounded up offset from %"PRIu64" to %"PRIu64"\n",
+					 f->file_name, f->file_offset,
+					 new_offset);
 				f->io_size -= (new_offset - f->file_offset);
 				f->file_offset = new_offset;
 			}
@@ -320,9 +550,9 @@ static bool zbd_verify_sizes(void)
 						 f->file_name);
 					return false;
 				}
-				log_info("%s: rounded down io_size from %llu to %llu\n",
-					 f->file_name, (unsigned long long) f->io_size,
-					 (unsigned long long) new_end - f->file_offset);
+				log_info("%s: rounded down io_size from %"PRIu64" to %"PRIu64"\n",
+					 f->file_name, f->io_size,
+					 new_end - f->file_offset);
 				f->io_size = new_end - f->file_offset;
 			}
 		}
@@ -335,18 +565,31 @@ static bool zbd_verify_bs(void)
 {
 	struct thread_data *td;
 	struct fio_file *f;
-	uint32_t zone_size;
 	int i, j, k;
 
 	for_each_td(td, i) {
+		if (td_trim(td) &&
+		    (td->o.min_bs[DDIR_TRIM] != td->o.max_bs[DDIR_TRIM] ||
+		     td->o.bssplit_nr[DDIR_TRIM])) {
+			log_info("bsrange and bssplit are not allowed for trim with zonemode=zbd\n");
+			return false;
+		}
 		for_each_file(td, f, j) {
+			uint64_t zone_size;
+
 			if (!f->zbd_info)
 				continue;
 			zone_size = f->zbd_info->zone_size;
+			if (td_trim(td) && td->o.bs[DDIR_TRIM] != zone_size) {
+				log_info("%s: trim block size %llu is not the zone size %"PRIu64"\n",
+					 f->file_name, td->o.bs[DDIR_TRIM],
+					 zone_size);
+				return false;
+			}
 			for (k = 0; k < FIO_ARRAY_SIZE(td->o.bs); k++) {
 				if (td->o.verify != VERIFY_NONE &&
 				    zone_size % td->o.bs[k] != 0) {
-					log_info("%s: block size %llu is not a divisor of the zone size %d\n",
+					log_info("%s: block size %llu is not a divisor of the zone size %"PRIu64"\n",
 						 f->file_name, td->o.bs[k],
 						 zone_size);
 					return false;
@@ -382,7 +625,7 @@ static int init_zone_info(struct thread_data *td, struct fio_file *f)
 	int i;
 
 	if (zone_size == 0) {
-		log_err("%s: Specifying the zone size is mandatory for regular block devices with --zonemode=zbd\n\n",
+		log_err("%s: Specifying the zone size is mandatory for regular file/block device with --zonemode=zbd\n\n",
 			f->file_name);
 		return 1;
 	}
@@ -398,11 +641,16 @@ static int init_zone_info(struct thread_data *td, struct fio_file *f)
 
 	if (zone_capacity > zone_size) {
 		log_err("%s: job parameter zonecapacity %llu is larger than zone size %llu\n",
-			f->file_name, (unsigned long long) td->o.zone_capacity,
-			(unsigned long long) td->o.zone_size);
+			f->file_name, td->o.zone_capacity, td->o.zone_size);
 		return 1;
 	}
 
+	if (f->real_file_size < zone_size) {
+		log_err("%s: file/device size %"PRIu64" is smaller than zone size %"PRIu64"\n",
+			f->file_name, f->real_file_size, zone_size);
+		return -EINVAL;
+	}
+
 	nr_zones = (f->real_file_size + zone_size - 1) / zone_size;
 	zbd_info = scalloc(1, sizeof(*zbd_info) +
 			   (nr_zones + 1) * sizeof(zbd_info->zone_info[0]));
@@ -469,15 +717,14 @@ static int parse_zone_info(struct thread_data *td, struct fio_file *f)
 	if (td->o.zone_size == 0) {
 		td->o.zone_size = zone_size;
 	} else if (td->o.zone_size != zone_size) {
-		log_err("fio: %s job parameter zonesize %llu does not match disk zone size %llu.\n",
-			f->file_name, (unsigned long long) td->o.zone_size,
-			(unsigned long long) zone_size);
+		log_err("fio: %s job parameter zonesize %llu does not match disk zone size %"PRIu64".\n",
+			f->file_name, td->o.zone_size, zone_size);
 		ret = -EINVAL;
 		goto out;
 	}
 
-	dprint(FD_ZBD, "Device %s has %d zones of size %llu KB\n", f->file_name,
-	       nr_zones, (unsigned long long) zone_size / 1024);
+	dprint(FD_ZBD, "Device %s has %d zones of size %"PRIu64" KB\n", f->file_name,
+	       nr_zones, zone_size / 1024);
 
 	zbd_info = scalloc(1, sizeof(*zbd_info) +
 			   (nr_zones + 1) * sizeof(zbd_info->zone_info[0]));
@@ -531,9 +778,8 @@ static int parse_zone_info(struct thread_data *td, struct fio_file *f)
 					   ZBD_REPORT_MAX_ZONES));
 		if (nrz < 0) {
 			ret = nrz;
-			log_info("fio: report zones (offset %llu) failed for %s (%d).\n",
-			 	 (unsigned long long)offset,
-				 f->file_name, -ret);
+			log_info("fio: report zones (offset %"PRIu64") failed for %s (%d).\n",
+				 offset, f->file_name, -ret);
 			goto out;
 		}
 	}
@@ -555,6 +801,55 @@ out:
 	return ret;
 }
 
+static int zbd_set_max_open_zones(struct thread_data *td, struct fio_file *f)
+{
+	struct zoned_block_device_info *zbd = f->zbd_info;
+	unsigned int max_open_zones;
+	int ret;
+
+	if (zbd->model != ZBD_HOST_MANAGED || td->o.ignore_zone_limits) {
+		/* Only host-managed devices have a max open limit */
+		zbd->max_open_zones = td->o.max_open_zones;
+		goto out;
+	}
+
+	/* If host-managed, get the max open limit */
+	ret = zbd_get_max_open_zones(td, f, &max_open_zones);
+	if (ret)
+		return ret;
+
+	if (!max_open_zones) {
+		/* No device limit */
+		zbd->max_open_zones = td->o.max_open_zones;
+	} else if (!td->o.max_open_zones) {
+		/* No user limit. Set limit to device limit */
+		zbd->max_open_zones = max_open_zones;
+	} else if (td->o.max_open_zones <= max_open_zones) {
+		/* Both user limit and dev limit. User limit not too large */
+		zbd->max_open_zones = td->o.max_open_zones;
+	} else {
+		/* Both user limit and dev limit. User limit too large */
+		td_verror(td, EINVAL,
+			  "Specified --max_open_zones is too large");
+		log_err("Specified --max_open_zones (%d) is larger than max (%u)\n",
+			td->o.max_open_zones, max_open_zones);
+		return -EINVAL;
+	}
+
+out:
+	/* Ensure that the limit is not larger than FIO's internal limit */
+	if (zbd->max_open_zones > ZBD_MAX_OPEN_ZONES) {
+		td_verror(td, EINVAL, "'max_open_zones' value is too large");
+		log_err("'max_open_zones' value is larger than %u\n", ZBD_MAX_OPEN_ZONES);
+		return -EINVAL;
+	}
+
+	dprint(FD_ZBD, "%s: using max open zones limit: %"PRIu32"\n",
+	       f->file_name, zbd->max_open_zones);
+
+	return 0;
+}
+
 /*
  * Allocate zone information and store it into f->zbd_info if zonemode=zbd.
  *
@@ -572,14 +867,16 @@ static int zbd_create_zone_info(struct thread_data *td, struct fio_file *f)
 		return ret;
 
 	switch (zbd_model) {
-	case ZBD_IGNORE:
-		return 0;
 	case ZBD_HOST_AWARE:
 	case ZBD_HOST_MANAGED:
 		ret = parse_zone_info(td, f);
+		if (ret)
+			return ret;
 		break;
 	case ZBD_NONE:
 		ret = init_zone_info(td, f);
+		if (ret)
+			return ret;
 		break;
 	default:
 		td_verror(td, EINVAL, "Unsupported zoned model");
@@ -587,11 +884,16 @@ static int zbd_create_zone_info(struct thread_data *td, struct fio_file *f)
 		return -EINVAL;
 	}
 
-	if (ret == 0) {
-		f->zbd_info->model = zbd_model;
-		f->zbd_info->max_open_zones = td->o.max_open_zones;
+	assert(f->zbd_info);
+	f->zbd_info->model = zbd_model;
+
+	ret = zbd_set_max_open_zones(td, f);
+	if (ret) {
+		zbd_free_zone_info(f);
+		return ret;
 	}
-	return ret;
+
+	return 0;
 }
 
 void zbd_free_zone_info(struct fio_file *f)
@@ -636,28 +938,61 @@ static int zbd_init_zone_info(struct thread_data *td, struct fio_file *file)
 			return 0;
 		}
 	}
-
-	ret = zbd_create_zone_info(td, file);
-	if (ret < 0)
-		td_verror(td, -ret, "zbd_create_zone_info() failed");
-	return ret;
+
+	ret = zbd_create_zone_info(td, file);
+	if (ret < 0)
+		td_verror(td, -ret, "zbd_create_zone_info() failed");
+	return ret;
+}
+
+int zbd_init_files(struct thread_data *td)
+{
+	struct fio_file *f;
+	int i;
+
+	for_each_file(td, f, i) {
+		if (zbd_init_zone_info(td, f))
+			return 1;
+	}
+	return 0;
+}
+
+void zbd_recalc_options_with_zone_granularity(struct thread_data *td)
+{
+	struct fio_file *f;
+	int i;
+
+	for_each_file(td, f, i) {
+		struct zoned_block_device_info *zbd = f->zbd_info;
+		// zonemode=strided doesn't get per-file zone size.
+		uint64_t zone_size = zbd ? zbd->zone_size : td->o.zone_size;
+
+		if (zone_size == 0)
+			continue;
+
+		if (td->o.size_nz > 0) {
+			td->o.size = td->o.size_nz * zone_size;
+		}
+		if (td->o.io_size_nz > 0) {
+			td->o.io_size = td->o.io_size_nz * zone_size;
+		}
+		if (td->o.start_offset_nz > 0) {
+			td->o.start_offset = td->o.start_offset_nz * zone_size;
+		}
+		if (td->o.offset_increment_nz > 0) {
+			td->o.offset_increment = td->o.offset_increment_nz * zone_size;
+		}
+		if (td->o.zone_skip_nz > 0) {
+			td->o.zone_skip = td->o.zone_skip_nz * zone_size;
+		}
+	}
 }
 
-static bool zbd_open_zone(struct thread_data *td, const struct fio_file *f,
-			  uint32_t zone_idx);
-static int zbd_reset_zone(struct thread_data *td, struct fio_file *f,
-			  struct fio_zone_info *z);
-
 int zbd_setup_files(struct thread_data *td)
 {
 	struct fio_file *f;
 	int i;
 
-	for_each_file(td, f, i) {
-		if (zbd_init_zone_info(td, f))
-			return 1;
-	}
-
 	if (!zbd_using_direct_io()) {
 		log_err("Using direct I/O is mandatory for writing to ZBD drives\n\n");
 		return 1;
@@ -674,8 +1009,7 @@ int zbd_setup_files(struct thread_data *td)
 		struct fio_zone_info *z;
 		int zi;
 
-		if (!zbd)
-			continue;
+		assert(zbd);
 
 		f->min_zone = zbd_zone_idx(f, f->file_offset);
 		f->max_zone = zbd_zone_idx(f, f->file_offset + f->io_size);
@@ -689,18 +1023,30 @@ int zbd_setup_files(struct thread_data *td)
 		if (zbd_is_seq_job(f))
 			assert(f->min_zone < f->max_zone);
 
-		zbd->max_open_zones = zbd->max_open_zones ?: ZBD_MAX_OPEN_ZONES;
-
 		if (td->o.max_open_zones > 0 &&
 		    zbd->max_open_zones != td->o.max_open_zones) {
 			log_err("Different 'max_open_zones' values\n");
 			return 1;
 		}
-		if (zbd->max_open_zones > ZBD_MAX_OPEN_ZONES) {
-			log_err("'max_open_zones' value is limited by %u\n", ZBD_MAX_OPEN_ZONES);
+
+		/*
+		 * The per job max open zones limit cannot be used without a
+		 * global max open zones limit. (As the tracking of open zones
+		 * is disabled when there is no global max open zones limit.)
+		 */
+		if (td->o.job_max_open_zones && !zbd->max_open_zones) {
+			log_err("'job_max_open_zones' cannot be used without a global open zones limit\n");
 			return 1;
 		}
 
+		/*
+		 * zbd->max_open_zones is the global limit shared for all jobs
+		 * that target the same zoned block device. Force sync the per
+		 * thread global limit with the actual global limit. (The real
+		 * per thread/job limit is stored in td->o.job_max_open_zones).
+		 */
+		td->o.max_open_zones = zbd->max_open_zones;
+
 		for (zi = f->min_zone; zi < f->max_zone; zi++) {
 			z = &zbd->zone_info[zi];
 			if (z->cond != ZBD_ZONE_COND_IMP_OPEN &&
@@ -722,132 +1068,6 @@ int zbd_setup_files(struct thread_data *td)
 	return 0;
 }
 
-static inline unsigned int zbd_zone_nr(const struct fio_file *f,
-				       struct fio_zone_info *zone)
-{
-	return zone - f->zbd_info->zone_info;
-}
-
-/**
- * zbd_reset_zone - reset the write pointer of a single zone
- * @td: FIO thread data.
- * @f: FIO file associated with the disk for which to reset a write pointer.
- * @z: Zone to reset.
- *
- * Returns 0 upon success and a negative error code upon failure.
- *
- * The caller must hold z->mutex.
- */
-static int zbd_reset_zone(struct thread_data *td, struct fio_file *f,
-			  struct fio_zone_info *z)
-{
-	uint64_t offset = z->start;
-	uint64_t length = (z+1)->start - offset;
-	uint64_t data_in_zone = z->wp - z->start;
-	int ret = 0;
-
-	if (!data_in_zone)
-		return 0;
-
-	assert(is_valid_offset(f, offset + length - 1));
-
-	dprint(FD_ZBD, "%s: resetting wp of zone %u.\n", f->file_name,
-		zbd_zone_nr(f, z));
-	switch (f->zbd_info->model) {
-	case ZBD_HOST_AWARE:
-	case ZBD_HOST_MANAGED:
-		ret = zbd_reset_wp(td, f, offset, length);
-		if (ret < 0)
-			return ret;
-		break;
-	default:
-		break;
-	}
-
-	pthread_mutex_lock(&f->zbd_info->mutex);
-	f->zbd_info->sectors_with_data -= data_in_zone;
-	f->zbd_info->wp_sectors_with_data -= data_in_zone;
-	pthread_mutex_unlock(&f->zbd_info->mutex);
-	z->wp = z->start;
-	z->verify_block = 0;
-
-	td->ts.nr_zone_resets++;
-
-	return ret;
-}
-
-/* The caller must hold f->zbd_info->mutex */
-static void zbd_close_zone(struct thread_data *td, const struct fio_file *f,
-			   unsigned int zone_idx)
-{
-	uint32_t open_zone_idx = 0;
-
-	for (; open_zone_idx < f->zbd_info->num_open_zones; open_zone_idx++) {
-		if (f->zbd_info->open_zones[open_zone_idx] == zone_idx)
-			break;
-	}
-	if (open_zone_idx == f->zbd_info->num_open_zones)
-		return;
-
-	dprint(FD_ZBD, "%s: closing zone %d\n", f->file_name, zone_idx);
-	memmove(f->zbd_info->open_zones + open_zone_idx,
-		f->zbd_info->open_zones + open_zone_idx + 1,
-		(ZBD_MAX_OPEN_ZONES - (open_zone_idx + 1)) *
-		sizeof(f->zbd_info->open_zones[0]));
-	f->zbd_info->num_open_zones--;
-	td->num_open_zones--;
-	get_zone(f, zone_idx)->open = 0;
-}
-
-/*
- * Reset a range of zones. Returns 0 upon success and 1 upon failure.
- * @td: fio thread data.
- * @f: fio file for which to reset zones
- * @zb: first zone to reset.
- * @ze: first zone not to reset.
- * @all_zones: whether to reset all zones or only those zones for which the
- *	write pointer is not a multiple of td->o.min_bs[DDIR_WRITE].
- */
-static int zbd_reset_zones(struct thread_data *td, struct fio_file *f,
-			   struct fio_zone_info *const zb,
-			   struct fio_zone_info *const ze, bool all_zones)
-{
-	struct fio_zone_info *z;
-	const uint32_t min_bs = td->o.min_bs[DDIR_WRITE];
-	bool reset_wp;
-	int res = 0;
-
-	assert(min_bs);
-
-	dprint(FD_ZBD, "%s: examining zones %u .. %u\n", f->file_name,
-		zbd_zone_nr(f, zb), zbd_zone_nr(f, ze));
-	for (z = zb; z < ze; z++) {
-		uint32_t nz = zbd_zone_nr(f, z);
-
-		if (!z->has_wp)
-			continue;
-		zone_lock(td, f, z);
-		if (all_zones) {
-			pthread_mutex_lock(&f->zbd_info->mutex);
-			zbd_close_zone(td, f, nz);
-			pthread_mutex_unlock(&f->zbd_info->mutex);
-
-			reset_wp = z->wp != z->start;
-		} else {
-			reset_wp = z->wp % min_bs != 0;
-		}
-		if (reset_wp) {
-			dprint(FD_ZBD, "%s: resetting zone %u\n",
-			       f->file_name, zbd_zone_nr(f, z));
-			if (zbd_reset_zone(td, f, z) < 0)
-				res = 1;
-		}
-		zone_unlock(z);
-	}
-
-	return res;
-}
-
 /*
  * Reset zbd_info.write_cnt, the counter that counts down towards the next
  * zone reset.
@@ -959,85 +1179,30 @@ void zbd_file_reset(struct thread_data *td, struct fio_file *f)
 	 * writing any data to avoid that a zone reset has to be issued while
 	 * writing data, which causes data loss.
 	 */
-	zbd_reset_zones(td, f, zb, ze, td->o.verify != VERIFY_NONE &&
-			td->runstate != TD_VERIFYING);
+	if (td->o.verify != VERIFY_NONE && td->runstate != TD_VERIFYING)
+		zbd_reset_zones(td, f, zb, ze);
 	zbd_reset_write_cnt(td, f);
 }
 
-/* The caller must hold f->zbd_info->mutex. */
-static bool is_zone_open(const struct thread_data *td, const struct fio_file *f,
-			 unsigned int zone_idx)
+/* Return random zone index for one of the open zones. */
+static uint32_t pick_random_zone_idx(const struct fio_file *f,
+				     const struct io_u *io_u)
 {
-	struct zoned_block_device_info *zbdi = f->zbd_info;
-	int i;
-
-	assert(td->o.job_max_open_zones == 0 || td->num_open_zones <= td->o.job_max_open_zones);
-	assert(td->o.job_max_open_zones <= zbdi->max_open_zones);
-	assert(zbdi->num_open_zones <= zbdi->max_open_zones);
-
-	for (i = 0; i < zbdi->num_open_zones; i++)
-		if (zbdi->open_zones[i] == zone_idx)
-			return true;
-
-	return false;
+	return (io_u->offset - f->file_offset) * f->zbd_info->num_open_zones /
+		f->io_size;
 }
 
-/*
- * Open a ZBD zone if it was not yet open. Returns true if either the zone was
- * already open or if opening a new zone is allowed. Returns false if the zone
- * was not yet open and opening a new zone would cause the zone limit to be
- * exceeded.
- */
-static bool zbd_open_zone(struct thread_data *td, const struct fio_file *f,
-			  uint32_t zone_idx)
+static bool any_io_in_flight(void)
 {
-	const uint32_t min_bs = td->o.min_bs[DDIR_WRITE];
-	struct fio_zone_info *z = get_zone(f, zone_idx);
-	bool res = true;
-
-	if (z->cond == ZBD_ZONE_COND_OFFLINE)
-		return false;
-
-	/*
-	 * Skip full zones with data verification enabled because resetting a
-	 * zone causes data loss and hence causes verification to fail.
-	 */
-	if (td->o.verify != VERIFY_NONE && zbd_zone_full(f, z, min_bs))
-		return false;
+	struct thread_data *td;
+	int i;
 
-	pthread_mutex_lock(&f->zbd_info->mutex);
-	if (is_zone_open(td, f, zone_idx)) {
-		/*
-		 * If the zone is already open and going to be full by writes
-		 * in-flight, handle it as a full zone instead of an open zone.
-		 */
-		if (z->wp >= zbd_zone_capacity_end(z))
-			res = false;
-		goto out;
+	for_each_td(td, i) {
+		if (td->io_u_in_flight)
+			return true;
 	}
-	res = false;
-	/* Zero means no limit */
-	if (td->o.job_max_open_zones > 0 &&
-	    td->num_open_zones >= td->o.job_max_open_zones)
-		goto out;
-	if (f->zbd_info->num_open_zones >= f->zbd_info->max_open_zones)
-		goto out;
-	dprint(FD_ZBD, "%s: opening zone %d\n", f->file_name, zone_idx);
-	f->zbd_info->open_zones[f->zbd_info->num_open_zones++] = zone_idx;
-	td->num_open_zones++;
-	z->open = 1;
-	res = true;
-
-out:
-	pthread_mutex_unlock(&f->zbd_info->mutex);
-	return res;
-}
 
-/* Anything goes as long as it is not a constant. */
-static uint32_t pick_random_zone_idx(const struct fio_file *f,
-				     const struct io_u *io_u)
-{
-	return io_u->offset * f->zbd_info->num_open_zones / f->real_file_size;
+	return false;
 }
 
 /*
@@ -1051,22 +1216,25 @@ static uint32_t pick_random_zone_idx(const struct fio_file *f,
 static struct fio_zone_info *zbd_convert_to_open_zone(struct thread_data *td,
 						      struct io_u *io_u)
 {
-	const uint32_t min_bs = td->o.min_bs[io_u->ddir];
+	const uint64_t min_bs = td->o.min_bs[io_u->ddir];
 	struct fio_file *f = io_u->file;
+	struct zoned_block_device_info *zbdi = f->zbd_info;
 	struct fio_zone_info *z;
 	unsigned int open_zone_idx = -1;
 	uint32_t zone_idx, new_zone_idx;
 	int i;
 	bool wait_zone_close;
+	bool in_flight;
+	bool should_retry = true;
 
 	assert(is_valid_offset(f, io_u->offset));
 
-	if (td->o.max_open_zones || td->o.job_max_open_zones) {
+	if (zbdi->max_open_zones || td->o.job_max_open_zones) {
 		/*
-		 * This statement accesses f->zbd_info->open_zones[] on purpose
+		 * This statement accesses zbdi->open_zones[] on purpose
 		 * without locking.
 		 */
-		zone_idx = f->zbd_info->open_zones[pick_random_zone_idx(f, io_u)];
+		zone_idx = zbdi->open_zones[pick_random_zone_idx(f, io_u)];
 	} else {
 		zone_idx = zbd_zone_idx(f, io_u->offset);
 	}
@@ -1078,9 +1246,9 @@ static struct fio_zone_info *zbd_convert_to_open_zone(struct thread_data *td,
 	       __func__, f->file_name, zone_idx, io_u->offset, io_u->buflen);
 
 	/*
-	 * Since z->mutex is the outer lock and f->zbd_info->mutex the inner
+	 * Since z->mutex is the outer lock and zbdi->mutex the inner
 	 * lock it can happen that the state of the zone with index zone_idx
-	 * has changed after 'z' has been assigned and before f->zbd_info->mutex
+	 * has changed after 'z' has been assigned and before zbdi->mutex
 	 * has been obtained. Hence the loop.
 	 */
 	for (;;) {
@@ -1089,12 +1257,12 @@ static struct fio_zone_info *zbd_convert_to_open_zone(struct thread_data *td,
 		z = get_zone(f, zone_idx);
 		if (z->has_wp)
 			zone_lock(td, f, z);
-		pthread_mutex_lock(&f->zbd_info->mutex);
+		pthread_mutex_lock(&zbdi->mutex);
 		if (z->has_wp) {
 			if (z->cond != ZBD_ZONE_COND_OFFLINE &&
-			    td->o.max_open_zones == 0 && td->o.job_max_open_zones == 0)
+			    zbdi->max_open_zones == 0 && td->o.job_max_open_zones == 0)
 				goto examine_zone;
-			if (f->zbd_info->num_open_zones == 0) {
+			if (zbdi->num_open_zones == 0) {
 				dprint(FD_ZBD, "%s(%s): no zones are open\n",
 				       __func__, f->file_name);
 				goto open_other_zone;
@@ -1108,14 +1276,14 @@ static struct fio_zone_info *zbd_convert_to_open_zone(struct thread_data *td,
 		 */
 		open_zone_idx = pick_random_zone_idx(f, io_u);
 		assert(!open_zone_idx ||
-		       open_zone_idx < f->zbd_info->num_open_zones);
+		       open_zone_idx < zbdi->num_open_zones);
 		tmp_idx = open_zone_idx;
-		for (i = 0; i < f->zbd_info->num_open_zones; i++) {
+		for (i = 0; i < zbdi->num_open_zones; i++) {
 			uint32_t tmpz;
 
-			if (tmp_idx >= f->zbd_info->num_open_zones)
+			if (tmp_idx >= zbdi->num_open_zones)
 				tmp_idx = 0;
-			tmpz = f->zbd_info->open_zones[tmp_idx];
+			tmpz = zbdi->open_zones[tmp_idx];
 			if (f->min_zone <= tmpz && tmpz < f->max_zone) {
 				open_zone_idx = tmp_idx;
 				goto found_candidate_zone;
@@ -1126,39 +1294,39 @@ static struct fio_zone_info *zbd_convert_to_open_zone(struct thread_data *td,
 
 		dprint(FD_ZBD, "%s(%s): no candidate zone\n",
 			__func__, f->file_name);
-		pthread_mutex_unlock(&f->zbd_info->mutex);
+		pthread_mutex_unlock(&zbdi->mutex);
 		if (z->has_wp)
 			zone_unlock(z);
 		return NULL;
 
 found_candidate_zone:
-		new_zone_idx = f->zbd_info->open_zones[open_zone_idx];
+		new_zone_idx = zbdi->open_zones[open_zone_idx];
 		if (new_zone_idx == zone_idx)
 			break;
 		zone_idx = new_zone_idx;
-		pthread_mutex_unlock(&f->zbd_info->mutex);
+		pthread_mutex_unlock(&zbdi->mutex);
 		if (z->has_wp)
 			zone_unlock(z);
 	}
 
-	/* Both z->mutex and f->zbd_info->mutex are held. */
+	/* Both z->mutex and zbdi->mutex are held. */
 
 examine_zone:
 	if (z->wp + min_bs <= zbd_zone_capacity_end(z)) {
-		pthread_mutex_unlock(&f->zbd_info->mutex);
+		pthread_mutex_unlock(&zbdi->mutex);
 		goto out;
 	}
 
 open_other_zone:
 	/* Check if number of open zones reaches one of limits. */
 	wait_zone_close =
-		f->zbd_info->num_open_zones == f->max_zone - f->min_zone ||
-		(td->o.max_open_zones &&
-		 f->zbd_info->num_open_zones == td->o.max_open_zones) ||
+		zbdi->num_open_zones == f->max_zone - f->min_zone ||
+		(zbdi->max_open_zones &&
+		 zbdi->num_open_zones == zbdi->max_open_zones) ||
 		(td->o.job_max_open_zones &&
 		 td->num_open_zones == td->o.job_max_open_zones);
 
-	pthread_mutex_unlock(&f->zbd_info->mutex);
+	pthread_mutex_unlock(&zbdi->mutex);
 
 	/* Only z->mutex is held. */
 
@@ -1172,8 +1340,9 @@ open_other_zone:
 		io_u_quiesce(td);
 	}
 
+retry:
 	/* Zone 'z' is full, so try to open a new zone. */
-	for (i = f->io_size / f->zbd_info->zone_size; i > 0; i--) {
+	for (i = f->io_size / zbdi->zone_size; i > 0; i--) {
 		zone_idx++;
 		if (z->has_wp)
 			zone_unlock(z);
@@ -1196,12 +1365,12 @@ open_other_zone:
 	/* Only z->mutex is held. */
 
 	/* Check whether the write fits in any of the already opened zones. */
-	pthread_mutex_lock(&f->zbd_info->mutex);
-	for (i = 0; i < f->zbd_info->num_open_zones; i++) {
-		zone_idx = f->zbd_info->open_zones[i];
+	pthread_mutex_lock(&zbdi->mutex);
+	for (i = 0; i < zbdi->num_open_zones; i++) {
+		zone_idx = zbdi->open_zones[i];
 		if (zone_idx < f->min_zone || zone_idx >= f->max_zone)
 			continue;
-		pthread_mutex_unlock(&f->zbd_info->mutex);
+		pthread_mutex_unlock(&zbdi->mutex);
 		zone_unlock(z);
 
 		z = get_zone(f, zone_idx);
@@ -1209,9 +1378,27 @@ open_other_zone:
 		zone_lock(td, f, z);
 		if (z->wp + min_bs <= zbd_zone_capacity_end(z))
 			goto out;
-		pthread_mutex_lock(&f->zbd_info->mutex);
+		pthread_mutex_lock(&zbdi->mutex);
 	}
-	pthread_mutex_unlock(&f->zbd_info->mutex);
+
+	/*
+	 * When any I/O is in-flight or when all I/Os in-flight get completed,
+	 * the I/Os might have closed zones then retry the steps to open a zone.
+	 * Before retry, call io_u_quiesce() to complete in-flight writes.
+	 */
+	in_flight = any_io_in_flight();
+	if (in_flight || should_retry) {
+		dprint(FD_ZBD, "%s(%s): wait zone close and retry open zones\n",
+		       __func__, f->file_name);
+		pthread_mutex_unlock(&zbdi->mutex);
+		zone_unlock(z);
+		io_u_quiesce(td);
+		zone_lock(td, f, z);
+		should_retry = in_flight;
+		goto retry;
+	}
+
+	pthread_mutex_unlock(&zbdi->mutex);
 	zone_unlock(z);
 	dprint(FD_ZBD, "%s(%s): did not open another zone\n", __func__,
 	       f->file_name);
@@ -1232,7 +1419,7 @@ static struct fio_zone_info *zbd_replay_write_order(struct thread_data *td,
 						    struct fio_zone_info *z)
 {
 	const struct fio_file *f = io_u->file;
-	const uint32_t min_bs = td->o.min_bs[DDIR_WRITE];
+	const uint64_t min_bs = td->o.min_bs[DDIR_WRITE];
 
 	if (!zbd_open_zone(td, f, zbd_zone_nr(f, z))) {
 		zone_unlock(z);
@@ -1241,8 +1428,8 @@ static struct fio_zone_info *zbd_replay_write_order(struct thread_data *td,
 	}
 
 	if (z->verify_block * min_bs >= z->capacity) {
-		log_err("%s: %d * %d >= %llu\n", f->file_name, z->verify_block,
-			min_bs, (unsigned long long)z->capacity);
+		log_err("%s: %d * %"PRIu64" >= %"PRIu64"\n", f->file_name, z->verify_block,
+			min_bs, z->capacity);
 		/*
 		 * If the assertion below fails during a test run, adding
 		 * "--experimental_verify=1" to the command line may help.
@@ -1251,8 +1438,8 @@ static struct fio_zone_info *zbd_replay_write_order(struct thread_data *td,
 	}
 	io_u->offset = z->start + z->verify_block * min_bs;
 	if (io_u->offset + io_u->buflen >= zbd_zone_capacity_end(z)) {
-		log_err("%s: %llu + %llu >= %llu\n", f->file_name, io_u->offset,
-			io_u->buflen, (unsigned long long) zbd_zone_capacity_end(z));
+		log_err("%s: %llu + %llu >= %"PRIu64"\n", f->file_name, io_u->offset,
+			io_u->buflen, zbd_zone_capacity_end(z));
 		assert(false);
 	}
 	z->verify_block += io_u->buflen / min_bs;
@@ -1261,18 +1448,16 @@ static struct fio_zone_info *zbd_replay_write_order(struct thread_data *td,
 }
 
 /*
- * Find another zone for which @io_u fits in the readable data in the zone.
- * Search in zones @zb + 1 .. @zl. For random workload, also search in zones
- * @zb - 1 .. @zf.
+ * Find another zone which has @min_bytes of readable data. Search in zones
+ * @zb + 1 .. @zl. For random workload, also search in zones @zb - 1 .. @zf.
  *
  * Either returns NULL or returns a zone pointer. When the zone has write
  * pointer, hold the mutex for the zone.
  */
 static struct fio_zone_info *
-zbd_find_zone(struct thread_data *td, struct io_u *io_u,
+zbd_find_zone(struct thread_data *td, struct io_u *io_u, uint64_t min_bytes,
 	      struct fio_zone_info *zb, struct fio_zone_info *zl)
 {
-	const uint32_t min_bs = td->o.min_bs[io_u->ddir];
 	struct fio_file *f = io_u->file;
 	struct fio_zone_info *z1, *z2;
 	const struct fio_zone_info *const zf = get_zone(f, f->min_zone);
@@ -1285,7 +1470,7 @@ zbd_find_zone(struct thread_data *td, struct io_u *io_u,
 		if (z1 < zl && z1->cond != ZBD_ZONE_COND_OFFLINE) {
 			if (z1->has_wp)
 				zone_lock(td, f, z1);
-			if (z1->start + min_bs <= z1->wp)
+			if (z1->start + min_bytes <= z1->wp)
 				return z1;
 			if (z1->has_wp)
 				zone_unlock(z1);
@@ -1296,14 +1481,14 @@ zbd_find_zone(struct thread_data *td, struct io_u *io_u,
 		    z2->cond != ZBD_ZONE_COND_OFFLINE) {
 			if (z2->has_wp)
 				zone_lock(td, f, z2);
-			if (z2->start + min_bs <= z2->wp)
+			if (z2->start + min_bytes <= z2->wp)
 				return z2;
 			if (z2->has_wp)
 				zone_unlock(z2);
 		}
 	}
-	dprint(FD_ZBD, "%s: adjusting random read offset failed\n",
-	       f->file_name);
+	dprint(FD_ZBD, "%s: no zone has %"PRIu64" bytes of readable data\n",
+	       f->file_name, min_bytes);
 	return NULL;
 }
 
@@ -1347,8 +1532,7 @@ static void zbd_queue_io(struct thread_data *td, struct io_u *io_u, int q,
 	uint32_t zone_idx;
 	uint64_t zone_end;
 
-	if (!zbd_info)
-		return;
+	assert(zbd_info);
 
 	zone_idx = zbd_zone_idx(f, io_u->offset);
 	assert(zone_idx < zbd_info->nr_zones);
@@ -1379,9 +1563,6 @@ static void zbd_queue_io(struct thread_data *td, struct io_u *io_u, int q,
 		pthread_mutex_unlock(&zbd_info->mutex);
 		z->wp = zone_end;
 		break;
-	case DDIR_TRIM:
-		assert(z->wp == z->start);
-		break;
 	default:
 		break;
 	}
@@ -1408,8 +1589,7 @@ static void zbd_put_io(struct thread_data *td, const struct io_u *io_u)
 	struct fio_zone_info *z;
 	uint32_t zone_idx;
 
-	if (!zbd_info)
-		return;
+	assert(zbd_info);
 
 	zone_idx = zbd_zone_idx(f, io_u->offset);
 	assert(zone_idx < zbd_info->nr_zones);
@@ -1465,6 +1645,7 @@ void setup_zbd_zone_mode(struct thread_data *td, struct io_u *io_u)
 
 	assert(td->o.zone_mode == ZONE_MODE_ZBD);
 	assert(td->o.zone_size);
+	assert(f->zbd_info);
 
 	zone_idx = zbd_zone_idx(f, f->last_pos[ddir]);
 	z = get_zone(f, zone_idx);
@@ -1479,10 +1660,9 @@ void setup_zbd_zone_mode(struct thread_data *td, struct io_u *io_u)
 	    f->last_pos[ddir] >= zbd_zone_capacity_end(z)) {
 		dprint(FD_ZBD,
 		       "%s: Jump from zone capacity limit to zone end:"
-		       " (%llu -> %llu) for zone %u (%llu)\n",
-		       f->file_name, (unsigned long long) f->last_pos[ddir],
-		       (unsigned long long) zbd_zone_end(z), zone_idx,
-		       (unsigned long long) z->capacity);
+		       " (%"PRIu64" -> %"PRIu64") for zone %u (%"PRIu64")\n",
+		       f->file_name, f->last_pos[ddir],
+		       zbd_zone_end(z), zone_idx, z->capacity);
 		td->io_skip_bytes += zbd_zone_end(z) - f->last_pos[ddir];
 		f->last_pos[ddir] = zbd_zone_end(z);
 	}
@@ -1539,6 +1719,7 @@ enum fio_ddir zbd_adjust_ddir(struct thread_data *td, struct io_u *io_u,
 	 * devices with all empty zones. Overwrite the first I/O direction as
 	 * write to make sure data to read exists.
 	 */
+	assert(io_u->file->zbd_info);
 	if (ddir != DDIR_READ || !td_rw(td))
 		return ddir;
 
@@ -1561,16 +1742,15 @@ enum fio_ddir zbd_adjust_ddir(struct thread_data *td, struct io_u *io_u,
 enum io_u_action zbd_adjust_block(struct thread_data *td, struct io_u *io_u)
 {
 	struct fio_file *f = io_u->file;
+	struct zoned_block_device_info *zbdi = f->zbd_info;
 	uint32_t zone_idx_b;
 	struct fio_zone_info *zb, *zl, *orig_zb;
 	uint32_t orig_len = io_u->buflen;
-	uint32_t min_bs = td->o.min_bs[io_u->ddir];
+	uint64_t min_bs = td->o.min_bs[io_u->ddir];
 	uint64_t new_len;
 	int64_t range;
 
-	if (!f->zbd_info)
-		return io_u_accept;
-
+	assert(zbdi);
 	assert(min_bs);
 	assert(is_valid_offset(f, io_u->offset));
 	assert(io_u->buflen);
@@ -1592,9 +1772,9 @@ enum io_u_action zbd_adjust_block(struct thread_data *td, struct io_u *io_u)
 
 		if (io_u->offset + min_bs > (zb + 1)->start) {
 			dprint(FD_IO,
-			       "%s: off=%llu + min_bs=%u > next zone %llu\n",
+			       "%s: off=%llu + min_bs=%"PRIu64" > next zone %"PRIu64"\n",
 			       f->file_name, io_u->offset,
-			       min_bs, (unsigned long long) (zb + 1)->start);
+			       min_bs, (zb + 1)->start);
 			io_u->offset = zb->start + (zb + 1)->start - io_u->offset;
 			new_len = min(io_u->buflen, (zb + 1)->start - io_u->offset);
 		} else {
@@ -1633,7 +1813,7 @@ enum io_u_action zbd_adjust_block(struct thread_data *td, struct io_u *io_u)
 		    ((!td_random(td)) && (io_u->offset + min_bs > zb->wp))) {
 			zone_unlock(zb);
 			zl = get_zone(f, f->max_zone);
-			zb = zbd_find_zone(td, io_u, zb, zl);
+			zb = zbd_find_zone(td, io_u, min_bs, zb, zl);
 			if (!zb) {
 				dprint(FD_ZBD,
 				       "%s: zbd_find_zone(%lld, %llu) failed\n",
@@ -1682,12 +1862,11 @@ enum io_u_action zbd_adjust_block(struct thread_data *td, struct io_u *io_u)
 		assert(io_u->offset + io_u->buflen <= zb->wp);
 		goto accept;
 	case DDIR_WRITE:
-		if (io_u->buflen > f->zbd_info->zone_size) {
+		if (io_u->buflen > zbdi->zone_size) {
 			td_verror(td, EINVAL, "I/O buflen exceeds zone size");
 			dprint(FD_IO,
-			       "%s: I/O buflen %llu exceeds zone size %llu\n",
-			       f->file_name, io_u->buflen,
-			       (unsigned long long) f->zbd_info->zone_size);
+			       "%s: I/O buflen %llu exceeds zone size %"PRIu64"\n",
+			       f->file_name, io_u->buflen, zbdi->zone_size);
 			goto eof;
 		}
 		if (!zbd_open_zone(td, f, zone_idx_b)) {
@@ -1698,11 +1877,10 @@ enum io_u_action zbd_adjust_block(struct thread_data *td, struct io_u *io_u)
 				       f->file_name);
 				goto eof;
 			}
-			zone_idx_b = zbd_zone_nr(f, zb);
 		}
 		/* Check whether the zone reset threshold has been exceeded */
 		if (td->o.zrf.u.f) {
-			if (f->zbd_info->wp_sectors_with_data >=
+			if (zbdi->wp_sectors_with_data >=
 			    f->io_size * td->o.zrt.u.f &&
 			    zbd_dec_and_reset_write_cnt(td, f)) {
 				zb->reset_zone = 1;
@@ -1725,9 +1903,8 @@ enum io_u_action zbd_adjust_block(struct thread_data *td, struct io_u *io_u)
 
 			if (zb->capacity < min_bs) {
 				td_verror(td, EINVAL, "ZCAP is less min_bs");
-				log_err("zone capacity %llu smaller than minimum block size %d\n",
-					(unsigned long long)zb->capacity,
-					min_bs);
+				log_err("zone capacity %"PRIu64" smaller than minimum block size %"PRIu64"\n",
+					zb->capacity, min_bs);
 				goto eof;
 			}
 		}
@@ -1757,12 +1934,27 @@ enum io_u_action zbd_adjust_block(struct thread_data *td, struct io_u *io_u)
 			goto accept;
 		}
 		td_verror(td, EIO, "zone remainder too small");
-		log_err("zone remainder %lld smaller than min block size %d\n",
+		log_err("zone remainder %lld smaller than min block size %"PRIu64"\n",
 			(zbd_zone_capacity_end(zb) - io_u->offset), min_bs);
 		goto eof;
 	case DDIR_TRIM:
-		/* fall-through */
+		/* Check random trim targets a non-empty zone */
+		if (!td_random(td) || zb->wp > zb->start)
+			goto accept;
+
+		/* Find out a non-empty zone to trim */
+		zone_unlock(zb);
+		zl = get_zone(f, f->max_zone);
+		zb = zbd_find_zone(td, io_u, 1, zb, zl);
+		if (zb) {
+			io_u->offset = zb->start;
+			dprint(FD_ZBD, "%s: found new zone(%lld) for trim\n",
+			       f->file_name, io_u->offset);
+			goto accept;
+		}
+		goto eof;
 	case DDIR_SYNC:
+		/* fall-through */
 	case DDIR_DATASYNC:
 	case DDIR_SYNC_FILE_RANGE:
 	case DDIR_WAIT:
@@ -1799,7 +1991,42 @@ char *zbd_write_status(const struct thread_stat *ts)
 {
 	char *res;
 
-	if (asprintf(&res, "; %llu zone resets", (unsigned long long) ts->nr_zone_resets) < 0)
+	if (asprintf(&res, "; %"PRIu64" zone resets", ts->nr_zone_resets) < 0)
 		return NULL;
 	return res;
 }
+
+/**
+ * zbd_do_io_u_trim - If reset zone is applicable, do reset zone instead of trim
+ *
+ * @td: FIO thread data.
+ * @io_u: FIO I/O unit.
+ *
+ * It is assumed that z->mutex is already locked.
+ * Return io_u_completed when reset zone succeeds. Return 0 when the target zone
+ * does not have write pointer. On error, return negative errno.
+ */
+int zbd_do_io_u_trim(const struct thread_data *td, struct io_u *io_u)
+{
+	struct fio_file *f = io_u->file;
+	struct fio_zone_info *z;
+	uint32_t zone_idx;
+	int ret;
+
+	zone_idx = zbd_zone_idx(f, io_u->offset);
+	z = get_zone(f, zone_idx);
+
+	if (!z->has_wp)
+		return 0;
+
+	if (io_u->offset != z->start) {
+		log_err("Trim offset not at zone start (%lld)\n", io_u->offset);
+		return -EINVAL;
+	}
+
+	ret = zbd_reset_zone((struct thread_data *)td, f, z);
+	if (ret < 0)
+		return ret;
+
+	return io_u_completed;
+}