return ret;
}
+/**
+ * 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.
+ *
+ * A @max_open_zones value set to zero means no limit.
+ *
+ * Returns 0 upon success and a negative error code upon failure.
+ */
+int zbd_get_max_open_zones(struct thread_data *td, struct fio_file *f,
+ unsigned int *max_open_zones)
+{
+ int ret;
+
+ 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;
+}
+
/**
* zbd_zone_idx - convert an offset into a zone number
* @f: file pointer.
return min(zone_idx, f->zbd_info->nr_zones);
}
-/**
- * zbd_zone_swr - Test whether a zone requires sequential writes
- * @z: zone info pointer.
- */
-static inline bool zbd_zone_swr(struct fio_zone_info *z)
-{
- return z->type == ZBD_ZONE_TYPE_SWR;
-}
-
/**
* zbd_zone_end - Return zone end location
* @z: zone info pointer.
{
assert((required & 511) == 0);
- return zbd_zone_swr(z) &&
+ return z->has_wp &&
z->wp + required > zbd_zone_capacity_end(z);
}
-static void zone_lock(struct thread_data *td, struct fio_file *f, struct fio_zone_info *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.
}
}
+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 bool is_valid_offset(const struct fio_file *f, uint64_t offset)
{
return (uint64_t)(offset - f->file_offset) < f->io_size;
}
+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];
+}
+
/* Verify whether direct I/O is used for all host-managed zoned drives. */
static bool zbd_using_direct_io(void)
{
zone_idx_b = zbd_zone_idx(f, f->file_offset);
zone_idx_e = zbd_zone_idx(f, f->file_offset + f->io_size - 1);
for (zone_idx = zone_idx_b; zone_idx <= zone_idx_e; zone_idx++)
- if (zbd_zone_swr(&f->zbd_info->zone_info[zone_idx]))
+ if (get_zone(f, zone_idx)->has_wp)
return true;
return false;
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);
}
zone_idx = zbd_zone_idx(f, f->file_offset);
- z = &f->zbd_info->zone_info[zone_idx];
+ z = get_zone(f, zone_idx);
if ((f->file_offset != z->start) &&
(td->o.td_ddir != TD_DDIR_READ)) {
new_offset = zbd_zone_end(z);
f->file_offset = new_offset;
}
zone_idx = zbd_zone_idx(f, f->file_offset + f->io_size);
- z = &f->zbd_info->zone_info[zone_idx];
+ z = get_zone(f, zone_idx);
new_end = z->start;
if ((td->o.td_ddir != TD_DDIR_READ) &&
(f->file_offset + f->io_size != new_end)) {
(unsigned long long) new_end - f->file_offset);
f->io_size = new_end - f->file_offset;
}
-
- f->min_zone = zbd_zone_idx(f, f->file_offset);
- f->max_zone = zbd_zone_idx(f, f->file_offset + f->io_size);
}
}
{
struct thread_data *td;
struct fio_file *f;
- uint32_t zone_size;
int i, j, k;
for_each_td(td, i) {
for_each_file(td, f, j) {
+ uint64_t zone_size;
+
if (!f->zbd_info)
continue;
zone_size = f->zbd_info->zone_size;
- for (k = 0; k < ARRAY_SIZE(td->o.bs); k++) {
+ 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 %llu\n",
f->file_name, td->o.bs[k],
- zone_size);
+ (unsigned long long)zone_size);
return false;
}
}
p->type = ZBD_ZONE_TYPE_SWR;
p->cond = ZBD_ZONE_COND_EMPTY;
p->capacity = zone_capacity;
+ p->has_wp = 1;
}
/* a sentinel */
p->start = nr_zones * zone_size;
struct fio_zone_info *p;
uint64_t zone_size, offset;
struct zoned_block_device_info *zbd_info = NULL;
- int i, j, ret = 0;
+ int i, j, ret = -ENOMEM;
zones = calloc(ZBD_REPORT_MAX_ZONES, sizeof(struct zbd_zone));
if (!zones)
zbd_info = scalloc(1, sizeof(*zbd_info) +
(nr_zones + 1) * sizeof(zbd_info->zone_info[0]));
- ret = -ENOMEM;
if (!zbd_info)
goto out;
mutex_init_pshared(&zbd_info->mutex);
p->wp = z->wp;
break;
}
+
+ switch (z->type) {
+ case ZBD_ZONE_TYPE_SWR:
+ p->has_wp = 1;
+ break;
+ default:
+ p->has_wp = 0;
+ }
p->type = z->type;
p->cond = z->cond;
+
if (j > 0 && p->start != p[-1].start + zone_size) {
log_info("%s: invalid zone data\n",
f->file_name);
offset = z->start + z->len;
if (j >= nr_zones)
break;
- nrz = zbd_report_zones(td, f, offset,
- zones, ZBD_REPORT_MAX_ZONES);
+ nrz = zbd_report_zones(td, f, offset, zones,
+ min((uint32_t)(nr_zones - j),
+ ZBD_REPORT_MAX_ZONES));
if (nrz < 0) {
ret = nrz;
log_info("fio: report zones (offset %llu) failed for %s (%d).\n",
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) {
+ /* 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 */
+ zbd->max_open_zones = min_not_zero(zbd->max_open_zones,
+ (uint32_t) ZBD_MAX_OPEN_ZONES);
+ 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.
*
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");
return -EINVAL;
}
- if (ret == 0) {
- f->zbd_info->model = zbd_model;
- f->zbd_info->max_open_zones = td->o.max_open_zones;
+ 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)
return ret;
}
-int zbd_setup_files(struct thread_data *td)
+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_init_files(struct thread_data *td)
{
struct fio_file *f;
int 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;
+ }
+ }
+}
+
+int zbd_setup_files(struct thread_data *td)
+{
+ struct fio_file *f;
+ int i;
if (!zbd_using_direct_io()) {
log_err("Using direct I/O is mandatory for writing to ZBD drives\n\n");
for_each_file(td, f, i) {
struct zoned_block_device_info *zbd = f->zbd_info;
+ struct fio_zone_info *z;
+ int zi;
if (!zbd)
continue;
- zbd->max_open_zones = zbd->max_open_zones ?: ZBD_MAX_OPEN_ZONES;
+ f->min_zone = zbd_zone_idx(f, f->file_offset);
+ f->max_zone = zbd_zone_idx(f, f->file_offset + f->io_size);
+
+ /*
+ * When all zones in the I/O range are conventional, io_size
+ * can be smaller than zone size, making min_zone the same
+ * as max_zone. This is why the assert below needs to be made
+ * conditional.
+ */
+ if (zbd_is_seq_job(f))
+ assert(f->min_zone < f->max_zone);
if (td->o.max_open_zones > 0 &&
zbd->max_open_zones != td->o.max_open_zones) {
log_err("'max_open_zones' value is limited by %u\n", ZBD_MAX_OPEN_ZONES);
return 1;
}
+
+ for (zi = f->min_zone; zi < f->max_zone; zi++) {
+ z = &zbd->zone_info[zi];
+ if (z->cond != ZBD_ZONE_COND_IMP_OPEN &&
+ z->cond != ZBD_ZONE_COND_EXP_OPEN)
+ continue;
+ if (zbd_open_zone(td, f, zi))
+ continue;
+ /*
+ * If the number of open zones exceeds specified limits,
+ * reset all extra open zones.
+ */
+ if (zbd_reset_zone(td, f, z) < 0) {
+ log_err("Failed to reest zone %d\n", zi);
+ return 1;
+ }
+ }
}
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_range - reset zones for a range of sectors
+ * zbd_reset_zone - reset the write pointer of a single zone
* @td: FIO thread data.
- * @f: Fio file for which to reset zones
- * @sector: Starting sector in units of 512 bytes
- * @nr_sectors: Number of sectors in units of 512 bytes
+ * @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_range(struct thread_data *td, struct fio_file *f,
- uint64_t offset, uint64_t length)
+static int zbd_reset_zone(struct thread_data *td, struct fio_file *f,
+ struct fio_zone_info *z)
{
- uint32_t zone_idx_b, zone_idx_e;
- struct fio_zone_info *zb, *ze, *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:
break;
}
- zone_idx_b = zbd_zone_idx(f, offset);
- zb = &f->zbd_info->zone_info[zone_idx_b];
- zone_idx_e = zbd_zone_idx(f, offset + length);
- ze = &f->zbd_info->zone_info[zone_idx_e];
- for (z = zb; z < ze; z++) {
- pthread_mutex_lock(&z->mutex);
- pthread_mutex_lock(&f->zbd_info->mutex);
- f->zbd_info->sectors_with_data -= z->wp - z->start;
- pthread_mutex_unlock(&f->zbd_info->mutex);
- z->wp = z->start;
- z->verify_block = 0;
- pthread_mutex_unlock(&z->mutex);
- }
+ 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 += ze - zb;
+ td->ts.nr_zone_resets++;
return ret;
}
-static unsigned int zbd_zone_nr(struct zoned_block_device_info *zbd_info,
- struct fio_zone_info *zone)
-{
- return zone - 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.
- */
-static int zbd_reset_zone(struct thread_data *td, struct fio_file *f,
- struct fio_zone_info *z)
-{
- dprint(FD_ZBD, "%s: resetting wp of zone %u.\n", f->file_name,
- zbd_zone_nr(f->zbd_info, z));
-
- return zbd_reset_range(td, f, z->start, zbd_zone_end(z) - z->start);
-}
-
/* The caller must hold f->zbd_info->mutex */
static void zbd_close_zone(struct thread_data *td, const struct fio_file *f,
- unsigned int open_zone_idx)
+ unsigned int zone_idx)
{
- uint32_t 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;
- assert(open_zone_idx < f->zbd_info->num_open_zones);
- zone_idx = f->zbd_info->open_zones[open_zone_idx];
+ 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--;
- f->zbd_info->zone_info[zone_idx].open = 0;
+ get_zone(f, zone_idx)->open = 0;
}
/*
* @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 *const ze)
{
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->zbd_info, zb), zbd_zone_nr(f->zbd_info, ze));
+ zbd_zone_nr(f, zb), zbd_zone_nr(f, ze));
for (z = zb; z < ze; z++) {
- uint32_t nz = z - f->zbd_info->zone_info;
+ uint32_t nz = zbd_zone_nr(f, z);
- if (!zbd_zone_swr(z))
+ if (!z->has_wp)
continue;
zone_lock(td, f, z);
- if (all_zones) {
- unsigned int i;
-
- pthread_mutex_lock(&f->zbd_info->mutex);
- for (i = 0; i < f->zbd_info->num_open_zones; i++) {
- if (f->zbd_info->open_zones[i] == nz)
- zbd_close_zone(td, f, i);
- }
- pthread_mutex_unlock(&f->zbd_info->mutex);
-
- reset_wp = z->wp != z->start;
- } else {
- reset_wp = z->wp % min_bs != 0;
- }
- if (reset_wp) {
+ 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->zbd_info, z));
+ f->file_name, zbd_zone_nr(f, z));
if (zbd_reset_zone(td, f, z) < 0)
res = 1;
}
- pthread_mutex_unlock(&z->mutex);
+ zone_unlock(z);
}
return res;
};
/* Calculate the number of sectors with data (swd) and perform action 'a' */
-static uint64_t zbd_process_swd(const struct fio_file *f, enum swd_action a)
+static uint64_t zbd_process_swd(struct thread_data *td,
+ const struct fio_file *f, enum swd_action a)
{
struct fio_zone_info *zb, *ze, *z;
uint64_t swd = 0;
+ uint64_t wp_swd = 0;
- zb = &f->zbd_info->zone_info[zbd_zone_idx(f, f->file_offset)];
- ze = &f->zbd_info->zone_info[zbd_zone_idx(f, f->file_offset +
- f->io_size)];
+ zb = get_zone(f, f->min_zone);
+ ze = get_zone(f, f->max_zone);
for (z = zb; z < ze; z++) {
- pthread_mutex_lock(&z->mutex);
+ if (z->has_wp) {
+ zone_lock(td, f, z);
+ wp_swd += z->wp - z->start;
+ }
swd += z->wp - z->start;
}
pthread_mutex_lock(&f->zbd_info->mutex);
switch (a) {
case CHECK_SWD:
assert(f->zbd_info->sectors_with_data == swd);
+ assert(f->zbd_info->wp_sectors_with_data == wp_swd);
break;
case SET_SWD:
f->zbd_info->sectors_with_data = swd;
+ f->zbd_info->wp_sectors_with_data = wp_swd;
break;
}
pthread_mutex_unlock(&f->zbd_info->mutex);
for (z = zb; z < ze; z++)
- pthread_mutex_unlock(&z->mutex);
+ if (z->has_wp)
+ zone_unlock(z);
return swd;
}
*/
static const bool enable_check_swd = false;
-/* Check whether the value of zbd_info.sectors_with_data is correct. */
-static void zbd_check_swd(const struct fio_file *f)
-{
- if (!enable_check_swd)
- return;
-
- zbd_process_swd(f, CHECK_SWD);
-}
-
-static void zbd_init_swd(struct fio_file *f)
+/* Check whether the values of zbd_info.*sectors_with_data are correct. */
+static void zbd_check_swd(struct thread_data *td, const struct fio_file *f)
{
- uint64_t swd;
-
if (!enable_check_swd)
return;
- swd = zbd_process_swd(f, SET_SWD);
- dprint(FD_ZBD, "%s(%s): swd = %" PRIu64 "\n", __func__, f->file_name,
- swd);
+ zbd_process_swd(td, f, CHECK_SWD);
}
void zbd_file_reset(struct thread_data *td, struct fio_file *f)
{
struct fio_zone_info *zb, *ze;
+ uint64_t swd;
if (!f->zbd_info || !td_write(td))
return;
- zb = &f->zbd_info->zone_info[f->min_zone];
- ze = &f->zbd_info->zone_info[f->max_zone];
- zbd_init_swd(f);
+ zb = get_zone(f, f->min_zone);
+ ze = get_zone(f, f->max_zone);
+ swd = zbd_process_swd(td, f, SET_SWD);
+ dprint(FD_ZBD, "%s(%s): swd = %" PRIu64 "\n", __func__, f->file_name,
+ swd);
/*
* If data verification is enabled reset the affected zones before
* 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);
}
* 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 io_u *io_u,
+static bool zbd_open_zone(struct thread_data *td, const struct fio_file *f,
uint32_t zone_idx)
{
const uint32_t min_bs = td->o.min_bs[DDIR_WRITE];
- const struct fio_file *f = io_u->file;
- struct fio_zone_info *z = &f->zbd_info->zone_info[zone_idx];
+ struct fio_zone_info *z = get_zone(f, zone_idx);
bool res = true;
if (z->cond == ZBD_ZONE_COND_OFFLINE)
return false;
pthread_mutex_lock(&f->zbd_info->mutex);
- if (is_zone_open(td, f, zone_idx))
+ 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;
+ }
res = false;
/* Zero means no limit */
if (td->o.job_max_open_zones > 0 &&
/*
* Modify the offset of an I/O unit that does not refer to an open zone such
* that it refers to an open zone. Close an open zone and open a new zone if
- * necessary. This algorithm can only work correctly if all write pointers are
+ * necessary. The open zone is searched across sequential zones.
+ * This algorithm can only work correctly if all write pointers are
* a multiple of the fio block size. The caller must neither hold z->mutex
* nor f->zbd_info->mutex. Returns with z->mutex held upon success.
*/
unsigned int open_zone_idx = -1;
uint32_t zone_idx, new_zone_idx;
int i;
+ bool wait_zone_close;
assert(is_valid_offset(f, io_u->offset));
for (;;) {
uint32_t tmp_idx;
- z = &f->zbd_info->zone_info[zone_idx];
-
- zone_lock(td, f, z);
+ z = get_zone(f, zone_idx);
+ if (z->has_wp)
+ zone_lock(td, f, z);
pthread_mutex_lock(&f->zbd_info->mutex);
- if (td->o.max_open_zones == 0 && td->o.job_max_open_zones == 0)
- goto examine_zone;
- if (f->zbd_info->num_open_zones == 0) {
- pthread_mutex_unlock(&f->zbd_info->mutex);
- pthread_mutex_unlock(&z->mutex);
- dprint(FD_ZBD, "%s(%s): no zones are open\n",
- __func__, f->file_name);
- return NULL;
+ if (z->has_wp) {
+ if (z->cond != ZBD_ZONE_COND_OFFLINE &&
+ td->o.max_open_zones == 0 && td->o.job_max_open_zones == 0)
+ goto examine_zone;
+ if (f->zbd_info->num_open_zones == 0) {
+ dprint(FD_ZBD, "%s(%s): no zones are open\n",
+ __func__, f->file_name);
+ goto open_other_zone;
+ }
}
/*
* Ignore zones which don't belong to thread's offset/size area.
*/
open_zone_idx = pick_random_zone_idx(f, io_u);
- assert(open_zone_idx < f->zbd_info->num_open_zones);
+ assert(!open_zone_idx ||
+ open_zone_idx < f->zbd_info->num_open_zones);
tmp_idx = open_zone_idx;
for (i = 0; i < f->zbd_info->num_open_zones; i++) {
uint32_t tmpz;
dprint(FD_ZBD, "%s(%s): no candidate zone\n",
__func__, f->file_name);
pthread_mutex_unlock(&f->zbd_info->mutex);
- pthread_mutex_unlock(&z->mutex);
+ if (z->has_wp)
+ zone_unlock(z);
return NULL;
found_candidate_zone:
break;
zone_idx = new_zone_idx;
pthread_mutex_unlock(&f->zbd_info->mutex);
- pthread_mutex_unlock(&z->mutex);
+ if (z->has_wp)
+ zone_unlock(z);
}
/* Both z->mutex and f->zbd_info->mutex are held. */
pthread_mutex_unlock(&f->zbd_info->mutex);
goto out;
}
- dprint(FD_ZBD, "%s(%s): closing zone %d\n", __func__, f->file_name,
- zone_idx);
- if (td->o.max_open_zones || td->o.job_max_open_zones)
- zbd_close_zone(td, f, open_zone_idx);
+
+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) ||
+ (td->o.job_max_open_zones &&
+ td->num_open_zones == td->o.job_max_open_zones);
+
pthread_mutex_unlock(&f->zbd_info->mutex);
/* Only z->mutex is held. */
+ /*
+ * When number of open zones reaches to one of limits, wait for
+ * zone close before opening a new zone.
+ */
+ if (wait_zone_close) {
+ dprint(FD_ZBD, "%s(%s): quiesce to allow open zones to close\n",
+ __func__, f->file_name);
+ io_u_quiesce(td);
+ }
+
/* Zone 'z' is full, so try to open a new zone. */
for (i = f->io_size / f->zbd_info->zone_size; i > 0; i--) {
zone_idx++;
- pthread_mutex_unlock(&z->mutex);
+ if (z->has_wp)
+ zone_unlock(z);
z++;
if (!is_valid_offset(f, z->start)) {
/* Wrap-around. */
zone_idx = f->min_zone;
- z = &f->zbd_info->zone_info[zone_idx];
+ z = get_zone(f, zone_idx);
}
assert(is_valid_offset(f, z->start));
+ if (!z->has_wp)
+ continue;
zone_lock(td, f, z);
if (z->open)
continue;
- if (zbd_open_zone(td, io_u, zone_idx))
+ if (zbd_open_zone(td, f, zone_idx))
goto out;
}
if (zone_idx < f->min_zone || zone_idx >= f->max_zone)
continue;
pthread_mutex_unlock(&f->zbd_info->mutex);
- pthread_mutex_unlock(&z->mutex);
+ zone_unlock(z);
- z = &f->zbd_info->zone_info[zone_idx];
+ z = get_zone(f, zone_idx);
zone_lock(td, f, z);
if (z->wp + min_bs <= zbd_zone_capacity_end(z))
pthread_mutex_lock(&f->zbd_info->mutex);
}
pthread_mutex_unlock(&f->zbd_info->mutex);
- pthread_mutex_unlock(&z->mutex);
+ zone_unlock(z);
dprint(FD_ZBD, "%s(%s): did not open another zone\n", __func__,
f->file_name);
return NULL;
dprint(FD_ZBD, "%s(%s): returning zone %d\n", __func__, f->file_name,
zone_idx);
io_u->offset = z->start;
+ assert(z->has_wp);
+ assert(z->cond != ZBD_ZONE_COND_OFFLINE);
return z;
}
const struct fio_file *f = io_u->file;
const uint32_t min_bs = td->o.min_bs[DDIR_WRITE];
- if (!zbd_open_zone(td, io_u, z - f->zbd_info->zone_info)) {
- pthread_mutex_unlock(&z->mutex);
+ if (!zbd_open_zone(td, f, zbd_zone_nr(f, z))) {
+ zone_unlock(z);
z = zbd_convert_to_open_zone(td, io_u);
assert(z);
}
- if (z->verify_block * min_bs >= z->capacity)
+ 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);
- io_u->offset = z->start + z->verify_block++ * min_bs;
+ /*
+ * If the assertion below fails during a test run, adding
+ * "--experimental_verify=1" to the command line may help.
+ */
+ assert(false);
+ }
+ 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));
+ assert(false);
+ }
+ z->verify_block += io_u->buflen / min_bs;
+
return z;
}
/*
- * Find another zone for which @io_u fits below the write pointer. Start
- * searching in zones @zb + 1 .. @zl and continue searching in zones
- * @zf .. @zb - 1.
+ * 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.
*
- * Either returns NULL or returns a zone pointer and holds the mutex for that
- * zone.
+ * 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,
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 =
- &f->zbd_info->zone_info[zbd_zone_idx(f, f->file_offset)];
+ const struct fio_zone_info *const zf = get_zone(f, f->min_zone);
/*
* Skip to the next non-empty zone in case of sequential I/O and to
*/
for (z1 = zb + 1, z2 = zb - 1; z1 < zl || z2 >= zf; z1++, z2--) {
if (z1 < zl && z1->cond != ZBD_ZONE_COND_OFFLINE) {
- zone_lock(td, f, z1);
+ if (z1->has_wp)
+ zone_lock(td, f, z1);
if (z1->start + min_bs <= z1->wp)
return z1;
- pthread_mutex_unlock(&z1->mutex);
+ if (z1->has_wp)
+ zone_unlock(z1);
} else if (!td_random(td)) {
break;
}
if (td_random(td) && z2 >= zf &&
z2->cond != ZBD_ZONE_COND_OFFLINE) {
- zone_lock(td, f, z2);
+ if (z2->has_wp)
+ zone_lock(td, f, z2);
if (z2->start + min_bs <= z2->wp)
return z2;
- pthread_mutex_unlock(&z2->mutex);
+ if (z2->has_wp)
+ zone_unlock(z2);
}
}
dprint(FD_ZBD, "%s: adjusting random read offset failed\n",
return NULL;
}
+/**
+ * zbd_end_zone_io - update zone status at command completion
+ * @io_u: I/O unit
+ * @z: zone info pointer
+ *
+ * If the write command made the zone full, close it.
+ *
+ * The caller must hold z->mutex.
+ */
+static void zbd_end_zone_io(struct thread_data *td, const struct io_u *io_u,
+ struct fio_zone_info *z)
+{
+ const struct fio_file *f = io_u->file;
+
+ if (io_u->ddir == DDIR_WRITE &&
+ io_u->offset + io_u->buflen >= zbd_zone_capacity_end(z)) {
+ pthread_mutex_lock(&f->zbd_info->mutex);
+ zbd_close_zone(td, f, zbd_zone_nr(f, z));
+ pthread_mutex_unlock(&f->zbd_info->mutex);
+ }
+}
+
/**
* zbd_queue_io - update the write pointer of a sequential zone
* @io_u: I/O unit
* For write and trim operations, update the write pointer of the I/O unit
* target zone.
*/
-static void zbd_queue_io(struct io_u *io_u, int q, bool success)
+static void zbd_queue_io(struct thread_data *td, struct io_u *io_u, int q,
+ bool success)
{
const struct fio_file *f = io_u->file;
struct zoned_block_device_info *zbd_info = f->zbd_info;
zone_idx = zbd_zone_idx(f, io_u->offset);
assert(zone_idx < zbd_info->nr_zones);
- z = &zbd_info->zone_info[zone_idx];
+ z = get_zone(f, zone_idx);
- if (!zbd_zone_swr(z))
- return;
+ assert(z->has_wp);
if (!success)
goto unlock;
* z->wp > zone_end means that one or more I/O errors
* have occurred.
*/
- if (z->wp <= zone_end)
+ if (z->wp <= zone_end) {
zbd_info->sectors_with_data += zone_end - z->wp;
+ zbd_info->wp_sectors_with_data += zone_end - z->wp;
+ }
pthread_mutex_unlock(&zbd_info->mutex);
z->wp = zone_end;
break;
break;
}
+ if (q == FIO_Q_COMPLETED && !io_u->error)
+ zbd_end_zone_io(td, io_u, z);
+
unlock:
if (!success || q != FIO_Q_QUEUED) {
/* BUSY or COMPLETED: unlock the zone */
- pthread_mutex_unlock(&z->mutex);
+ zone_unlock(z);
io_u->zbd_put_io = NULL;
}
}
* zbd_put_io - Unlock an I/O unit target zone lock
* @io_u: I/O unit
*/
-static void zbd_put_io(const struct io_u *io_u)
+static void zbd_put_io(struct thread_data *td, const struct io_u *io_u)
{
const struct fio_file *f = io_u->file;
struct zoned_block_device_info *zbd_info = f->zbd_info;
struct fio_zone_info *z;
uint32_t zone_idx;
- int ret;
if (!zbd_info)
return;
zone_idx = zbd_zone_idx(f, io_u->offset);
assert(zone_idx < zbd_info->nr_zones);
- z = &zbd_info->zone_info[zone_idx];
+ z = get_zone(f, zone_idx);
- if (!zbd_zone_swr(z))
- return;
+ assert(z->has_wp);
dprint(FD_ZBD,
"%s: terminate I/O (%lld, %llu) for zone %u\n",
f->file_name, io_u->offset, io_u->buflen, zone_idx);
- ret = pthread_mutex_unlock(&z->mutex);
- assert(ret == 0);
- zbd_check_swd(f);
+ zbd_end_zone_io(td, io_u, z);
+
+ zone_unlock(z);
+ zbd_check_swd(td, f);
}
/*
assert(td->o.zone_size);
zone_idx = zbd_zone_idx(f, f->last_pos[ddir]);
- z = &f->zbd_info->zone_info[zone_idx];
+ z = get_zone(f, zone_idx);
/*
* When the zone capacity is smaller than the zone size and the I/O is
"%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),
- zbd_zone_nr(f->zbd_info, z),
+ (unsigned long long) zbd_zone_end(z), zone_idx,
(unsigned long long) z->capacity);
td->io_skip_bytes += zbd_zone_end(z) - f->last_pos[ddir];
f->last_pos[ddir] = zbd_zone_end(z);
assert(is_valid_offset(f, io_u->offset));
assert(io_u->buflen);
zone_idx_b = zbd_zone_idx(f, io_u->offset);
- zb = &f->zbd_info->zone_info[zone_idx_b];
+ zb = get_zone(f, zone_idx_b);
orig_zb = zb;
- /* Accept the I/O offset for conventional zones. */
- if (!zbd_zone_swr(zb))
+ if (!zb->has_wp) {
+ /* Accept non-write I/Os for conventional zones. */
+ if (io_u->ddir != DDIR_WRITE)
+ return io_u_accept;
+ /*
+ * Make sure that writes to conventional zones
+ * don't cross over to any sequential zones.
+ */
+ if (!(zb + 1)->has_wp ||
+ io_u->offset + io_u->buflen <= (zb + 1)->start)
+ return io_u_accept;
+
+ if (io_u->offset + min_bs > (zb + 1)->start) {
+ dprint(FD_IO,
+ "%s: off=%llu + min_bs=%u > next zone %llu\n",
+ f->file_name, io_u->offset,
+ min_bs, (unsigned long long) (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 {
+ new_len = (zb + 1)->start - io_u->offset;
+ }
+ io_u->buflen = new_len / min_bs * min_bs;
return io_u_accept;
+ }
/*
* Accept the I/O offset for reads if reading beyond the write pointer
io_u->ddir == DDIR_READ && td->o.read_beyond_wp)
return io_u_accept;
- zbd_check_swd(f);
+ zbd_check_swd(td, f);
zone_lock(td, f, zb);
switch (io_u->ddir) {
case DDIR_READ:
- if (td->runstate == TD_VERIFYING) {
- if (td_write(td))
- zb = zbd_replay_write_order(td, io_u, zb);
+ if (td->runstate == TD_VERIFYING && td_write(td)) {
+ zb = zbd_replay_write_order(td, io_u, zb);
goto accept;
}
/*
zb->wp - zb->start : 0;
if (range < min_bs ||
((!td_random(td)) && (io_u->offset + min_bs > zb->wp))) {
- pthread_mutex_unlock(&zb->mutex);
- zl = &f->zbd_info->zone_info[zbd_zone_idx(f,
- f->file_offset + f->io_size)];
+ zone_unlock(zb);
+ zl = get_zone(f, f->max_zone);
zb = zbd_find_zone(td, io_u, zb, zl);
if (!zb) {
dprint(FD_ZBD,
io_u->offset = zb->start +
((io_u->offset - orig_zb->start) %
(range - io_u->buflen)) / min_bs * min_bs;
+ /*
+ * When zbd_find_zone() returns a conventional zone,
+ * we can simply accept the new i/o offset here.
+ */
+ if (!zb->has_wp)
+ return io_u_accept;
/*
* Make sure the I/O does not cross over the zone wp position.
*/
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 > f->zbd_info->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);
goto eof;
- if (!zbd_open_zone(td, io_u, zone_idx_b)) {
- pthread_mutex_unlock(&zb->mutex);
+ }
+ if (!zbd_open_zone(td, f, zone_idx_b)) {
+ zone_unlock(zb);
zb = zbd_convert_to_open_zone(td, io_u);
- if (!zb)
+ if (!zb) {
+ dprint(FD_IO, "%s: can't convert to open zone",
+ f->file_name);
goto eof;
- zone_idx_b = zb - f->zbd_info->zone_info;
+ }
+ 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->sectors_with_data >=
+ if (f->zbd_info->wp_sectors_with_data >=
f->io_size * td->o.zrt.u.f &&
zbd_dec_and_reset_write_cnt(td, f)) {
zb->reset_zone = 1;
goto eof;
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);
assert(!zbd_zone_full(f, zb, min_bs));
io_u->offset = zb->wp;
if (!is_valid_offset(f, io_u->offset)) {
- dprint(FD_ZBD, "Dropped request with offset %llu\n",
- io_u->offset);
+ td_verror(td, EINVAL, "invalid WP value");
+ dprint(FD_ZBD, "%s: dropped request with offset %llu\n",
+ f->file_name, io_u->offset);
goto eof;
}
/*
orig_len, io_u->buflen);
goto accept;
}
- log_err("Zone remainder %lld smaller than minimum block size %d\n",
- (zbd_zone_capacity_end(zb) - io_u->offset),
- min_bs);
+ td_verror(td, EIO, "zone remainder too small");
+ log_err("zone remainder %lld smaller than min block size %d\n",
+ (zbd_zone_capacity_end(zb) - io_u->offset), min_bs);
goto eof;
case DDIR_TRIM:
/* fall-through */
assert(false);
accept:
- assert(zb);
+ assert(zb->has_wp);
assert(zb->cond != ZBD_ZONE_COND_OFFLINE);
assert(!io_u->zbd_queue_io);
assert(!io_u->zbd_put_io);
io_u->zbd_queue_io = zbd_queue_io;
io_u->zbd_put_io = zbd_put_io;
+ /*
+ * Since we return with the zone lock still held,
+ * add an annotation to let Coverity know that it
+ * is intentional.
+ */
+ /* coverity[missing_unlock] */
return io_u_accept;
eof:
- if (zb)
- pthread_mutex_unlock(&zb->mutex);
+ if (zb && zb->has_wp)
+ zone_unlock(zb);
return io_u_eof;
}