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 inline void zone_unlock(struct fio_zone_info *z)
+{
+ int ret;
+
+ 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;
}
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)) {
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 0;
}
-static unsigned int zbd_zone_nr(struct zoned_block_device_info *zbd_info,
- struct fio_zone_info *zone)
+static inline unsigned int zbd_zone_nr(const struct fio_file *f,
+ struct fio_zone_info *zone)
{
- return zone - zbd_info->zone_info;
+ return zone - f->zbd_info->zone_info;
}
/**
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->zbd_info, z));
+ zbd_zone_nr(f, z));
switch (f->zbd_info->model) {
case ZBD_HOST_AWARE:
case ZBD_HOST_MANAGED:
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;
}
/*
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) {
}
if (reset_wp) {
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;
struct fio_zone_info *zb, *ze, *z;
uint64_t swd = 0;
- zb = &f->zbd_info->zone_info[f->min_zone];
- ze = &f->zbd_info->zone_info[f->max_zone];
+ 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);
swd += z->wp - z->start;
}
pthread_mutex_unlock(&f->zbd_info->mutex);
for (z = zb; z < ze; z++)
- pthread_mutex_unlock(&z->mutex);
+ zone_unlock(z);
return 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];
+ zb = get_zone(f, f->min_zone);
+ ze = get_zone(f, f->max_zone);
zbd_init_swd(f);
/*
* If data verification is enabled reset the affected zones before
uint32_t zone_idx)
{
const uint32_t min_bs = td->o.min_bs[DDIR_WRITE];
- 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)
/*
* 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.
*/
for (;;) {
uint32_t tmp_idx;
- z = &f->zbd_info->zone_info[zone_idx];
+ z = get_zone(f, zone_idx);
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)
+ 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",
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);
+ 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);
+ zone_unlock(z);
}
/* Both z->mutex and f->zbd_info->mutex are held. */
/* 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 (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, f, 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);
}
}
/*
- * 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[f->min_zone];
+ 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",
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, z - f->zbd_info->zone_info);
+ zbd_close_zone(td, f, zbd_zone_nr(f, z));
pthread_mutex_unlock(&f->zbd_info->mutex);
}
}
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))
+ if (!z->has_wp)
return;
if (!success)
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;
}
}
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))
+ if (!z->has_wp)
return;
dprint(FD_ZBD,
zbd_end_zone_io(td, io_u, z);
- ret = pthread_mutex_unlock(&z->mutex);
- assert(ret == 0);
+ zone_unlock(z);
zbd_check_swd(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)
return io_u_accept;
/*
case DDIR_READ:
if (td->runstate == TD_VERIFYING && td_write(td)) {
zb = zbd_replay_write_order(td, io_u, zb);
- pthread_mutex_unlock(&zb->mutex);
+ /*
+ * Since we return with the zone lock still held,
+ * add an annotation to let Coverity know that it
+ * is intentional.
+ */
+ /* coverity[missing_unlock] */
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[f->max_zone];
+ zone_unlock(zb);
+ zl = get_zone(f, f->max_zone);
zb = zbd_find_zone(td, io_u, zb, zl);
if (!zb) {
dprint(FD_ZBD,
if (io_u->buflen > f->zbd_info->zone_size)
goto eof;
if (!zbd_open_zone(td, f, zone_idx_b)) {
- pthread_mutex_unlock(&zb->mutex);
+ zone_unlock(zb);
zb = zbd_convert_to_open_zone(td, io_u);
if (!zb)
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) {
eof:
if (zb)
- pthread_mutex_unlock(&zb->mutex);
+ zone_unlock(zb);
return io_u_eof;
}