The following changes since commit 2459bd33b3dbb7a34f28c612d595311a6bc7593d:
ioengines: fix crash with --enghelp option (2021-08-04 12:49:57 -0600)
are available in the Git repository at:
git://git.kernel.dk/fio.git master
for you to fetch changes up to faff87e6f0da68853908652a95f0ec40dd12869d:
t/zbd: Add test #58 to test zone reset by trim workload (2021-08-06 16:39:31 -0600)
----------------------------------------------------------------
Shin'ichiro Kawasaki (5):
zbd: Add min_bytes argument to zbd_find_zone()
zbd: Support zone reset by trim
engines/libzbc: Enable trim for libzbc I/O engine
HOWTO/man: Describe trim support by zone reset for zoned devices
t/zbd: Add test #58 to test zone reset by trim workload
HOWTO | 8 +++++
engines/libzbc.c | 13 ++++----
fio.1 | 9 +++---
io_u.c | 9 ++++++
t/zbd/test-zbd-support | 26 +++++++++++++++
zbd.c | 85 +++++++++++++++++++++++++++++++++++++++++---------
zbd.h | 2 ++
7 files changed, 128 insertions(+), 24 deletions(-)
---
Diff of recent changes:
diff --git a/HOWTO b/HOWTO
index d4e620de..04ea284b 100644
--- a/HOWTO
+++ b/HOWTO
@@ -992,6 +992,9 @@ Target file/device
single zone. The :option:`zoneskip` parameter
is ignored. :option:`zonerange` and
:option:`zonesize` must be identical.
+ Trim is handled using a zone reset operation.
+ Trim only considers non-empty sequential write
+ required and sequential write preferred zones.
.. option:: zonerange=int
@@ -1965,6 +1968,11 @@ I/O engine
character devices. This engine supports trim operations.
The sg engine includes engine specific options.
+ **libzbc**
+ Read, write, trim and ZBC/ZAC operations to a zoned
+ block device using libzbc library. The target can be
+ either an SG character device or a block device file.
+
**null**
Doesn't transfer any data, just pretends to. This is mainly used to
exercise fio itself and for debugging/testing purposes.
diff --git a/engines/libzbc.c b/engines/libzbc.c
index 7f2bc431..abee2043 100644
--- a/engines/libzbc.c
+++ b/engines/libzbc.c
@@ -14,6 +14,7 @@
#include "fio.h"
#include "err.h"
#include "zbd_types.h"
+#include "zbd.h"
struct libzbc_data {
struct zbc_device *zdev;
@@ -63,7 +64,7 @@ static int libzbc_open_dev(struct thread_data *td, struct fio_file *f,
return -EINVAL;
}
- if (td_write(td)) {
+ if (td_write(td) || td_trim(td)) {
if (!read_only)
flags |= O_RDWR;
} else if (td_read(td)) {
@@ -71,10 +72,6 @@ static int libzbc_open_dev(struct thread_data *td, struct fio_file *f,
flags |= O_RDWR;
else
flags |= O_RDONLY;
- } else if (td_trim(td)) {
- td_verror(td, EINVAL, "libzbc does not support trim");
- log_err("%s: libzbc does not support trim\n", f->file_name);
- return -EINVAL;
}
if (td->o.oatomic) {
@@ -411,7 +408,11 @@ static enum fio_q_status libzbc_queue(struct thread_data *td, struct io_u *io_u)
ret = zbc_flush(ld->zdev);
if (ret)
log_err("zbc_flush error %zd\n", ret);
- } else if (io_u->ddir != DDIR_TRIM) {
+ } else if (io_u->ddir == DDIR_TRIM) {
+ ret = zbd_do_io_u_trim(td, io_u);
+ if (!ret)
+ ret = EINVAL;
+ } else {
log_err("Unsupported operation %u\n", io_u->ddir);
ret = -EINVAL;
}
diff --git a/fio.1 b/fio.1
index 9c12ad13..ff100a1c 100644
--- a/fio.1
+++ b/fio.1
@@ -766,6 +766,8 @@ starts. The \fBzonecapacity\fR parameter is ignored.
Zoned block device mode. I/O happens sequentially in each zone, even if random
I/O has been selected. Random I/O happens across all zones instead of being
restricted to a single zone.
+Trim is handled using a zone reset operation. Trim only considers non-empty
+sequential write required and sequential write preferred zones.
.RE
.RE
.TP
@@ -1761,10 +1763,9 @@ character devices. This engine supports trim operations. The
sg engine includes engine specific options.
.TP
.B libzbc
-Synchronous I/O engine for SMR hard-disks using the \fBlibzbc\fR
-library. The target can be either an sg character device or
-a block device file. This engine supports the zonemode=zbd zone
-operations.
+Read, write, trim and ZBC/ZAC operations to a zoned block device using
+\fBlibzbc\fR library. The target can be either an SG character device or
+a block device file.
.TP
.B null
Doesn't transfer any data, just pretends to. This is mainly used to
diff --git a/io_u.c b/io_u.c
index 9a1cd547..696d25cd 100644
--- a/io_u.c
+++ b/io_u.c
@@ -2317,10 +2317,19 @@ int do_io_u_trim(const struct thread_data *td, struct io_u *io_u)
struct fio_file *f = io_u->file;
int ret;
+ if (td->o.zone_mode == ZONE_MODE_ZBD) {
+ ret = zbd_do_io_u_trim(td, io_u);
+ if (ret == io_u_completed)
+ return io_u->xfer_buflen;
+ if (ret)
+ goto err;
+ }
+
ret = os_trim(f, io_u->offset, io_u->xfer_buflen);
if (!ret)
return io_u->xfer_buflen;
+err:
io_u->error = ret;
return 0;
#endif
diff --git a/t/zbd/test-zbd-support b/t/zbd/test-zbd-support
index 57e6d05e..5103c406 100755
--- a/t/zbd/test-zbd-support
+++ b/t/zbd/test-zbd-support
@@ -1215,6 +1215,32 @@ test57() {
>> "${logfile}.${test_number}" 2>&1 || return $?
}
+# Random writes and random trims to sequential write required zones for 30s.
+test58() {
+ local off size bs
+
+ require_seq_zones 128 || return $SKIP_TESTCASE
+
+ size=$((zone_size * 128))
+ bs="$(max $((zone_size / 128)) "$logical_block_size")"
+ prep_write
+ off=$((first_sequential_zone_sector * 512))
+ run_fio --zonemode=zbd --direct=1 --zonesize="${zone_size}" --thread=1 \
+ --filename="${dev}" --norandommap=1 \
+ --name="precondition" --rw=write "$(ioengine "psync")" \
+ --offset="${off}" --size=$((zone_size * 16)) --bs="${bs}" \
+ "${job_var_opts[@]}" \
+ --name=wjob --wait_for="precondition" --rw=randwrite \
+ "$(ioengine "libaio")" --iodepth=8 \
+ --offset="${off}" --size="${size}" --bs="${bs}" \
+ --time_based --runtime=30s --flow=128 "${job_var_opts[@]}" \
+ --name=trimjob --wait_for="precondition" --rw=randtrim \
+ "$(ioengine "psync")" \
+ --offset="${off}" --size="${size}" --bs="${zone_size}" \
+ --time_based --runtime=30s --flow=1 "${job_var_opts[@]}" \
+ >>"${logfile}.${test_number}" 2>&1
+}
+
SECONDS=0
tests=()
dynamic_analyzer=()
diff --git a/zbd.c b/zbd.c
index 43f12b45..1b933ce4 100644
--- a/zbd.c
+++ b/zbd.c
@@ -375,12 +375,24 @@ static bool zbd_verify_bs(void)
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 %llu\n",
+ f->file_name, td->o.bs[DDIR_TRIM],
+ (unsigned long long)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) {
@@ -1414,18 +1426,16 @@ 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, uint32_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);
@@ -1438,7 +1448,7 @@ 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);
@@ -1449,14 +1459,14 @@ 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 %d bytes of readable data\n",
+ f->file_name, min_bytes);
return NULL;
}
@@ -1531,9 +1541,6 @@ 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;
}
@@ -1785,7 +1792,7 @@ 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",
@@ -1913,8 +1920,23 @@ enum io_u_action zbd_adjust_block(struct thread_data *td, struct io_u *io_u)
(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:
@@ -1955,3 +1977,38 @@ char *zbd_write_status(const struct thread_stat *ts)
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;
+}
diff --git a/zbd.h b/zbd.h
index 39dc45e3..0a73b41d 100644
--- a/zbd.h
+++ b/zbd.h
@@ -17,6 +17,7 @@ struct fio_file;
enum io_u_action {
io_u_accept = 0,
io_u_eof = 1,
+ io_u_completed = 2,
};
/**
@@ -99,6 +100,7 @@ enum fio_ddir zbd_adjust_ddir(struct thread_data *td, struct io_u *io_u,
enum fio_ddir ddir);
enum io_u_action zbd_adjust_block(struct thread_data *td, struct io_u *io_u);
char *zbd_write_status(const struct thread_stat *ts);
+int zbd_do_io_u_trim(const struct thread_data *td, struct io_u *io_u);
static inline void zbd_close_file(struct fio_file *f)
{
