* [PATCH v8 1/4] file-posix: add tracking of the zone write pointers
2023-04-04 15:32 [PATCH v8 0/4] Add zone append write for zoned device Sam Li
@ 2023-04-04 15:32 ` Sam Li
2023-04-05 20:26 ` Stefan Hajnoczi
2023-04-04 15:32 ` [PATCH v8 2/4] block: introduce zone append write for zoned devices Sam Li
` (2 subsequent siblings)
3 siblings, 1 reply; 7+ messages in thread
From: Sam Li @ 2023-04-04 15:32 UTC (permalink / raw)
To: qemu-devel
Cc: Fam Zheng, hare, Hanna Reitz, dmitry.fomichev, Julia Suvorova,
Stefano Garzarella, damien.lemoal, Stefan Hajnoczi, Aarushi Mehta,
Kevin Wolf, qemu-block, Sam Li
Since Linux doesn't have a user API to issue zone append operations to
zoned devices from user space, the file-posix driver is modified to add
zone append emulation using regular writes. To do this, the file-posix
driver tracks the wp location of all zones of the device. It uses an
array of uint64_t. The most significant bit of each wp location indicates
if the zone type is conventional zones.
The zones wp can be changed due to the following operations issued:
- zone reset: change the wp to the start offset of that zone
- zone finish: change to the end location of that zone
- write to a zone
- zone append
Signed-off-by: Sam Li <faithilikerun@gmail.com>
---
block/file-posix.c | 168 ++++++++++++++++++++++++++++++-
include/block/block-common.h | 14 +++
include/block/block_int-common.h | 5 +
3 files changed, 184 insertions(+), 3 deletions(-)
diff --git a/block/file-posix.c b/block/file-posix.c
index 65efe5147e..bc58f7193b 100644
--- a/block/file-posix.c
+++ b/block/file-posix.c
@@ -1324,6 +1324,88 @@ static int hdev_get_max_segments(int fd, struct stat *st)
#endif
}
+#if defined(CONFIG_BLKZONED)
+/*
+ * If the reset_all flag is true, then the wps of zone whose state is
+ * not readonly or offline should be all reset to the start sector.
+ * Else, take the real wp of the device.
+ */
+static int get_zones_wp(int fd, BlockZoneWps *wps, int64_t offset,
+ unsigned int nrz, bool reset_all)
+{
+ struct blk_zone *blkz;
+ size_t rep_size;
+ uint64_t sector = offset >> BDRV_SECTOR_BITS;
+ int ret, n = 0, i = 0;
+ rep_size = sizeof(struct blk_zone_report) + nrz * sizeof(struct blk_zone);
+ g_autofree struct blk_zone_report *rep = NULL;
+
+ rep = g_malloc(rep_size);
+ blkz = (struct blk_zone *)(rep + 1);
+ while (n < nrz) {
+ memset(rep, 0, rep_size);
+ rep->sector = sector;
+ rep->nr_zones = nrz - n;
+
+ do {
+ ret = ioctl(fd, BLKREPORTZONE, rep);
+ } while (ret != 0 && errno == EINTR);
+ if (ret != 0) {
+ error_report("%d: ioctl BLKREPORTZONE at %" PRId64 " failed %d",
+ fd, offset, errno);
+ return -errno;
+ }
+
+ if (!rep->nr_zones) {
+ break;
+ }
+
+ for (i = 0; i < rep->nr_zones; i++, n++) {
+ /*
+ * The wp tracking cares only about sequential writes required and
+ * sequential write preferred zones so that the wp can advance to
+ * the right location.
+ * Use the most significant bit of the wp location to indicate the
+ * zone type: 0 for SWR/SWP zones and 1 for conventional zones.
+ */
+ if (blkz[i].type == BLK_ZONE_TYPE_CONVENTIONAL) {
+ wps->wp[i] &= 1ULL << 63;
+ } else {
+ switch(blkz[i].cond) {
+ case BLK_ZONE_COND_FULL:
+ case BLK_ZONE_COND_READONLY:
+ /* Zone not writable */
+ wps->wp[i] = (blkz[i].start + blkz[i].len) << BDRV_SECTOR_BITS;
+ break;
+ case BLK_ZONE_COND_OFFLINE:
+ /* Zone not writable nor readable */
+ wps->wp[i] = (blkz[i].start) << BDRV_SECTOR_BITS;
+ break;
+ default:
+ if (reset_all) {
+ wps->wp[i] = blkz[i].start << BDRV_SECTOR_BITS;
+ } else {
+ wps->wp[i] = blkz[i].wp << BDRV_SECTOR_BITS;
+ }
+ break;
+ }
+ }
+ }
+ sector = blkz[i - 1].start + blkz[i - 1].len;
+ }
+
+ return 0;
+}
+
+static void update_zones_wp(int fd, BlockZoneWps *wps, int64_t offset,
+ unsigned int nrz)
+{
+ if (get_zones_wp(fd, wps, offset, nrz, 0) < 0) {
+ error_report("update zone wp failed");
+ }
+}
+#endif
+
static void raw_refresh_limits(BlockDriverState *bs, Error **errp)
{
BDRVRawState *s = bs->opaque;
@@ -1413,6 +1495,23 @@ static void raw_refresh_limits(BlockDriverState *bs, Error **errp)
if (ret >= 0) {
bs->bl.max_active_zones = ret;
}
+
+ ret = get_sysfs_long_val(&st, "physical_block_size");
+ if (ret >= 0) {
+ bs->bl.write_granularity = ret;
+ }
+
+ /* The refresh_limits() function can be called multiple times. */
+ bs->wps = NULL;
+ bs->wps = g_malloc(sizeof(BlockZoneWps) +
+ sizeof(int64_t) * bs->bl.nr_zones);
+ ret = get_zones_wp(s->fd, bs->wps, 0, bs->bl.nr_zones, 0);
+ if (ret < 0) {
+ error_setg_errno(errp, -ret, "report wps failed");
+ bs->wps = NULL;
+ return;
+ }
+ qemu_co_mutex_init(&bs->wps->colock);
return;
}
out:
@@ -2338,9 +2437,15 @@ static int coroutine_fn raw_co_prw(BlockDriverState *bs, uint64_t offset,
{
BDRVRawState *s = bs->opaque;
RawPosixAIOData acb;
+ int ret;
if (fd_open(bs) < 0)
return -EIO;
+#if defined(CONFIG_BLKZONED)
+ if (type & QEMU_AIO_WRITE && bs->wps) {
+ QEMU_LOCK_GUARD(&bs->wps->colock);
+ }
+#endif
/*
* When using O_DIRECT, the request must be aligned to be able to use
@@ -2354,14 +2459,16 @@ static int coroutine_fn raw_co_prw(BlockDriverState *bs, uint64_t offset,
} else if (s->use_linux_io_uring) {
LuringState *aio = aio_get_linux_io_uring(bdrv_get_aio_context(bs));
assert(qiov->size == bytes);
- return luring_co_submit(bs, aio, s->fd, offset, qiov, type);
+ ret = luring_co_submit(bs, aio, s->fd, offset, qiov, type);
+ goto out;
#endif
#ifdef CONFIG_LINUX_AIO
} else if (s->use_linux_aio) {
LinuxAioState *aio = aio_get_linux_aio(bdrv_get_aio_context(bs));
assert(qiov->size == bytes);
- return laio_co_submit(bs, aio, s->fd, offset, qiov, type,
+ ret = laio_co_submit(bs, aio, s->fd, offset, qiov, type,
s->aio_max_batch);
+ goto out;
#endif
}
@@ -2378,7 +2485,29 @@ static int coroutine_fn raw_co_prw(BlockDriverState *bs, uint64_t offset,
};
assert(qiov->size == bytes);
- return raw_thread_pool_submit(bs, handle_aiocb_rw, &acb);
+ ret = raw_thread_pool_submit(bs, handle_aiocb_rw, &acb);
+
+out:
+#if defined(CONFIG_BLKZONED)
+ BlockZoneWps *wps = bs->wps;
+ if (ret == 0) {
+ if (type & QEMU_AIO_WRITE && wps && bs->bl.zone_size) {
+ uint64_t *wp = &wps->wp[offset / bs->bl.zone_size];
+ if (!BDRV_ZT_IS_CONV(*wp)) {
+ /* Advance the wp if needed */
+ if (offset + bytes > *wp) {
+ *wp = offset + bytes;
+ }
+ }
+ }
+ } else {
+ if (type & QEMU_AIO_WRITE) {
+ update_zones_wp(s->fd, bs->wps, 0, 1);
+ }
+ }
+
+#endif
+ return ret;
}
static int coroutine_fn raw_co_preadv(BlockDriverState *bs, int64_t offset,
@@ -2486,6 +2615,9 @@ static void raw_close(BlockDriverState *bs)
BDRVRawState *s = bs->opaque;
if (s->fd >= 0) {
+#if defined(CONFIG_BLKZONED)
+ g_free(bs->wps);
+#endif
qemu_close(s->fd);
s->fd = -1;
}
@@ -3283,6 +3415,7 @@ static int coroutine_fn raw_co_zone_mgmt(BlockDriverState *bs, BlockZoneOp op,
const char *op_name;
unsigned long zo;
int ret;
+ BlockZoneWps *wps = bs->wps;
int64_t capacity = bs->total_sectors << BDRV_SECTOR_BITS;
zone_size = bs->bl.zone_size;
@@ -3300,6 +3433,15 @@ static int coroutine_fn raw_co_zone_mgmt(BlockDriverState *bs, BlockZoneOp op,
return -EINVAL;
}
+ QEMU_LOCK_GUARD(&wps->colock);
+ uint32_t i = offset / bs->bl.zone_size;
+ uint32_t nrz = len / bs->bl.zone_size;
+ uint64_t *wp = &wps->wp[i];
+ if (BDRV_ZT_IS_CONV(*wp) && len != capacity) {
+ error_report("zone mgmt operations are not allowed for conventional zones");
+ return -EIO;
+ }
+
switch (op) {
case BLK_ZO_OPEN:
op_name = "BLKOPENZONE";
@@ -3337,8 +3479,28 @@ static int coroutine_fn raw_co_zone_mgmt(BlockDriverState *bs, BlockZoneOp op,
len >> BDRV_SECTOR_BITS);
ret = raw_thread_pool_submit(bs, handle_aiocb_zone_mgmt, &acb);
if (ret != 0) {
+ update_zones_wp(s->fd, wps, offset, i);
ret = -errno;
error_report("ioctl %s failed %d", op_name, ret);
+ return ret;
+ }
+
+ if (zo == BLKRESETZONE && len == capacity) {
+ ret = get_zones_wp(s->fd, wps, 0, bs->bl.nr_zones, 1);
+ if (ret < 0) {
+ error_report("reporting single wp failed");
+ return ret;
+ }
+ } else if (zo == BLKRESETZONE) {
+ for (int j = 0; j < nrz; ++j) {
+ wp[j] = offset + j * zone_size;
+ }
+ } else if (zo == BLKFINISHZONE) {
+ for (int j = 0; j < nrz; ++j) {
+ /* The zoned device allows the last zone smaller that the
+ * zone size. */
+ wp[j] = MIN(offset + (j + 1) * zone_size, offset + len);
+ }
}
return ret;
diff --git a/include/block/block-common.h b/include/block/block-common.h
index 1576fcf2ed..93196229ac 100644
--- a/include/block/block-common.h
+++ b/include/block/block-common.h
@@ -118,6 +118,14 @@ typedef struct BlockZoneDescriptor {
BlockZoneState state;
} BlockZoneDescriptor;
+/*
+ * Track write pointers of a zone in bytes.
+ */
+typedef struct BlockZoneWps {
+ CoMutex colock;
+ uint64_t wp[];
+} BlockZoneWps;
+
typedef struct BlockDriverInfo {
/* in bytes, 0 if irrelevant */
int cluster_size;
@@ -240,6 +248,12 @@ typedef enum {
#define BDRV_SECTOR_BITS 9
#define BDRV_SECTOR_SIZE (1ULL << BDRV_SECTOR_BITS)
+/*
+ * Get the first most significant bit of wp. If it is zero, then
+ * the zone type is SWR.
+ */
+#define BDRV_ZT_IS_CONV(wp) (wp & (1ULL << 63))
+
#define BDRV_REQUEST_MAX_SECTORS MIN_CONST(SIZE_MAX >> BDRV_SECTOR_BITS, \
INT_MAX >> BDRV_SECTOR_BITS)
#define BDRV_REQUEST_MAX_BYTES (BDRV_REQUEST_MAX_SECTORS << BDRV_SECTOR_BITS)
diff --git a/include/block/block_int-common.h b/include/block/block_int-common.h
index 1bd2aef4d5..b34a7f175d 100644
--- a/include/block/block_int-common.h
+++ b/include/block/block_int-common.h
@@ -884,6 +884,8 @@ typedef struct BlockLimits {
/* maximum number of active zones */
int64_t max_active_zones;
+
+ int64_t write_granularity;
} BlockLimits;
typedef struct BdrvOpBlocker BdrvOpBlocker;
@@ -1245,6 +1247,9 @@ struct BlockDriverState {
CoMutex bsc_modify_lock;
/* Always non-NULL, but must only be dereferenced under an RCU read guard */
BdrvBlockStatusCache *block_status_cache;
+
+ /* array of write pointers' location of each zone in the zoned device. */
+ BlockZoneWps *wps;
};
struct BlockBackendRootState {
--
2.39.2
^ permalink raw reply related [flat|nested] 7+ messages in thread* Re: [PATCH v8 1/4] file-posix: add tracking of the zone write pointers
2023-04-04 15:32 ` [PATCH v8 1/4] file-posix: add tracking of the zone write pointers Sam Li
@ 2023-04-05 20:26 ` Stefan Hajnoczi
0 siblings, 0 replies; 7+ messages in thread
From: Stefan Hajnoczi @ 2023-04-05 20:26 UTC (permalink / raw)
To: Sam Li
Cc: qemu-devel, Fam Zheng, hare, Hanna Reitz, dmitry.fomichev,
Julia Suvorova, Stefano Garzarella, damien.lemoal, Aarushi Mehta,
Kevin Wolf, qemu-block
[-- Attachment #1: Type: text/plain, Size: 6749 bytes --]
On Tue, Apr 04, 2023 at 11:32:36PM +0800, Sam Li wrote:
> Since Linux doesn't have a user API to issue zone append operations to
> zoned devices from user space, the file-posix driver is modified to add
> zone append emulation using regular writes. To do this, the file-posix
> driver tracks the wp location of all zones of the device. It uses an
> array of uint64_t. The most significant bit of each wp location indicates
> if the zone type is conventional zones.
>
> The zones wp can be changed due to the following operations issued:
> - zone reset: change the wp to the start offset of that zone
> - zone finish: change to the end location of that zone
> - write to a zone
> - zone append
>
> Signed-off-by: Sam Li <faithilikerun@gmail.com>
> ---
> block/file-posix.c | 168 ++++++++++++++++++++++++++++++-
> include/block/block-common.h | 14 +++
> include/block/block_int-common.h | 5 +
> 3 files changed, 184 insertions(+), 3 deletions(-)
>
> diff --git a/block/file-posix.c b/block/file-posix.c
> index 65efe5147e..bc58f7193b 100644
> --- a/block/file-posix.c
> +++ b/block/file-posix.c
> @@ -1324,6 +1324,88 @@ static int hdev_get_max_segments(int fd, struct stat *st)
> #endif
> }
>
> +#if defined(CONFIG_BLKZONED)
> +/*
> + * If the reset_all flag is true, then the wps of zone whose state is
> + * not readonly or offline should be all reset to the start sector.
> + * Else, take the real wp of the device.
> + */
> +static int get_zones_wp(int fd, BlockZoneWps *wps, int64_t offset,
> + unsigned int nrz, bool reset_all)
> +{
> + struct blk_zone *blkz;
> + size_t rep_size;
> + uint64_t sector = offset >> BDRV_SECTOR_BITS;
> + int ret, n = 0, i = 0;
> + rep_size = sizeof(struct blk_zone_report) + nrz * sizeof(struct blk_zone);
> + g_autofree struct blk_zone_report *rep = NULL;
> +
> + rep = g_malloc(rep_size);
> + blkz = (struct blk_zone *)(rep + 1);
> + while (n < nrz) {
> + memset(rep, 0, rep_size);
> + rep->sector = sector;
> + rep->nr_zones = nrz - n;
> +
> + do {
> + ret = ioctl(fd, BLKREPORTZONE, rep);
> + } while (ret != 0 && errno == EINTR);
> + if (ret != 0) {
> + error_report("%d: ioctl BLKREPORTZONE at %" PRId64 " failed %d",
> + fd, offset, errno);
> + return -errno;
> + }
> +
> + if (!rep->nr_zones) {
> + break;
> + }
> +
> + for (i = 0; i < rep->nr_zones; i++, n++) {
> + /*
> + * The wp tracking cares only about sequential writes required and
> + * sequential write preferred zones so that the wp can advance to
> + * the right location.
> + * Use the most significant bit of the wp location to indicate the
> + * zone type: 0 for SWR/SWP zones and 1 for conventional zones.
> + */
> + if (blkz[i].type == BLK_ZONE_TYPE_CONVENTIONAL) {
> + wps->wp[i] &= 1ULL << 63;
Should this be |= instead of &=? I think the intention is to set the
bit.
> + } else {
> + switch(blkz[i].cond) {
> + case BLK_ZONE_COND_FULL:
> + case BLK_ZONE_COND_READONLY:
> + /* Zone not writable */
> + wps->wp[i] = (blkz[i].start + blkz[i].len) << BDRV_SECTOR_BITS;
wps->wp[i] looks wrong in two cases:
1. After the first iteration of the while (n < nrz) loop.
2. When offset > 0.
I think there should be a j variable that tracks the index into wp[]. It
should be initialized outside the while loop based on offset and
incremented inside the for loop.
> + break;
> + case BLK_ZONE_COND_OFFLINE:
> + /* Zone not writable nor readable */
> + wps->wp[i] = (blkz[i].start) << BDRV_SECTOR_BITS;
> + break;
> + default:
> + if (reset_all) {
> + wps->wp[i] = blkz[i].start << BDRV_SECTOR_BITS;
> + } else {
> + wps->wp[i] = blkz[i].wp << BDRV_SECTOR_BITS;
> + }
> + break;
> + }
> + }
> + }
> + sector = blkz[i - 1].start + blkz[i - 1].len;
> + }
> +
> + return 0;
> +}
> +
> +static void update_zones_wp(int fd, BlockZoneWps *wps, int64_t offset,
> + unsigned int nrz)
> +{
> + if (get_zones_wp(fd, wps, offset, nrz, 0) < 0) {
> + error_report("update zone wp failed");
> + }
> +}
> +#endif
> +
> static void raw_refresh_limits(BlockDriverState *bs, Error **errp)
> {
> BDRVRawState *s = bs->opaque;
> @@ -1413,6 +1495,23 @@ static void raw_refresh_limits(BlockDriverState *bs, Error **errp)
> if (ret >= 0) {
> bs->bl.max_active_zones = ret;
> }
> +
> + ret = get_sysfs_long_val(&st, "physical_block_size");
> + if (ret >= 0) {
> + bs->bl.write_granularity = ret;
> + }
> +
> + /* The refresh_limits() function can be called multiple times. */
> + bs->wps = NULL;
This needs to be g_free(bs->wps) to avoid leaking the odl bs->wps
memory.
(There are more complex solutions that reuse bs->wps when nr_zones has
not gotten larger, but freeing and allocating a new one is the simple
solution for now. This code isn't performance-critical.)
> + bs->wps = g_malloc(sizeof(BlockZoneWps) +
> + sizeof(int64_t) * bs->bl.nr_zones);
> + ret = get_zones_wp(s->fd, bs->wps, 0, bs->bl.nr_zones, 0);
> + if (ret < 0) {
> + error_setg_errno(errp, -ret, "report wps failed");
> + bs->wps = NULL;
> + return;
> + }
> + qemu_co_mutex_init(&bs->wps->colock);
> return;
> }
> out:
> @@ -2338,9 +2437,15 @@ static int coroutine_fn raw_co_prw(BlockDriverState *bs, uint64_t offset,
> {
> BDRVRawState *s = bs->opaque;
> RawPosixAIOData acb;
> + int ret;
>
> if (fd_open(bs) < 0)
> return -EIO;
> +#if defined(CONFIG_BLKZONED)
> + if (type & QEMU_AIO_WRITE && bs->wps) {
> + QEMU_LOCK_GUARD(&bs->wps->colock);
> + }
QEMU_LOCK_GUARD() has lexical scope so its lifetime ends at the end of
the {} block. Therefore it doesn't lock for the remainder of the
function.
This is a case where it's necessary to use qemu_co_mutex_lock() directly
and remember to qemu_co_mutex_unlock() at the exit point of this
function.
Stefan
[-- Attachment #2: signature.asc --]
[-- Type: application/pgp-signature, Size: 488 bytes --]
^ permalink raw reply [flat|nested] 7+ messages in thread
* [PATCH v8 2/4] block: introduce zone append write for zoned devices
2023-04-04 15:32 [PATCH v8 0/4] Add zone append write for zoned device Sam Li
2023-04-04 15:32 ` [PATCH v8 1/4] file-posix: add tracking of the zone write pointers Sam Li
@ 2023-04-04 15:32 ` Sam Li
2023-04-05 20:32 ` Stefan Hajnoczi
2023-04-04 15:32 ` [PATCH v8 3/4] qemu-iotests: test zone append operation Sam Li
2023-04-04 15:32 ` [PATCH v8 4/4] block: add some trace events for zone append Sam Li
3 siblings, 1 reply; 7+ messages in thread
From: Sam Li @ 2023-04-04 15:32 UTC (permalink / raw)
To: qemu-devel
Cc: Fam Zheng, hare, Hanna Reitz, dmitry.fomichev, Julia Suvorova,
Stefano Garzarella, damien.lemoal, Stefan Hajnoczi, Aarushi Mehta,
Kevin Wolf, qemu-block, Sam Li
A zone append command is a write operation that specifies the first
logical block of a zone as the write position. When writing to a zoned
block device using zone append, the byte offset of the call may point at
any position within the zone to which the data is being appended. Upon
completion the device will respond with the position where the data has
been written in the zone.
Signed-off-by: Sam Li <faithilikerun@gmail.com>
Reviewed-by: Dmitry Fomichev <dmitry.fomichev@wdc.com>
---
block/block-backend.c | 60 +++++++++++++++++++++++++++++++
block/file-posix.c | 56 +++++++++++++++++++++++++----
block/io.c | 27 ++++++++++++++
block/io_uring.c | 4 +++
block/linux-aio.c | 3 ++
block/raw-format.c | 8 +++++
include/block/block-io.h | 4 +++
include/block/block_int-common.h | 3 ++
include/block/raw-aio.h | 4 ++-
include/sysemu/block-backend-io.h | 9 +++++
10 files changed, 171 insertions(+), 7 deletions(-)
diff --git a/block/block-backend.c b/block/block-backend.c
index f70b08e3f6..bcb3a1eff0 100644
--- a/block/block-backend.c
+++ b/block/block-backend.c
@@ -1888,6 +1888,45 @@ BlockAIOCB *blk_aio_zone_mgmt(BlockBackend *blk, BlockZoneOp op,
return &acb->common;
}
+static void coroutine_fn blk_aio_zone_append_entry(void *opaque)
+{
+ BlkAioEmAIOCB *acb = opaque;
+ BlkRwCo *rwco = &acb->rwco;
+
+ rwco->ret = blk_co_zone_append(rwco->blk, (int64_t *)acb->bytes,
+ rwco->iobuf, rwco->flags);
+ blk_aio_complete(acb);
+}
+
+BlockAIOCB *blk_aio_zone_append(BlockBackend *blk, int64_t *offset,
+ QEMUIOVector *qiov, BdrvRequestFlags flags,
+ BlockCompletionFunc *cb, void *opaque) {
+ BlkAioEmAIOCB *acb;
+ Coroutine *co;
+ IO_CODE();
+
+ blk_inc_in_flight(blk);
+ acb = blk_aio_get(&blk_aio_em_aiocb_info, blk, cb, opaque);
+ acb->rwco = (BlkRwCo) {
+ .blk = blk,
+ .ret = NOT_DONE,
+ .flags = flags,
+ .iobuf = qiov,
+ };
+ acb->bytes = (int64_t)offset;
+ acb->has_returned = false;
+
+ co = qemu_coroutine_create(blk_aio_zone_append_entry, acb);
+ aio_co_enter(blk_get_aio_context(blk), co);
+ acb->has_returned = true;
+ if (acb->rwco.ret != NOT_DONE) {
+ replay_bh_schedule_oneshot_event(blk_get_aio_context(blk),
+ blk_aio_complete_bh, acb);
+ }
+
+ return &acb->common;
+}
+
/*
* Send a zone_report command.
* offset is a byte offset from the start of the device. No alignment
@@ -1939,6 +1978,27 @@ int coroutine_fn blk_co_zone_mgmt(BlockBackend *blk, BlockZoneOp op,
return ret;
}
+/*
+ * Send a zone_append command.
+ */
+int coroutine_fn blk_co_zone_append(BlockBackend *blk, int64_t *offset,
+ QEMUIOVector *qiov, BdrvRequestFlags flags)
+{
+ int ret;
+ IO_CODE();
+
+ blk_inc_in_flight(blk);
+ blk_wait_while_drained(blk);
+ if (!blk_is_available(blk)) {
+ blk_dec_in_flight(blk);
+ return -ENOMEDIUM;
+ }
+
+ ret = bdrv_co_zone_append(blk_bs(blk), offset, qiov, flags);
+ blk_dec_in_flight(blk);
+ return ret;
+}
+
void blk_drain(BlockBackend *blk)
{
BlockDriverState *bs = blk_bs(blk);
diff --git a/block/file-posix.c b/block/file-posix.c
index bc58f7193b..a7130b1024 100644
--- a/block/file-posix.c
+++ b/block/file-posix.c
@@ -160,6 +160,7 @@ typedef struct BDRVRawState {
bool has_write_zeroes:1;
bool use_linux_aio:1;
bool use_linux_io_uring:1;
+ int64_t *offset; /* offset of zone append operation */
int page_cache_inconsistent; /* errno from fdatasync failure */
bool has_fallocate;
bool needs_alignment;
@@ -1685,7 +1686,7 @@ static ssize_t handle_aiocb_rw_vector(RawPosixAIOData *aiocb)
ssize_t len;
len = RETRY_ON_EINTR(
- (aiocb->aio_type & QEMU_AIO_WRITE) ?
+ (aiocb->aio_type & (QEMU_AIO_WRITE | QEMU_AIO_ZONE_APPEND)) ?
qemu_pwritev(aiocb->aio_fildes,
aiocb->io.iov,
aiocb->io.niov,
@@ -1714,7 +1715,7 @@ static ssize_t handle_aiocb_rw_linear(RawPosixAIOData *aiocb, char *buf)
ssize_t len;
while (offset < aiocb->aio_nbytes) {
- if (aiocb->aio_type & QEMU_AIO_WRITE) {
+ if (aiocb->aio_type & (QEMU_AIO_WRITE | QEMU_AIO_ZONE_APPEND)) {
len = pwrite(aiocb->aio_fildes,
(const char *)buf + offset,
aiocb->aio_nbytes - offset,
@@ -1807,7 +1808,7 @@ static int handle_aiocb_rw(void *opaque)
}
nbytes = handle_aiocb_rw_linear(aiocb, buf);
- if (!(aiocb->aio_type & QEMU_AIO_WRITE)) {
+ if (!(aiocb->aio_type & (QEMU_AIO_WRITE | QEMU_AIO_ZONE_APPEND))) {
char *p = buf;
size_t count = aiocb->aio_nbytes, copy;
int i;
@@ -2442,8 +2443,12 @@ static int coroutine_fn raw_co_prw(BlockDriverState *bs, uint64_t offset,
if (fd_open(bs) < 0)
return -EIO;
#if defined(CONFIG_BLKZONED)
- if (type & QEMU_AIO_WRITE && bs->wps) {
+ if ((type & (QEMU_AIO_WRITE | QEMU_AIO_ZONE_APPEND)) && bs->wps) {
QEMU_LOCK_GUARD(&bs->wps->colock);
+ if (type & QEMU_AIO_ZONE_APPEND && bs->bl.zone_size) {
+ int index = offset / bs->bl.zone_size;
+ offset = bs->wps->wp[index];
+ }
}
#endif
@@ -2491,9 +2496,13 @@ out:
#if defined(CONFIG_BLKZONED)
BlockZoneWps *wps = bs->wps;
if (ret == 0) {
- if (type & QEMU_AIO_WRITE && wps && bs->bl.zone_size) {
+ if ((type & (QEMU_AIO_WRITE | QEMU_AIO_ZONE_APPEND))
+ && wps && bs->bl.zone_size) {
uint64_t *wp = &wps->wp[offset / bs->bl.zone_size];
if (!BDRV_ZT_IS_CONV(*wp)) {
+ if (type & QEMU_AIO_ZONE_APPEND) {
+ *s->offset = *wp;
+ }
/* Advance the wp if needed */
if (offset + bytes > *wp) {
*wp = offset + bytes;
@@ -2501,7 +2510,7 @@ out:
}
}
} else {
- if (type & QEMU_AIO_WRITE) {
+ if (type & (QEMU_AIO_WRITE | QEMU_AIO_ZONE_APPEND)) {
update_zones_wp(s->fd, bs->wps, 0, 1);
}
}
@@ -3507,6 +3516,40 @@ static int coroutine_fn raw_co_zone_mgmt(BlockDriverState *bs, BlockZoneOp op,
}
#endif
+#if defined(CONFIG_BLKZONED)
+static int coroutine_fn raw_co_zone_append(BlockDriverState *bs,
+ int64_t *offset,
+ QEMUIOVector *qiov,
+ BdrvRequestFlags flags) {
+ assert(flags == 0);
+ int64_t zone_size_mask = bs->bl.zone_size - 1;
+ int64_t iov_len = 0;
+ int64_t len = 0;
+ BDRVRawState *s = bs->opaque;
+ s->offset = offset;
+
+ if (*offset & zone_size_mask) {
+ error_report("sector offset %" PRId64 " is not aligned to zone size "
+ "%" PRId32 "", *offset / 512, bs->bl.zone_size / 512);
+ return -EINVAL;
+ }
+
+ int64_t wg = bs->bl.write_granularity;
+ int64_t wg_mask = wg - 1;
+ for (int i = 0; i < qiov->niov; i++) {
+ iov_len = qiov->iov[i].iov_len;
+ if (iov_len & wg_mask) {
+ error_report("len of IOVector[%d] %" PRId64 " is not aligned to "
+ "block size %" PRId64 "", i, iov_len, wg);
+ return -EINVAL;
+ }
+ len += iov_len;
+ }
+
+ return raw_co_prw(bs, *offset, len, qiov, QEMU_AIO_ZONE_APPEND);
+}
+#endif
+
static coroutine_fn int
raw_do_pdiscard(BlockDriverState *bs, int64_t offset, int64_t bytes,
bool blkdev)
@@ -4268,6 +4311,7 @@ static BlockDriver bdrv_host_device = {
/* zone management operations */
.bdrv_co_zone_report = raw_co_zone_report,
.bdrv_co_zone_mgmt = raw_co_zone_mgmt,
+ .bdrv_co_zone_append = raw_co_zone_append,
#endif
};
diff --git a/block/io.c b/block/io.c
index 5dbf1e50f2..3186faa278 100644
--- a/block/io.c
+++ b/block/io.c
@@ -3152,6 +3152,33 @@ out:
return co.ret;
}
+int coroutine_fn bdrv_co_zone_append(BlockDriverState *bs, int64_t *offset,
+ QEMUIOVector *qiov,
+ BdrvRequestFlags flags)
+{
+ int ret;
+ BlockDriver *drv = bs->drv;
+ CoroutineIOCompletion co = {
+ .coroutine = qemu_coroutine_self(),
+ };
+ IO_CODE();
+
+ ret = bdrv_check_qiov_request(*offset, qiov->size, qiov, 0, NULL);
+ if (ret < 0) {
+ return ret;
+ }
+
+ bdrv_inc_in_flight(bs);
+ if (!drv || !drv->bdrv_co_zone_append || bs->bl.zoned == BLK_Z_NONE) {
+ co.ret = -ENOTSUP;
+ goto out;
+ }
+ co.ret = drv->bdrv_co_zone_append(bs, offset, qiov, flags);
+out:
+ bdrv_dec_in_flight(bs);
+ return co.ret;
+}
+
void *qemu_blockalign(BlockDriverState *bs, size_t size)
{
IO_CODE();
diff --git a/block/io_uring.c b/block/io_uring.c
index 973e15d876..f7488c241a 100644
--- a/block/io_uring.c
+++ b/block/io_uring.c
@@ -345,6 +345,10 @@ static int luring_do_submit(int fd, LuringAIOCB *luringcb, LuringState *s,
io_uring_prep_writev(sqes, fd, luringcb->qiov->iov,
luringcb->qiov->niov, offset);
break;
+ case QEMU_AIO_ZONE_APPEND:
+ io_uring_prep_writev(sqes, fd, luringcb->qiov->iov,
+ luringcb->qiov->niov, offset);
+ break;
case QEMU_AIO_READ:
io_uring_prep_readv(sqes, fd, luringcb->qiov->iov,
luringcb->qiov->niov, offset);
diff --git a/block/linux-aio.c b/block/linux-aio.c
index d2cfb7f523..1959834156 100644
--- a/block/linux-aio.c
+++ b/block/linux-aio.c
@@ -389,6 +389,9 @@ static int laio_do_submit(int fd, struct qemu_laiocb *laiocb, off_t offset,
case QEMU_AIO_WRITE:
io_prep_pwritev(iocbs, fd, qiov->iov, qiov->niov, offset);
break;
+ case QEMU_AIO_ZONE_APPEND:
+ io_prep_pwritev(iocbs, fd, qiov->iov, qiov->niov, offset);
+ break;
case QEMU_AIO_READ:
io_prep_preadv(iocbs, fd, qiov->iov, qiov->niov, offset);
break;
diff --git a/block/raw-format.c b/block/raw-format.c
index 72e23e7b55..64e7d48d04 100644
--- a/block/raw-format.c
+++ b/block/raw-format.c
@@ -332,6 +332,13 @@ raw_co_zone_mgmt(BlockDriverState *bs, BlockZoneOp op,
return bdrv_co_zone_mgmt(bs->file->bs, op, offset, len);
}
+static int coroutine_fn GRAPH_RDLOCK
+raw_co_zone_append(BlockDriverState *bs,int64_t *offset, QEMUIOVector *qiov,
+ BdrvRequestFlags flags)
+{
+ return bdrv_co_zone_append(bs->file->bs, offset, qiov, flags);
+}
+
static int64_t coroutine_fn GRAPH_RDLOCK
raw_co_getlength(BlockDriverState *bs)
{
@@ -635,6 +642,7 @@ BlockDriver bdrv_raw = {
.bdrv_co_pdiscard = &raw_co_pdiscard,
.bdrv_co_zone_report = &raw_co_zone_report,
.bdrv_co_zone_mgmt = &raw_co_zone_mgmt,
+ .bdrv_co_zone_append = &raw_co_zone_append,
.bdrv_co_block_status = &raw_co_block_status,
.bdrv_co_copy_range_from = &raw_co_copy_range_from,
.bdrv_co_copy_range_to = &raw_co_copy_range_to,
diff --git a/include/block/block-io.h b/include/block/block-io.h
index 19d1fad9cf..55fca02991 100644
--- a/include/block/block-io.h
+++ b/include/block/block-io.h
@@ -120,6 +120,10 @@ int coroutine_fn GRAPH_RDLOCK bdrv_co_zone_report(BlockDriverState *bs,
int coroutine_fn GRAPH_RDLOCK bdrv_co_zone_mgmt(BlockDriverState *bs,
BlockZoneOp op,
int64_t offset, int64_t len);
+int coroutine_fn GRAPH_RDLOCK bdrv_co_zone_append(BlockDriverState *bs,
+ int64_t *offset,
+ QEMUIOVector *qiov,
+ BdrvRequestFlags flags);
bool bdrv_can_write_zeroes_with_unmap(BlockDriverState *bs);
int bdrv_block_status(BlockDriverState *bs, int64_t offset,
diff --git a/include/block/block_int-common.h b/include/block/block_int-common.h
index b34a7f175d..efa5a8e967 100644
--- a/include/block/block_int-common.h
+++ b/include/block/block_int-common.h
@@ -724,6 +724,9 @@ struct BlockDriver {
BlockZoneDescriptor *zones);
int coroutine_fn (*bdrv_co_zone_mgmt)(BlockDriverState *bs, BlockZoneOp op,
int64_t offset, int64_t len);
+ int coroutine_fn (*bdrv_co_zone_append)(BlockDriverState *bs,
+ int64_t *offset, QEMUIOVector *qiov,
+ BdrvRequestFlags flags);
/* removable device specific */
bool coroutine_fn GRAPH_RDLOCK_PTR (*bdrv_co_is_inserted)(
diff --git a/include/block/raw-aio.h b/include/block/raw-aio.h
index eda6a7a253..fb9c9f5a01 100644
--- a/include/block/raw-aio.h
+++ b/include/block/raw-aio.h
@@ -30,6 +30,7 @@
#define QEMU_AIO_TRUNCATE 0x0080
#define QEMU_AIO_ZONE_REPORT 0x0100
#define QEMU_AIO_ZONE_MGMT 0x0200
+#define QEMU_AIO_ZONE_APPEND 0x0400
#define QEMU_AIO_TYPE_MASK \
(QEMU_AIO_READ | \
QEMU_AIO_WRITE | \
@@ -40,7 +41,8 @@
QEMU_AIO_COPY_RANGE | \
QEMU_AIO_TRUNCATE | \
QEMU_AIO_ZONE_REPORT | \
- QEMU_AIO_ZONE_MGMT)
+ QEMU_AIO_ZONE_MGMT | \
+ QEMU_AIO_ZONE_APPEND)
/* AIO flags */
#define QEMU_AIO_MISALIGNED 0x1000
diff --git a/include/sysemu/block-backend-io.h b/include/sysemu/block-backend-io.h
index f575ab5b6b..e716591a1a 100644
--- a/include/sysemu/block-backend-io.h
+++ b/include/sysemu/block-backend-io.h
@@ -53,6 +53,9 @@ BlockAIOCB *blk_aio_zone_report(BlockBackend *blk, int64_t offset,
BlockAIOCB *blk_aio_zone_mgmt(BlockBackend *blk, BlockZoneOp op,
int64_t offset, int64_t len,
BlockCompletionFunc *cb, void *opaque);
+BlockAIOCB *blk_aio_zone_append(BlockBackend *blk, int64_t *offset,
+ QEMUIOVector *qiov, BdrvRequestFlags flags,
+ BlockCompletionFunc *cb, void *opaque);
BlockAIOCB *blk_aio_pdiscard(BlockBackend *blk, int64_t offset, int64_t bytes,
BlockCompletionFunc *cb, void *opaque);
void blk_aio_cancel_async(BlockAIOCB *acb);
@@ -201,6 +204,12 @@ int coroutine_fn blk_co_zone_mgmt(BlockBackend *blk, BlockZoneOp op,
int64_t offset, int64_t len);
int co_wrapper_mixed blk_zone_mgmt(BlockBackend *blk, BlockZoneOp op,
int64_t offset, int64_t len);
+int coroutine_fn blk_co_zone_append(BlockBackend *blk, int64_t *offset,
+ QEMUIOVector *qiov,
+ BdrvRequestFlags flags);
+int co_wrapper_mixed blk_zone_append(BlockBackend *blk, int64_t *offset,
+ QEMUIOVector *qiov,
+ BdrvRequestFlags flags);
int co_wrapper_mixed blk_pdiscard(BlockBackend *blk, int64_t offset,
int64_t bytes);
--
2.39.2
^ permalink raw reply related [flat|nested] 7+ messages in thread* Re: [PATCH v8 2/4] block: introduce zone append write for zoned devices
2023-04-04 15:32 ` [PATCH v8 2/4] block: introduce zone append write for zoned devices Sam Li
@ 2023-04-05 20:32 ` Stefan Hajnoczi
0 siblings, 0 replies; 7+ messages in thread
From: Stefan Hajnoczi @ 2023-04-05 20:32 UTC (permalink / raw)
To: Sam Li
Cc: qemu-devel, Fam Zheng, hare, Hanna Reitz, dmitry.fomichev,
Julia Suvorova, Stefano Garzarella, damien.lemoal, Aarushi Mehta,
Kevin Wolf, qemu-block
[-- Attachment #1: Type: text/plain, Size: 1223 bytes --]
On Tue, Apr 04, 2023 at 11:32:37PM +0800, Sam Li wrote:
> A zone append command is a write operation that specifies the first
> logical block of a zone as the write position. When writing to a zoned
> block device using zone append, the byte offset of the call may point at
> any position within the zone to which the data is being appended. Upon
> completion the device will respond with the position where the data has
> been written in the zone.
>
> Signed-off-by: Sam Li <faithilikerun@gmail.com>
> Reviewed-by: Dmitry Fomichev <dmitry.fomichev@wdc.com>
> ---
> block/block-backend.c | 60 +++++++++++++++++++++++++++++++
> block/file-posix.c | 56 +++++++++++++++++++++++++----
> block/io.c | 27 ++++++++++++++
> block/io_uring.c | 4 +++
> block/linux-aio.c | 3 ++
> block/raw-format.c | 8 +++++
> include/block/block-io.h | 4 +++
> include/block/block_int-common.h | 3 ++
> include/block/raw-aio.h | 4 ++-
> include/sysemu/block-backend-io.h | 9 +++++
> 10 files changed, 171 insertions(+), 7 deletions(-)
Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com>
[-- Attachment #2: signature.asc --]
[-- Type: application/pgp-signature, Size: 488 bytes --]
^ permalink raw reply [flat|nested] 7+ messages in thread
* [PATCH v8 3/4] qemu-iotests: test zone append operation
2023-04-04 15:32 [PATCH v8 0/4] Add zone append write for zoned device Sam Li
2023-04-04 15:32 ` [PATCH v8 1/4] file-posix: add tracking of the zone write pointers Sam Li
2023-04-04 15:32 ` [PATCH v8 2/4] block: introduce zone append write for zoned devices Sam Li
@ 2023-04-04 15:32 ` Sam Li
2023-04-04 15:32 ` [PATCH v8 4/4] block: add some trace events for zone append Sam Li
3 siblings, 0 replies; 7+ messages in thread
From: Sam Li @ 2023-04-04 15:32 UTC (permalink / raw)
To: qemu-devel
Cc: Fam Zheng, hare, Hanna Reitz, dmitry.fomichev, Julia Suvorova,
Stefano Garzarella, damien.lemoal, Stefan Hajnoczi, Aarushi Mehta,
Kevin Wolf, qemu-block, Sam Li
The patch tests zone append writes by reporting the zone wp after
the completion of the call. "zap -p" option can print the sector
offset value after completion, which should be the start sector
where the append write begins.
Signed-off-by: Sam Li <faithilikerun@gmail.com>
Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com>
---
qemu-io-cmds.c | 75 ++++++++++++++++++++++++++++++
tests/qemu-iotests/tests/zoned | 16 +++++++
tests/qemu-iotests/tests/zoned.out | 16 +++++++
3 files changed, 107 insertions(+)
diff --git a/qemu-io-cmds.c b/qemu-io-cmds.c
index f35ea627d7..3f75d2f5a6 100644
--- a/qemu-io-cmds.c
+++ b/qemu-io-cmds.c
@@ -1874,6 +1874,80 @@ static const cmdinfo_t zone_reset_cmd = {
.oneline = "reset a zone write pointer in zone block device",
};
+static int do_aio_zone_append(BlockBackend *blk, QEMUIOVector *qiov,
+ int64_t *offset, int flags, int *total)
+{
+ int async_ret = NOT_DONE;
+
+ blk_aio_zone_append(blk, offset, qiov, flags, aio_rw_done, &async_ret);
+ while (async_ret == NOT_DONE) {
+ main_loop_wait(false);
+ }
+
+ *total = qiov->size;
+ return async_ret < 0 ? async_ret : 1;
+}
+
+static int zone_append_f(BlockBackend *blk, int argc, char **argv)
+{
+ int ret;
+ bool pflag = false;
+ int flags = 0;
+ int total = 0;
+ int64_t offset;
+ char *buf;
+ int c, nr_iov;
+ int pattern = 0xcd;
+ QEMUIOVector qiov;
+
+ if (optind > argc - 3) {
+ return -EINVAL;
+ }
+
+ if ((c = getopt(argc, argv, "p")) != -1) {
+ pflag = true;
+ }
+
+ offset = cvtnum(argv[optind]);
+ if (offset < 0) {
+ print_cvtnum_err(offset, argv[optind]);
+ return offset;
+ }
+ optind++;
+ nr_iov = argc - optind;
+ buf = create_iovec(blk, &qiov, &argv[optind], nr_iov, pattern,
+ flags & BDRV_REQ_REGISTERED_BUF);
+ if (buf == NULL) {
+ return -EINVAL;
+ }
+ ret = do_aio_zone_append(blk, &qiov, &offset, flags, &total);
+ if (ret < 0) {
+ printf("zone append failed: %s\n", strerror(-ret));
+ goto out;
+ }
+
+ if (pflag) {
+ printf("After zap done, the append sector is 0x%" PRIx64 "\n",
+ tosector(offset));
+ }
+
+out:
+ qemu_io_free(blk, buf, qiov.size,
+ flags & BDRV_REQ_REGISTERED_BUF);
+ qemu_iovec_destroy(&qiov);
+ return ret;
+}
+
+static const cmdinfo_t zone_append_cmd = {
+ .name = "zone_append",
+ .altname = "zap",
+ .cfunc = zone_append_f,
+ .argmin = 3,
+ .argmax = 4,
+ .args = "offset len [len..]",
+ .oneline = "append write a number of bytes at a specified offset",
+};
+
static int truncate_f(BlockBackend *blk, int argc, char **argv);
static const cmdinfo_t truncate_cmd = {
.name = "truncate",
@@ -2672,6 +2746,7 @@ static void __attribute((constructor)) init_qemuio_commands(void)
qemuio_add_command(&zone_close_cmd);
qemuio_add_command(&zone_finish_cmd);
qemuio_add_command(&zone_reset_cmd);
+ qemuio_add_command(&zone_append_cmd);
qemuio_add_command(&truncate_cmd);
qemuio_add_command(&length_cmd);
qemuio_add_command(&info_cmd);
diff --git a/tests/qemu-iotests/tests/zoned b/tests/qemu-iotests/tests/zoned
index 56f60616b5..3d23ce9cc1 100755
--- a/tests/qemu-iotests/tests/zoned
+++ b/tests/qemu-iotests/tests/zoned
@@ -82,6 +82,22 @@ echo "(5) resetting the second zone"
$QEMU_IO $IMG -c "zrs 268435456 268435456"
echo "After resetting a zone:"
$QEMU_IO $IMG -c "zrp 268435456 1"
+echo
+echo
+echo "(6) append write" # the physical block size of the device is 4096
+$QEMU_IO $IMG -c "zrp 0 1"
+$QEMU_IO $IMG -c "zap -p 0 0x1000 0x2000"
+echo "After appending the first zone firstly:"
+$QEMU_IO $IMG -c "zrp 0 1"
+$QEMU_IO $IMG -c "zap -p 0 0x1000 0x2000"
+echo "After appending the first zone secondly:"
+$QEMU_IO $IMG -c "zrp 0 1"
+$QEMU_IO $IMG -c "zap -p 268435456 0x1000 0x2000"
+echo "After appending the second zone firstly:"
+$QEMU_IO $IMG -c "zrp 268435456 1"
+$QEMU_IO $IMG -c "zap -p 268435456 0x1000 0x2000"
+echo "After appending the second zone secondly:"
+$QEMU_IO $IMG -c "zrp 268435456 1"
# success, all done
echo "*** done"
diff --git a/tests/qemu-iotests/tests/zoned.out b/tests/qemu-iotests/tests/zoned.out
index b2d061da49..fe53ba4744 100644
--- a/tests/qemu-iotests/tests/zoned.out
+++ b/tests/qemu-iotests/tests/zoned.out
@@ -50,4 +50,20 @@ start: 0x80000, len 0x80000, cap 0x80000, wptr 0x100000, zcond:14, [type: 2]
(5) resetting the second zone
After resetting a zone:
start: 0x80000, len 0x80000, cap 0x80000, wptr 0x80000, zcond:1, [type: 2]
+
+
+(6) append write
+start: 0x0, len 0x80000, cap 0x80000, wptr 0x0, zcond:1, [type: 2]
+After zap done, the append sector is 0x0
+After appending the first zone firstly:
+start: 0x0, len 0x80000, cap 0x80000, wptr 0x18, zcond:2, [type: 2]
+After zap done, the append sector is 0x18
+After appending the first zone secondly:
+start: 0x0, len 0x80000, cap 0x80000, wptr 0x30, zcond:2, [type: 2]
+After zap done, the append sector is 0x80000
+After appending the second zone firstly:
+start: 0x80000, len 0x80000, cap 0x80000, wptr 0x80018, zcond:2, [type: 2]
+After zap done, the append sector is 0x80018
+After appending the second zone secondly:
+start: 0x80000, len 0x80000, cap 0x80000, wptr 0x80030, zcond:2, [type: 2]
*** done
--
2.39.2
^ permalink raw reply related [flat|nested] 7+ messages in thread* [PATCH v8 4/4] block: add some trace events for zone append
2023-04-04 15:32 [PATCH v8 0/4] Add zone append write for zoned device Sam Li
` (2 preceding siblings ...)
2023-04-04 15:32 ` [PATCH v8 3/4] qemu-iotests: test zone append operation Sam Li
@ 2023-04-04 15:32 ` Sam Li
3 siblings, 0 replies; 7+ messages in thread
From: Sam Li @ 2023-04-04 15:32 UTC (permalink / raw)
To: qemu-devel
Cc: Fam Zheng, hare, Hanna Reitz, dmitry.fomichev, Julia Suvorova,
Stefano Garzarella, damien.lemoal, Stefan Hajnoczi, Aarushi Mehta,
Kevin Wolf, qemu-block, Sam Li
Signed-off-by: Sam Li <faithilikerun@gmail.com>
Reviewed-by: Dmitry Fomichev <dmitry.fomichev@wdc.com>
Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com>
---
block/file-posix.c | 3 +++
block/trace-events | 2 ++
2 files changed, 5 insertions(+)
diff --git a/block/file-posix.c b/block/file-posix.c
index a7130b1024..825301467e 100644
--- a/block/file-posix.c
+++ b/block/file-posix.c
@@ -2502,6 +2502,8 @@ out:
if (!BDRV_ZT_IS_CONV(*wp)) {
if (type & QEMU_AIO_ZONE_APPEND) {
*s->offset = *wp;
+ trace_zbd_zone_append_complete(bs, *s->offset
+ >> BDRV_SECTOR_BITS);
}
/* Advance the wp if needed */
if (offset + bytes > *wp) {
@@ -3546,6 +3548,7 @@ static int coroutine_fn raw_co_zone_append(BlockDriverState *bs,
len += iov_len;
}
+ trace_zbd_zone_append(bs, *offset >> BDRV_SECTOR_BITS);
return raw_co_prw(bs, *offset, len, qiov, QEMU_AIO_ZONE_APPEND);
}
#endif
diff --git a/block/trace-events b/block/trace-events
index 3f4e1d088a..32665158d6 100644
--- a/block/trace-events
+++ b/block/trace-events
@@ -211,6 +211,8 @@ file_hdev_is_sg(int type, int version) "SG device found: type=%d, version=%d"
file_flush_fdatasync_failed(int err) "errno %d"
zbd_zone_report(void *bs, unsigned int nr_zones, int64_t sector) "bs %p report %d zones starting at sector offset 0x%" PRIx64 ""
zbd_zone_mgmt(void *bs, const char *op_name, int64_t sector, int64_t len) "bs %p %s starts at sector offset 0x%" PRIx64 " over a range of 0x%" PRIx64 " sectors"
+zbd_zone_append(void *bs, int64_t sector) "bs %p append at sector offset 0x%" PRIx64 ""
+zbd_zone_append_complete(void *bs, int64_t sector) "bs %p returns append sector 0x%" PRIx64 ""
# ssh.c
sftp_error(const char *op, const char *ssh_err, int ssh_err_code, int sftp_err_code) "%s failed: %s (libssh error code: %d, sftp error code: %d)"
--
2.39.2
^ permalink raw reply related [flat|nested] 7+ messages in thread