Skip to contentSkip to conversation

Recent changes (master)

PATCH Jens Axboe 1 participant 1 message Jun 2, 2022 Kbuild

lore
Share & tools
lore

Jens Axboe

author
#0 lore raw

The following changes since commit 5ceed0be62f3ce8903d5747674f9f70f44e736d6:

docs: update language setting for Sphinx build (2022-05-31 20:58:00 -0600)

are available in the Git repository at:

git://git.kernel.dk/fio.git master

for you to fetch changes up to 26faead0f3c6e7608b89a51373f1455b91377fcb:

t/zbd: skip test case #13 when max_open_zones is too small (2022-06-02 03:58:31 -0600)

----------------------------------------------------------------
Ankit Kumar (5):
configure: check nvme uring command support
nvme: add nvme opcodes, structures and helper functions
docs: document options for io_uring_cmd I/O engine
zbd: Check for direct flag only if its block device engines/io_uring: Enable zone device support for io_uring_cmd I/O engine

Anuj Gupta (4):
io_uring.h: add IORING_SETUP_SQE128 and IORING_SETUP_CQE32
init: return error incase an invalid value is passed as option engines/io_uring: add new I/O engine for uring passthrough support
examples: add 2 example job file for io_uring_cmd engine

Jens Axboe (3):
engines/io_uring: cleanup supported case engines/nvme: fix 'fd' leak in error handling engines/nvme: ioctl return value is an int

Shin'ichiro Kawasaki (1):
t/zbd: skip test case #13 when max_open_zones is too small

 HOWTO.rst                    |  41 +++--
 Makefile                     |   4 +-
 configure                    |  21 +++
 engines/io_uring.c           | 346 +++++++++++++++++++++++++++++++++++++++++-
 engines/nvme.c               | 347 +++++++++++++++++++++++++++++++++++++++++++
 engines/nvme.h               | 214 ++++++++++++++++++++++++++
 examples/uring-cmd-ng.fio    |  25 ++++
 examples/uring-cmd-zoned.fio |  31 ++++
 file.h                       |  12 +-
 fio.1                        |  33 +++-
 init.c                       |   9 ++
 os/linux/io_uring.h          |  45 +++++-
 t/zbd/test-zbd-support       |  23 ++-
 zbd.c                        |   4 +-
 14 files changed, 1123 insertions(+), 32 deletions(-)
 create mode 100644 engines/nvme.c
 create mode 100644 engines/nvme.h
 create mode 100644 examples/uring-cmd-ng.fio
 create mode 100644 examples/uring-cmd-zoned.fio

---

Diff of recent changes:

HOWTO.rst +31 -10
index 8ab3ac4b..28ac2b7c 100644
@@ -1952,6 +1952,10 @@ I/O engine
 			for both direct and buffered IO.
 			This engine defines engine specific options.
 
+		**io_uring_cmd**
+			Fast Linux native asynchronous I/O for pass through commands.
+			This engine defines engine specific options.
+
 		**libaio**
 			Linux native asynchronous I/O. Note that Linux may only support
 			queued behavior with non-buffered I/O (set ``direct=1`` or
@@ -2255,22 +2259,34 @@ with the caveat that when used on the command line, they must come after the
 	values for trim IOs are ignored. This option is mutually exclusive with
 	the :option:`cmdprio_percentage` option.
 
-.. option:: fixedbufs : [io_uring]
+.. option:: fixedbufs : [io_uring] [io_uring_cmd]
+
+	If fio is asked to do direct IO, then Linux will map pages for each
+	IO call, and release them when IO is done. If this option is set, the
+	pages are pre-mapped before IO is started. This eliminates the need to
+	map and release for each IO. This is more efficient, and reduces the
+	IO latency as well.
+
+.. option:: nonvectored : [io_uring] [io_uring_cmd]
 
-    If fio is asked to do direct IO, then Linux will map pages for each
-    IO call, and release them when IO is done. If this option is set, the
-    pages are pre-mapped before IO is started. This eliminates the need to
-    map and release for each IO. This is more efficient, and reduces the
-    IO latency as well.
+	With this option, fio will use non-vectored read/write commands, where
+	address must contain the address directly. Default is -1.
 
-.. option:: registerfiles : [io_uring]
+.. option:: force_async=int : [io_uring] [io_uring_cmd]
+
+	Normal operation for io_uring is to try and issue an sqe as
+	non-blocking first, and if that fails, execute it in an async manner.
+	With this option set to N, then every N request fio will ask sqe to
+	be issued in an async manner. Default is 0.
+
+.. option:: registerfiles : [io_uring] [io_uring_cmd]
 
 	With this option, fio registers the set of files being used with the
 	kernel. This avoids the overhead of managing file counts in the kernel,
 	making the submission and completion part more lightweight. Required
 	for the below :option:`sqthread_poll` option.
 
-.. option:: sqthread_poll : [io_uring] [xnvme]
+.. option:: sqthread_poll : [io_uring] [io_uring_cmd] [xnvme]
 
 	Normally fio will submit IO by issuing a system call to notify the
 	kernel of available items in the SQ ring. If this option is set, the
@@ -2278,14 +2294,19 @@ with the caveat that when used on the command line, they must come after the
 	This frees up cycles for fio, at the cost of using more CPU in the
 	system.
 
-.. option:: sqthread_poll_cpu : [io_uring]
+.. option:: sqthread_poll_cpu : [io_uring] [io_uring_cmd]
 
 	When :option:`sqthread_poll` is set, this option provides a way to
 	define which CPU should be used for the polling thread.
 
+.. option:: cmd_type=str : [io_uring_cmd]
+
+	Specifies the type of uring passthrough command to be used. Supported
+	value is nvme. Default is nvme.
+
 .. option:: hipri
 
-   [io_uring], [xnvme]
+   [io_uring] [io_uring_cmd] [xnvme]
 
         If this option is set, fio will attempt to use polled IO completions.
         Normal IO completions generate interrupts to signal the completion of
Makefile +2 -2
index ed66305a..188a74d7 100644
@@ -231,7 +231,7 @@ ifdef CONFIG_LIBXNVME
 endif
 ifeq ($(CONFIG_TARGET_OS), Linux)
   SOURCE += diskutil.c fifo.c blktrace.c cgroup.c trim.c engines/sg.c \
-		oslib/linux-dev-lookup.c engines/io_uring.c
+		oslib/linux-dev-lookup.c engines/io_uring.c engines/nvme.c
   cmdprio_SRCS = engines/cmdprio.c
 ifdef CONFIG_HAS_BLKZONED
   SOURCE += oslib/linux-blkzoned.c
@@ -241,7 +241,7 @@ endif
 endif
 ifeq ($(CONFIG_TARGET_OS), Android)
   SOURCE += diskutil.c fifo.c blktrace.c cgroup.c trim.c profiles/tiobench.c \
-		oslib/linux-dev-lookup.c engines/io_uring.c
+		oslib/linux-dev-lookup.c engines/io_uring.c engines/nvme.c
   cmdprio_SRCS = engines/cmdprio.c
 ifdef CONFIG_HAS_BLKZONED
   SOURCE += oslib/linux-blkzoned.c
configure +21 -0
index 4ee536a0..8182322b 100755
@@ -2587,6 +2587,27 @@ if test "$libzbc" != "no" ; then
 fi
 print_config "libzbc engine" "$libzbc"
 
+if test "$targetos" = "Linux" ; then
+##########################################
+# Check NVME_URING_CMD support
+cat > $TMPC << EOF
+#include <linux/nvme_ioctl.h>
+int main(void)
+{
+  struct nvme_uring_cmd *cmd;
+
+  return sizeof(struct nvme_uring_cmd);
+}
+EOF
+if compile_prog "" "" "nvme uring cmd"; then
+  output_sym "CONFIG_NVME_URING_CMD"
+  nvme_uring_cmd="yes"
+else
+  nvme_uring_cmd="no"
+fi
+print_config "NVMe uring command support" "$nvme_uring_cmd"
+fi
+
 ##########################################
 # Check if we have xnvme
 if test "$xnvme" != "yes" ; then
engines/io_uring.c +340 -6

422 lines not on this page · raw message

engines/nvme.c new file +347 -0

347 lines not on this page · raw message

engines/nvme.h new file +214 -0

214 lines not on this page · raw message

examples/uring-cmd-ng.fio new file +25 -0
new file mode 100644
index 00000000..b2888a00
@@ -0,0 +1,25 @@
+# io_uring_cmd I/O engine for nvme-ns generic character device
+
+[global]
+filename=/dev/ng0n1
+ioengine=io_uring_cmd
+cmd_type=nvme
+size=1G
+iodepth=32
+bs=4K
+thread=1
+stonewall=1
+
+[rand-write]
+rw=randwrite
+sqthread_poll=1
+
+[rand-read]
+rw=randread
+
+[write-opts]
+rw=write
+sqthread_poll=1
+sqthread_poll_cpu=0
+nonvectored=1
+registerfiles=1
examples/uring-cmd-zoned.fio new file +31 -0
new file mode 100644
index 00000000..58e8f79e
@@ -0,0 +1,31 @@
+# io_uring_cmd I/O engine for nvme-ns generic zoned character device
+#
+# NOTE: with write workload iodepth must be set to 1 as there is no IO
+# scheduler.
+
+[global]
+filename=/dev/ng0n1
+ioengine=io_uring_cmd
+cmd_type=nvme
+zonemode=zbd
+size=1G
+iodepth=1
+bs=256K
+verify=crc32c
+stonewall=1
+
+[rand-write]
+rw=randwrite
+
+[write-opts]
+rw=write
+registerfiles=1
+sqthread_poll=1
+sqthread_poll_cpu=0
+
+[randwrite-opts]
+rw=randwrite
+sqthread_poll=1
+sqthread_poll_cpu=0
+nonvectored=1
+registerfiles=1
file.h +7 -5
index faf65a2a..da1b8947 100644
@@ -126,12 +126,14 @@ struct fio_file {
 	unsigned int last_write_idx;
 
 	/*
-	 * For use by the io engine for offset or private data storage
+	 * For use by the io engine to store offset
 	 */
-	union {
-		uint64_t engine_pos;
-		void *engine_data;
-	};
+	uint64_t engine_pos;
+
+	/*
+	 * For use by the io engine for private data storage
+	 */
+	void *engine_data;
 
 	/*
 	 * if io is protected by a semaphore, this is set
fio.1 +28 -5
index bdba3142..948c01f9 100644
@@ -1739,6 +1739,15 @@ Basic \fBpreadv\fR\|(2) or \fBpwritev\fR\|(2) I/O.
 .B pvsync2
 Basic \fBpreadv2\fR\|(2) or \fBpwritev2\fR\|(2) I/O.
 .TP
+.B io_uring
+Fast Linux native asynchronous I/O. Supports async IO
+for both direct and buffered IO.
+This engine defines engine specific options.
+.TP
+.B io_uring_cmd
+Fast Linux native asynchronous I/O for passthrough commands.
+This engine defines engine specific options.
+.TP
 .B libaio
 Linux native asynchronous I/O. Note that Linux may only support
 queued behavior with non-buffered I/O (set `direct=1' or
@@ -2040,35 +2049,49 @@ for trim IOs are ignored. This option is mutually exclusive with the
 \fBcmdprio_percentage\fR option.
 .RE
 .TP
-.BI (io_uring)fixedbufs
+.BI (io_uring,io_uring_cmd)fixedbufs
 If fio is asked to do direct IO, then Linux will map pages for each IO call, and
 release them when IO is done. If this option is set, the pages are pre-mapped
 before IO is started. This eliminates the need to map and release for each IO.
 This is more efficient, and reduces the IO latency as well.
 .TP
-.BI (io_uring,xnvme)hipri
+.BI (io_uring,io_uring_cmd)nonvectored
+With this option, fio will use non-vectored read/write commands, where address
+must contain the address directly. Default is -1.
+.TP
+.BI (io_uring,io_uring_cmd)force_async
+Normal operation for io_uring is to try and issue an sqe as non-blocking first,
+and if that fails, execute it in an async manner. With this option set to N,
+then every N request fio will ask sqe to be issued in an async manner. Default
+is 0.
+.TP
+.BI (io_uring,io_uring_cmd,xnvme)hipri
 If this option is set, fio will attempt to use polled IO completions. Normal IO
 completions generate interrupts to signal the completion of IO, polled
 completions do not. Hence they are require active reaping by the application.
 The benefits are more efficient IO for high IOPS scenarios, and lower latencies
 for low queue depth IO.
 .TP
-.BI (io_uring)registerfiles
+.BI (io_uring,io_uring_cmd)registerfiles
 With this option, fio registers the set of files being used with the kernel.
 This avoids the overhead of managing file counts in the kernel, making the
 submission and completion part more lightweight. Required for the below
 sqthread_poll option.
 .TP
-.BI (io_uring,xnvme)sqthread_poll
+.BI (io_uring,io_uring_cmd,xnvme)sqthread_poll
 Normally fio will submit IO by issuing a system call to notify the kernel of
 available items in the SQ ring. If this option is set, the act of submitting IO
 will be done by a polling thread in the kernel. This frees up cycles for fio, at
 the cost of using more CPU in the system.
 .TP
-.BI (io_uring)sqthread_poll_cpu
+.BI (io_uring,io_uring_cmd)sqthread_poll_cpu
 When `sqthread_poll` is set, this option provides a way to define which CPU
 should be used for the polling thread.
 .TP
+.BI (io_uring_cmd)cmd_type \fR=\fPstr
+Specifies the type of uring passthrough command to be used. Supported
+value is nvme. Default is nvme.
+.TP
 .BI (libaio)userspace_reap
 Normally, with the libaio engine in use, fio will use the
 \fBio_getevents\fR\|(3) system call to reap newly returned events. With
init.c +9 -0
index f7d702f8..da800776 100644
@@ -2810,6 +2810,15 @@ int parse_cmd_line(int argc, char *argv[], int client_type)
 				break;
 
 			ret = fio_cmd_ioengine_option_parse(td, opt, val);
+
+			if (ret) {
+				if (td) {
+					put_job(td);
+					td = NULL;
+				}
+				do_exit++;
+				exit_val = 1;
+			}
 			break;
 		}
 		case 'w':
os/linux/io_uring.h +44 -1

75 lines not on this page · raw message

t/zbd/test-zbd-support +22 -1
index 7e2fff00..d4aaa813 100755
@@ -229,6 +229,14 @@ require_regular_block_dev() {
 	return 0
 }
 
+require_block_dev() {
+	if [[ -b "$realdev" ]]; then
+		return 0
+	fi
+	SKIP_REASON="$dev is not a block device"
+	return 1
+}
+
 require_seq_zones() {
 	local req_seq_zones=${1}
 	local seq_bytes=$((disk_size - first_sequential_zone_sector * 512))
@@ -251,8 +259,19 @@ require_conv_zones() {
 	return 0
 }
 
-# Check whether buffered writes are refused.
+require_max_open_zones() {
+	local min=${1}
+
+	if ((max_open_zones !=0 && max_open_zones < min)); then
+		SKIP_REASON="max_open_zones of $dev is smaller than $min"
+		return 1
+	fi
+	return 0
+}
+
+# Check whether buffered writes are refused for block devices.
 test1() {
+    require_block_dev || return $SKIP_TESTCASE
     run_fio --name=job1 --filename="$dev" --rw=write --direct=0 --bs=4K	\
 	    "$(ioengine "psync")" --size="${zone_size}" --thread=1	\
 	    --zonemode=zbd --zonesize="${zone_size}" 2>&1 |
@@ -453,6 +472,8 @@ test12() {
 test13() {
     local size off capacity
 
+    require_max_open_zones 4 || return $SKIP_TESTCASE
+
     prep_write
     size=$((8 * zone_size))
     off=$((first_sequential_zone_sector * 512))
zbd.c +2 -2
index b1fd6b4b..627fb968 100644
@@ -466,7 +466,7 @@ out:
 	return res;
 }
 
-/* Verify whether direct I/O is used for all host-managed zoned drives. */
+/* Verify whether direct I/O is used for all host-managed zoned block drives. */
 static bool zbd_using_direct_io(void)
 {
 	struct thread_data *td;
@@ -477,7 +477,7 @@ static bool zbd_using_direct_io(void)
 		if (td->o.odirect || !(td->o.td_ddir & TD_DDIR_WRITE))
 			continue;
 		for_each_file(td, f, j) {
-			if (f->zbd_info &&
+			if (f->zbd_info && f->filetype == FIO_TYPE_BLOCK &&
 			    f->zbd_info->model == ZBD_HOST_MANAGED)
 				return false;
 		}