[v2,3/5] block/null_blk: Add support for pipelining zoned writes

Commit Message

Bart Van Assche July 10, 2023, 6:01 p.m. UTC

Add a new configfs attribute for enabling pipelining of zoned writes.
The test script below reports 250 K IOPS with no I/O scheduler, 6 K IOPS
with mq-deadline and pipelining disabled and 123 K IOPS with mq-deadline
and pipelining enabled. This shows that pipelining results in about 20
times more IOPS for this particular test case.

    #!/bin/bash

    for mode in "none 0" "mq-deadline 0" "mq-deadline 1"; do
        set +e
        for d in /sys/kernel/config/nullb/*; do
            [ -d "$d" ] && rmdir "$d"
        done
        modprobe -r null_blk
        set -e
        read -r iosched pipelining <<<"$mode"
        modprobe null_blk nr_devices=0
        (
            cd /sys/kernel/config/nullb
            mkdir nullb0
            cd nullb0
            params=(
                completion_nsec=100000
                hw_queue_depth=64
                irqmode=2                # NULL_IRQ_TIMER
                max_sectors=$((4096/512))
                memory_backed=1
                pipeline_zoned_writes="${pipelining}"
                size=1
                submit_queues=1
                zone_size=1
                zoned=1
                power=1
            )
            for p in "${params[@]}"; do
                echo "${p//*=}" > "${p//=*}"
            done
        )
        udevadm settle
        dev=/dev/nullb0
        [ -b "${dev}" ]
        params=(
            --direct=1
            --filename="${dev}"
            --iodepth=64
            --iodepth_batch=16
            --ioengine=io_uring
            --ioscheduler="${iosched}"
            --gtod_reduce=1
            --hipri=0
            --name=nullb0
            --runtime=30
            --rw=write
            --time_based=1
            --zonemode=zbd
        )
        fio "${params[@]}"
    done

Cc: Damien Le Moal <[e-mail]>
Signed-off-by: Bart Van Assche <[e-mail]>
---
 drivers/block/null_blk/main.c     | 2 ++
 drivers/block/null_blk/null_blk.h | 1 +
 drivers/block/null_blk/zoned.c    | 3 +++
 3 files changed, 6 insertions(+)

Patch

diff --git a/drivers/block/null_blk/main.c b/drivers/block/null_blk/main.c
index 864013019d6b..1cd6eb4e2c16 100644
--- a/drivers/block/null_blk/main.c
+++ b/drivers/block/null_blk/main.c
@@ -424,6 +424,7 @@  NULLB_DEVICE_ATTR(zone_capacity, ulong, NULL);
 NULLB_DEVICE_ATTR(zone_nr_conv, uint, NULL);
 NULLB_DEVICE_ATTR(zone_max_open, uint, NULL);
 NULLB_DEVICE_ATTR(zone_max_active, uint, NULL);
+NULLB_DEVICE_ATTR(pipeline_zoned_writes, bool, NULL);
 NULLB_DEVICE_ATTR(virt_boundary, bool, NULL);
 NULLB_DEVICE_ATTR(no_sched, bool, NULL);
 NULLB_DEVICE_ATTR(shared_tag_bitmap, bool, NULL);
@@ -569,6 +570,7 @@  static struct configfs_attribute *nullb_device_attrs[] = {
 	&nullb_device_attr_zone_max_active,
 	&nullb_device_attr_zone_readonly,
 	&nullb_device_attr_zone_offline,
+	&nullb_device_attr_pipeline_zoned_writes,
 	&nullb_device_attr_virt_boundary,
 	&nullb_device_attr_no_sched,
 	&nullb_device_attr_shared_tag_bitmap,
diff --git a/drivers/block/null_blk/null_blk.h b/drivers/block/null_blk/null_blk.h
index 929f659dd255..248acf288a8e 100644
--- a/drivers/block/null_blk/null_blk.h
+++ b/drivers/block/null_blk/null_blk.h
@@ -117,6 +117,7 @@  struct nullb_device {
 	bool memory_backed; /* if data is stored in memory */
 	bool discard; /* if support discard */
 	bool zoned; /* if device is zoned */
+	bool pipeline_zoned_writes;
 	bool virt_boundary; /* virtual boundary on/off for the device */
 	bool no_sched; /* no IO scheduler for the device */
 	bool shared_tag_bitmap; /* use hostwide shared tags */
diff --git a/drivers/block/null_blk/zoned.c b/drivers/block/null_blk/zoned.c
index 635ce0648133..2bfd5f7cee67 100644
--- a/drivers/block/null_blk/zoned.c
+++ b/drivers/block/null_blk/zoned.c
@@ -96,6 +96,9 @@  int null_init_zoned_dev(struct nullb_device *dev, struct request_queue *q)
 
 	spin_lock_init(&dev->zone_res_lock);
 
+	if (dev->pipeline_zoned_writes)
+		blk_queue_flag_set(QUEUE_FLAG_PIPELINE_ZONED_WRITES, q);
+
 	if (dev->zone_nr_conv >= dev->nr_zones) {
 		dev->zone_nr_conv = dev->nr_zones - 1;
 		pr_info("changed the number of conventional zones to %u",