mirrors/linux
1
0
Fork 0
mirror of https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git synced 2025-12-27 15:51:30 -05:00
Code Issues Packages Projects Releases Wiki Activity

dm-delay: don't busy-wait in kthread

Browse Source 
When using a kthread to delay the IOs, dm-delay would continuously loop,
checking if IOs were ready to submit. It had a cond_resched() call in
the loop, but might still loop hundreds of millions of times waiting for
an IO that was scheduled to be submitted 10s of ms in the future. With
the change to make dm-delay over zoned devices always use kthreads
regardless of the length of the delay, this wasted work only gets worse.

To solve this and still keep roughly the same precision for very short
delays, dm-delay now calls fsleep() for 1/8th of the smallest non-zero
delay it will place on IOs, or 1 ms, whichever is smaller. The reason
that dm-delay doesn't just use the actual expiration time of the next
delayed IO to calculated the sleep time is that delay_dtr() must wait
for the kthread to finish before deleting the table. If a zoned device
with a long delay queued an IO shortly before being suspended and
removed, the IO would be flushed in delay_presuspend(), but the removing
the device would still have to wait for the remainder of the long delay.
This time is now capped at 1 ms.

Signed-off-by: Benjamin Marzinski <bmarzins@redhat.com>
Reviewed-by: Damien Le Moal <dlemoal@kernel.org>
Tested-by: Damien Le Moal <dlemoal@kernel.org>
Signed-off-by: Mikulas Patocka <mpatocka@redhat.com>
This commit is contained in:
Benjamin Marzinski
2025-04-14 15:28:36 +02:00
committed by Mikulas Patocka
parent ad320ae276
commit 33304b75df
1 changed files with 14 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files

17
drivers/md/dm-delay.c
View File

@@ -14,11 +14,14 @@
#include <linux/bio.h>
#include <linux/slab.h>
#include <linux/kthread.h>
#include <linux/delay.h>
#include <linux/device-mapper.h>
#define DM_MSG_PREFIX "delay"
#define SLEEP_SHIFT 3
struct delay_class {
struct dm_dev *dev;
sector_t start;
@@ -34,6 +37,7 @@ struct delay_c {
struct work_struct flush_expired_bios;
struct list_head delayed_bios;
struct task_struct *worker;
unsigned int worker_sleep_us;
bool may_delay;
struct delay_class read;
@@ -136,6 +140,7 @@ static int flush_worker_fn(void *data)
schedule();
} else {
spin_unlock(&dc->delayed_bios_lock);
fsleep(dc->worker_sleep_us);
cond_resched();
}
}
@@ -212,7 +217,7 @@ static int delay_ctr(struct dm_target *ti, unsigned int argc, char **argv)
{
struct delay_c *dc;
int ret;
unsigned int max_delay;
unsigned int max_delay, min_delay;
if (argc != 3 && argc != 6 && argc != 9) {
ti->error = "Requires exactly 3, 6 or 9 arguments";
@@ -235,7 +240,7 @@ static int delay_ctr(struct dm_target *ti, unsigned int argc, char **argv)
ret = delay_class_ctr(ti, &dc->read, argv);
if (ret)
goto bad;
max_delay = dc->read.delay;
min_delay = max_delay = dc->read.delay;
if (argc == 3) {
ret = delay_class_ctr(ti, &dc->write, argv);
@@ -251,6 +256,7 @@ static int delay_ctr(struct dm_target *ti, unsigned int argc, char **argv)
if (ret)
goto bad;
max_delay = max(max_delay, dc->write.delay);
min_delay = min_not_zero(min_delay, dc->write.delay);
if (argc == 6) {
ret = delay_class_ctr(ti, &dc->flush, argv + 3);
@@ -263,9 +269,14 @@ static int delay_ctr(struct dm_target *ti, unsigned int argc, char **argv)
if (ret)
goto bad;
max_delay = max(max_delay, dc->flush.delay);
min_delay = min_not_zero(min_delay, dc->flush.delay);
out:
if (max_delay < 50) {
if (min_delay >> SLEEP_SHIFT)
dc->worker_sleep_us = 1000;
else
dc->worker_sleep_us = (min_delay * 1000) >> SLEEP_SHIFT;
/*
* In case of small requested delays, use kthread instead of
* timers and workqueue to achieve better latency.
@@ -438,7 +449,7 @@ static int delay_iterate_devices(struct dm_target *ti,
static struct target_type delay_target = {
.name = "delay",
.version = {1, 4, 0},
.version = {1, 5, 0},
.features = DM_TARGET_PASSES_INTEGRITY | DM_TARGET_ZONED_HM,
.module = THIS_MODULE,
.ctr = delay_ctr,