On Tue, 2017-09-26 at 22:59 +0800, Ming Lei wrote:
> On Tue, Sep 26, 2017 at 02:42:07PM +0000, Bart Van Assche wrote:
> > On Tue, 2017-09-26 at 19:17 +0800, Ming Lei wrote:
> > > Just test this patch a bit and the following failure of freezing task
> > > is triggered during suspend: [ ... ]
> >
> > What kernel version did you start from and which patches were applied on top of
> > that kernel? Only patch 1/7 or all seven patches? What storage configuration did
>
> It is v4.14-rc1+, and top commit is 8d93c7a43157, with all your 7 patches
> applied.
>
> > you use in your test and what command(s) did you use to trigger suspend?
>
> Follows my pm test script:
>
> #!/bin/sh
>
> echo check > /sys/block/md127/md/sync_action
>
> mkfs.ext4 -F /dev/md127
>
> mount /dev/md0 /mnt/data
>
> dd if=/dev/zero of=/mnt/data/d1.img bs=4k count=128k&
>
> echo 9 > /proc/sys/kernel/printk
> echo devices > /sys/power/pm_test
> echo mem > /sys/power/state
>
> wait
> umount /mnt/data
>
> Storage setting:
>
> sudo mdadm --create /dev/md/test /dev/sda /dev/sdb --level=1 --raid-devices=2
> both /dev/sda and /dev/sdb are virtio-scsi.
Thanks for the detailed reply. I have been able to reproduce the freeze failure
you reported. The output of SysRq-t learned me that the md reboot notifier was
waiting for the frozen md sync thread and that this caused the freeze failure. So
I have started testing the patch below instead of the patch at the start of this
e-mail thread:
Subject: [PATCH] md: Stop resync and reshape upon system freeze
Some people use the md driver on laptops and use the suspend and
resume functionality. Since it is essential that submitting of
new I/O requests stops before a hibernation image is created,
interrupt the md resync and reshape actions if the system is
being frozen. Note: the resync and reshape will restart after
the system is resumed and a message similar to the following
will appear in the system log:
md: md0: data-check interrupted.
---
drivers/md/md.c | 34 ++++++++++++++++++++--------------
1 file changed, 20 insertions(+), 14 deletions(-)
diff --git a/drivers/md/md.c b/drivers/md/md.c
index 08fcaebc61bd..1e9d50f7345e 100644
--- a/drivers/md/md.c
+++ b/drivers/md/md.c
@@ -66,6 +66,7 @@
#include <linux/raid/md_u.h>
#include <linux/slab.h>
#include <linux/percpu-refcount.h>
+#include <linux/freezer.h>
#include <trace/events/block.h>
#include "md.h"
@@ -8103,6 +8104,12 @@ void md_allow_write(struct mddev *mddev)
}
EXPORT_SYMBOL_GPL(md_allow_write);
+static bool md_sync_interrupted(struct mddev *mddev)
+{
+ return test_bit(MD_RECOVERY_INTR, &mddev->recovery) ||
+ freezing(current);
+}
+
#define SYNC_MARKS 10
#define SYNC_MARK_STEP (3*HZ)
#define UPDATE_FREQUENCY (5*60*HZ)
@@ -8133,6 +8140,8 @@ void md_do_sync(struct md_thread *thread)
return;
}
+ set_freezable();
+
if (mddev_is_clustered(mddev)) {
ret = md_cluster_ops->resync_start(mddev);
if (ret)
@@ -8184,7 +8193,7 @@ void md_do_sync(struct md_thread *thread)
mddev->curr_resync = 2;
try_again:
- if (test_bit(MD_RECOVERY_INTR, &mddev->recovery))
+ if (md_sync_interrupted(mddev))
goto skip;
for_each_mddev(mddev2, tmp) {
if (mddev2 == mddev)
@@ -8208,7 +8217,7 @@ void md_do_sync(struct md_thread *thread)
* be caught by 'softlockup'
*/
prepare_to_wait(&resync_wait, &wq, TASK_INTERRUPTIBLE);
- if (!test_bit(MD_RECOVERY_INTR, &mddev->recovery) &&
+ if (!md_sync_interrupted(mddev) &&
mddev2->curr_resync >= mddev->curr_resync) {
if (mddev2_minor != mddev2->md_minor) {
mddev2_minor = mddev2->md_minor;
@@ -8335,8 +8344,7 @@ void md_do_sync(struct md_thread *thread)
sysfs_notify(&mddev->kobj, NULL, "sync_completed");
}
- while (j >= mddev->resync_max &&
- !test_bit(MD_RECOVERY_INTR, &mddev->recovery)) {
+ while (j >= mddev->resync_max && !md_sync_interrupted(mddev)) {
/* As this condition is controlled by user-space,
* we can block indefinitely, so use '_interruptible'
* to avoid triggering warnings.
@@ -8348,7 +8356,7 @@ void md_do_sync(struct md_thread *thread)
&mddev->recovery));
}
- if (test_bit(MD_RECOVERY_INTR, &mddev->recovery))
+ if (md_sync_interrupted(mddev))
break;
sectors = mddev->pers->sync_request(mddev, j, &skipped);
@@ -8362,7 +8370,7 @@ void md_do_sync(struct md_thread *thread)
atomic_add(sectors, &mddev->recovery_active);
}
- if (test_bit(MD_RECOVERY_INTR, &mddev->recovery))
+ if (md_sync_interrupted(mddev))
break;
j += sectors;
@@ -8394,7 +8402,7 @@ void md_do_sync(struct md_thread *thread)
last_mark = next;
}
- if (test_bit(MD_RECOVERY_INTR, &mddev->recovery))
+ if (md_sync_interrupted(mddev))
break;
/*
@@ -8427,8 +8435,7 @@ void md_do_sync(struct md_thread *thread)
}
}
pr_info("md: %s: %s %s.\n",mdname(mddev), desc,
- test_bit(MD_RECOVERY_INTR, &mddev->recovery)
- ? "interrupted" : "done");
+ md_sync_interrupted(mddev) ? "interrupted" : "done");
/*
* this also signals 'finished resyncing' to md_stop
*/
@@ -8436,8 +8443,7 @@ void md_do_sync(struct md_thread *thread)
wait_event(mddev->recovery_wait, !atomic_read(&mddev->recovery_active));
if (!test_bit(MD_RECOVERY_RESHAPE, &mddev->recovery) &&
- !test_bit(MD_RECOVERY_INTR, &mddev->recovery) &&
- mddev->curr_resync > 3) {
+ !md_sync_interrupted(mddev) && mddev->curr_resync > 3) {
mddev->curr_resync_completed = mddev->curr_resync;
sysfs_notify(&mddev->kobj, NULL, "sync_completed");
}
@@ -8446,7 +8452,7 @@ void md_do_sync(struct md_thread *thread)
if (!test_bit(MD_RECOVERY_CHECK, &mddev->recovery) &&
mddev->curr_resync > 3) {
if (test_bit(MD_RECOVERY_SYNC, &mddev->recovery)) {
- if (test_bit(MD_RECOVERY_INTR, &mddev->recovery)) {
+ if (md_sync_interrupted(mddev)) {
if (mddev->curr_resync >= mddev->recovery_cp) {
pr_debug("md: checkpointing %s of %s.\n",
desc, mdname(mddev));
@@ -8461,7 +8467,7 @@ void md_do_sync(struct md_thread *thread)
} else
mddev->recovery_cp = MaxSector;
} else {
- if (!test_bit(MD_RECOVERY_INTR, &mddev->recovery))
+ if (!md_sync_interrupted(mddev))
mddev->curr_resync = MaxSector;
rcu_read_lock();
rdev_for_each_rcu(rdev, mddev)
@@ -8483,7 +8489,7 @@ void md_do_sync(struct md_thread *thread)
BIT(MD_SB_CHANGE_PENDING) | BIT(MD_SB_CHANGE_DEVS));
spin_lock(&mddev->lock);
- if (!test_bit(MD_RECOVERY_INTR, &mddev->recovery)) {
+ if (!md_sync_interrupted(mddev)) {
/* We completed so min/max setting can be forgotten if used. */
if (test_bit(MD_RECOVERY_REQUESTED, &mddev->recovery))
mddev->resync_min = 0;
