lkml.org 
[lkml]   [2023]   [Aug]   [3]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
 
Messages in this thread
Patch in this message
/
From
Subject[PATCH -next 12/13] md: delay choosing sync direction to md_start_sync()
Date
From: Yu Kuai <yukuai3@huawei.com>

Before this patch, for read-write array:

1) md_check_recover() found that something need to be done, and it'll
try to grab 'reconfig_mutex'. The case that md_check_recover() need
to do something:
- array is not suspend;
- super_block need to be updated;
- 'MD_RECOVERY_NEEDED' or ''MD_RECOVERY_DONE' is set;
- unusual case related to safemode;

2) if 'MD_RECOVERY_RUNNING' is not set, and 'MD_RECOVERY_NEEDED' is set,
md_check_recover() will try to choose a sync direction, and then
queue a work md_start_sync().

3) md_start_sync() register sync_thread;

After this patch,

1) is the same;
2) if 'MD_RECOVERY_RUNNING' is not set, and 'MD_RECOVERY_NEEDED' is set,
queue a work md_start_sync() directly;
3) md_start_sync() will try to choose a sync direction, and then
register sync_thread();

Because 'MD_RECOVERY_RUNNING' is cleared when sync_thread is done, 2)
and 3) is always runned in serial and they can never concurrent, this
change should not introduce any behavior change for now.

Also fix a problem that md_start_sync() can clear 'MD_RECOVERY_RUNNING'
without protection in error path, which might affect the logical in
md_check_recovery().

The advantage to change this is that array reconfiguration is
independent from daemon now, and it'll be much easier to synchronize it
with io, consider that io may rely on daemon thread to be done.

Signed-off-by: Yu Kuai <yukuai3@huawei.com>
---
drivers/md/md.c | 126 +++++++++++++++++++++++++-----------------------
1 file changed, 67 insertions(+), 59 deletions(-)

diff --git a/drivers/md/md.c b/drivers/md/md.c
index 8980a41bfe97..ef88581d9a39 100644
--- a/drivers/md/md.c
+++ b/drivers/md/md.c
@@ -9261,6 +9261,44 @@ static int remove_and_add_spares(struct mddev *mddev)
static void md_start_sync(struct work_struct *ws)
{
struct mddev *mddev = container_of(ws, struct mddev, sync_work);
+ int spares = 0;
+
+ mddev_lock_nointr(mddev);
+
+ /*
+ * No recovery is running, remove any failed drives, then add spares if
+ * possible. Spares are also removed and re-added, to allow the
+ * personality to fail the re-add.
+ */
+ if (mddev->reshape_position != MaxSector) {
+ if (mddev->pers->check_reshape == NULL ||
+ mddev->pers->check_reshape(mddev) != 0)
+ /* Cannot proceed */
+ goto not_running;
+ set_bit(MD_RECOVERY_RESHAPE, &mddev->recovery);
+ clear_bit(MD_RECOVERY_RECOVER, &mddev->recovery);
+ } else if ((spares = remove_and_add_spares(mddev))) {
+ clear_bit(MD_RECOVERY_SYNC, &mddev->recovery);
+ clear_bit(MD_RECOVERY_CHECK, &mddev->recovery);
+ clear_bit(MD_RECOVERY_REQUESTED, &mddev->recovery);
+ set_bit(MD_RECOVERY_RECOVER, &mddev->recovery);
+ } else if (mddev->recovery_cp < MaxSector) {
+ set_bit(MD_RECOVERY_SYNC, &mddev->recovery);
+ clear_bit(MD_RECOVERY_RECOVER, &mddev->recovery);
+ } else if (!test_bit(MD_RECOVERY_SYNC, &mddev->recovery)) {
+ /* nothing to be done ... */
+ goto not_running;
+ }
+
+ if (!mddev->pers->sync_request)
+ goto not_running;
+
+ /*
+ * We are adding a device or devices to an array which has the bitmap
+ * stored on all devices. So make sure all bitmap pages get written.
+ */
+ if (spares)
+ md_bitmap_write_all(mddev->bitmap);

rcu_assign_pointer(mddev->sync_thread,
md_register_thread(md_do_sync, mddev, "resync"));
@@ -9268,20 +9306,27 @@ static void md_start_sync(struct work_struct *ws)
pr_warn("%s: could not start resync thread...\n",
mdname(mddev));
/* leave the spares where they are, it shouldn't hurt */
- clear_bit(MD_RECOVERY_SYNC, &mddev->recovery);
- clear_bit(MD_RECOVERY_RESHAPE, &mddev->recovery);
- clear_bit(MD_RECOVERY_REQUESTED, &mddev->recovery);
- clear_bit(MD_RECOVERY_CHECK, &mddev->recovery);
- clear_bit(MD_RECOVERY_RUNNING, &mddev->recovery);
- wake_up(&resync_wait);
- if (test_and_clear_bit(MD_RECOVERY_RECOVER,
- &mddev->recovery))
- if (mddev->sysfs_action)
- sysfs_notify_dirent_safe(mddev->sysfs_action);
- } else
- md_wakeup_thread(mddev->sync_thread);
+ goto not_running;
+ }
+
+ mddev_unlock(mddev);
+ md_wakeup_thread(mddev->sync_thread);
sysfs_notify_dirent_safe(mddev->sysfs_action);
md_new_event();
+ return;
+
+not_running:
+ clear_bit(MD_RECOVERY_SYNC, &mddev->recovery);
+ clear_bit(MD_RECOVERY_RESHAPE, &mddev->recovery);
+ clear_bit(MD_RECOVERY_REQUESTED, &mddev->recovery);
+ clear_bit(MD_RECOVERY_CHECK, &mddev->recovery);
+ clear_bit(MD_RECOVERY_RUNNING, &mddev->recovery);
+ mddev_unlock(mddev);
+
+ wake_up(&resync_wait);
+ if (test_and_clear_bit(MD_RECOVERY_RECOVER, &mddev->recovery) &&
+ mddev->sysfs_action)
+ sysfs_notify_dirent_safe(mddev->sysfs_action);
}

/*
@@ -9349,7 +9394,6 @@ void md_check_recovery(struct mddev *mddev)
return;

if (mddev_trylock(mddev)) {
- int spares = 0;
bool try_set_sync = mddev->safemode != 0;

if (!mddev->external && mddev->safemode == 1)
@@ -9436,56 +9480,20 @@ void md_check_recovery(struct mddev *mddev)
clear_bit(MD_RECOVERY_INTR, &mddev->recovery);
clear_bit(MD_RECOVERY_DONE, &mddev->recovery);

- if (!test_and_clear_bit(MD_RECOVERY_NEEDED, &mddev->recovery) ||
- test_bit(MD_RECOVERY_FROZEN, &mddev->recovery))
- goto not_running;
- /* no recovery is running.
- * remove any failed drives, then
- * add spares if possible.
- * Spares are also removed and re-added, to allow
- * the personality to fail the re-add.
- */
-
- if (mddev->reshape_position != MaxSector) {
- if (mddev->pers->check_reshape == NULL ||
- mddev->pers->check_reshape(mddev) != 0)
- /* Cannot proceed */
- goto not_running;
- set_bit(MD_RECOVERY_RESHAPE, &mddev->recovery);
- clear_bit(MD_RECOVERY_RECOVER, &mddev->recovery);
- } else if ((spares = remove_and_add_spares(mddev))) {
- clear_bit(MD_RECOVERY_SYNC, &mddev->recovery);
- clear_bit(MD_RECOVERY_CHECK, &mddev->recovery);
- clear_bit(MD_RECOVERY_REQUESTED, &mddev->recovery);
- set_bit(MD_RECOVERY_RECOVER, &mddev->recovery);
- } else if (mddev->recovery_cp < MaxSector) {
- set_bit(MD_RECOVERY_SYNC, &mddev->recovery);
- clear_bit(MD_RECOVERY_RECOVER, &mddev->recovery);
- } else if (!test_bit(MD_RECOVERY_SYNC, &mddev->recovery))
- /* nothing to be done ... */
- goto not_running;
-
- if (mddev->pers->sync_request) {
- if (spares) {
- /* We are adding a device or devices to an array
- * which has the bitmap stored on all devices.
- * So make sure all bitmap pages get written
- */
- md_bitmap_write_all(mddev->bitmap);
- }
+ if (test_and_clear_bit(MD_RECOVERY_NEEDED, &mddev->recovery) &&
+ !test_bit(MD_RECOVERY_FROZEN, &mddev->recovery)) {
+ /*
+ * Before this sync thread is done and
+ * MD_RECOVERY_RUNNING is cleared, new sync_work won't
+ * be queued.
+ */
queue_work(md_misc_wq, &mddev->sync_work);
- goto unlock;
- }
- not_running:
- if (!mddev->sync_thread) {
+ } else {
clear_bit(MD_RECOVERY_RUNNING, &mddev->recovery);
wake_up(&resync_wait);
- if (test_and_clear_bit(MD_RECOVERY_RECOVER,
- &mddev->recovery))
- if (mddev->sysfs_action)
- sysfs_notify_dirent_safe(mddev->sysfs_action);
}
- unlock:
+
+unlock:
wake_up(&mddev->sb_wait);
mddev_unlock(mddev);
}
--
2.39.2
\
 
 \ /
  Last update: 2023-08-03 15:29    [W:0.108 / U:2.068 seconds]
©2003-2020 Jasper Spaans|hosted at Digital Ocean and TransIP|Read the blog|Advertise on this site