[PATCH] (2nd try) force parallel resync

[PATCH] (2nd try) force parallel resync

[Bernd Schubert]

Hello,

here is the second version of the patch. With this version also on  
setting /sys/block/*/md/sync_force_parallel the sync_thread is woken up. 
Though, I still don't understand why md_wakeup_thread() is not working.


Signed-off-by: Bernd Schubert <bs@q-leap.de>


Index: linux-2.6.22/drivers/md/md.c
===================================================================
--- linux-2.6.22.orig/drivers/md/md.c	2007-12-06 19:51:55.000000000 +0100
+++ linux-2.6.22/drivers/md/md.c	2007-12-06 19:52:33.000000000 +0100
@@ -2843,6 +2843,41 @@ __ATTR(sync_speed_max, S_IRUGO|S_IWUSR, 
 
 
 static ssize_t
+sync_force_parallel_show(mddev_t *mddev, char *page)
+{
+        return sprintf(page, "%d\n", mddev->parallel_resync);
+}
+
+static ssize_t
+sync_force_parallel_store(mddev_t *mddev, const char *buf, size_t len)
+{
+	char *e;
+	unsigned long n = simple_strtoul(buf, &e, 10);
+
+	if (!*buf || (*e && *e != '\n') || (n != 0 && n != 1))
+		return -EINVAL;
+
+	mddev->parallel_resync = n;
+
+	if (mddev->sync_thread) {
+		dprintk("md: waking up MD thread %s.\n",
+		       mddev->sync_thread->tsk->comm);
+		set_bit(THREAD_WAKEUP, &mddev->sync_thread->flags);
+		wake_up_process(mddev->sync_thread->tsk);
+
+/*		FIXME: why does md_wakeup_thread() not work?,
+		somehow related to:  wake_up(&thread->wqueue);
+		md_wakeup_thread(mddev->sync_thread); */
+	}
+	return len;
+}
+
+/* force parallel resync, even with shared block devices */
+static struct md_sysfs_entry md_sync_force_parallel =
+__ATTR(sync_force_parallel, S_IRUGO|S_IWUSR,
+       sync_force_parallel_show, sync_force_parallel_store);
+
+static ssize_t
 sync_speed_show(mddev_t *mddev, char *page)
 {
 	unsigned long resync, dt, db;
@@ -2980,6 +3015,7 @@ static struct attribute *md_redundancy_a
 	&md_sync_min.attr,
 	&md_sync_max.attr,
 	&md_sync_speed.attr,
+	&md_sync_force_parallel.attr,
 	&md_sync_completed.attr,
 	&md_suspend_lo.attr,
 	&md_suspend_hi.attr,
@@ -5264,8 +5300,9 @@ void md_do_sync(mddev_t *mddev)
 		ITERATE_MDDEV(mddev2,tmp) {
 			if (mddev2 == mddev)
 				continue;
-			if (mddev2->curr_resync && 
-			    match_mddev_units(mddev,mddev2)) {
+			if (!mddev->parallel_resync
+			&&  mddev2->curr_resync
+			&&  match_mddev_units(mddev,mddev2)) {
 				DEFINE_WAIT(wq);
 				if (mddev < mddev2 && mddev->curr_resync == 2) {
 					/* arbitrarily yield */
Index: linux-2.6.22/include/linux/raid/md_k.h
===================================================================
--- linux-2.6.22.orig/include/linux/raid/md_k.h	2007-12-06 19:51:55.000000000 
+0100
+++ linux-2.6.22/include/linux/raid/md_k.h	2007-12-06 19:52:33.000000000 +0100
@@ -170,6 +170,9 @@ struct mddev_s
 	int				sync_speed_min;
 	int				sync_speed_max;
 
+	/* resync even though the same disks are shared among md-devices */
+	int				parallel_resync;
+
 	int				ok_start_degraded;
 	/* recovery/resync flags 
 	 * NEEDED:   we might need to start a resync/recover


-- 
Bernd Schubert
Q-Leap Networks GmbH

Re: [PATCH] (2nd try) force parallel resync

[Neil Brown]

On Thursday December 6, bs@q-leap.de wrote:
> Hello,
> 
> here is the second version of the patch. With this version also on  
> setting /sys/block/*/md/sync_force_parallel the sync_thread is woken up. 
> Though, I still don't understand why md_wakeup_thread() is not working.

Could give a little more detail on why you want this?  When do you
want multiple arrays on the same device to sync at the same time?
What exactly is the hardware like?

md threads generally run for a little while to perform some task, then
stop and wait to be needed again.  md_wakeup_thread says "you are
needed again".

The resync/recovery thread is a bit different.  It just run md_do_sync
once.  md_wakeup_thread is not really meaningful in that context.

What you want is:
		wake_up(&resync_wait);

that will get any thread that is waiting for some other array to
resync to wake up and see if something needs to be done.

NeilBrown

Re: [PATCH] (2nd try) force parallel resync

[Bernd Schubert]

Hello Neil,

On Friday 07 December 2007 03:10:37 Neil Brown wrote:
> On Thursday December 6, bs@q-leap.de wrote:
> > Hello,
> >
> > here is the second version of the patch. With this version also on
> > setting /sys/block/*/md/sync_force_parallel the sync_thread is woken up.
> > Though, I still don't understand why md_wakeup_thread() is not working.
>
> Could give a little more detail on why you want this?  When do you
> want multiple arrays on the same device to sync at the same time?
> What exactly is the hardware like?

I did describe it in my first mail, I guess you just missed this one. So I'm 
pasting this part here:

On Monday 03 December 2007 14:37:03 Bernd Schubert wrote:
> Hello Neil,
>
>
> on doing software-raid over some Infortrend hardware raid boxes, we can
> easily bring a single cpu to 100%, while the hardware-raid boxes are still
> only utilized for 50% or less.
> So we are using *several* software raids instead of only one. However, for
> us it then also doesn't make sense to have a resync for only one of the
> md-raids. Below is a patch to force parallel resync for specified md-sets
> via sysfs.
> This still leaves a problem, though. If a resync starts before settings
> this parameter, I don't know how to wake up the sleeping resync-thread. Any
> ideas?
>


>
> md threads generally run for a little while to perform some task, then
> stop and wait to be needed again.  md_wakeup_thread says "you are
> needed again".
>
> The resync/recovery thread is a bit different.  It just run md_do_sync
> once.  md_wakeup_thread is not really meaningful in that context.
>
> What you want is:
> 		wake_up(&resync_wait);
>
> that will get any thread that is waiting for some other array to
> resync to wake up and see if something needs to be done.

Ah thanks a lot! Now I understand. What about this?


Signed-off-by: Bernd Schubert <bs@q-leap.de>


Index: linux-2.6.22/drivers/md/md.c
===================================================================
--- linux-2.6.22.orig/drivers/md/md.c	2007-12-06 19:51:55.000000000 +0100
+++ linux-2.6.22/drivers/md/md.c	2007-12-07 12:07:47.000000000 +0100
@@ -74,6 +74,8 @@ static DEFINE_SPINLOCK(pers_lock);
 
 static void md_print_devices(void);
 
+static DECLARE_WAIT_QUEUE_HEAD(resync_wait);
+
 #define MD_BUG(x...) { printk("md: bug in file %s, line %d\n", __FILE__, 
__LINE__); md_print_devices(); }
 
 /*
@@ -2843,6 +2845,34 @@ __ATTR(sync_speed_max, S_IRUGO|S_IWUSR, 
 
 
 static ssize_t
+sync_force_parallel_show(mddev_t *mddev, char *page)
+{
+        return sprintf(page, "%d\n", mddev->parallel_resync);
+}
+
+static ssize_t
+sync_force_parallel_store(mddev_t *mddev, const char *buf, size_t len)
+{
+	char *e;
+	unsigned long n = simple_strtoul(buf, &e, 10);
+
+	if (!*buf || (*e && *e != '\n') || (n != 0 && n != 1))
+		return -EINVAL;
+
+	mddev->parallel_resync = n;
+
+	if (mddev->sync_thread) {
+		wake_up(&resync_wait);
+	}
+	return len;
+}
+
+/* force parallel resync, even with shared block devices */
+static struct md_sysfs_entry md_sync_force_parallel =
+__ATTR(sync_force_parallel, S_IRUGO|S_IWUSR,
+       sync_force_parallel_show, sync_force_parallel_store);
+
+static ssize_t
 sync_speed_show(mddev_t *mddev, char *page)
 {
 	unsigned long resync, dt, db;
@@ -2980,6 +3010,7 @@ static struct attribute *md_redundancy_a
 	&md_sync_min.attr,
 	&md_sync_max.attr,
 	&md_sync_speed.attr,
+	&md_sync_force_parallel.attr,
 	&md_sync_completed.attr,
 	&md_suspend_lo.attr,
 	&md_suspend_hi.attr,
@@ -5199,8 +5230,6 @@ void md_allow_write(mddev_t *mddev)
 }
 EXPORT_SYMBOL_GPL(md_allow_write);
 
-static DECLARE_WAIT_QUEUE_HEAD(resync_wait);
-
 #define SYNC_MARKS	10
 #define	SYNC_MARK_STEP	(3*HZ)
 void md_do_sync(mddev_t *mddev)
@@ -5264,8 +5293,9 @@ void md_do_sync(mddev_t *mddev)
 		ITERATE_MDDEV(mddev2,tmp) {
 			if (mddev2 == mddev)
 				continue;
-			if (mddev2->curr_resync && 
-			    match_mddev_units(mddev,mddev2)) {
+			if (!mddev->parallel_resync
+			&&  mddev2->curr_resync
+			&&  match_mddev_units(mddev,mddev2)) {
 				DEFINE_WAIT(wq);
 				if (mddev < mddev2 && mddev->curr_resync == 2) {
 					/* arbitrarily yield */
Index: linux-2.6.22/include/linux/raid/md_k.h
===================================================================
--- linux-2.6.22.orig/include/linux/raid/md_k.h	2007-12-06 19:51:55.000000000 
+0100
+++ linux-2.6.22/include/linux/raid/md_k.h	2007-12-06 19:52:33.000000000 +0100
@@ -170,6 +170,9 @@ struct mddev_s
 	int				sync_speed_min;
 	int				sync_speed_max;
 
+	/* resync even though the same disks are shared among md-devices */
+	int				parallel_resync;
+
 	int				ok_start_degraded;
 	/* recovery/resync flags 
 	 * NEEDED:   we might need to start a resync/recover


-- 
Bernd Schubert
Q-Leap Networks GmbH