raid 4, and bitmap.

raid 4, and bitmap.

[JaniD++]

Hello, list, Neil,

I try to add bitmaps to raid4, and mdadm is done this fine.
In the /proc/mdstat shows this, and it is really works well.

But on reboot, the kernel drops the bitmap(, and resync the entire array if
it is unclean). :(

It is still uncomplete now? (2.6.16-rc1)

Thanks,
Janos

Re: raid 4, and bitmap.

[Neil Brown]

On Friday February 3, djani22@dynamicweb.hu wrote:
> Hello, list, Neil,
> 
> I try to add bitmaps to raid4, and mdadm is done this fine.
> In the /proc/mdstat shows this, and it is really works well.
> 
> But on reboot, the kernel drops the bitmap(, and resync the entire array if
> it is unclean). :(
> 
> It is still uncomplete now? (2.6.16-rc1)


It is an 'internal' bitmap, or is the bitmap in a file?

If the bitmap is in a file, you need to me sure that the file is
provided by mdadm when the array is assembled - using in-kernel
autodetect won't work.

If it is an internal bitmap.... it should work.  
Are there any kernel messages during boot that might be interesting?

NeilBrown

Re: raid 4, and bitmap.

[JaniD++]

----- Original Message ----- 
From: "Neil Brown" <neilb@suse.de>
To: "JaniD++" <djani22@dynamicweb.hu>
Cc: <linux-raid@vger.kernel.org>
Sent: Friday, February 03, 2006 1:09 AM
Subject: Re: raid 4, and bitmap.


> On Friday February 3, djani22@dynamicweb.hu wrote:
> > Hello, list, Neil,
> >
> > I try to add bitmaps to raid4, and mdadm is done this fine.
> > In the /proc/mdstat shows this, and it is really works well.
> >
> > But on reboot, the kernel drops the bitmap(, and resync the entire array
if
> > it is unclean). :(
> >
> > It is still uncomplete now? (2.6.16-rc1)
>
>
> It is an 'internal' bitmap, or is the bitmap in a file?

It is internal.
The external bitmap is not works for me, because on the boot, only the NFS
is reachable, and it cause crash.

(note: this is raid4 not raid5!)

>
> If the bitmap is in a file, you need to me sure that the file is
> provided by mdadm when the array is assembled - using in-kernel
> autodetect won't work.
>
> If it is an internal bitmap.... it should work.
> Are there any kernel messages during boot that might be interesting?

It is something, i will find it one minute! :-)

>
> NeilBrown

Re: raid 4, and bitmap.

[Neil Brown]

On Friday February 3, djani22@dynamicweb.hu wrote:
> >
> > If it is an internal bitmap.... it should work.
> > Are there any kernel messages during boot that might be interesting?
> 
> Sorry, i did not log this, and i dont want to restart the sync and system
> for this.
> Anyway, i add back the bitmap, and the next crash we will see....
> 
> I mean this was:
> "bitmap is only support in raid1.
> bitmap is removed."
> 
> But not so sure. :(

Close enough.  Here is the fix.

NeilBrown

Signed-off-by: Neil Brown <neilb@suse.de>

### Diffstat output
 ./drivers/md/md.c |    3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff ./drivers/md/md.c~current~ ./drivers/md/md.c
--- ./drivers/md/md.c~current~	2006-02-03 08:57:28.000000000 +1100
+++ ./drivers/md/md.c	2006-02-03 11:22:57.000000000 +1100
@@ -763,7 +763,8 @@ static int super_90_validate(mddev_t *md
 
 		if (sb->state & (1<<MD_SB_BITMAP_PRESENT) &&
 		    mddev->bitmap_file == NULL) {
-			if (mddev->level != 1 && mddev->level != 5 && mddev->level != 6
+			if (mddev->level != 1 && && mddev->level != 4
+			    && mddev->level != 5 && mddev->level != 6
 			    && mddev->level != 10) {
 				/* FIXME use a better test */
 				printk(KERN_WARNING "md: bitmaps not supported for this level.\n");

Re: raid 4, and bitmap.

[JaniD++]

----- Original Message ----- 
From: "Neil Brown" <neilb@suse.de>
To: "JaniD++" <djani22@dynamicweb.hu>
Cc: <linix-raid@vger.kernel.org>
Sent: Friday, February 03, 2006 1:23 AM
Subject: Re: raid 4, and bitmap.


> On Friday February 3, djani22@dynamicweb.hu wrote:
> > >
> > > If it is an internal bitmap.... it should work.
> > > Are there any kernel messages during boot that might be interesting?
> >
> > Sorry, i did not log this, and i dont want to restart the sync and
system
> > for this.
> > Anyway, i add back the bitmap, and the next crash we will see....
> >
> > I mean this was:
> > "bitmap is only support in raid1.
> > bitmap is removed."
> >
> > But not so sure. :(
>
> Close enough.  Here is the fix.

Thanks!

This was fast! :)

Ahh, i almost forget!
The mdadm is sometimes drop "cannot allocate memory" and next try "segfault"
when i try -G --bitmap=internal on 2TB arrays!
And after segfault, the full raid is stops...

Cheers,
Janos

>
> NeilBrown
>
> Signed-off-by: Neil Brown <neilb@suse.de>
>
> ### Diffstat output
>  ./drivers/md/md.c |    3 ++-
>  1 file changed, 2 insertions(+), 1 deletion(-)
>
> diff ./drivers/md/md.c~current~ ./drivers/md/md.c
> --- ./drivers/md/md.c~current~ 2006-02-03 08:57:28.000000000 +1100
> +++ ./drivers/md/md.c 2006-02-03 11:22:57.000000000 +1100
> @@ -763,7 +763,8 @@ static int super_90_validate(mddev_t *md
>
>   if (sb->state & (1<<MD_SB_BITMAP_PRESENT) &&
>       mddev->bitmap_file == NULL) {
> - if (mddev->level != 1 && mddev->level != 5 && mddev->level != 6
> + if (mddev->level != 1 && && mddev->level != 4
> +     && mddev->level != 5 && mddev->level != 6
>       && mddev->level != 10) {
>   /* FIXME use a better test */
>   printk(KERN_WARNING "md: bitmaps not supported for this level.\n");

Re: raid 4, and bitmap.

[JaniD++]

> Ahh, i almost forget!
> The mdadm is sometimes drop "cannot allocate memory" and next try
"segfault"
> when i try -G --bitmap=internal on 2TB arrays!
> And after segfault, the full raid is stops...
>
> Cheers,
> Janos

I think i found the bug, its me. :-)

Today it happens again, and i see, i have misstyped the "internal" word like
"intarnal".
The mdadm is accepted that, and try to make the bitmap on NFS again, and
crashed the raid.

I think it is neccessary to better test:

- the bitmap file's fs
- the filename itself.
(i mean did not allow the current directory, or the internal and none to be
a separated option)

Cheers,
Janos

Re: raid 4, and bitmap.

[Neil Brown]

On Saturday February 4, djani22@dynamicweb.hu wrote:
> > Ahh, i almost forget!
> > The mdadm is sometimes drop "cannot allocate memory" and next try
> "segfault"
> > when i try -G --bitmap=internal on 2TB arrays!
> > And after segfault, the full raid is stops...
> >
> > Cheers,
> > Janos
> 
> I think i found the bug, its me. :-)
> 
> Today it happens again, and i see, i have misstyped the "internal" word like
> "intarnal".
> The mdadm is accepted that, and try to make the bitmap on NFS again, and
> crashed the raid.
> 
> I think it is neccessary to better test:
> 
> - the bitmap file's fs
> - the filename itself.
> (i mean did not allow the current directory, or the internal and none to be
> a separated option)

That sound's like a good idea... require a filename to contain at
least one '/', and quite possibly test the filesystem type.  bitmaps
are known to have problems on reiserfs and nfs.  They were developed
and tested on ext3 and there is some slightly hairy code in there...

Thanks for the suggestions.

NeilBrown