Re: Any benefity to write intent bitmaps on Raid1

[Neil Brown <neilb@suse.de>]

On Thursday April 9, davidsen@tmr.com wrote:
> Neil Brown wrote:
> > On Thursday April 9, steven@openmedia.co.nz wrote:
> >   
> >> Given I have a pair of 1TB drives Raid1 I'd prefer to reduce any recovery
> >> sync time. Would an internal bitmap help dramatically, and are there any
> >> other benefits.
> >>     
> >
> > Bryan answered some of this but...
> >
> >  - if your machine crashes, then resync will be much faster if you
> >    have a bitmap.
> >  - If one drive becomes disconnected, and then can be reconnected,
> >    recovery will be much faster.
> >  - if one drive fails and has to be replaced, a bitmap makes no
> >    difference(*).
> >  - there might be performance hit - it is very dependant on your
> >    workload.
> >  - You can add or remove a bitmap at any time, so you can try to
> >    measure the impact on your particular workload fairly easily.
> >
> >
> > (*) I've been wondering about adding another bitmap which would record
> > which sections of the array have valid data.  Initially nothing would
> > be valid and so wouldn't need recovery.  Every time we write to a new
> > section we add that section to the 'valid' sections and make sure that
> > section is in-sync.
> > When a device was replaced, we would only need to recover the parts of
> > the array that are known to be invalid.
> > As filesystem start using the new "invalidate" command for block
> > devices, we could clear bits for sections that the filesystem says are
> > not needed any more...
> > But currently it is just a vague idea.
> >   
> 
> It's obvious that this idea would provide a speedup, and might be useful 
> in terms of doing some physical dump software which would just save the 
> "used" portions of the array. Only you have an idea of how much effort 
> this would take, although my thought is "very little" for the stable 
> case and "bunches" for the case of an array size change.

The only difficulty I can see with the "size change" case is needing
to find space for a bigger bitmap.  If the space exists, you just copy
the bitmap (if needed) and you are done.
If the space doesn't exist, you change the chunk size (space covered
per bit) and use the same space.
The rest, I agree, should be fairly easy.

One possibly awkwardness is that every time you write to a new segment
which requires setting a new bit, you would need to kick-off a resync
for that segment.  That could have an adverse and unpredictable effect
on throughput.
Ofcourse you don't *need* that resync to complete until a reboot so
you could do it with very low priority, so it might be OK.

> 
> I have been trying making a COW copy of an entire drive with qemu-img, 
> then booting it under KCM, and besides giving an interesting slant to 
> the term "dual boot," I can back up the changes files (a sparse file) 
> quickly and into small space with a backup which knows about sparse 
> files. There is lots of room to imagine uses for this if we had it.

Interesting ideas...

NeilBrown