Re: WAPBL panic

[Stephen Borrill <netbsd%precedence.co.uk@localhost>]

On Fri, 20 Nov 2015, Christos Zoulas wrote:
> On Nov 20,  1:45pm, manu%netbsd.org@localhost (Emmanuel Dreyfus) wrote:
> -- Subject: Re: WAPBL panic
>
> | On Fri, Nov 20, 2015 at 08:06:02AM -0500, Christos Zoulas wrote:
> | > I don't know. Can you reproduce it? Removing a very large file or tree?
> |
> | Well I would rather prefer to not reproduce it since this is a production
> | server, and that recovery is harsh: raid parity reconstruction eats the
> | disks bandwith while swarms of clients reconnect.
>
> Are you still running -6? Because on -7 parity reconstruction is blazing fast
> since it only reconstructs the broken blocks.

From CHANGES-5.1:

        Pull up the RAIDframe parity map Summer Of Code project.
        Drastically reduces the amount of time spent rewriting parity
        after an unclean shutdown by keeping better track of which
        regions might have had outstanding writes.  Enabled by default;
        can be disabled on a per-set basis, or tuned, with the new
        raidctl(8) commands.

Or are you referring to something else?

--
Stephen