Re: gmirror(8) and graid3(8) changes.

From: Phil Regnauld <regnauld_at_x0.dk>
Date: Tue, 7 Mar 2006 16:46:04 +0100
On Tue, Mar 07, 2006 at 04:16:36PM +0100, Pawel Jakub Dawidek wrote:
> +> 
> +> 	I've been experiencing lockups with gmirror, ATA/SATA on both
> +> 	i386 and amd64, under severe I/O (very heavily loaded Postgres DB). 
> +> 	This has been on several different machines (remotely located, with
> +> 	no possibility of breaking into the debugger).
> +> 
> +> 	Do you think these patches are worth testing in my case ?
> 
> Are you sure it was gmirror's fault?

	It doesn't happen if I use either underlying "raw" disk without
	gmirror.

> It will be quite hard for gmirror
> to hang machine so badly that we are not able to enter ddb...

	No, I meant, I couldn't access the box's DDB remotely as it was
	in a hosting center without access to a physical console, and I had
	to have someone restart it.

> Anyway, I'd prefer to test those patches not in production environment
> yet.

	It is a test machine, so I don't mind, was just curious if this could
	be related.
Received on Tue Mar 07 2006 - 14:46:07 UTC

This archive was generated by hypermail 2.4.0 : Wed May 19 2021 - 11:38:53 UTC