Re: [PATCH] multipath: Retry host transient errors for rdac checker

[Christophe Varoqui <christophe.varoqui@gmail.com>]

On mar., 2011-03-01 at 12:08 -0700, Moger, Babu wrote:
> Sometimes if the host is in transient state, we need to wait till the devloss timeout to
> expire before switching path group. We have seen in some cases path group switch happens
> even before the devloss timeout expire. This patch fixes the problem for rdac checker..
> 
I did not see comments on this patch.
It's now applied upstream.

-- 
Christophe Varoqui <christophe.varoqui@opensvc.com>
OpenSVC

> Signed-off-by: Babu Moger <babu.moger@lsi.com>
> ---
> --- multipath-tools/libmultipath/checkers/rdac.c.orig	2011-02-16 13:58:06.000000000 -0600
> +++ multipath-tools/libmultipath/checkers/rdac.c	2011-02-17 12:01:23.000000000 -0600
> @@ -48,7 +48,9 @@
>  	unsigned char inqCmdBlk[INQUIRY_CMDLEN] = { INQUIRY_CMD, 1, 0, 0, 0, 0 };
>  	unsigned char sense_b[SENSE_BUFF_LEN];
>  	struct sg_io_hdr io_hdr;
> +	int retry_rdac = 5;
>  
> +retry:
>  	inqCmdBlk[2] = (unsigned char) pg_op;
>  	inqCmdBlk[4] = (unsigned char) (mx_resp_len & 0xff);
>  	memset(&io_hdr, 0, sizeof (struct sg_io_hdr));
> @@ -72,6 +74,22 @@
>  	if ((0 == io_hdr.status) && (0 == io_hdr.host_status) &&
>  	    (0 == io_hdr.driver_status))
>  		return 0;
> +
> +	/* check if we need to retry this error */
> +	if (io_hdr.info & SG_INFO_OK_MASK) {
> +		switch (io_hdr.host_status) {
> +		case DID_BUS_BUSY:
> +		case DID_ERROR:
> +		case DID_TRANSPORT_DISRUPTED:
> +			/* Transport error, retry */
> +			if (--retry_rdac)
> +				goto retry;
> +			break;
> +		default:
> +			break;
> +		}
> +	}
> +
>  	if ((SCSI_CHECK_CONDITION == io_hdr.status) ||
>  	    (SCSI_COMMAND_TERMINATED == io_hdr.status) ||
>  	    (SG_ERR_DRIVER_SENSE == (0xf & io_hdr.driver_status))) {
> 
>