[dm-devel] [PATCH] libmultipath: update INFINIDAT builtin config
Xose Vazquez Perez
xose.vazquez at gmail.com
Fri Aug 25 00:26:55 UTC 2017
On 08/22/2017 03:37 PM, Arnon Yaari wrote:
> Based on the manufacturer documentation:
> https://support.infinidat.com/hc/en-us/articles/202319222
>
> Signed-off-by: Arnon Yaari <arnony at infinidat.com>
NACK.
> ---
> libmultipath/hwtable.c | 12 +++++++++++-
> 1 file changed, 11 insertions(+), 1 deletion(-)> diff --git a/libmultipath/hwtable.c b/libmultipath/hwtable.c
> index 9e14ec1e..1ea48d58 100644
> --- a/libmultipath/hwtable.c
> +++ b/libmultipath/hwtable.c
> @@ -969,8 +969,18 @@ static struct hwentry default_hw[] = {
> .vendor = "NFINIDAT",
> .product = "InfiniBox",
> .pgpolicy = GROUP_BY_PRIO,
> - .pgfailback = -FAILBACK_IMMEDIATE,
> + .pgfailback = 30,
Why is it needed?
> .prio_name = PRIO_ALUA,
> + .checker_name = TUR,
Default value.
> + .selector = "round-robin 0",
round-robin is the dumbest, queue-length is smarter and
service-time is the smartest and default selector.
> + .features = "0",
Default value.
> + .rr_weight = RR_WEIGHT_PRIO,
Useless with service-time
> + .no_path_retry = NO_PATH_RETRY_FAIL,
Default value.
> + .minio = 1,
Useless with service-time
> + .minio_rq = 1,
Useless with service-time
> + .flush_on_last_del = FLUSH_ENABLED,
Why is it needed?
> + .fast_io_fail = 15,
Why is it needed?
> + .dev_loss = 15,
Why is it needed?
> },
> /*
> * Nimble Storage
>
There is minimal info on how to send patches at the header of hwtable.c
$ grep -A64 "Tuning suggestions" libmultipath/hwtable.c | less -S
Thank you.
More information about the dm-devel
mailing list