Re: [PATCH] RDMA/cma: Make CM response timeout and # CM retries configurable

[Jason Gunthorpe]

On Sun, Feb 17, 2019 at 06:09:09PM +0100, HÃkon Bugge wrote:
> During certain workloads, the default CM response timeout is too
> short, leading to excessive retries. Hence, make it configurable
> through sysctl. While at it, also make number of CM retries
> configurable.
> 
> The defaults are not changed.
> 
> Signed-off-by: HÃkon Bugge <haakon.bugge@xxxxxxxxxx>
>  drivers/infiniband/core/cma.c | 51 ++++++++++++++++++++++++++++++-----
>  1 file changed, 44 insertions(+), 7 deletions(-)
> 
> diff --git a/drivers/infiniband/core/cma.c b/drivers/infiniband/core/cma.c
> index c43512752b8a..ce99e1cd1029 100644
> +++ b/drivers/infiniband/core/cma.c
> @@ -43,6 +43,7 @@
>  #include <linux/inetdevice.h>
>  #include <linux/slab.h>
>  #include <linux/module.h>
> +#include <linux/sysctl.h>
>  #include <net/route.h>
>  
>  #include <net/net_namespace.h>
> @@ -68,13 +69,46 @@ MODULE_AUTHOR("Sean Hefty");
>  MODULE_DESCRIPTION("Generic RDMA CM Agent");
>  MODULE_LICENSE("Dual BSD/GPL");
>  
> -#define CMA_CM_RESPONSE_TIMEOUT 20
>  #define CMA_QUERY_CLASSPORT_INFO_TIMEOUT 3000
> -#define CMA_MAX_CM_RETRIES 15
>  #define CMA_CM_MRA_SETTING (IB_CM_MRA_FLAG_DELAY | 24)
>  #define CMA_IBOE_PACKET_LIFETIME 18
>  #define CMA_PREFERRED_ROCE_GID_TYPE IB_GID_TYPE_ROCE_UDP_ENCAP
>  
> +#define CMA_DFLT_CM_RESPONSE_TIMEOUT 20
> +static int cma_cm_response_timeout = CMA_DFLT_CM_RESPONSE_TIMEOUT;
> +static int cma_cm_response_timeout_min = 8;
> +static int cma_cm_response_timeout_max = 31;
> +#undef CMA_DFLT_CM_RESPONSE_TIMEOUT
> +
> +#define CMA_DFLT_MAX_CM_RETRIES 15
> +static int cma_max_cm_retries = CMA_DFLT_MAX_CM_RETRIES;
> +static int cma_max_cm_retries_min = 1;
> +static int cma_max_cm_retries_max = 100;
> +#undef CMA_DFLT_MAX_CM_RETRIES
> +
> +static struct ctl_table_header *cma_ctl_table_hdr;
> +static struct ctl_table cma_ctl_table[] = {
> +	{
> +		.procname	= "cma_cm_response_timeout",
> +		.data		= &cma_cm_response_timeout,
> +		.maxlen		= sizeof(cma_cm_response_timeout),
> +		.mode		= 0644,
> +		.proc_handler	= proc_dointvec_minmax,
> +		.extra1		= &cma_cm_response_timeout_min,
> +		.extra2		= &cma_cm_response_timeout_max,
> +	},
> +	{
> +		.procname	= "cma_max_cm_retries",
> +		.data		= &cma_max_cm_retries,
> +		.maxlen		= sizeof(cma_max_cm_retries),
> +		.mode		= 0644,
> +		.proc_handler	= proc_dointvec_minmax,
> +		.extra1		= &cma_max_cm_retries_min,
> +		.extra2		= &cma_max_cm_retries_max,
> +	},
> +	{ }
> +};

Is sysctl the right approach here? Should it be rdma tool instead?

Jason