On Tue, Dec 27, 2016 at 09:25:47AM +0100, Matthias Tafelmeier wrote:
> Oftenly, introducing side effects on packet processing on the other half
> of the stack by adjusting one of TX/RX via sysctl is not desirable.
> There are cases of demand for asymmetric, orthogonal configurability.
>
> This holds true especially for nodes where RPS for RFS usage on top is
> configured and therefore use the 'old dev_weight'. This is quite a
> common base configuration setup nowadays, even with NICs of superior
> processing
> support (e.g. aRFS).
>
> A good example use case are nodes acting as noSQL data bases with a
> large number of tiny requests and rather fewer but large packets as responses.
> It's affordable to have large budget and rx dev_weights for the
> requests. But as a side effect having this large a number on TX
> processed in one run can overwhelm drivers.
>
> This patch therefore introduces an independent configurability via sysctl to
> userland.
> ---
> include/linux/netdevice.h | 2 ++
> net/core/dev.c | 4 +++-
> net/core/sysctl_net_core.c | 14 ++++++++++++++
> net/sched/sch_generic.c | 2 +-
> 4 files changed, 20 insertions(+), 2 deletions(-)
>
> diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
> index 994f742..bb331e0 100644
> --- a/include/linux/netdevice.h
> +++ b/include/linux/netdevice.h
> @@ -3795,6 +3795,8 @@ void netdev_stats_to_stats64(struct rtnl_link_stats64
> *stats64,
> extern int netdev_max_backlog;
> extern int netdev_tstamp_prequeue;
> extern int weight_p;
> +extern int dev_w_rx_bias;
> +extern int dev_w_tx_bias;
>
> bool netdev_has_upper_dev(struct net_device *dev, struct net_device
> *upper_dev);
> struct net_device *netdev_upper_get_next_dev_rcu(struct net_device *dev,
> diff --git a/net/core/dev.c b/net/core/dev.c
> index 8db5a0b..0dcbd28 100644
> --- a/net/core/dev.c
> +++ b/net/core/dev.c
> @@ -3428,6 +3428,8 @@ EXPORT_SYMBOL(netdev_max_backlog);
> int netdev_tstamp_prequeue __read_mostly = 1;
> int netdev_budget __read_mostly = 300;
> int weight_p __read_mostly = 64; /* old backlog weight */
> +int dev_w_rx_bias __read_mostly = 1; /* bias for backlog weight */
> +int dev_w_tx_bias __read_mostly = 1; /* bias for output_queue
> quota */
>
> /* Called with irq disabled */
> static inline void ____napi_schedule(struct softnet_data *sd,
> @@ -4833,7 +4835,7 @@ static int process_backlog(struct napi_struct *napi,
> int quota)
> net_rps_action_and_irq_enable(sd);
> }
>
> - napi->weight = weight_p;
> + napi->weight = weight_p * dev_w_rx_bias;
> while (again) {
> struct sk_buff *skb;
>
> diff --git a/net/core/sysctl_net_core.c b/net/core/sysctl_net_core.c
> index 2a46e40..a2ab149 100644
> --- a/net/core/sysctl_net_core.c
> +++ b/net/core/sysctl_net_core.c
> @@ -276,6 +276,20 @@ static struct ctl_table net_core_table[] = {
> .proc_handler = proc_dointvec
> },
> {
> + .procname = "dev_w_rx_bias",
> + .data = &dev_w_rx_bias,
> + .maxlen = sizeof(int),
> + .mode = 0644,
> + .proc_handler = proc_dointvec
> + },
> + {
> + .procname = "dev_w_tx_bias",
> + .data = &dev_w_tx_bias,
> + .maxlen = sizeof(int),
> + .mode = 0644,
> + .proc_handler = proc_dointvec
> + },
> + {
Please describe these at Documentation/sysctl/net.txt, probably right
after dev_weight.
I'm not sure about the abbreviation, maybe it would be better the longer
name as it doesn't block tab completion.
dev_weight_tx_bias
dev_weight_rx_bias
dev_weight
> .procname = "netdev_max_backlog",
> .data = &netdev_max_backlog,
> .maxlen = sizeof(int),
> diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c
> index 6eb9c8e..4c07780 100644
> --- a/net/sched/sch_generic.c
> +++ b/net/sched/sch_generic.c
> @@ -247,7 +247,7 @@ static inline int qdisc_restart(struct Qdisc *q, int
> *packets)
>
> void __qdisc_run(struct Qdisc *q)
> {
> - int quota = weight_p;
> + int quota = weight_p * dev_w_tx_bias;
> int packets;
>
> while (qdisc_restart(q, &packets)) {
> --
> 2.7.4
>
