Replace 2 jiffies with sysctl netdev_budget_usecs to enable softirq tuning

Constants used for tuning are generally a bad idea, especially as hardware
changes over time. Replace the constant 2 jiffies with sysctl variable
netdev_budget_usecs to enable sysadmins to tune the softirq processing.
Also document the variable.

For example, a very fast machine might tune this to 1000 microseconds,
while my regression testing 486DX-25 needs it to be 4000 microseconds on
a nearly idle network to prevent time_squeeze from being incremented.

Version 2: changed jiffies to microseconds for predictable units.

Signed-off-by: Matthew Whitehead <tedheadster@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

Documentation/sysctl/net.txt

@@ -188,7 +188,16 @@ netdev_budget
 
 Maximum number of packets taken from all interfaces in one polling cycle (NAPI
 poll). In one polling cycle interfaces which are registered to polling are
-probed in a round-robin manner.
+probed in a round-robin manner. Also, a polling cycle may not exceed
+netdev_budget_usecs microseconds, even if netdev_budget has not been
+exhausted.
+
+netdev_budget_usecs
+---------------------
+
+Maximum number of microseconds in one NAPI polling cycle. Polling
+will exit when either netdev_budget_usecs have elapsed during the
+poll cycle or the number of packets processed reaches netdev_budget.
 
 netdev_max_backlog
 ------------------

include/linux/netdevice.h

@@ -3296,6 +3296,7 @@ static __always_inline int ____dev_forward_skb(struct net_device *dev,
 void dev_queue_xmit_nit(struct sk_buff *skb, struct net_device *dev);
 
 extern int		netdev_budget;
+extern unsigned int	netdev_budget_usecs;
 
 /* Called by rtnetlink.c:rtnl_unlock() */
 void netdev_run_todo(void);

include/uapi/linux/sysctl.h

@@ -274,6 +274,7 @@ enum
 	NET_CORE_AEVENT_ETIME=20,
 	NET_CORE_AEVENT_RSEQTH=21,
 	NET_CORE_WARNINGS=22,
+	NET_CORE_BUDGET_USECS=23,
 };
 
 /* /proc/sys/net/ethernet */

kernel/sysctl_binary.c

@@ -197,6 +197,7 @@ static const struct bin_table bin_net_core_table[] = {
 	{ CTL_INT,	NET_CORE_AEVENT_ETIME,	"xfrm_aevent_etime" },
 	{ CTL_INT,	NET_CORE_AEVENT_RSEQTH,	"xfrm_aevent_rseqth" },
 	{ CTL_INT,	NET_CORE_WARNINGS,	"warnings" },
+	{ CTL_INT,	NET_CORE_BUDGET_USECS,	"netdev_budget_usecs" },
 	{},
 };
 

net/core/dev.c

@@ -3441,6 +3441,7 @@ EXPORT_SYMBOL(netdev_max_backlog);
 
 int netdev_tstamp_prequeue __read_mostly = 1;
 int netdev_budget __read_mostly = 300;
+unsigned int __read_mostly netdev_budget_usecs = 2000;
 int weight_p __read_mostly = 64;           /* old backlog weight */
 int dev_weight_rx_bias __read_mostly = 1;  /* bias for backlog weight */
 int dev_weight_tx_bias __read_mostly = 1;  /* bias for output_queue quota */
@@ -5307,7 +5308,8 @@ static int napi_poll(struct napi_struct *n, struct list_head *repoll)
 static __latent_entropy void net_rx_action(struct softirq_action *h)
 {
 	struct softnet_data *sd = this_cpu_ptr(&softnet_data);
-	unsigned long time_limit = jiffies + 2;
+	unsigned long time_limit = jiffies +
+		usecs_to_jiffies(netdev_budget_usecs);
 	int budget = netdev_budget;
 	LIST_HEAD(list);
 	LIST_HEAD(repoll);

net/core/sysctl_net_core.c

@@ -452,6 +452,14 @@ static struct ctl_table net_core_table[] = {
 		.extra1		= &one,
 		.extra2		= &max_skb_frags,
 	},
+	{
+		.procname	= "netdev_budget_usecs",
+		.data		= &netdev_budget_usecs,
+		.maxlen		= sizeof(unsigned int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec_minmax,
+		.extra1		= &zero,
+	},
 	{ }
 };