The following patch (which applies to 2.6.12rc4) adds a new sysctl
parameter called 'netdev_packet_weight'. This parameter controls how many
backlog work units each RX packet is worth.
With the parameter set to 0 (the default), NAPI polling works exactly as
it does today: each packet is worth one backlog work unit, and the
maximum number of received packets that will be processed in any given
softirq is controlled by the 'netdev_max_backlog' parameter.
By setting the netdev_packet_weight to a nonzero value, we make each
packet worth more than one backlog work unit. Since it's a shift value, a
setting of 1 makes each packet worth 2 work units, a setting of 2 makes
each packet worth 4 units, etc. Under normal circumstances you would
never use a value higher than 3, though 4 might work for Gigabit and 10
Gigabit networks.
By increasing the packet weight, we accomplish two things: first, we
cause the individual NAPI RX loops in each driver to process fewer
packets. This means that they will free up RX resources to the hardware
more often, which reduces the possibility of dropped packets. Second, it
shortens the total time spent in the NAPI softirq, which can free the CPU
to handle other tasks more often, thus reducing overall latency.
Performance tests in our lab have shown that tweaking this parameter,
along with the netdev_max_backlog parameter, can provide significant
performance increase -- greater than 100Mbps improvement -- over default
settings. I tested with both e1000 and tg3 drivers and saw improvement in
both cases. I did not see higher CPU utilization, even with the increased
throughput.
The caveat, of course, is that different systems and network
configurations require different settings. On the other hand, that's
really no different than what we see with the max_backlog parameter today.
On some systems neither parameter makes any difference.
Still, we feel that there is value to having this in the kernel. Please
test and comment as you have time available.
Thanks!
-Mitch Williams
mitch.a.williams@xxxxxxxxx
diff -urpN -x dontdiff rc4-clean/Documentation/filesystems/proc.txt
linux-2.6.12-rc4/Documentation/filesystems/proc.txt
--- rc4-clean/Documentation/filesystems/proc.txt 2005-05-18
16:35:43.000000000 -0700
+++ linux-2.6.12-rc4/Documentation/filesystems/proc.txt 2005-05-19
11:16:10.000000000 -0700
@@ -1378,7 +1378,13 @@ netdev_max_backlog
------------------
Maximum number of packets, queued on the INPUT side, when the interface
-receives packets faster than kernel can process them.
+receives packets faster than kernel can process them. This is also the
+maximum number of packets handled in a single softirq under NAPI.
+
+netdev_packet_weight
+--------------------
+The value, in netdev_max_backlog unit, of each received packet. This is a
+shift value, and should be set no higher than 3.
optmem_max
----------
diff -urpN -x dontdiff rc4-clean/include/linux/sysctl.h
linux-2.6.12-rc4/include/linux/sysctl.h
--- rc4-clean/include/linux/sysctl.h 2005-05-18 16:36:06.000000000 -0700
+++ linux-2.6.12-rc4/include/linux/sysctl.h 2005-05-18 16:44:07.000000000
-0700
@@ -242,6 +242,7 @@ enum
NET_CORE_MOD_CONG=16,
NET_CORE_DEV_WEIGHT=17,
NET_CORE_SOMAXCONN=18,
+ NET_CORE_PACKET_WEIGHT=19,
};
/* /proc/sys/net/ethernet */
diff -urpN -x dontdiff rc4-clean/net/core/dev.c linux-2.6.12-rc4/net/core/dev.c
--- rc4-clean/net/core/dev.c 2005-05-18 16:36:07.000000000 -0700
+++ linux-2.6.12-rc4/net/core/dev.c 2005-05-19 11:16:57.000000000 -0700
@@ -1352,6 +1352,7 @@ out:
=======================================================================*/
int netdev_max_backlog = 300;
+int netdev_packet_weight = 0; /* each packet is worth 1 backlog unit */
int weight_p = 64; /* old backlog weight */
/* These numbers are selected based on intuition and some
* experimentatiom, if you have more scientific way of doing this
@@ -1778,6 +1779,7 @@ static void net_rx_action(struct softirq
struct softnet_data *queue = &__get_cpu_var(softnet_data);
unsigned long start_time = jiffies;
int budget = netdev_max_backlog;
+ int budget_temp;
local_irq_disable();
@@ -1793,21 +1795,22 @@ static void net_rx_action(struct softirq
dev = list_entry(queue->poll_list.next,
struct net_device, poll_list);
netpoll_poll_lock(dev);
-
- if (dev->quota <= 0 || dev->poll(dev, &budget)) {
+ budget_temp = budget;
+ if (dev->quota <= 0 || dev->poll(dev, &budget_temp)) {
netpoll_poll_unlock(dev);
local_irq_disable();
list_del(&dev->poll_list);
list_add_tail(&dev->poll_list, &queue->poll_list);
if (dev->quota < 0)
- dev->quota += dev->weight;
+ dev->quota += dev->weight >>
netdev_packet_weight;
else
- dev->quota = dev->weight;
+ dev->quota = dev->weight >>
netdev_packet_weight;
} else {
netpoll_poll_unlock(dev);
dev_put(dev);
local_irq_disable();
}
+ budget -= (budget - budget_temp) << netdev_packet_weight;
}
out:
local_irq_enable();
diff -urpN -x dontdiff rc4-clean/net/core/sysctl_net_core.c
linux-2.6.12-rc4/net/core/sysctl_net_core.c
--- rc4-clean/net/core/sysctl_net_core.c 2005-03-01 23:38:03.000000000
-0800
+++ linux-2.6.12-rc4/net/core/sysctl_net_core.c 2005-05-18 16:44:09.000000000
-0700
@@ -13,6 +13,7 @@
#ifdef CONFIG_SYSCTL
extern int netdev_max_backlog;
+extern int netdev_packet_weight;
extern int weight_p;
extern int no_cong_thresh;
extern int no_cong;
@@ -91,6 +92,14 @@ ctl_table core_table[] = {
.proc_handler = &proc_dointvec
},
{
+ .ctl_name = NET_CORE_PACKET_WEIGHT,
+ .procname = "netdev_packet_weight",
+ .data = &netdev_packet_weight,
+ .maxlen = sizeof(int),
+ .mode = 0644,
+ .proc_handler = &proc_dointvec
+ },
+ {
.ctl_name = NET_CORE_MAX_BACKLOG,
.procname = "netdev_max_backlog",
.data = &netdev_max_backlog,
|