man.bsd.lv manual page server

Manual Page Search Parameters

POLLING(4) Device Drivers Manual POLLING(4)

pollingnetwork device driver polling support

options IFPOLL_ENABLE

Network device polling ( polling for brevity) refers to a technique that lets the operating system periodically poll network devices, instead of relying on the network devices to generate interrupts when they need attention. This might seem inefficient and counterintuitive, but when done properly, polling gives more control to the operating system on when and how to handle network devices, with a number of advantages in terms of system responsiveness and performance.

In particular, polling reduces the overhead for context switches which is incurred when servicing interrupts, and gives more control on the scheduling of a CPU between various tasks (user processes, software interrupts, device handling) which ultimately reduces the chances of livelock in the system.

In the normal, interrupt-based mode, network devices generate an interrupt whenever they need attention. This in turn causes a context switch and the execution of an interrupt handler which performs whatever processing is needed by the network device. The duration of the interrupt handler is potentially unbounded unless the network device driver has been programmed with real-time concerns in mind (which is generally not the case for DragonFly drivers). Furthermore, under heavy traffic load, the system might be persistently processing interrupts without being able to complete other work, either in the kernel or in userland.

Network device polling disables interrupts by polling network devices on clock interrupts. This way, the context switch overhead is removed. Furthermore, the operating system can control accurately how much work to spend in handling network device events, and thus prevent livelock by reserving some amount of CPU to other tasks.

Enabling polling also changes the way software network interrupts are scheduled, so there is never the risk of livelock because packets are not processed to completion.

It is turned on and off with help of ifconfig(8) command. An interface does not have to be “up” in order to turn on its polling feature.

The following tunables can be set from loader.conf(5) (X is the CPU number):

net.ifpoll.burst_max
Default value for net.ifpoll.X.rx.burst_max sysctl nodes.

net.ifpoll.each_burst
Default value for net.ifpoll.X.rx.each_burst sysctl nodes.

net.ifpoll.user_frac
Default value for net.ifpoll.X.rx.user_frac sysctl nodes.

net.ifpoll.pollhz
Default value for net.ifpoll.X.pollhz sysctl nodes.

net.ifpoll.status_frac
Default value for net.ifpoll.0.status_frac sysctl node.

net.ifpoll.tx_frac
Default value for net.ifpoll.X.tx_frac sysctl nodes.

The operation of polling is controlled by the following per CPU sysctl(8) MIB variables (X is the CPU number):

net.ifpoll.X.pollhz
The polling frequency, whose range is 1 to 30000. Default is 6000.

net.ifpoll.X.rx.user_frac
When polling is enabled, and provided that there is some work to do, up to this percent of the CPU cycles is reserved to userland tasks, the remaining fraction being available for polling processing. Default is 50.

net.ifpoll.X.rx.burst
Maximum number of packets grabbed from each network interface in each timer tick. This number is dynamically adjusted by the kernel, according to the programmed user_frac, burst_max, CPU speed, and system load.

net.ifpoll.X.rx.each_burst
The burst above is split into smaller chunks of this number of packets, going round-robin among all interfaces registered for polling. This prevents the case that a large burst from a single interface can saturate the IP interrupt queue. Default is 50.

net.ifpoll.X.rx.burst_max
Upper bound for net.ifpoll.X.rx.burst. Note that when polling is enabled, each interface can receive at most (pollhz * burst_max) packets per second unless there are spare CPU cycles available for polling in the idle loop. This number should be tuned to match the expected load. Default is 250 which is adequate for 1000Mbit network and pollhz=6000.

net.ifpoll.X.rx.handlers
How many active network devices have registered for packet reception polling.

net.ifpoll.X.tx_frac
Controls how often (every tx_frac / pollhz seconds) the tranmission queue is checked for packet transmission done events. Increasing this value reduces the time spent on checking packets transmission done events thus reduces bus load, but it also increases chance that the transmission queue getting saturated. Default is 1.

net.ifpoll.X.tx.handlers
How many active network devices have registered for packet transmission polling.

net.ifpoll.0.status_frac
Controls how often (every status_frac / pollhz seconds) the status registers of the network device are checked for error conditions and the like. Increasing this value reduces the load on the bus, but also delays the error detection. Default is 120.

net.ifpoll.0.status.handlers
How many active network devices have registered for status polling.

net.ifpoll.X.rx.short_ticks
 
net.ifpoll.X.rx.lost_polls
 
net.ifpoll.X.rx.pending_polls
 
net.ifpoll.X.rx.residual_burst
 
net.ifpoll.X.rx.phase
 
net.ifpoll.X.rx.suspect
 
net.ifpoll.X.rx.stalled
 
net.ifpoll.X.tx.short_ticks
 
net.ifpoll.X.tx.lost_polls
 
net.ifpoll.X.tx.pending_polls
 
net.ifpoll.X.tx.residual_burst
 
net.ifpoll.X.tx.phase
 
net.ifpoll.X.tx.suspect
 
net.ifpoll.X.tx.stalled
Debugging variables.

Network device polling requires explicit modifications to the network device drivers. As of this writing, the bce(4), bge(4), bnx(4), dc(4), em(4), emx(4), fwe(4), fxp(4), igb(4), ix(4), jme(4), mxge(4), nfe(4), nge(4), re(4), rl(4), sis(4), stge(4), vge(4), vr(4), and xl(4) devices are supported, with others in the works. The bce(4), bnx(4), emx(4), igb(4), ix(4), jme(4), and mxge(4), support multiple reception queues based polling. The bce(4), bnx(4), certain types of emx(4), igb(4), and ix(4) support multiple transmission queues based polling. The modifications are rather straightforward, consisting in the extraction of the inner part of the interrupt service routine and writing a callback function, (), which is invoked to probe the network device for events and process them. (See the conditionally compiled sections of the network devices mentioned above for more details.)

In order to reduce the latency in processing packets, it is advisable to set the sysctl(8) variable net.ifpoll.X.pollhz to at least 1000.

Network device polling first appeared in FreeBSD 4.6. It was rewritten in DragonFly 1.3.

The network device polling code was rewritten by Matt Dillon based on the original code by Luigi Rizzo <luigi@iet.unipi.it>. Sepherosa Ziehau made the polling frequency settable at runtime, added per CPU polling and added multiple reception and tranmission queue polling support.

May 23, 2013 DragonFly-5.6.1