diff options
Diffstat (limited to 'Documentation')
| -rw-r--r-- | Documentation/devicetree/bindings/net/davicom-dm9000.txt | 26 | ||||
| -rw-r--r-- | Documentation/devicetree/bindings/net/via-velocity.txt | 20 | ||||
| -rw-r--r-- | Documentation/devicetree/bindings/vendor-prefixes.txt | 1 | ||||
| -rw-r--r-- | Documentation/networking/scaling.txt | 58 | ||||
| -rw-r--r-- | Documentation/sysctl/net.txt | 3 |
5 files changed, 106 insertions, 2 deletions
diff --git a/Documentation/devicetree/bindings/net/davicom-dm9000.txt b/Documentation/devicetree/bindings/net/davicom-dm9000.txt new file mode 100644 index 0000000..2d39c99 --- /dev/null +++ b/Documentation/devicetree/bindings/net/davicom-dm9000.txt @@ -0,0 +1,26 @@ +Davicom DM9000 Fast Ethernet controller + +Required properties: +- compatible = "davicom,dm9000"; +- reg : physical addresses and sizes of registers, must contain 2 entries: + first entry : address register, + second entry : data register. +- interrupt-parent : interrupt controller to which the device is connected +- interrupts : interrupt specifier specific to interrupt controller + +Optional properties: +- local-mac-address : A bytestring of 6 bytes specifying Ethernet MAC address + to use (from firmware or bootloader) +- davicom,no-eeprom : Configuration EEPROM is not available +- davicom,ext-phy : Use external PHY + +Example: + + ethernet@18000000 { + compatible = "davicom,dm9000"; + reg = <0x18000000 0x2 0x18000004 0x2>; + interrupt-parent = <&gpn>; + interrupts = <7 4>; + local-mac-address = [00 00 de ad be ef]; + davicom,no-eeprom; + }; diff --git a/Documentation/devicetree/bindings/net/via-velocity.txt b/Documentation/devicetree/bindings/net/via-velocity.txt new file mode 100644 index 0000000..b3db469 --- /dev/null +++ b/Documentation/devicetree/bindings/net/via-velocity.txt @@ -0,0 +1,20 @@ +* VIA Velocity 10/100/1000 Network Controller + +Required properties: +- compatible : Should be "via,velocity-vt6110" +- reg : Address and length of the io space +- interrupts : Should contain the controller interrupt line + +Optional properties: +- no-eeprom : PCI network cards use an external EEPROM to store data. Embedded + devices quite often set this data in uboot and do not provide an eeprom. + Specify this option if you have no external eeprom. + +Examples: + +eth0@d8004000 { + compatible = "via,velocity-vt6110"; + reg = <0xd8004000 0x400>; + interrupts = <10>; + no-eeprom; +}; diff --git a/Documentation/devicetree/bindings/vendor-prefixes.txt b/Documentation/devicetree/bindings/vendor-prefixes.txt index 6931c43..2fe74e6 100644 --- a/Documentation/devicetree/bindings/vendor-prefixes.txt +++ b/Documentation/devicetree/bindings/vendor-prefixes.txt @@ -18,6 +18,7 @@ chrp Common Hardware Reference Platform cirrus Cirrus Logic, Inc. cortina Cortina Systems, Inc. dallas Maxim Integrated Products (formerly Dallas Semiconductor) +davicom DAVICOM Semiconductor, Inc. denx Denx Software Engineering emmicro EM Microelectronic epson Seiko Epson Corp. diff --git a/Documentation/networking/scaling.txt b/Documentation/networking/scaling.txt index 579994a..ca6977f 100644 --- a/Documentation/networking/scaling.txt +++ b/Documentation/networking/scaling.txt @@ -163,6 +163,64 @@ and unnecessary. If there are fewer hardware queues than CPUs, then RPS might be beneficial if the rps_cpus for each queue are the ones that share the same memory domain as the interrupting CPU for that queue. +==== RPS Flow Limit + +RPS scales kernel receive processing across CPUs without introducing +reordering. The trade-off to sending all packets from the same flow +to the same CPU is CPU load imbalance if flows vary in packet rate. +In the extreme case a single flow dominates traffic. Especially on +common server workloads with many concurrent connections, such +behavior indicates a problem such as a misconfiguration or spoofed +source Denial of Service attack. + +Flow Limit is an optional RPS feature that prioritizes small flows +during CPU contention by dropping packets from large flows slightly +ahead of those from small flows. It is active only when an RPS or RFS +destination CPU approaches saturation. Once a CPU's input packet +queue exceeds half the maximum queue length (as set by sysctl +net.core.netdev_max_backlog), the kernel starts a per-flow packet +count over the last 256 packets. If a flow exceeds a set ratio (by +default, half) of these packets when a new packet arrives, then the +new packet is dropped. Packets from other flows are still only +dropped once the input packet queue reaches netdev_max_backlog. +No packets are dropped when the input packet queue length is below +the threshold, so flow limit does not sever connections outright: +even large flows maintain connectivity. + +== Interface + +Flow limit is compiled in by default (CONFIG_NET_FLOW_LIMIT), but not +turned on. It is implemented for each CPU independently (to avoid lock +and cache contention) and toggled per CPU by setting the relevant bit +in sysctl net.core.flow_limit_cpu_bitmap. It exposes the same CPU +bitmap interface as rps_cpus (see above) when called from procfs: + + /proc/sys/net/core/flow_limit_cpu_bitmap + +Per-flow rate is calculated by hashing each packet into a hashtable +bucket and incrementing a per-bucket counter. The hash function is +the same that selects a CPU in RPS, but as the number of buckets can +be much larger than the number of CPUs, flow limit has finer-grained +identification of large flows and fewer false positives. The default +table has 4096 buckets. This value can be modified through sysctl + + net.core.flow_limit_table_len + +The value is only consulted when a new table is allocated. Modifying +it does not update active tables. + +== Suggested Configuration + +Flow limit is useful on systems with many concurrent connections, +where a single connection taking up 50% of a CPU indicates a problem. +In such environments, enable the feature on all CPUs that handle +network rx interrupts (as set in /proc/irq/N/smp_affinity). + +The feature depends on the input packet queue length to exceed +the flow limit threshold (50%) + the flow history length (256). +Setting net.core.netdev_max_backlog to either 1000 or 10000 +performed well in experiments. + RFS: Receive Flow Steering ========================== diff --git a/Documentation/sysctl/net.txt b/Documentation/sysctl/net.txt index 98335b7..c1f8640 100644 --- a/Documentation/sysctl/net.txt +++ b/Documentation/sysctl/net.txt @@ -93,8 +93,7 @@ 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. The limit of packets in one such probe can be -set per-device via sysfs class/net/<device>/weight . +probed in a round-robin manner. netdev_max_backlog ------------------ |
