Groups | Search | Server Info | Keyboard shortcuts | Login | Register [http] [https] [nntp] [nntps]
Groups > linux.kernel > #1481382
| From | kan.liang@intel.com |
|---|---|
| Newsgroups | linux.kernel |
| Subject | [RFC V3 PATCH 26/26] Documentation/networking: Document NET policy |
| Date | 2016-09-12 17:00 +0200 |
| Message-ID | <sgASd-4DC-11@gated-at.bofh.it> (permalink) |
| References | <sgASd-4DC-5@gated-at.bofh.it> |
| Organization | linux.* mail to news gateway |
From: Kan Liang <kan.liang@intel.com> Signed-off-by: Kan Liang <kan.liang@intel.com> --- Documentation/networking/netpolicy.txt | 157 +++++++++++++++++++++++++++++++++ 1 file changed, 157 insertions(+) create mode 100644 Documentation/networking/netpolicy.txt diff --git a/Documentation/networking/netpolicy.txt b/Documentation/networking/netpolicy.txt new file mode 100644 index 0000000..b8e3d4c --- /dev/null +++ b/Documentation/networking/netpolicy.txt @@ -0,0 +1,157 @@ +What is Linux Net Policy? + +It is a big challenge to get good network performance. First, the network +performance is not good with default system settings. Second, it is too +difficult to do automatic tuning for all possible workloads, since workloads +have different requirements. Some workloads may want high throughput. Some may +need low latency. Last but not least, there are lots of manual configurations. +Fine grained configuration is too difficult for users. + +"NET policy" intends to simplify the network configuration and get a +good network performance according to the hints(policy) which is applied by +user. It provides some typical "policies" for user which can be set +per-socket, per-task or per-device. The kernel automatically figures out +how to merge different requests to get good network performance. + +"Net policy" is designed for multiqueue network devices. This document +describes the concepts and APIs of "net policy" support. + +NET POLICY CONCEPTS + +Scope of Net Policies + + Device net policy: this policy applies to the whole device. Once the + device net policy is set, it automatically configures the system + according to the applied policy. The configuration usually includes IRQ + affinity, IRQ balance disable, interrupt moderation, and so on. But the + device net policy does not change the packet direction. + + Task net policy: this is a per-task policy. When it is applied to specific + task, all packet transmissions of the task will be redirected to the + assigned queues accordingly. If a task does not define a task policy, + it "falls back" to the system default way to direct the packets. The + per-task policy must be compatible with device net policy. + + Socket net policy: this is a per-socket policy. When it is applied to + specific socket, all packet transmissions of the socket will be redirected + to the assigned queues accordingly. If a socket does not define a socket + policy, it "falls back" to the system default way to direct the packets. + The per-socket policy must be compatible with both device net policy and + per-task policy. + +Components of Net Policies + + Net policy object: it is a combination of CPU and queue. The queue IRQ has + to set affinity with the CPU. It can be shared between sockets and tasks. + A reference counter is used to track the sharing number. + + Net policy object list: each device policy has an object list. Once the + device policy is determined, the net policy object will be inserted into + the net policy object list. The net policy object list does not change + unless the CPU/queue number is changed, the netpolicy is disabled or + the device policy is changed. + The network performance for objects could be different because of the + CPU/queue topology and dev location. The objects which can bring high + performance are in the front of the list. + + RCU hash table: an RCU hash table to maintain the relationship between + the task/socket and the assigned object. The task/socket can get the + assigned object by searching the table. + If it is the first time, there is no assigned object in the table. It will + go through the object list to find the available object based on position + and reference number. + If the net policy object list changes, all the assigned objects will become + invalid. + +NET POLICY APIs + +Interfaces between net policy and device driver + + int (*ndo_netpolicy_init)(struct net_device *dev, + struct netpolicy_info *info); + + The device driver who has NET policy support must implement this interface. + In this interface, the device driver does necessory initialization, and fill + the info for net policy module. The information could include supported + policy, MIX policy support, queue pair support and so on. + + int (*ndo_get_irq_info)(struct net_device *dev, + struct netpolicy_dev_info *info); + + This interface is used to get more accurate device IRQ information. + + int (*ndo_set_net_policy)(struct net_device *dev, + enum netpolicy_name name); + + This interface is used to set device net policy by name. It is device driver's + responsibility to set driver specific configuration for the given policy. + +Interfaces between net policy and kernel + + int netpolicy_register(struct netpolicy_instance *instance); + void netpolicy_unregister(struct netpolicy_instance *instance); + + This interface is used to register per task/socket net policy. + The socket/task can only be benefited when it register itself with specific + policy. After registeration, a record will be created and inserted into RCU + hash table, which include all the NET policy related information for the + socket/task, such as pointor, policy, object and so on. + + int netpolicy_pick_queue(struct netpolicy_instance *instance, bool is_rx); + + This interface is used to find the proper queue(object) for packet + receiving and transmitting. The proper queue is picked from object list + according to policy, reference, location and so on. + + + int netpolicy_set_rules(struct netpolicy_instance *instance); + + This interface is used to add device specific rules. Once the rule is + applied, the packet from specific IP and port will be redirected to the + given queue. This interface is usually used on receive side. + +NET POLICY INTERFACE + +Device net policy setting + + /proc/net/netpolicy/$DEV/policy + + Concatenating(cat) the "policy" file can show the available device + policies, if there is no device policy applied. Otherwise, the device + policy name will be printed out. If it is MIX policy, the policy for each + queue will also be printed out. + User can set device net policy by writing policy name. + +Task policy setting + + /proc/$PID/net_policy + + Concatenating(cat) the "net_policy" file can show the applied per task + policy. + User can set per task net policy by writing policy name. + + OR + + prctl(PR_SET_NETPOLICY, POLICY_NAME, NULL, NULL, NULL) + + "prctl" is an alternative way to set/get per task policy. + +Socket policy setting + + setsockopt(sockfd,SOL_SOCKET,SO_NETPOLICY,&policy,sizeof(int)) + + The socket net policy can be set by option SO_NETPOLICY of setsockopt. + +AVAILABLE NET POLICIES + + The available net policies are defined as below: + - CPU: intends to get higher throughput and lower CPU% (power saving). + This policy can be applied as either device net policy or + task/socket net policy. + - BULK: intends to get highest throughput. This policy can be applied as + either device net policy or task/socket net policy. + - LATENCY: intends to get lowest latency. This policy can be applied as + either device net policy or task/socket net policy. + - MIX: combination of other policies, which allows each queue to have a + different policy. This policy can only be set as device net policy. + -- 2.5.5
Back to linux.kernel | Previous | Next — Previous in thread | Next in thread | Find similar | Unroll thread
[RFC V3 PATCH 00/26] Kernel NET policy kan.liang@intel.com - 2016-09-12 17:00 +0200
[RFC V3 PATCH 26/26] Documentation/networking: Document NET policy kan.liang@intel.com - 2016-09-12 17:00 +0200
[RFC V3 PATCH 05/26] net/netpolicy: create CPU and queue mapping kan.liang@intel.com - 2016-09-12 17:00 +0200
[RFC V3 PATCH 22/26] net/netpolicy: set per task policy by proc kan.liang@intel.com - 2016-09-12 17:00 +0200
Re: [RFC V3 PATCH 22/26] net/netpolicy: set per task policy by proc Sergei Shtylyov <sergei.shtylyov@cogentembedded.com> - 2016-09-12 19:10 +0200
[RFC V3 PATCH 08/26] net/netpolicy: introduce NET policy object kan.liang@intel.com - 2016-09-12 17:00 +0200
[RFC V3 PATCH 21/26] net/netpolicy: introduce per task net policy kan.liang@intel.com - 2016-09-12 17:00 +0200
[RFC V3 PATCH 24/26] net/netpolicy: optimize for queue pair kan.liang@intel.com - 2016-09-12 17:00 +0200
[RFC V3 PATCH 20/26] net/netpolicy: set Rx queues according to policy kan.liang@intel.com - 2016-09-12 17:00 +0200
[RFC V3 PATCH 25/26] net/netpolicy: limit the total record number kan.liang@intel.com - 2016-09-12 17:00 +0200
[RFC V3 PATCH 10/26] net/netpolicy: add three new NET policies kan.liang@intel.com - 2016-09-12 17:10 +0200
[RFC V3 PATCH 09/26] net/netpolicy: set NET policy by policy name kan.liang@intel.com - 2016-09-12 17:10 +0200
[RFC V3 PATCH 18/26] net/netpolicy: set tx queues according to policy kan.liang@intel.com - 2016-09-12 17:10 +0200
Re: [RFC V3 PATCH 18/26] net/netpolicy: set tx queues according to policy Tom Herbert <tom@herbertland.com> - 2016-09-12 22:30 +0200
RE: [RFC V3 PATCH 18/26] net/netpolicy: set tx queues according to policy "Liang, Kan" <kan.liang@intel.com> - 2016-09-13 14:30 +0200
[RFC V3 PATCH 02/26] net/netpolicy: init NET policy kan.liang@intel.com - 2016-09-12 17:10 +0200
[RFC V3 PATCH 01/26] net: introduce NET policy kan.liang@intel.com - 2016-09-12 17:10 +0200
[RFC V3 PATCH 14/26] net/netpolicy: handle channel changes kan.liang@intel.com - 2016-09-12 17:10 +0200
[RFC V3 PATCH 13/26] net/netpolicy: support CPU hotplug kan.liang@intel.com - 2016-09-12 17:10 +0200
[RFC V3 PATCH 11/26] net/netpolicy: add MIX policy kan.liang@intel.com - 2016-09-12 17:10 +0200
[RFC V3 PATCH 17/26] net/netpolicy: introduce netpolicy_pick_queue kan.liang@intel.com - 2016-09-12 17:10 +0200
[RFC V3 PATCH 03/26] net/netpolicy: get device queue irq information kan.liang@intel.com - 2016-09-12 17:10 +0200
Re: [RFC V3 PATCH 03/26] net/netpolicy: get device queue irq information Sergei Shtylyov <sergei.shtylyov@cogentembedded.com> - 2016-09-12 18:50 +0200
RE: [RFC V3 PATCH 03/26] net/netpolicy: get device queue irq information "Liang, Kan" <kan.liang@intel.com> - 2016-09-13 14:30 +0200
Re: [RFC V3 PATCH 03/26] net/netpolicy: get device queue irq information Alexander Duyck <alexander.duyck@gmail.com> - 2016-09-13 15:20 +0200
RE: [RFC V3 PATCH 03/26] net/netpolicy: get device queue irq information "Liang, Kan" <kan.liang@intel.com> - 2016-09-13 15:30 +0200
[RFC V3 PATCH 15/26] net/netpolicy: implement netpolicy register kan.liang@intel.com - 2016-09-12 17:10 +0200
[RFC V3 PATCH 19/26] net/netpolicy: tc bpf extension to pick Tx queue kan.liang@intel.com - 2016-09-12 17:10 +0200
[RFC V3 PATCH 12/26] net/netpolicy: NET device hotplug kan.liang@intel.com - 2016-09-12 17:10 +0200
[RFC V3 PATCH 04/26] net/netpolicy: get CPU information kan.liang@intel.com - 2016-09-12 17:10 +0200
Re: [RFC V3 PATCH 00/26] Kernel NET policy Florian Westphal <fw@strlen.de> - 2016-09-12 17:40 +0200
Re: [RFC V3 PATCH 00/26] Kernel NET policy Cong Wang <xiyou.wangcong@gmail.com> - 2016-09-12 19:30 +0200
Re: [RFC V3 PATCH 00/26] Kernel NET policy Eric Dumazet <eric.dumazet@gmail.com> - 2016-09-12 18:00 +0200
Re: [RFC V3 PATCH 00/26] Kernel NET policy Stephen Hemminger <stephen@networkplumber.org> - 2016-09-19 22:40 +0200
csiph-web