速记符	匹配项
ip	dl_type=0x800
ipv6	dl_type=0x86dd
icmp	dl_type=0x0800,nw_proto=1
icmp6	dl_type=0x86dd,nw_proto=58
tcp	dl_type=0x0800,nw_proto=6
tcp6	dl_type=0x86dd,nw_proto=6
udp	dl_type=0x0800,nw_proto=17
udp6	dl_type=0x86dd,nw_proto=17
sctp	dl_type=0x0800,nw_proto=132
sctp6	dl_type=0x86dd,nw_proto=132
arp	dl_type=0x0806
rarp	dl_type=0x8035
mpls	dl_type=0x8847
mplsm	dl_type=0x8848

NXM字段	报文字段
NXM_OF_ETH_SRC	源MAC
NXM_OF_ETH_DST	目的MAC
NXM_OF_ETH_TYPE	以太网类型
NXM_OF_VLAN_TCI	vid
NXM_OF_IP_PROTO	IP协议号
NXM_OF_IP_TOS	IP ToS值
NXM_NX_IP_ECN	IP ToS ECN
NXM_OF_IP_SRC	源IP
NXM_OF_IP_DST	目的IP
NXM_OF_TCP_SRC	TCP源端口
NXM_OF_TCP_DST	TCP目的端口
NXM_OF_UDP_SRC	UDP源端口
NXM_OF_UDP_DST	UDP目的端口
NXM_OF_SCTP_SRC	SCTP源端口
NXM_OF_SCTP_DST	SCTP目的端口

2.设计考虑

2.1.总体数据结构

ovs datapath classifier涉及的数据结构主要有以下。

网桥数据结构

struct datapath {

struct rcu_head rcu;

/* 该结构使用双链表组织 */

struct list_head list_node;

/* 从属该datapath的流表项 */

struct flow_table table;

/* 从属该datapath的vport信息 */

struct hlist_head *ports;

…

}

流表数据结构

struct flow_table {

/* 用key组织的流表实例 */

struct table_instance *ti;

/* 用unique flow identifier(ufid)组织的流表实例 */

struct table_instance *ufid_ti;

/* 掩码信息缓存表 */

struct mask_cache_entry *mask_cache;

/* 掩码信息列表 */

struct mask_array *mask_array;

/* 记录当前节拍数 */

unsigned long last_rehash;

/* ti流表实例中存储的流表项数目 */

unsigned int count;

/* ufid_ti流表实例中存储的流表项数目 */

unsigned int ufid_count;

}

流表实例数据结构

struct table_instance {

/* 哈希桶,用于组织各个流表项的具体信息. */

struct flex_array *buckets;

/* 哈希桶大小 */

unsigned int n_buckets;

struct rcu_head rcu;

int node_ver;

u32 hash_seed;

bool keep_flows;

}

掩码信息列表数据结构

struct mask_array {

struct rcu_head rcu;

/* 当前已存储的掩码信息数目 */

int count;

/* 一共能够存储掩码信息的总数目 */

int max;

/* 具体的掩码信息 */

struct sw_flow_mask *masks[];

}

struct sw_flow_mask {

/* 引用计数 */

int ref_count;

struct rcu_head rcu;

/* 匹配关键字的有效范围,下文会具体解释 */

struct sw_flow_key_range range;

/* 匹配关键字信息 */

struct sw_flow_key key;

}

掩码信息缓存表数据结构

struct mask_cache_entry {

/* hash值 */

u32 skb_hash;

/* 对应哪个掩码信息,索引值 */

u32 mask_index;

}

哈希桶数据结构

struct flex_array {

union {

struct {

/* 实际等于sizeof(struct hlist_head) */

int element_size;

/* 一共有多少个struct hlist_head指针. */

int total_nr_elements;

/* 每一个part(页)能够存储多少个struct hlist_head指针 */

int elems_per_part;

u32 reciprocal_value reciprocal_elems;

/* 具体存储struct hlist_head指针的缓冲区 */

struct flex_array_part *parts[];

};

/* 填充字段.表明了整个结构的大小=页大小(4096字节) */

char padding[FLEX_ARRAY_BASE_SIZE];

}

struct flex_array_part {

/* 缓冲区.一个页大小,即:4096字节 */

char elements[FLEX_ARRAY_PART_SIZE];

};

上述这些数据结构是在源码中的ovs_flow_tbl_init函数里面进行初始化操做的。初始化后以及上述这些数据结构之间的关系以下图所示。

2.2.关键信息范围

从上面2.1节可知，掩码信息(struct sw_flow_mask结构)中记录了一个范围(struct sw_flow_key_range结构)，该范围用于标识须要匹配的关键信息最小偏移和最大偏移。为何须要这样作？我的感受和ovs-dpdk datapath classifier中描述的miniflow相似，即：匹配过程当中并不是使用报文的全部字段去匹配，而是使用部分字段，例如使用报文的五元组信息(源IP、目的IP、协议号、源端口、目的端口)。那么使用sw_flow_key_range结构来标识这五元组信息中最小偏移和最大偏移。实际源码中，关键信息是使用struct sw_flow_key结构来描述的。因为该结构字段较多，这里不详细给出。以报文五元组信息为例，这里给出的五元组信息所在sw_flow_key结构的位置和实际源码对应的位置是不相同的，这里只是给出计算最小偏移和最大偏移的概念，以下图所示，关键信息的有效范围为：
最小偏移=M，最大偏移=N

2.3.更新过程

在源码中，对应更新过程的入口函数是：ovs_flow_cmd_new。这个入口函数是处于内核模块中，在接收到报文时，经过下面2.4节所述的查找过程，查找失败时，会将报文的相关信息upcall到用户空间，在用户空间经过查找”慢路径”将对应的actions和mask信息下发到内核空间，在内核空间，处理的入口函数正是ovs_flow_cmd_new。下面将对这个函数的处理过程做详细描述。描述以前，先掌握一些相关的数据结构，以下所示：

struct sw_flow {

struct rcu_head rcu;

/* 哈希桶链表 */

struct {

struct hlist_node node[2];

u32 hash;

} flow_table, ufid_table;

int stats_last_writer;

/* 关键信息.通过掩码运算后的 */

struct sw_flow_key key;

/* 流id信息 */

struct sw_flow_id id;

/* 指向的掩码信息 */

struct sw_flow_mask *mask;

/* 指向的流动做信息 */

struct sw_flow_actions *sf_acts;

struct flow_stats *stats[];

}

struct sw_flow_id {

u32 ufid_len;

union {

/* ufid为128比特,共16字节 */

u32 ufid[4];

struct sw_flow_key *unmasked_key;

}

struct sw_flow_actions {

struct rcu_head rcu;

size_t orig_len;

u32 actions_len;

struct nlattr actions[];

}

struct sw_flow_match {

struct sw_flow_key *key;

struct sw_flow_key_range range;

struct sw_flow_mask *mask;

}

具体流程以下所示：
1)初始化struct sw_flow *new_flow。分配空间给new_flow，并设置部分的成员值，以下：
new_flow->sf_acts = null;
new_flow->mask = null;
new_flow->id.ufid_len=0;
new_flow->id.unmasked_key=null;
2)构建struct sw_flow_match match信息。根据接收到的关键信息和掩码信息，存储在match.key和match.mask中。

3)计算new_flow->key = match.key & match.mask。
4)将ufid信息提取出来存储在new_flow->id.ufid_len和new_flow->id.ufid中。若是未提供任何的UFID信息(此时的new_flow->id.ufid_len为0)，则将match.key信息拷贝一份到new_flow->id.unmasked_key中存储。
5)将actions信息存储在变量struct sw_flow_actions acts中。
6)根据接收到的dp_ifindex获取struct datapath dp信息。
7)若是new_flow->id.ufid_len不为0，则使用new_flow->id.ufid信息去dp->table.ufid_ti指向的哈希桶中找到对应的struct sw_flow信息。假设找不到。
8)而若是new_flow->id.ufid_len为0，则须要在dp->table.ti，同时配合在2)中构建出来的match.key和dp->table.mask_array配合找出对应的struct sw_flow信息。这个详细过程能够参考下面的2.4节。这里也假设找不到。
9)通过上面7)和8)步都没找到对应的struct sw_flow信息。首先设置new_flow->sf_acts=acts(在5)步中获取)。而后使用match.mask去dp->table.mask_array中查找是否已存在该match.mask信息。若是不存在则接着分配一个struct sw_flow_mask *mask。设置mask->key=match.mask->key, mask->range=match.mask->range, mask->ref_count=1。而且在dp->table.mask_array.masks[i]中存储该mask的地址。添加完毕以后，以下图所示。变化的地方用绿色标注出来了。同时new_flow->mask=mask。

10)根据new_flow->key和new_flow->mask.range计算出new_flow->flow_table.hash值。
11)在dp->table.ti->buckets指向的哈希桶中插入new_flow。以下图所示(假设插入的位置为part[0]对应的第0个位置)。dp->table.count。
12)若是new_flow->id.ufid_len不为0，则使用new_flow->id.ufid信息计算出new_flow->ufid_table.hash。而后根据这个hash值在dp->table.ufid_ti->buckets中找到合适的哈希桶存储对应的new_flow信息。这里假设找到的位置为parts[0]的第0个位置。以下图所示。插入new_flow信息以后，dp->table.ufid_count。

到此为止，更新过程完毕。

2.4.查找过程

在源码中，对应查找过程的入口函数是：ovs_vport_receive。具体过程以下：
1)从接收到的报文信息中提取出关键信息。存储到struct sw_flow_key key。
2)从接收到的报文信息中获取struct vport信息，再从vport信息获取struct datapath信息，假设为dp。
3)若是接收到的报文中未带有skb_hash值信息，则执行：
遍历每个掩码，即:dp->table.mask_array->masks[i]。这里简单记为mask。将1)提取出来的关键新key与这个掩码mask作逻辑与运算，得出掩码过的信息，记为masked_key。经过masked_key和mask.range信息计算出hash值在dp->table.ti->buckets中找到对应的哈希桶，并遍历该桶上的全部struct sw_flow信息，记为flow。执行比较：若是flow->mask指向的是mask，flow->flow_table.hash值和计算出的hash值相等，且flow->key和masked_key信息在mask.range指定的范围内彻底相同，则认为成功匹配，返回flow信息。不然匹配失败，返回NULL。
4)若是接收到的报文中带有skb_hash值信息，则执行：
4)-1：根据旧的skb_hash值和key->recirc_id值从新计算出新的skb_hash值。
4)-2：将skb_hash值分红4段，每段1字节，记为hash。遍历每一段的hash值，执行：获取dp->table.mask_cache[hash]表项，记为entry，若是entry.skb_hash值和skb_hash值相等，则使用entry.mask_index指向的掩码信息去dp->table.ti->buckets中找到对应的struct sw_flow信息(过程和上述第3)步相同)。若是找到对应的flow，则返回flow，过程当中会更新entry.mask_index值来实际指向具体的掩码信息索引。不然，匹配失败，将entry.skb_hash值置0，返回NULL。而若是每个entry.skb_hash值和skb_hash值不相等，则遍历完每一段hash值以后，从中选择最佳候选entry，最佳候选的条件是：其skb_hash值最小者，假设记为ce。最后使用ce.mask_index指向的掩码信息去dp->table.ti->buckets中找到对应的struct sw_flow信息(过程和上述第3)步相同)。若是找到对应的flow，则返回flow，同时将ce->skb_hash值更新为skb_hash值。固然在查找的过程当中(上述第3)步)，也会更新ce->mask_index来指向实际的掩码信息索引。
5) 若是在上述第3)和第4)步中都匹配失败了，则须要将报文的信息upcall到用户空间，由用户空间负责查找对应的流动做信息，返回给内核。这个过程具体请参考上述2.3节。
到此为止，查找过程结束。

2.5.执行过程

在2.4节查找过程当中，若是查找成功，则须要执行对应的流动做。入口函数是：ovs_execute_actions。
而若是查找失败，upcall到用户空间，找到对应的流动做以后，调用执行，到内核空间，入口函数对应的是：ovs_packet_cmd_execute。该函数最终会调用到ovs_execute_actions。

2.6.掩码信息比较

在上述2.3和2.4节所述的更新过程和查找过程当中都会碰见用新构造的掩码信息与datapath结构的table.mask_array做比较，以检测掩码信息是否须要新增。而比较的方法以下：
假设新构造的掩码信息为mask，与table.mask_array->masksi比较：
1)mask.range.start和exist_mask.range.start相等。
2)mask.range.end和exist_mask.range.end相等。
3)mask和exist_mask在range范围内彻底相同。
同时符合上面三个条件才认为两个掩码彻底相同。

2.7.流信息比较

在上述2.4节所述的查找过程当中，对接收到的报文进行匹配表项时，须要对流信息做比较。假设接收到的报文提取出来的关键信息为key，匹配的掩码信息为mask，经过mask & key计算出掩码后的报文关键信息，记为masked_key，经过masked_key和mask.range计算出hash值。根据这个hash值找到对应的哈希桶，遍历这个哈希桶中存储的每个流信息，记为flow。如今须要比较flow信息进而找到匹配的流表项。比较以下：
1)flow->mask指向的是mask。
2)flow->flow_table.hash和计算出的hash值相等。
3)flow->key和masked_key在mask.range范围内彻底相同。
同时符合上面三个条件才认为找到匹配的流表项。

2.8.mask_cache表项

在ovs_dp_process_packet函数中查找匹配的流表项时，若是报文的skb中已经带有skb_hash值，则将这个skb_hash值(32比特)分为4段，每段8比特，每段的哈希值暂记为hash，用这个hash值去datapath结构中的table.mask_cache缓存表中查找对应的掩码信息索引。每一个表项(struct mask_cache_entry结构)存储了skb_hash和mask_index信息。初始化的时候，这个缓存表中全部表项都置0，所以，用报文的skb_hash值，分4段去查找，都没法找到合适的表项。这时须要从中选出最佳候选的表项，而最佳候选的表项为其skb_hash值最小。所以，初始化的时候，最终会选择table.mask_cache[0]为最佳候选表项。
接着根据上述2.4节所述的查找过程，找到合适的流表项信息。若是匹配成功，则最佳候选表项table.mask_cache[0].mask_index记录了掩码信息索引(index)，即：table.mask_array->masks[index]。同时table.mask_cache[0].skb_hash赋值为skb_hash。假设index为0，则对应以下图所示。
后续若是收到的报文带的skb_hash值与table.mask_cache[0].skb_hash值相等时，则首先使用table.mask_cache[0].mask_index索引的掩码信息去找匹配的流表信息。固然，若是匹配成功，table.mask_cache[0].mask_index可能并不是为0(以前存储的值)，有可能更新为其余值。而若是匹配失败，则table.mask_cache[0].skb_hash置0。

2.9.mask_array扩充

当datapath结构中的table.mask_array->count >= table.mask_array->max时，则须要扩充mask_array空间。已当前table.mask_array->max * 2的大小进行扩充。扩充先后的效果以下图所示。橙色线指向的掩码信息在扩充以后，会释放掉old的掩码信息空间。扩充老是按照当前max数值的2倍大小进行扩充，例如：16 -> 32 -> 64 -> 128 -> …。从源码中暂时未看到这个扩充的最大值。

2.10.table_instance扩充

table_instance扩充有两个条件触发：
1)当datapath结构中的table.count > table.ti->n_buckets时，触发扩充。
2)datapath结构中的table.last_rehash记录了上次执行扩充或初始化table时系统的jiffies值。若是超过10分钟，则须要从新扩充，只是此次的扩充并不是增大空间，而是以相同的大小从新分配空间。以为这样作的意义是从新生成table_instance结构中的hash_seed值，从新安排哈希桶的链表长度，分散存储，减小匹配的比较次数。
咱们主要以第一种条件为例，描述扩充的过程。这种扩充是在原有的哈希桶数目(n_buckets)基础之上，以2倍的大小进行扩充。扩充先后，table_instance结构的变化以下图所示。

根据上图可知，扩充以后，table_instance中的hash_seed更新为新的随机数了。这样，在从旧的table_instance将哈希桶中对应的各个流信息拷贝到新的table_instance时，须要从新计算哈希桶的位置，从新安排了。这样作的好处时：能够从新分散每一个哈希桶中流信息链表的长度，减小在匹配时流的比较次数。以下图所示，以前Flow_A和Flow_B都位于第0个哈希桶，扩充以后，Flow_A处于了第0个哈希桶，而Flow_B则处于第1025个哈希桶了。这样在查找Flow_B的时候，比较的次数就减小了一次。在大规模查找的过程当中，这种改变能够大大提升查找的效率。

2.11.示例

假设ovs用户空间的”慢路径”存储的流表信息以下所示：

table=0, src_ip=11.11.11.0/24, dst_ip=192.0.0.0/8, actions=output:1

table=0, src_ip=2.2.2.0/24, dst_ip=2.0.0.0/8, actions=output:2

table=0, dst_ip=8.0.0.0/8, actions=drop

初始化的时候，ovs内核空间的”快路径”没有存储任何的流路径信息。以下图所示：

收到第一个报文：src_ip=11.11.11.25, dst_ip=192.1.1.1
收到第一个报文，匹配结果Miss，upcall到用户空间，查表将结果发送回内核空间的datapath。根据上述2.3节所述的更新过程，会新增相应的掩码信息(mask_A)和流信息(flow_A)。以下图所示。

收到第二个报文：src_ip=11.11.11.63, dst_ip=192.168.7.8
根据上述2.4节所述的查找过程，匹配成功。

收到第三个报文：src_ip=2.2.2.4, dst_ip=2.7.7.7
根据上述2.4节所述的查找过程，匹配失败。由于掩码信息和mask_A彻底相同，所以无需新增掩码信息，只须要将mask_A的ref_count引用计数加1便可。可是须要新增相应的流信息(flow_B)，以下图所示。

收到第四个报文：dst_ip=8.12.34.56
根据上述2.4节所述的查找过程，匹配失败。须要新增相应的掩码信息(mask_B)和流信息(flow_C)。以下图所示

As part of my work in OpenDaylight, we are looking at creating a router using Open vSwitch... Why? Well OpenStack requires some limited L3 capabilities and we think that we can handle those in a distributed router.

Test Topology

My test topology looks like this:

We have a host in an external network 172.16.1.0/24, one host in an internal network 10.10.10.0/24 and two hosts in another internal network 10.10.20.0/24.

As such, The hosts in the 10.x.x.x range should be able to speak to each other, but should not be able to speak to external hosts.

The host 10.10.10.2 has a floating IP of 172.16.1.10 and should be reachable on this address from the external 172.16.1.0/24network. To do this, we'll use DNAT for traffic from 172.16.1.2 -> 172.16.1.10 and SNAT for traffic back from10.10.10.2 -> 172.16.1.2

If you'd like to recreate this topology you can checkout the OpenDaylight OVSDB project source on GitHub and:

 
               vagrant up mininet
vagrant ssh mininet
cd /vagrant/resources/mininet
sudo mn --custom topo.py --topo l3 
              

The Pipeline

Our router is implemented using the following pipeline:

Table 0 - Classifier

In this table we work out what traffic is interesting for us before pushing it further along the pipeline

Table 100 - ACL

While we don't use this table today, the idea would be to filter traffic in this table (or series of tables) and to then resubmit to the classifier once we have scrubbed them.

Table 105 - ARP Responder

In this table we use some OVS-Jitsu to take an incoming ARP Request and turn it in to an ARP reply

Table 5 - L3 Rewrite

In this table, we make any L3 modifications we need to before a packet is routed

Table 10 - L3 Routing

The L3 routing table is where the routing magic happens. Here we modify the Source MAC address, Decrement the TTL and push to the L2 tables for forwarding

Table 15 - L3 Forwarding

In the L3 forwarding table we resolve a destination IP address to the correct MAC address for L2 forwarding.

Table 20 - L2 Rewrites

While we aren't using this table in this example, typically we would push/pop any L2 encapsulations here like a VLAN tag or a VXLAN/GRE Tunnel ID.

Table 25 - L2 Forwarding

In this table we do our L2 lookup and forward out the correct port. We also handle L2 BUM traffic here using OpenFlow Groups - no VLANs!

The Flows

To program the flows, paste the following in to mininet:

## Set Bridge to use OpenFlow 1.3
sh ovs-vsctl set Bridge s1 "protocols=OpenFlow13"

## Create Groups
sh ovs-ofctl add-group -OOpenFlow13 s1 group_id=1,type=all,bucket=output:1
sh ovs-ofctl add-group -OOpenFlow13 s1 group_id=2,type=all,bucket=output:2,4
sh ovs-ofctl add-group -OOpenFlow13 s1 group_id=3,type=all,bucket=output:3

## Table 0 - Classifier
# Send ARP to ARP Responder
sh ovs-ofctl add-flow -OOpenFlow13 s1 "table=0, priority=1000, dl_type=0x0806, actions=goto_table=105"
# Send L3 traffic to L3 Rewrite Table
sh ovs-ofctl add-flow -OOpenFlow13 s1 "table=0, priority=100, dl_dst=00:00:5E:00:02:01, action=goto_table=5"
sh ovs-ofctl add-flow -OOpenFlow13 s1 "table=0, priority=100, dl_dst=00:00:5E:00:02:02, action=goto_table=5"
sh ovs-ofctl add-flow -OOpenFlow13 s1 "table=0, priority=100, dl_dst=00:00:5E:00:02:03, action=goto_table=5"
# Send L3 to L2 Rewrite Table
sh ovs-ofctl add-flow -OOpenFlow13 s1 "table=0, priority=0, action=goto_table=20"

## Table 5 - L3 Rewrites
# Exclude connected subnets
sh ovs-ofctl add-flow -OOpenFlow13 s1 "table=5, priority=65535, dl_type=0x0800, nw_dst=10.10.10.0/24 actions=goto_table=10"
sh ovs-ofctl add-flow -OOpenFlow13 s1 "table=5, priority=65535, dl_type=0x0800, nw_dst=10.10.20.0/24 actions=goto_table=10"
# DNAT
sh ovs-ofctl add-flow -OOpenFlow13 s1 "table=5, priority=100, dl_type=0x0800,  nw_dst=172.16.1.10 actions=mod_nw_dst=10.10.10.2, goto_table=10"
# SNAT
sh ovs-ofctl add-flow -OOpenFlow13 s1 "table=5, priority=100, dl_type=0x0800,  nw_src=10.10.10.2, actions=mod_nw_src=172.16.1.10,  goto_table=10"
# If no rewrite needed, continue to table 10
sh ovs-ofctl add-flow -OOpenFlow13 s1 "table=5, priority=0, actions=goto_table=10"

## Table 10 - IPv4 Routing
sh  ovs-ofctl add-flow -OOpenFlow13 s1 "table=10, dl_type=0x0800, nw_dst=10.10.10.0/24, actions=mod_dl_src=00:00:5E:00:02:01, dec_ttl, goto_table=15"
sh  ovs-ofctl add-flow -OOpenFlow13 s1 "table=10, dl_type=0x0800, nw_dst=10.10.20.0/24, actions=mod_dl_src=00:00:5E:00:02:02, dec_ttl, goto_table=15"
sh  ovs-ofctl add-flow -OOpenFlow13 s1 "table=10, dl_type=0x0800, nw_dst=172.16.1.0/24, actions=mod_dl_src=00:00:5E:00:02:03, dec_ttl, goto_table=15"
# Explicit drop if cannot route
sh  ovs-ofctl add-flow -OOpenFlow13 s1 "table=10, priority=0, actions=output:0"

## Table 15 - L3 Forwarding
sh ovs-ofctl add-flow -OOpenFlow13 s1 "table=15, dl_type=0x0800, nw_dst=10.10.10.2, actions=mod_dl_dst:00:00:00:00:00:01, goto_table=20"
sh ovs-ofctl add-flow -OOpenFlow13 s1 "table=15, dl_type=0x0800, nw_dst=10.10.20.2, actions=mod_dl_dst:00:00:00:00:00:02, goto_table=20"
sh ovs-ofctl add-flow -OOpenFlow13 s1 "table=15, dl_type=0x0800, nw_dst=10.10.20.4, actions=mod_dl_dst:00:00:00:00:00:04, goto_table=20"
sh ovs-ofctl add-flow -OOpenFlow13 s1 "table=15, dl_type=0x0800, nw_dst=172.16.1.2, actions=mod_dl_dst:00:00:00:00:00:03, goto_table=20"
sh ovs-ofctl add-flow -OOpenFlow13 s1 "table=15, priority=0, actions=goto_table=20"

## Table 20 - L2 Rewrite
# Go to next table
sh  ovs-ofctl add-flow -OOpenFlow13 s1 "table=20, priority=0, actions=goto_table=25"

## Table 25 - L2 Forwarding
# Use groups for BUM traffic
sh ovs-ofctl add-flow -OOpenFlow13 s1 "table=25, in_port=1, dl_dst=01:00:00:00:00:00/01:00:00:00:00:00, actions=group=1"
sh ovs-ofctl add-flow -OOpenFlow13 s1 "table=25, in_port=2, dl_dst=01:00:00:00:00:00/01:00:00:00:00:00, actions=group=2"
sh ovs-ofctl add-flow -OOpenFlow13 s1 "table=25, in_port=3, dl_dst=01:00:00:00:00:00/01:00:00:00:00:00, actions=group=3"
sh ovs-ofctl add-flow -OOpenFlow13 s1 "table=25, in_port=4, dl_dst=01:00:00:00:00:00/01:00:00:00:00:00, actions=group=2"
sh ovs-ofctl add-flow -OOpenFlow13 s1 "table=25, dl_dst=00:00:00:00:00:01,actions=output=1"
sh ovs-ofctl add-flow -OOpenFlow13 s1 "table=25, dl_dst=00:00:00:00:00:02,actions=output=2"
sh ovs-ofctl add-flow -OOpenFlow13 s1 "table=25, dl_dst=00:00:00:00:00:03,actions=output=3"
sh ovs-ofctl add-flow -OOpenFlow13 s1 "table=25, dl_dst=00:00:00:00:00:04,actions=output=4"

## Table 105 - ARP Responder
# Respond to ARP for Router Addresses
sh ovs-ofctl add-flow -OOpenFlow13 s1 "table=105, dl_type=0x0806, nw_dst=10.10.10.1, actions=move:NXM_OF_ETH_SRC[]->NXM_OF_ETH_DST[], mod_dl_src:00:00:5E:00:02:01, load:0x2->NXM_OF_ARP_OP[], move:NXM_NX_ARP_SHA[]->NXM_NX_ARP_THA[], move:NXM_OF_ARP_SPA[]->NXM_OF_ARP_TPA[], load:0x00005e000201->NXM_NX_ARP_SHA[], load:0x0a0a0a01->NXM_OF_ARP_SPA[], in_port"
sh ovs-ofctl add-flow -OOpenFlow13 s1 "table=105,  dl_type=0x0806, nw_dst=10.10.20.1, actions=move:NXM_OF_ETH_SRC[]->NXM_OF_ETH_DST[],  mod_dl_src:00:00:5E:00:02:02, load:0x2->NXM_OF_ARP_OP[], move:NXM_NX_ARP_SHA[]->NXM_NX_ARP_THA[], move:NXM_OF_ARP_SPA[]->NXM_OF_ARP_TPA[], load:0x00005e000202->NXM_NX_ARP_SHA[], load:0xa0a1401->NXM_OF_ARP_SPA[], in_port"
sh ovs-ofctl add-flow -OOpenFlow13 s1 "table=105,  dl_type=0x0806, nw_dst=172.16.1.1, actions=move:NXM_OF_ETH_SRC[]->NXM_OF_ETH_DST[],  mod_dl_src:00:00:5E:00:02:03, load:0x2->NXM_OF_ARP_OP[], move:NXM_NX_ARP_SHA[]->NXM_NX_ARP_THA[], move:NXM_OF_ARP_SPA[]->NXM_OF_ARP_TPA[], load:0x00005e000203->NXM_NX_ARP_SHA[], load:0xac100101->NXM_OF_ARP_SPA[], in_port"
# Proxy ARP for all floating IPs go below
sh ovs-ofctl add-flow -OOpenFlow13 s1 "table=105, dl_type=0x0806, nw_dst=172.16.1.10, actions=move:NXM_OF_ETH_SRC[]->NXM_OF_ETH_DST[], mod_dl_src:00:00:5E:00:02:03, load:0x2->NXM_OF_ARP_OP[], move:NXM_NX_ARP_SHA[]->NXM_NX_ARP_THA[], move:NXM_OF_ARP_SPA[]->NXM_OF_ARP_TPA[], load:0x00005e000203->NXM_NX_ARP_SHA[], load:0xac10010a->NXM_OF_ARP_SPA[], in_port"
# if we made it here, the arp packet is to be handled as any other regular L2 packet
sh ovs-ofctl add-flow -OOpenFlow13 s1 "table=105, priority=0, action=resubmit(,20)"

If you'd like to paste these in without comments, you can use this Gist

Testing

We can run a pingall to test this out:

mininet> pingall
*** Ping: testing ping reachability
h1 -> h2 h3 h4
h2 -> h1 X h4
h3 -> X X X
h4 -> h1 h2 X
*** Results: 41% dropped (7/12 received)

hosts 1,2 and 4 can speak to each other. Everything initiated by h3 is dropped (as expected) but h1 can speak to h3 (thanks to NAT). We can test our DNAT and Proxy ARP for Floating IP's using this command:

mininet> h3 ping 172.16.1.10
PING 172.16.1.10 (172.16.1.10) 56(84) bytes of data.
64 bytes from 172.16.1.10: icmp_seq=1 ttl=63 time=1.30 ms
64 bytes from 172.16.1.10: icmp_seq=2 ttl=63 time=0.043 ms
64 bytes from 172.16.1.10: icmp_seq=3 ttl=63 time=0.045 ms
64 bytes from 172.16.1.10: icmp_seq=4 ttl=63 time=0.050 ms
^C
--- 172.16.1.10 ping statistics ---
4 packets transmitted, 4 received, 0% packet loss, time 2999ms
rtt min/avg/max/mdev = 0.043/0.360/1.305/0.545 ms

Cool! It works!

Conclusion

So far we've implemented the nuts and bolts of routing, but we are missing one crucial piece - ICMP handling. Without this useful things like Path MTU Discovery won't work and neither will diagnostics tools like Ping and Traceroute. I think we can do this using a Open vSwitch but first we'll need to add some new NXM fields to ICMP Data and ICMP Checksum and to also make the existing OXM's writable through set_field. I'm going to start talking to the OVS community about this to see if it's possible so watch this space!

@dave_tucker

Helpful Links and Further Reading

ovs-ofctl Man Page Neutron ARP Responder Write Up Address Resolution Protocol OpenFlow 1.3.1 Spec

基于Open vSwitch搭建虚拟路由器

Test Topology

My test topology looks like this:

We have a host in an external network 172.16.1.0/24, one host in an internal network 10.10.10.0/24 and two hosts in another internal network 10.10.20.0/24.

As such, The hosts in the 10.x.x.x range should be able to speak to each other, but should not be able to speak to external hosts.

If you'd like to recreate this topology you can checkout the OpenDaylight OVSDB project source on GitHub and:

 
                   vagrant up mininet
vagrant ssh mininet
cd /vagrant/resources/mininet
sudo mn --custom topo.py --topo l3 
                  

The Pipeline

Our router is implemented using the following pipeline:

Table 0 - Classifier

In this table we work out what traffic is interesting for us before pushing it further along the pipeline

Table 100 - ACL

While we don't use this table today, the idea would be to filter traffic in this table (or series of tables) and to then resubmit to the classifier once we have scrubbed them.

Table 105 - ARP Responder

In this table we use some OVS-Jitsu to take an incoming ARP Request and turn it in to an ARP reply

Table 5 - L3 Rewrite

In this table, we make any L3 modifications we need to before a packet is routed

Table 10 - L3 Routing

The L3 routing table is where the routing magic happens. Here we modify the Source MAC address, Decrement the TTL and push to the L2 tables for forwarding

Table 15 - L3 Forwarding

In the L3 forwarding table we resolve a destination IP address to the correct MAC address for L2 forwarding.

Table 20 - L2 Rewrites

While we aren't using this table in this example, typically we would push/pop any L2 encapsulations here like a VLAN tag or a VXLAN/GRE Tunnel ID.

Table 25 - L2 Forwarding

In this table we do our L2 lookup and forward out the correct port. We also handle L2 BUM traffic here using OpenFlow Groups - no VLANs!

The Flows

To program the flows, paste the following in to mininet:

## Set Bridge to use OpenFlow 1.3
sh ovs-vsctl set Bridge s1 "protocols=OpenFlow13"

## Create Groups
sh ovs-ofctl add-group -OOpenFlow13 s1 group_id=1,type=all,bucket=output:1
sh ovs-ofctl add-group -OOpenFlow13 s1 group_id=2,type=all,bucket=output:2,4
sh ovs-ofctl add-group -OOpenFlow13 s1 group_id=3,type=all,bucket=output:3

## Table 0 - Classifier
# Send ARP to ARP Responder
sh ovs-ofctl add-flow -OOpenFlow13 s1 "table=0, priority=1000, dl_type=0x0806, actions=goto_table=105"
# Send L3 traffic to L3 Rewrite Table
sh ovs-ofctl add-flow -OOpenFlow13 s1 "table=0, priority=100, dl_dst=00:00:5E:00:02:01, action=goto_table=5"
sh ovs-ofctl add-flow -OOpenFlow13 s1 "table=0, priority=100, dl_dst=00:00:5E:00:02:02, action=goto_table=5"
sh ovs-ofctl add-flow -OOpenFlow13 s1 "table=0, priority=100, dl_dst=00:00:5E:00:02:03, action=goto_table=5"
# Send L3 to L2 Rewrite Table
sh ovs-ofctl add-flow -OOpenFlow13 s1 "table=0, priority=0, action=goto_table=20"

## Table 5 - L3 Rewrites
# Exclude connected subnets
sh ovs-ofctl add-flow -OOpenFlow13 s1 "table=5, priority=65535, dl_type=0x0800, nw_dst=10.10.10.0/24 actions=goto_table=10"
sh ovs-ofctl add-flow -OOpenFlow13 s1 "table=5, priority=65535, dl_type=0x0800, nw_dst=10.10.20.0/24 actions=goto_table=10"
# DNAT
sh ovs-ofctl add-flow -OOpenFlow13 s1 "table=5, priority=100, dl_type=0x0800,  nw_dst=172.16.1.10 actions=mod_nw_dst=10.10.10.2, goto_table=10"
# SNAT
sh ovs-ofctl add-flow -OOpenFlow13 s1 "table=5, priority=100, dl_type=0x0800,  nw_src=10.10.10.2, actions=mod_nw_src=172.16.1.10,  goto_table=10"
# If no rewrite needed, continue to table 10
sh ovs-ofctl add-flow -OOpenFlow13 s1 "table=5, priority=0, actions=goto_table=10"

## Table 10 - IPv4 Routing
sh  ovs-ofctl add-flow -OOpenFlow13 s1 "table=10, dl_type=0x0800, nw_dst=10.10.10.0/24, actions=mod_dl_src=00:00:5E:00:02:01, dec_ttl, goto_table=15"
sh  ovs-ofctl add-flow -OOpenFlow13 s1 "table=10, dl_type=0x0800, nw_dst=10.10.20.0/24, actions=mod_dl_src=00:00:5E:00:02:02, dec_ttl, goto_table=15"
sh  ovs-ofctl add-flow -OOpenFlow13 s1 "table=10, dl_type=0x0800, nw_dst=172.16.1.0/24, actions=mod_dl_src=00:00:5E:00:02:03, dec_ttl, goto_table=15"
# Explicit drop if cannot route
sh  ovs-ofctl add-flow -OOpenFlow13 s1 "table=10, priority=0, actions=output:0"

## Table 15 - L3 Forwarding
sh ovs-ofctl add-flow -OOpenFlow13 s1 "table=15, dl_type=0x0800, nw_dst=10.10.10.2, actions=mod_dl_dst:00:00:00:00:00:01, goto_table=20"
sh ovs-ofctl add-flow -OOpenFlow13 s1 "table=15, dl_type=0x0800, nw_dst=10.10.20.2, actions=mod_dl_dst:00:00:00:00:00:02, goto_table=20"
sh ovs-ofctl add-flow -OOpenFlow13 s1 "table=15, dl_type=0x0800, nw_dst=10.10.20.4, actions=mod_dl_dst:00:00:00:00:00:04, goto_table=20"
sh ovs-ofctl add-flow -OOpenFlow13 s1 "table=15, dl_type=0x0800, nw_dst=172.16.1.2, actions=mod_dl_dst:00:00:00:00:00:03, goto_table=20"
sh ovs-ofctl add-flow -OOpenFlow13 s1 "table=15, priority=0, actions=goto_table=20"

## Table 20 - L2 Rewrite
# Go to next table
sh  ovs-ofctl add-flow -OOpenFlow13 s1 "table=20, priority=0, actions=goto_table=25"

## Table 25 - L2 Forwarding
# Use groups for BUM traffic
sh ovs-ofctl add-flow -OOpenFlow13 s1 "table=25, in_port=1, dl_dst=01:00:00:00:00:00/01:00:00:00:00:00, actions=group=1"
sh ovs-ofctl add-flow -OOpenFlow13 s1 "table=25, in_port=2, dl_dst=01:00:00:00:00:00/01:00:00:00:00:00, actions=group=2"
sh ovs-ofctl add-flow -OOpenFlow13 s1 "table=25, in_port=3, dl_dst=01:00:00:00:00:00/01:00:00:00:00:00, actions=group=3"
sh ovs-ofctl add-flow -OOpenFlow13 s1 "table=25, in_port=4, dl_dst=01:00:00:00:00:00/01:00:00:00:00:00, actions=group=2"
sh ovs-ofctl add-flow -OOpenFlow13 s1 "table=25, dl_dst=00:00:00:00:00:01,actions=output=1"
sh ovs-ofctl add-flow -OOpenFlow13 s1 "table=25, dl_dst=00:00:00:00:00:02,actions=output=2"
sh ovs-ofctl add-flow -OOpenFlow13 s1 "table=25, dl_dst=00:00:00:00:00:03,actions=output=3"
sh ovs-ofctl add-flow -OOpenFlow13 s1 "table=25, dl_dst=00:00:00:00:00:04,actions=output=4"

## Table 105 - ARP Responder
# Respond to ARP for Router Addresses
sh ovs-ofctl add-flow -OOpenFlow13 s1 "table=105, dl_type=0x0806, nw_dst=10.10.10.1, actions=move:NXM_OF_ETH_SRC[]->NXM_OF_ETH_DST[], mod_dl_src:00:00:5E:00:02:01, load:0x2->NXM_OF_ARP_OP[], move:NXM_NX_ARP_SHA[]->NXM_NX_ARP_THA[], move:NXM_OF_ARP_SPA[]->NXM_OF_ARP_TPA[], load:0x00005e000201->NXM_NX_ARP_SHA[], load:0x0a0a0a01->NXM_OF_ARP_SPA[], in_port"
sh ovs-ofctl add-flow -OOpenFlow13 s1 "table=105,  dl_type=0x0806, nw_dst=10.10.20.1, actions=move:NXM_OF_ETH_SRC[]->NXM_OF_ETH_DST[],  mod_dl_src:00:00:5E:00:02:02, load:0x2->NXM_OF_ARP_OP[], move:NXM_NX_ARP_SHA[]->NXM_NX_ARP_THA[], move:NXM_OF_ARP_SPA[]->NXM_OF_ARP_TPA[], load:0x00005e000202->NXM_NX_ARP_SHA[], load:0xa0a1401->NXM_OF_ARP_SPA[], in_port"
sh ovs-ofctl add-flow -OOpenFlow13 s1 "table=105,  dl_type=0x0806, nw_dst=172.16.1.1, actions=move:NXM_OF_ETH_SRC[]->NXM_OF_ETH_DST[],  mod_dl_src:00:00:5E:00:02:03, load:0x2->NXM_OF_ARP_OP[], move:NXM_NX_ARP_SHA[]->NXM_NX_ARP_THA[], move:NXM_OF_ARP_SPA[]->NXM_OF_ARP_TPA[], load:0x00005e000203->NXM_NX_ARP_SHA[], load:0xac100101->NXM_OF_ARP_SPA[], in_port"
# Proxy ARP for all floating IPs go below
sh ovs-ofctl add-flow -OOpenFlow13 s1 "table=105, dl_type=0x0806, nw_dst=172.16.1.10, actions=move:NXM_OF_ETH_SRC[]->NXM_OF_ETH_DST[], mod_dl_src:00:00:5E:00:02:03, load:0x2->NXM_OF_ARP_OP[], move:NXM_NX_ARP_SHA[]->NXM_NX_ARP_THA[], move:NXM_OF_ARP_SPA[]->NXM_OF_ARP_TPA[], load:0x00005e000203->NXM_NX_ARP_SHA[], load:0xac10010a->NXM_OF_ARP_SPA[], in_port"
# if we made it here, the arp packet is to be handled as any other regular L2 packet
sh ovs-ofctl add-flow -OOpenFlow13 s1 "table=105, priority=0, action=resubmit(,20)"

If you'd like to paste these in without comments, you can use this Gist

Testing

We can run a pingall to test this out:

mininet> pingall
*** Ping: testing ping reachability
h1 -> h2 h3 h4
h2 -> h1 X h4
h3 -> X X X
h4 -> h1 h2 X
*** Results: 41% dropped (7/12 received)

mininet> h3 ping 172.16.1.10
PING 172.16.1.10 (172.16.1.10) 56(84) bytes of data.
64 bytes from 172.16.1.10: icmp_seq=1 ttl=63 time=1.30 ms
64 bytes from 172.16.1.10: icmp_seq=2 ttl=63 time=0.043 ms
64 bytes from 172.16.1.10: icmp_seq=3 ttl=63 time=0.045 ms
64 bytes from 172.16.1.10: icmp_seq=4 ttl=63 time=0.050 ms
^C
--- 172.16.1.10 ping statistics ---
4 packets transmitted, 4 received, 0% packet loss, time 2999ms
rtt min/avg/max/mdev = 0.043/0.360/1.305/0.545 ms

Cool! It works!

Conclusion

@dave_tucker

Helpful Links and Further Reading

ovs-ofctl Man Page Neutron ARP Responder Write Up Address Resolution Protocol OpenFlow 1.3.1 Spec

端口	说明
p0	IP 地址: 192.168.1.100/24 网络名称空间: ns0 网络接口 MAC地址: 66:4e:cc:ae:4d:20 OpenFlow Port Number: 100
p1	IP 地址: 192.168.1.101/24 网络名称空间: ns1 网络接口 MAC地址: 46:54:8a:95:dd:f8 OpenFlow Port Number: 101
p2	IP 地址: 192.168.1.102/24, 网络名称空间: ns2 网络接口 MAC地址: 86:3b:c8:d0:44:10 OpenFlow Port Number: 102

OVS——大杂烩

OVS架构解析--dpdk datapath数据通路

1. 架构说明

1.1. 总体架构

1.2. 核心组件及其关联关系

1.3. 内部模块及其关联关系

2. vswitchd和ovsdb通讯

2.1. 创建链接

2.2. 接收数据

2.3. json数据解析

2.4. 更新数据改变标记

3. dpdk加速处理

3.1. ovs dpdk加速配置

3.2. dpdk初始化

4. 数据结构抽象关系

4.1. 分层抽象

4.2. 主要数据结构关系

5. vswitchd启动

6. 附录-数据结构查询

6.1. ofproto_class

6.2. dpif_class

6.3. netdev_class

6.4. bridge

6.5. ofproto

6.6. port

6.7. iface

6.8. ofport

6.9. ofport_dpif

6.10. ofproto_port

6.11. dpif_port

6.12. ofproto_dpif

6.13. dpif_backer

6.14. udpif

6.15. dpif

6.16. dpif_netdev

6.17. dp_netdev

6.18. dp_netdev_port

6.19. netdev

6.20. netdev_dpdk

6.21. dp_netdev_rxq

6.22. netdev_rxq

6.23. netdev_rxq_dpdk

6.24. dp_netdev_pmd_thread

6.25. rxq_poll

6.26. tx_port

OVS 架构

OVS 源码结构

数据转发流程

总结

建立一个OVS 交换机

建立的端口信息

使用 ovs-ofctl 建立并测试 OpenFlow 命令

查看 datapath 的信息

屏蔽数据包

修改数据包

重定向数据包

修改数据包的 VLAN Tag

其余 OpenFlow 经常使用的操做

OVS架构解析--dpdk datapath数据通路

https://blog.csdn.net/chen98765432101/article/details/79835435

1. 架构说明

1.1. 总体架构

1.2. 核心组件及其关联关系

1.3. 内部模块及其关联关系

2. vswitchd和ovsdb通讯

2.1. 创建链接

2.2. 接收数据

2.3. json数据解析

2.4. 更新数据改变标记

3. dpdk加速处理

3.1. ovs dpdk加速配置

3.2. dpdk初始化

4. 数据结构抽象关系

4.1. 分层抽象

4.2. 主要数据结构关系

5. vswitchd启动

6. 附录-数据结构查询

6.1. ofproto_class

6.2. dpif_class

6.3. netdev_class