標籤:
簡述: 支援MPTCP的鏈路中存在多條子路徑,因此在發送資料的時候需要選擇最優路徑來進行操作。MPTCP利用核心通知鏈對MPTCP中各子路徑進行增加路徑、刪除路徑、修改路徑優先順序的操作。MPTCP根據相應的策略進行直接選取。
直接選取的代碼實現 直接選取的關鍵在於從多個子路徑中選擇其中一個進行資料的發送。此過程通過下面的函數實現:
"net/mptcp/mptcp_sched.c" line 114 of 496114 static struct sock *get_available_subflow(struct sock *meta_sk,115 struct sk_buff *skb,116 bool zero_wnd_test)117 {118 struct mptcp_cb *mpcb = tcp_sk(meta_sk)->mpcb; //MPTCP核心實現的三個組成部分之一:Multi-path control bock(mpcb) 119 struct sock *sk, *bestsk = NULL, *lowpriosk = NULL, *backupsk = NULL;120 u32 min_time_to_peer = 0xffffffff, lowprio_min_time_to_peer = 0xffffffff;121 int cnt_backups = 0;122123 /* if there is only one subflow, bypass the scheduling function */ 124 if (mpcb->cnt_subflows == 1) {125 bestsk = (struct sock *)mpcb->connection_list;126 if (!mptcp_is_available(bestsk, skb, zero_wnd_test))127 bestsk = NULL;128 return bestsk;129 }130131 /* Answer data_fin on same subflow!!! */132 if (meta_sk->sk_shutdown & RCV_SHUTDOWN &&133 skb && mptcp_is_data_fin(skb)) {134 mptcp_for_each_sk(mpcb, sk) {135 if (tcp_sk(sk)->mptcp->path_index == mpcb->dfin_path_index &&136 mptcp_is_available(sk, skb, zero_wnd_test))137 return sk;138 }139 }View Code第124行的代碼是處理只有一個子路徑的特殊情況。第132行是對關閉操作進行了處理,在收包過程中對接收關閉包的子路徑進行記錄,然後回包的時候使用相同的子路徑。
"net/mptcp/mptcp_input.c" line 876 of 2293875 /* Record it, because we want to send our data_fin on the same path */876 if (tp->mptcp->map_data_fin) {877 mpcb->dfin_path_index = tp->mptcp->path_index;878 mpcb->dfin_combined = !!(sk->sk_shutdown & RCV_SHUTDOWN);879 }第876行是對子路徑關閉的處理,關於data_fin可以參考https://tools.ietf.org/html/rfc6824#section-3.3.3。 下面的代碼遍曆mpcb下管理的sk,選擇最合適的sk。
"net/mptcp/mptcp_sched.c" line 142 of 496141 /* First, find the best subflow */142 mptcp_for_each_sk(mpcb, sk) {143 struct tcp_sock *tp = tcp_sk(sk);144145 if (tp->mptcp->rcv_low_prio || tp->mptcp->low_prio)146 cnt_backups++;147148 if ((tp->mptcp->rcv_low_prio || tp->mptcp->low_prio) &&149 tp->srtt < lowprio_min_time_to_peer) {150 if (!mptcp_is_available(sk, skb, zero_wnd_test))151 continue;152153 if (mptcp_dont_reinject_skb(tp, skb)) {154 backupsk = sk;155 continue;156 }157158 lowprio_min_time_to_peer = tp->srtt;159 lowpriosk = sk;160 } else if (!(tp->mptcp->rcv_low_prio || tp->mptcp->low_prio) &&161 tp->srtt < min_time_to_peer) {162 if (!mptcp_is_available(sk, skb, zero_wnd_test))163 continue;164165 if (mptcp_dont_reinject_skb(tp, skb)) {166 backupsk = sk;167 continue;168 }169170 min_time_to_peer = tp->srtt;171 bestsk = sk;172 }173 }View Code從上面的代碼可以看出,選擇sk的依據有4條:1. “tp->mptcp->rcv_low_prio ” which stands for priority level in the remote machine.2. "tp->mptcp->low_prio" which stands for priority level in the local machine.3. whether the skb has already been enqueued into this subsocket4. "tp->srtt" stands for smoothed round trip time.
"net/mptcp/mptcp_sched.c" line 175 of 496175 if (mpcb->cnt_established == cnt_backups && lowpriosk) {176 sk = lowpriosk; 177 } else if (bestsk) {178 sk = bestsk;179 } else if (backupsk) {180 /* It has been sent on all subflows once - let‘s give it a181 * chance again by restarting its pathmask.182 */183 if (skb)184 TCP_SKB_CB(skb)->path_mask = 0;185 sk = backupsk;186 }187188 return sk;189 }View Code第176行的情況說明所有的子路徑都處於backup狀態。而第178行則是存在bestsk。 總結:1.控制直接選取的因素有下面四個:此路徑在對端機器的優先順序此路徑在本地的優先順序此次發送的skb是否已經使用此路徑發送過,不能在同一路徑重複發送。tp->srtt 2.調整 low_prio 和 rcv_low_prio 可以通過下面命令:
ip link set dev eth0 multipath backup當通訊雙方的一端被設定為backup後,可以通過MP_PRIO通知對端。具體內容可以參考:https://tools.ietf.org/html/rfc6824#section-3.3.8 3.srtt的調整通過函數 tcp_ack_update_rtt 實現。
MPTCP 源碼分析(三) 子路徑選擇