mptcp: re-enable snd buf autotune
Subsystems (2)
Paolo Abeni
cover mptcp: re-enable snd buf autotune
It was lost in a recent refactor.
With great power come great responsability, so we need a more accurate packet scheduler decision, or b/w usage for assimetric links will be sub-optimal.
Patches 2 && 3 are the minimal changes I was able to cook somehow addressing the above
There are still some sporadic self-test failures for assimetric links. Looks like they are caused by retransmissions/receiver dropping packets due to MPTCP level OoO check.
I'll try to address that asap, but I still consider this series for inclusion, so that it can stage a bit in the export branch.
Note: patch 3 re-introduces the workqueue usage for the datapath (yes, it makes me feel sick, sad and tired :(. I was unable to avoid it.
There is weird and convoluted schema to possibly avoiding (again) the workqueue usage. If you don't feel too scaring using a fake NAPI instance to delegate actions to other mptcp subflows, I can try to cook that...
Paolo Abeni (3):
mptcp: re-enable sndbuf autotune
mptcp: do not queue excessive data on subflows.
mptcp: schedule work for better snd subflow selection
net/mptcp/protocol.c | 85 +++++++++++++++++++++++++------------------- net/mptcp/protocol.h | 20 +++++++++++ net/mptcp/subflow.c | 10 +++++- 3 files changed, 77 insertions(+), 38 deletions(-)
Signature · 1 line
2.26.2
Paolo Abeni
PATCH 1/3 mptcp: re-enable sndbuf autotune
After commit 6e628cd3a8f7 ("mptcp: use mptcp release_cb for delayed tasks"), MPTCP never sets the flag bit SOCK_NOSPACE on its subflow. As a side effect, autotune never takes place, as it happens inside tcp_new_space(), which in turn is called only when the mentioned bit is set.
Let's sendmsg() set the subflows NOSPACE bit when looking for more memory. Additionally, cleanup the sndbuf propagation from subflow into the msk, leveraging the subflow write space callback and dropping a bunch of duplicate code.
This also makes the SNDBUF_LIMITED chrono relevant again for MPTCP subflows.
--- net/mptcp/protocol.c | 70 ++++++++++++++++++++++++-------------------- net/mptcp/protocol.h | 20 +++++++++++++ net/mptcp/subflow.c | 10 ++++++- 3 files changed, 67 insertions(+), 33 deletions(-)
net/mptcp/protocol.c +38 -32
@@ -734,10 +734,14 @@ void mptcp_data_ready(struct sock *sk, struct sock *ssk)void __mptcp_flush_join_list (struct mptcp_sock *msk) { +struct mptcp_subflow_context *subflow; +if (likely (list_empty (&msk->join_list)))return ;spin_lock_bh (&msk->join_list_lock); +list_for_each_entry (subflow, &msk->join_list, node) +mptcp_propagate_sndbuf ((struct sock *)msk,mptcp_subflow_tcp_sock (subflow));list_splice_tail_init (&msk->join_list, &msk->conn_list);spin_unlock_bh (&msk->join_list_lock); }
@@ -1037,13 +1041,7 @@ static void __mptcp_clean_una(struct sock *sk)__mptcp_update_wmem (sk);sk_mem_reclaim_partial (sk); } - -if (sk_stream_is_writeable (sk)) { -/* pairs with memory barrier in mptcp_poll */ -smp_mb (); -if (test_and_clear_bit (MPTCP_NOSPACE , &msk->flags)) -sk_stream_write_space (sk); - } +mptcp_write_space (sk); }if (snd_una ==READ_ONCE (msk->snd_nxt)) {
@@ -1351,6 +1349,26 @@ static int mptcp_sendmsg_frag(struct sock *sk, struct sock *ssk,return ret; } +static void mptcp_start_sndbuf_autotune (struct mptcp_sock *msk) +{ +struct mptcp_subflow_context *subflow; + +mptcp_for_each_subflow (msk, subflow) { +struct sock *ssk =mptcp_subflow_tcp_sock (subflow); +struct socket *sock; + +/* on all active, unorphaned, subflows matching the current +* msk backup status +*/ +if (!mptcp_subflow_active (subflow) || + subflow->backup != msk->use_backup || + !(sock =READ_ONCE (ssk->sk_socket))) +continue ; + +set_bit (SOCK_NOSPACE , &sock->flags); + } +} +#define MPTCP_SEND_BURST_SIZE ((1 << 16) - \ sizeof(struct tcphdr) - \ MAX_TCP_OPTION_SPACE - \
@@ -1362,8 +1380,7 @@ struct subflow_send_info {u64 ratio; }; -static struct sock *mptcp_subflow_get_send (struct mptcp_sock *msk, -u32 *sndbuf) +static struct sock *mptcp_subflow_get_send (struct mptcp_sock *msk) {struct subflow_send_info send_info[2 ];struct mptcp_subflow_context *subflow;
@@ -1374,24 +1391,17 @@ static struct sock *mptcp_subflow_get_send(struct mptcp_sock *msk,sock_owned_by_me ((struct sock *)msk); - *sndbuf =0 ;if (__mptcp_check_fallback (msk)) {if (!msk->first)return NULL ; - *sndbuf = msk->first->sk_sndbuf;return sk_stream_memory_free (msk->first) ? msk->first :NULL ; }/* re-use last subflow, if the burst allow that */ if (msk->last_snd && msk->snd_burst >0 &&sk_stream_memory_free (msk->last_snd) && -mptcp_subflow_active (mptcp_subflow_ctx (msk->last_snd))) { -mptcp_for_each_subflow (msk, subflow) { - ssk =mptcp_subflow_tcp_sock (subflow); - *sndbuf =max (tcp_sk (ssk)->snd_wnd, *sndbuf); - } +mptcp_subflow_active (mptcp_subflow_ctx (msk->last_snd)))return msk->last_snd; - }/* pick the subflow with the lower wmem/wspace ratio */ for (i =0 ; i <2 ; ++i) {
@@ -1404,7 +1414,6 @@ static struct sock *mptcp_subflow_get_send(struct mptcp_sock *msk,continue ; nr_active += !subflow->backup; - *sndbuf =max (tcp_sk (ssk)->snd_wnd, *sndbuf);if (!sk_stream_memory_free (subflow->tcp_sock))continue ;
@@ -1425,7 +1434,8 @@ static struct sock *mptcp_subflow_get_send(struct mptcp_sock *msk, send_info[1].ssk, send_info[1].ratio);/* pick the best backup if no other subflow is active */ -if (!nr_active) + msk->use_backup = !nr_active; +if (msk->use_backup) send_info[0 ].ssk = send_info[1 ].ssk;if (send_info[0 ].ssk) {
@@ -1434,6 +1444,7 @@ static struct sock *mptcp_subflow_get_send(struct mptcp_sock *msk, sk_stream_wspace(msk->last_snd));return msk->last_snd; } +return NULL ; }
@@ -1454,7 +1465,6 @@ static void mptcp_push_pending(struct sock *sk, unsigned int flags) };struct mptcp_data_frag *dfrag;int len, copied =0 ; -u32 sndbuf;while ((dfrag =mptcp_send_head (sk))) { info.sent = dfrag->already_sent;
@@ -1465,12 +1475,7 @@ static void mptcp_push_pending(struct sock *sk, unsigned int flags) prev_ssk = ssk;__mptcp_flush_join_list (msk); - ssk =mptcp_subflow_get_send (msk, &sndbuf); - -/* do auto tuning */ -if (!(sk->sk_userlocks &SOCK_SNDBUF_LOCK ) && - sndbuf >READ_ONCE (sk->sk_sndbuf)) -WRITE_ONCE (sk->sk_sndbuf, sndbuf); + ssk =mptcp_subflow_get_send (msk);/* try to keep the subflow socket lock across * consecutive xmit on the same socket
@@ -1537,11 +1542,6 @@ static void __mptcp_subflow_push_pending(struct sock *sk, struct sock *ssk)while (len >0 ) {int ret =0 ; -/* do auto tuning */ -if (!(sk->sk_userlocks &SOCK_SNDBUF_LOCK ) && - ssk->sk_sndbuf >READ_ONCE (sk->sk_sndbuf)) -WRITE_ONCE (sk->sk_sndbuf, ssk->sk_sndbuf); -if (unlikely (mptcp_must_reclaim_memory (sk, ssk))) {__mptcp_update_wmem (sk);sk_mem_reclaim_partial (sk);
@@ -1680,6 +1680,7 @@ static int mptcp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)continue ; wait_for_memory: +mptcp_start_sndbuf_autotune (msk);set_bit (MPTCP_NOSPACE , &msk->flags);mptcp_push_pending (sk, msg->msg_flags); ret =sk_stream_wait_memory (sk, &timeo);
@@ -1687,8 +1688,11 @@ static int mptcp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) goto out; } -if (copied) +if (copied) { +if (!sk_stream_is_writeable (sk)) +mptcp_start_sndbuf_autotune (msk);mptcp_push_pending (sk, msg->msg_flags); + } out:release_sock (sk);
@@ -2359,6 +2363,7 @@ static int __mptcp_init_sock(struct sock *sk) msk->tx_pending_data =0 ; msk->size_goal_cache =TCP_BASE_MSS ; + msk->use_backup = false; msk->ack_hint =NULL ; msk->first =NULL ;inet_csk (sk)->icsk_sync_mss = mptcp_sync_mss;
@@ -3285,6 +3290,7 @@ static int mptcp_stream_accept(struct socket *sock, struct socket *newsock,mptcp_copy_inaddrs (newsk, msk->first);mptcp_rcv_space_init (msk, msk->first); +mptcp_propagate_sndbuf (newsk, msk->first);/* set ssk->sk_socket of accept()ed flows to mptcp socket. * This is needed so NOSPACE flag can be set from tcp stack.
net/mptcp/protocol.h +20 -0
@@ -248,6 +248,7 @@ struct mptcp_sock {bool snd_data_fin_enable;bool rcv_fastclose;bool use_64bit_ack;/* Set when we received a 64-bit DSN */ +bool use_backup;/* only backup subflow available */ spinlock_t join_list_lock;struct sock *ack_hint;struct work_struct work;
@@ -521,6 +522,25 @@ static inline bool mptcp_data_fin_enabled(const struct mptcp_sock *msk)READ_ONCE (msk->write_seq) ==READ_ONCE (msk->snd_nxt); } +static inline bool mptcp_propagate_sndbuf (struct sock *sk,struct sock *ssk) +{ +if ((sk->sk_userlocks &SOCK_SNDBUF_LOCK ) || ssk->sk_sndbuf <=READ_ONCE (sk->sk_sndbuf)) +return false; + +WRITE_ONCE (sk->sk_sndbuf, ssk->sk_sndbuf); +return true; +} + +static inline void mptcp_write_space (struct sock *sk) +{ +if (sk_stream_is_writeable (sk)) { +/* pairs with memory barrier in mptcp_poll */ +smp_mb (); +if (test_and_clear_bit (MPTCP_NOSPACE , &mptcp_sk (sk)->flags)) +sk_stream_write_space (sk); + } +} +void mptcp_destroy_common (struct mptcp_sock *msk);void __init mptcp_token_init (void );
net/mptcp/subflow.c +9 -1
@@ -343,6 +343,7 @@ static void subflow_finish_connect(struct sock *sk, const struct sk_buff *skb)if (subflow->conn_finished)return ; +mptcp_propagate_sndbuf (parent, sk); subflow->rel_write_seq =1 ; subflow->conn_finished =1 ; subflow->ssn_offset =TCP_SKB_CB (skb)->seq;
@@ -1040,7 +1041,13 @@ static void subflow_data_ready(struct sock *sk)static void subflow_write_space (struct sock *ssk) { -/* we take action in __mptcp_clean_una() */ +struct socket *sock = ssk->sk_socket; + +if (mptcp_propagate_sndbuf (mptcp_subflow_ctx (ssk)->conn, ssk)) +mptcp_write_space (ssk); + +if (sk_stream_is_writeable (ssk) && sock) +clear_bit (SOCK_NOSPACE , &sock->flags); } static struct inet_connection_sock_af_ops *
@@ -1299,6 +1306,7 @@ static void subflow_state_change(struct sock *sk)__subflow_state_change (sk);if (subflow_simultaneous_connect (sk)) { +mptcp_propagate_sndbuf (parent, sk);mptcp_do_fallback (sk);mptcp_rcv_space_init (mptcp_sk (parent), sk);pr_fallback (mptcp_sk (parent));
Signature · 1 line
2.26.2
Paolo Abeni
PATCH 2/3 mptcp: do not queue excessive data on subflows.
In reply to Paolo AbeniThe current packet scheduler can enqueue up to sndbuf data on each subflow. If the send buffer is large and the subflows are not symmetric, this could lead to suboptimal aggregate bandwidth utilization.
Limit the amount of queued data to the maximum cwnd.
--- net/mptcp/protocol.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-)
net/mptcp/protocol.c +2 -2
@@ -1414,7 +1414,7 @@ static struct sock *mptcp_subflow_get_send(struct mptcp_sock *msk)continue ; nr_active += !subflow->backup; -if (!sk_stream_memory_free (subflow->tcp_sock)) +if (!sk_stream_memory_free (subflow->tcp_sock) || !tcp_sk (ssk)->snd_wnd)continue ; pace =READ_ONCE (ssk->sk_pacing_rate);
@@ -1441,7 +1441,7 @@ static struct sock *mptcp_subflow_get_send(struct mptcp_sock *msk)if (send_info[0 ].ssk) { msk->last_snd = send_info[0 ].ssk; msk->snd_burst =min_t (int,MPTCP_SEND_BURST_SIZE , -sk_stream_wspace (msk->last_snd)); +tcp_sk (msk->last_snd)->snd_wnd);return msk->last_snd; }
Signature · 1 line
2.26.2
Paolo Abeni
PATCH 3/3 mptcp: schedule work for better snd subflow selection
In reply to Paolo AbeniOtherwise the packet scheduler policy will not be enforced when pushing pending data at MPTCP-level ack reception time.
---
I'm very sad to re-introduce the worker usage for the datapath, but I could not find an easy way to avoid it.
I'm thinking of some weird schema involving a dummy percpu napi instance serving/processing a queue of mptcp sockets instead of actual packets. Any BH user can enqueue an MPTCP subflow there to delegate some action to the latter.
The above will require also overriding the tcp_release_cb() with something able to process this delegated events.
Yep, crazy, but possibly doable without any core change and possibly could be used to avoid the worker usage even for data fin processing/sending.
--- net/mptcp/protocol.c | 11 ++++++++--- 1 file changed, 8 insertions(+), 3 deletions(-)
net/mptcp/protocol.c +8 -3
@@ -2271,6 +2271,7 @@ static void mptcp_worker(struct work_struct *work)if (unlikely (state ==TCP_CLOSE )) goto unlock; +mptcp_push_pending (sk,0 );mptcp_check_data_fin_ack (sk);__mptcp_flush_join_list (msk);
@@ -2934,10 +2935,14 @@ void __mptcp_check_push(struct sock *sk, struct sock *ssk)if (!mptcp_send_head (sk))return ; -if (!sock_owned_by_user (sk)) -__mptcp_subflow_push_pending (sk, ssk); -else +if (!sock_owned_by_user (sk)) { +if (mptcp_subflow_get_send (mptcp_sk (sk)) == ssk) +__mptcp_subflow_push_pending (sk, ssk); +else +mptcp_schedule_work (sk); + }else {set_bit (MPTCP_PUSH_PENDING , &mptcp_sk (sk)->flags); + } }#define MPTCP_DEFERRED_ALL (TCPF_WRITE_TIMER_DEFERRED)
Signature · 1 line
2.26.2