From patchwork Thu May 28 13:02:38 2020 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Florian Westphal X-Patchwork-Id: 1299790 Return-Path: X-Original-To: incoming@patchwork.ozlabs.org Delivered-To: patchwork-incoming@bilbo.ozlabs.org Authentication-Results: ozlabs.org; spf=none (no SPF record) smtp.mailfrom=lists.01.org (client-ip=198.145.21.10; helo=ml01.01.org; envelope-from=mptcp-bounces@lists.01.org; receiver=) Authentication-Results: ozlabs.org; dmarc=none (p=none dis=none) header.from=strlen.de Received: from ml01.01.org (ml01.01.org [198.145.21.10]) (using TLSv1.3 with cipher TLS_AES_256_GCM_SHA384 (256/256 bits) key-exchange X25519 server-signature RSA-PSS (4096 bits) server-digest SHA256) (No client certificate requested) by ozlabs.org (Postfix) with ESMTPS id 49Xntz4Pltz9sSJ for ; Thu, 28 May 2020 23:03:23 +1000 (AEST) Received: from ml01.vlan13.01.org (localhost [IPv6:::1]) by ml01.01.org (Postfix) with ESMTP id A3396122C8664; Thu, 28 May 2020 05:59:03 -0700 (PDT) Received-SPF: Pass (mailfrom) identity=mailfrom; client-ip=2a0a:51c0:0:12e:520::1; helo=chamillionaire.breakpoint.cc; envelope-from=fw@breakpoint.cc; receiver= Received: from Chamillionaire.breakpoint.cc (Chamillionaire.breakpoint.cc [IPv6:2a0a:51c0:0:12e:520::1]) (using TLSv1.3 with cipher TLS_AES_256_GCM_SHA384 (256/256 bits)) (No client certificate requested) by ml01.01.org (Postfix) with ESMTPS id AB87B122C8661 for ; Thu, 28 May 2020 05:59:00 -0700 (PDT) Received: from fw by Chamillionaire.breakpoint.cc with local (Exim 4.92) (envelope-from ) id 1jeIBo-0008Ql-KL; Thu, 28 May 2020 15:03:16 +0200 From: Florian Westphal To: Cc: Florian Westphal Date: Thu, 28 May 2020 15:02:38 +0200 Message-Id: <20200528130239.16498-2-fw@strlen.de> X-Mailer: git-send-email 2.26.2 In-Reply-To: <20200528130239.16498-1-fw@strlen.de> References: <20200528130239.16498-1-fw@strlen.de> MIME-Version: 1.0 Message-ID-Hash: ZNBQV2W6OK7UNP6QKS762QRDRG6EETS7 X-Message-ID-Hash: ZNBQV2W6OK7UNP6QKS762QRDRG6EETS7 X-MailFrom: fw@breakpoint.cc X-Mailman-Rule-Misses: dmarc-mitigation; no-senders; approved; emergency; loop; banned-address; member-moderation; nonmember-moderation; administrivia; implicit-dest; max-recipients; max-size; news-moderation; no-subject; suspicious-header X-Mailman-Version: 3.1.1 Precedence: list Subject: [MPTCP] [PATCH mptcp-next 1/2] selftests: mptcp: add option to specify size of file to transfer List-Id: Discussions regarding MPTCP upstreaming Archived-At: List-Archive: List-Help: List-Post: List-Subscribe: List-Unsubscribe: The script generates two random files that are then sent via tcp and mptcp connections. In order to compare throughput over consecutive runs add an option to provide the file size on the command line: "-f 128000". Also add an option, -t, to enable tcp tests. This is useful to compare throughput of mptcp connections and tcp connections. Example: run tests with a 4mb file size, 300ms delay 0.01% loss, default gso/tso/gro settings and with large write/blocking io: mptcp_connect.sh -t -f $((4 * 1024 * 1024)) -d 300 -l 0.01% -r 0 -e "" -m mmap Signed-off-by: Florian Westphal --- .../selftests/net/mptcp/mptcp_connect.sh | 52 ++++++++++++++----- 1 file changed, 39 insertions(+), 13 deletions(-) diff --git a/tools/testing/selftests/net/mptcp/mptcp_connect.sh b/tools/testing/selftests/net/mptcp/mptcp_connect.sh index acf02e156d20..d9e83efd438b 100755 --- a/tools/testing/selftests/net/mptcp/mptcp_connect.sh +++ b/tools/testing/selftests/net/mptcp/mptcp_connect.sh @@ -3,7 +3,7 @@ time_start=$(date +%s) -optstring="S:R:d:e:l:r:h4cm:" +optstring="S:R:d:e:l:r:h4cm:f:t" ret=0 sin="" sout="" @@ -21,6 +21,8 @@ testmode="" sndbuf=0 rcvbuf=0 options_log=true +do_tcp=0 +filesize=0 if [ $tc_loss -eq 100 ];then tc_loss=1% @@ -40,9 +42,11 @@ usage() { echo -e "\t-e: ethtool features to disable, e.g.: \"-e tso -e gso\" (default: randomly disable any of tso/gso/gro)" echo -e "\t-4: IPv4 only: disable IPv6 tests (default: test both IPv4 and IPv6)" echo -e "\t-c: capture packets for each test using tcpdump (default: no capture)" + echo -e "\t-s: size of file to transfer in bytes (default random)" echo -e "\t-S: set sndbuf value (default: use kernel default)" echo -e "\t-R: set rcvbuf value (default: use kernel default)" echo -e "\t-m: test mode (poll, sendfile; default: poll)" + echo -e "\t-t: also run tests with TCP (use twice to non-fallback tcp)" } while getopts "$optstring" option;do @@ -94,6 +98,12 @@ while getopts "$optstring" option;do "m") testmode="$OPTARG" ;; + "f") + filesize="$OPTARG" + ;; + "t") + do_tcp=$((do_tcp+1)) + ;; "?") usage $0 exit 1 @@ -449,20 +459,25 @@ make_file() { local name=$1 local who=$2 + local SIZE=$filesize + local ksize + local rem - local SIZE TSIZE - SIZE=$((RANDOM % (1024 * 8))) - TSIZE=$((SIZE * 1024)) + if [ $SIZE -eq 0 ]; then + local MAXSIZE=$((1024 * 1024 * 8)) + local MINSIZE=$((1024 * 256)) - dd if=/dev/urandom of="$name" bs=1024 count=$SIZE 2> /dev/null + SIZE=$(((RANDOM * RANDOM + MINSIZE) % MAXSIZE)) + fi - SIZE=$((RANDOM % 1024)) - SIZE=$((SIZE + 128)) - TSIZE=$((TSIZE + SIZE)) - dd if=/dev/urandom conv=notrunc of="$name" bs=1 count=$SIZE 2> /dev/null + ksize=$((SIZE / 1024)) + rem=$((SIZE - (ksize * 1024))) + + dd if=/dev/urandom of="$name" bs=1024 count=$ksize 2> /dev/null + dd if=/dev/urandom conv=notrunc of="$name" bs=1 count=$rem 2> /dev/null echo -e "\nMPTCP_TEST_FILE_END_MARKER" >> "$name" - echo "Created $name (size $TSIZE) containing data sent by $who" + echo "Created $name (size $(du -b "$name")) containing data sent by $who" } run_tests_lo() @@ -497,9 +512,11 @@ run_tests_lo() return 1 fi - # don't bother testing fallback tcp except for loopback case. - if [ ${listener_ns} != ${connector_ns} ]; then - return 0 + if [ $do_tcp -eq 0 ]; then + # don't bother testing fallback tcp except for loopback case. + if [ ${listener_ns} != ${connector_ns} ]; then + return 0 + fi fi do_transfer ${listener_ns} ${connector_ns} MPTCP TCP ${connect_addr} ${local_addr} @@ -516,6 +533,15 @@ run_tests_lo() return 1 fi + if [ $do_tcp -gt 1 ] ;then + do_transfer ${listener_ns} ${connector_ns} TCP TCP ${connect_addr} ${local_addr} + lret=$? + if [ $lret -ne 0 ]; then + ret=$lret + return 1 + fi + fi + return 0 } From patchwork Thu May 28 13:02:39 2020 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Florian Westphal X-Patchwork-Id: 1299791 Return-Path: X-Original-To: incoming@patchwork.ozlabs.org Delivered-To: patchwork-incoming@bilbo.ozlabs.org Authentication-Results: ozlabs.org; spf=none (no SPF record) smtp.mailfrom=lists.01.org (client-ip=198.145.21.10; helo=ml01.01.org; envelope-from=mptcp-bounces@lists.01.org; receiver=) Authentication-Results: ozlabs.org; dmarc=none (p=none dis=none) header.from=strlen.de Received: from ml01.01.org (ml01.01.org [198.145.21.10]) (using TLSv1.3 with cipher TLS_AES_256_GCM_SHA384 (256/256 bits) key-exchange X25519 server-signature RSA-PSS (4096 bits)) (No client certificate requested) by ozlabs.org (Postfix) with ESMTPS id 49Xnv21VJpz9sSF for ; Thu, 28 May 2020 23:03:25 +1000 (AEST) Received: from ml01.vlan13.01.org (localhost [IPv6:::1]) by ml01.01.org (Postfix) with ESMTP id B2903122C8668; Thu, 28 May 2020 05:59:06 -0700 (PDT) Received-SPF: Pass (mailfrom) identity=mailfrom; client-ip=2a0a:51c0:0:12e:520::1; helo=chamillionaire.breakpoint.cc; envelope-from=fw@breakpoint.cc; receiver= Received: from Chamillionaire.breakpoint.cc (Chamillionaire.breakpoint.cc [IPv6:2a0a:51c0:0:12e:520::1]) (using TLSv1.3 with cipher TLS_AES_256_GCM_SHA384 (256/256 bits)) (No client certificate requested) by ml01.01.org (Postfix) with ESMTPS id 4AA30122C85FF for ; Thu, 28 May 2020 05:59:05 -0700 (PDT) Received: from fw by Chamillionaire.breakpoint.cc with local (Exim 4.92) (envelope-from ) id 1jeIBt-0008R5-JC; Thu, 28 May 2020 15:03:21 +0200 From: Florian Westphal To: Cc: Florian Westphal Date: Thu, 28 May 2020 15:02:39 +0200 Message-Id: <20200528130239.16498-3-fw@strlen.de> X-Mailer: git-send-email 2.26.2 In-Reply-To: <20200528130239.16498-1-fw@strlen.de> References: <20200528130239.16498-1-fw@strlen.de> MIME-Version: 1.0 Message-ID-Hash: P2TKBIVP4EFHJRXEIVAV5BQOWUVJNJYX X-Message-ID-Hash: P2TKBIVP4EFHJRXEIVAV5BQOWUVJNJYX X-MailFrom: fw@breakpoint.cc X-Mailman-Rule-Misses: dmarc-mitigation; no-senders; approved; emergency; loop; banned-address; member-moderation; nonmember-moderation; administrivia; implicit-dest; max-recipients; max-size; news-moderation; no-subject; suspicious-header X-Mailman-Version: 3.1.1 Precedence: list Subject: [MPTCP] [PATCH mptcp-next 2/2] mptcp: add receive buffer auto-tuning List-Id: Discussions regarding MPTCP upstreaming Archived-At: List-Archive: List-Help: List-Post: List-Subscribe: List-Unsubscribe: When mptcp is used, userspace doesn't read from the tcp (subflow) socket but from the parent (mptcp) socket receive queue. skbs are moved from the subflow socket to the mptcp rx queue either from 'data_ready' callback (if mptcp socket can be locked), a work queue, or the socket receive function. This means tcp_rcv_space_adjust() is never called and thus no receive buffer size auto-tuning is done. An earlier (not merged) patch added tcp_rcv_space_adjust() calls to the function that moves skbs from subflow to mptcp socket. While this enabled autotuning, it also meant tuning was done even if userspace was reading the mptcp socket very slowly. This adds mptcp_rcv_space_adjust() and calls it after userspace has read data from the mptcp socket rx queue. Its very similar to tcp_rcv_space_adjust, with two differences: 1. The rtt estimate is the largest one observed on a subflow 2. The rcvbuf size and window clamp of all subflows is adjusted to the mptcp-level rcvbuf. Otherwise, we get spurious drops at tcp (subflow) socket level if the skbs are not moved to the mptcp socket fast enough and reduced throughput.. Before: time mptcp_connect.sh -t -f $((4*1024*1024)) -d 300 -l 0.01% -r 0 -e "" -m mmap [..] ns4 MPTCP -> ns3 (10.0.3.2:10108 ) MPTCP (duration 40562ms) [ OK ] ns4 MPTCP -> ns3 (10.0.3.2:10109 ) TCP (duration 5415ms) [ OK ] ns4 TCP -> ns3 (10.0.3.2:10110 ) MPTCP (duration 5413ms) [ OK ] ns4 MPTCP -> ns3 (dead:beef:3::2:10111) MPTCP (duration 41331ms) [ OK ] ns4 MPTCP -> ns3 (dead:beef:3::2:10112) TCP (duration 5415ms) [ OK ] ns4 TCP -> ns3 (dead:beef:3::2:10113) MPTCP (duration 5714ms) [ OK ] Time: 846 seconds After: ns4 MPTCP -> ns3 (10.0.3.2:10108 ) MPTCP (duration 5417ms) [ OK ] ns4 MPTCP -> ns3 (10.0.3.2:10109 ) TCP (duration 5429ms) [ OK ] ns4 TCP -> ns3 (10.0.3.2:10110 ) MPTCP (duration 5418ms) [ OK ] ns4 MPTCP -> ns3 (dead:beef:3::2:10111) MPTCP (duration 5423ms) [ OK ] ns4 MPTCP -> ns3 (dead:beef:3::2:10112) TCP (duration 5715ms) [ OK ] ns4 TCP -> ns3 (dead:beef:3::2:10113) MPTCP (duration 5415ms) [ OK ] Time: 275 seconds Signed-off-by: Florian Westphal Reviewed-by: Christoph Paasch --- net/mptcp/protocol.c | 117 ++++++++++++++++++++++++++++++++++++++++--- net/mptcp/protocol.h | 6 +++ 2 files changed, 116 insertions(+), 7 deletions(-) diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c index b2c8b57e7942..7c1b50ee751b 100644 --- a/net/mptcp/protocol.c +++ b/net/mptcp/protocol.c @@ -207,13 +207,6 @@ static bool __mptcp_move_skbs_from_subflow(struct mptcp_sock *msk, return false; } - if (!(sk->sk_userlocks & SOCK_RCVBUF_LOCK)) { - int rcvbuf = max(ssk->sk_rcvbuf, sk->sk_rcvbuf); - - if (rcvbuf > sk->sk_rcvbuf) - sk->sk_rcvbuf = rcvbuf; - } - tp = tcp_sk(ssk); do { u32 map_remaining, offset; @@ -928,6 +921,95 @@ static int __mptcp_recvmsg_mskq(struct mptcp_sock *msk, return copied; } +/* receive buffer autotuning. See tcp_rcv_space_adjust for more information. + * + * Only difference: Use highest rtt estimate of the subflows in use. + */ +static void mptcp_rcv_space_adjust(struct mptcp_sock *msk, int copied) +{ + struct mptcp_subflow_context *subflow; + struct sock *sk = (struct sock *)msk; + u32 time, advmss = 1; + u64 rtt_us, mstamp; + + sock_owned_by_me(sk); + + if (copied <= 0) + return; + + msk->rcvq_space.copied += copied; + + rtt_us = 0; + mptcp_for_each_subflow(msk, subflow) { + const struct tcp_sock *tp; + u64 sf_rtt_us; + u32 sf_advmss; + + tp = tcp_sk(mptcp_subflow_tcp_sock(subflow)); + + sf_rtt_us = READ_ONCE(tp->rcv_rtt_est.rtt_us); + sf_advmss = READ_ONCE(tp->advmss); + + rtt_us = max(sf_rtt_us, rtt_us); + advmss = max(sf_advmss, advmss); + } + + mstamp = div_u64(tcp_clock_ns(), NSEC_PER_USEC); + + time = tcp_stamp_us_delta(mstamp, msk->rcvq_space.time); + if (time < (rtt_us >> 3) || rtt_us == 0) + return; + + copied = msk->rcvq_space.copied - msk->rcvq_space.seq; + if (copied <= msk->rcvq_space.space) + goto new_measure; + + if (sock_net(sk)->ipv4.sysctl_tcp_moderate_rcvbuf && + !(sk->sk_userlocks & SOCK_RCVBUF_LOCK)) { + int rcvmem, rcvbuf; + u64 rcvwin, grow; + + rcvwin = ((u64)copied << 1) + 16 * advmss; + + grow = rcvwin * (copied - msk->rcvq_space.space); + do_div(grow, msk->rcvq_space.space); + rcvwin += (grow << 1); + + rcvmem = SKB_TRUESIZE(advmss + MAX_TCP_HEADER); + while (tcp_win_from_space(sk, rcvmem) < advmss) + rcvmem += 128; + + do_div(rcvwin, advmss); + rcvbuf = min_t(u64, rcvwin * rcvmem, + sock_net(sk)->ipv4.sysctl_tcp_rmem[2]); + + if (rcvbuf > sk->sk_rcvbuf) { + u32 window_clamp; + + window_clamp = tcp_win_from_space(sk, rcvbuf); + WRITE_ONCE(sk->sk_rcvbuf, rcvbuf); + + /* Make subflows follow along. If we do not do this, we + * get drops at subflow level if skbs can't be moved to + * the mptcp rx queue fast enough (announced rcv_win can + * exceed ssk->sk_rcvbuf). + */ + mptcp_for_each_subflow(msk, subflow) { + struct sock *ssk; + + ssk = mptcp_subflow_tcp_sock(subflow); + WRITE_ONCE(ssk->sk_rcvbuf, rcvbuf); + tcp_sk(ssk)->window_clamp = window_clamp; + } + } + } + + msk->rcvq_space.space = copied; +new_measure: + msk->rcvq_space.seq = msk->rcvq_space.copied; + msk->rcvq_space.time = mstamp; +} + static bool __mptcp_move_skbs(struct mptcp_sock *msk) { unsigned int moved = 0; @@ -1050,6 +1132,8 @@ static int mptcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, set_bit(MPTCP_DATA_READY, &msk->flags); } out_err: + mptcp_rcv_space_adjust(msk, copied); + release_sock(sk); return copied; } @@ -1280,6 +1364,7 @@ static int mptcp_init_sock(struct sock *sk) return ret; sk_sockets_allocated_inc(sk); + sk->sk_rcvbuf = sock_net(sk)->ipv4.sysctl_tcp_rmem[1]; sk->sk_sndbuf = sock_net(sk)->ipv4.sysctl_tcp_wmem[2]; return 0; @@ -1475,6 +1560,21 @@ struct sock *mptcp_sk_clone(const struct sock *sk, return nsk; } +static void mptcp_rcv_space_init(struct mptcp_sock *msk, struct sock *ssk) +{ + struct tcp_sock *tp = tcp_sk(ssk); + + msk->rcvq_space.seq = 0; + msk->rcvq_space.copied = 0; + + tcp_mstamp_refresh(tp); + msk->rcvq_space.time = tp->tcp_mstamp; + + /* initial rcv_space offering made to peer */ + msk->rcvq_space.space = min_t(u32, tp->rcv_wnd, + TCP_INIT_CWND * tp->advmss); +} + static struct sock *mptcp_accept(struct sock *sk, int flags, int *err, bool kern) { @@ -1524,6 +1624,7 @@ static struct sock *mptcp_accept(struct sock *sk, int flags, int *err, list_add(&subflow->node, &msk->conn_list); inet_sk_state_store(newsk, TCP_ESTABLISHED); + mptcp_rcv_space_init(msk, ssk); bh_unlock_sock(new_mptcp_sock); __MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_MPCAPABLEPASSIVEACK); @@ -1678,6 +1779,8 @@ void mptcp_finish_connect(struct sock *ssk) atomic64_set(&msk->snd_una, msk->write_seq); mptcp_pm_new_connection(msk, 0); + + mptcp_rcv_space_init(msk, ssk); } static void mptcp_sock_graft(struct sock *sk, struct socket *parent) diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h index 809687d3f410..f39cfecc22f9 100644 --- a/net/mptcp/protocol.h +++ b/net/mptcp/protocol.h @@ -210,6 +210,12 @@ struct mptcp_sock { struct socket *subflow; /* outgoing connect/listener/!mp_capable */ struct sock *first; struct mptcp_pm_data pm; + struct { + u32 space; + u32 copied; + u32 seq; + u64 time; + } rcvq_space; }; #define mptcp_for_each_subflow(__msk, __subflow) \