Re: [PATCH RFT 4/5] tcp, tap: Don't increase tap-side sequence counter for dropped frames

[David Gibson <david@gibson.dropbear.id.au>]

[-- Attachment #1: Type: text/plain, Size: 8687 bytes --]

On Sat, Sep 23, 2023 at 12:06:09AM +0200, Stefano Brivio wrote:
> ...so that we'll retry sending them, instead of more-or-less silently
> dropping them. This happens quite frequently if our sending buffer on
> the UNIX domain socket is heavily constrained (for instance, by the
> 208 KiB default memory limit).
> 
> It might be argued that dropping frames is part of the expected TCP
> flow: we don't dequeue those from the socket anyway, so we'll
> eventually retransmit them.
> 
> But we don't need the receiver to tell us (by the way of duplicate or
> missing ACKs) that we couldn't send them: we already know as
> sendmsg() reports that. This seems to considerably increase
> throughput stability and throughput itself for TCP connections with
> default wmem_max values.
> 
> Unfortunately, the 16 bits left as padding in the frame descriptors

I assume you're referring to the 'pad' fields in tcp[46]_l2_buf_t,
yes?  For AVX2 we have substantially more space here.  Couldn't we put
a conn (or seq) pointer in here at the cost of a few bytes MSS for
non-AVX2 and zero cost for AVX2 (which is probably the majority case)?

> we use internally aren't enough to uniquely identify for which
> connection we should update sequence numbers: create a parallel
> array of pointers to sequence numbers and L4 lengths, of
> TCP_FRAMES_MEM size, and go through it after calling sendmsg().
> 
> Signed-off-by: Stefano Brivio <sbrivio@redhat.com>
> ---
>  tap.c | 10 +++++++---
>  tap.h |  2 +-
>  tcp.c | 43 ++++++++++++++++++++++++++++++++++++-------
>  3 files changed, 44 insertions(+), 11 deletions(-)
> 
> diff --git a/tap.c b/tap.c
> index 93db989..b30ff81 100644
> --- a/tap.c
> +++ b/tap.c
> @@ -413,13 +413,15 @@ static size_t tap_send_frames_passt(const struct ctx *c,
>   * @c:		Execution context
>   * @iov:	Array of buffers, each containing one frame (with L2 headers)
>   * @n:		Number of buffers/frames in @iov
> + *
> + * Return: number of frames actually sent
>   */
> -void tap_send_frames(struct ctx *c, const struct iovec *iov, size_t n)
> +size_t tap_send_frames(struct ctx *c, const struct iovec *iov, size_t n)
>  {
>  	size_t m;
>  
>  	if (!n)
> -		return;
> +		return 0;
>  
>  	if (c->mode == MODE_PASST)
>  		m = tap_send_frames_passt(c, iov, n);
> @@ -427,9 +429,11 @@ void tap_send_frames(struct ctx *c, const struct iovec *iov, size_t n)
>  		m = tap_send_frames_pasta(c, iov, n);
>  
>  	if (m < n)
> -		debug("tap: dropped %lu frames of %lu due to short send", n - m, n);
> +		debug("tap: failed to send %lu frames of %lu", n - m, n);
>  
>  	pcap_multiple(iov, m, c->mode == MODE_PASST ? sizeof(uint32_t) : 0);
> +
> +	return m;
>  }
>  
>  /**
> diff --git a/tap.h b/tap.h
> index 021fb7c..952fafc 100644
> --- a/tap.h
> +++ b/tap.h
> @@ -73,7 +73,7 @@ void tap_icmp6_send(const struct ctx *c,
>  		    const struct in6_addr *src, const struct in6_addr *dst,
>  		    void *in, size_t len);
>  int tap_send(const struct ctx *c, const void *data, size_t len);
> -void tap_send_frames(struct ctx *c, const struct iovec *iov, size_t n);
> +size_t tap_send_frames(struct ctx *c, const struct iovec *iov, size_t n);
>  void tap_update_mac(struct tap_hdr *taph,
>  		    const unsigned char *eth_d, const unsigned char *eth_s);
>  void tap_listen_handler(struct ctx *c, uint32_t events);
> diff --git a/tcp.c b/tcp.c
> index 4606f17..76b7b8d 100644
> --- a/tcp.c
> +++ b/tcp.c
> @@ -434,6 +434,16 @@ static int tcp_sock_ns		[NUM_PORTS][IP_VERSIONS];
>   */
>  static union inany_addr low_rtt_dst[LOW_RTT_TABLE_SIZE];
>  
> +/**
> + * tcp_buf_seq_update - Sequences to update with length of frames once sent
> + * @seq:	Pointer to sequence number sent to tap-side, to be updated
> + * @len:	TCP payload length
> + */
> +struct tcp_buf_seq_update {
> +	uint32_t *seq;
> +	uint16_t len;
> +};
> +
>  /* Static buffers */
>  
>  /**
> @@ -462,6 +472,8 @@ static struct tcp4_l2_buf_t {
>  #endif
>  tcp4_l2_buf[TCP_FRAMES_MEM];
>  
> +static struct tcp_buf_seq_update tcp4_l2_buf_seq_update[TCP_FRAMES_MEM];
> +
>  static unsigned int tcp4_l2_buf_used;
>  
>  /**
> @@ -490,6 +502,8 @@ struct tcp6_l2_buf_t {
>  #endif
>  tcp6_l2_buf[TCP_FRAMES_MEM];
>  
> +static struct tcp_buf_seq_update tcp6_l2_buf_seq_update[TCP_FRAMES_MEM];
> +
>  static unsigned int tcp6_l2_buf_used;
>  
>  /* recvmsg()/sendmsg() data for tap */
> @@ -1369,10 +1383,17 @@ static void tcp_l2_flags_buf_flush(struct ctx *c)
>   */
>  static void tcp_l2_data_buf_flush(struct ctx *c)
>  {
> -	tap_send_frames(c, tcp6_l2_iov, tcp6_l2_buf_used);
> +	unsigned i;
> +	size_t m;
> +
> +	m = tap_send_frames(c, tcp6_l2_iov, tcp6_l2_buf_used);
> +	for (i = 0; i < m; i++)
> +		*tcp6_l2_buf_seq_update[i].seq += tcp6_l2_buf_seq_update[i].len;
>  	tcp6_l2_buf_used = 0;
>  
> -	tap_send_frames(c, tcp4_l2_iov, tcp4_l2_buf_used);
> +	m = tap_send_frames(c, tcp4_l2_iov, tcp4_l2_buf_used);
> +	for (i = 0; i < m; i++)
> +		*tcp4_l2_buf_seq_update[i].seq += tcp4_l2_buf_seq_update[i].len;
>  	tcp4_l2_buf_used = 0;
>  }
>  
> @@ -2149,10 +2170,11 @@ static int tcp_sock_consume(struct tcp_tap_conn *conn, uint32_t ack_seq)
>   * @plen:	Payload length at L4
>   * @no_csum:	Don't compute IPv4 checksum, use the one from previous buffer
>   * @seq:	Sequence number to be sent
> - * @now:	Current timestamp
> + * @seq_update:	Pointer to sequence number to update on successful send
>   */
>  static void tcp_data_to_tap(struct ctx *c, struct tcp_tap_conn *conn,
> -			    ssize_t plen, int no_csum, uint32_t seq)
> +			    ssize_t plen, int no_csum, uint32_t seq,
> +			    uint32_t *seq_update)

seq_update is always &conn->seq_to_tap, so there's no need for an
additional parameter.

>  {
>  	struct iovec *iov;
>  
> @@ -2160,6 +2182,9 @@ static void tcp_data_to_tap(struct ctx *c, struct tcp_tap_conn *conn,
>  		struct tcp4_l2_buf_t *b = &tcp4_l2_buf[tcp4_l2_buf_used];
>  		uint16_t *check = no_csum ? &(b - 1)->iph.check : NULL;
>  
> +		tcp4_l2_buf_seq_update[tcp4_l2_buf_used].seq = seq_update;
> +		tcp4_l2_buf_seq_update[tcp4_l2_buf_used].len = plen;
> +
>  		iov = tcp4_l2_iov + tcp4_l2_buf_used++;
>  		iov->iov_len = tcp_l2_buf_fill_headers(c, conn, b, plen,
>  						       check, seq);
> @@ -2168,6 +2193,9 @@ static void tcp_data_to_tap(struct ctx *c, struct tcp_tap_conn *conn,
>  	} else if (CONN_V6(conn)) {
>  		struct tcp6_l2_buf_t *b = &tcp6_l2_buf[tcp6_l2_buf_used];
>  
> +		tcp6_l2_buf_seq_update[tcp6_l2_buf_used].seq = seq_update;
> +		tcp6_l2_buf_seq_update[tcp6_l2_buf_used].len = plen;
> +
>  		iov = tcp6_l2_iov + tcp6_l2_buf_used++;
>  		iov->iov_len = tcp_l2_buf_fill_headers(c, conn, b, plen,
>  						       NULL, seq);
> @@ -2193,7 +2221,7 @@ static int tcp_data_from_sock(struct ctx *c, struct tcp_tap_conn *conn)
>  	int s = conn->sock, i, ret = 0;
>  	struct msghdr mh_sock = { 0 };
>  	uint16_t mss = MSS_GET(conn);
> -	uint32_t already_sent;
> +	uint32_t already_sent, seq;
>  	struct iovec *iov;
>  
>  	already_sent = conn->seq_to_tap - conn->seq_ack_from_tap;
> @@ -2282,14 +2310,15 @@ static int tcp_data_from_sock(struct ctx *c, struct tcp_tap_conn *conn)
>  
>  	/* Finally, queue to tap */
>  	plen = mss;
> +	seq = conn->seq_to_tap;

This will only be correct if tcp_l2_data_buf_flush() is *always*
called between tcp_data_from_sock() calls for the same socket.  That
should be true for the normal course of things.  However, couldn't it
happen that we get a normal socket EPOLLIN event for a particular
connection - calling tcp_data_from_sock() - but in the same epoll()
round we also get a tap ack for the same connection which causes
another call to tcp_data_from_sock() (with the change from patch
2/5).  IIRC those would both happen before the deferred handling and
therefore the data_buf_flush().

Not sure how to deal with that short of separate 'seq_queued' and
'seq_sent' counters in the connection structure, which is a bit
unfortunate.

>  	for (i = 0; i < send_bufs; i++) {
>  		int no_csum = i && i != send_bufs - 1 && tcp4_l2_buf_used;
>  
>  		if (i == send_bufs - 1)
>  			plen = last_len;
>  
> -		tcp_data_to_tap(c, conn, plen, no_csum, conn->seq_to_tap);
> -		conn->seq_to_tap += plen;
> +		tcp_data_to_tap(c, conn, plen, no_csum, seq, &conn->seq_to_tap);
> +		seq += plen;
>  	}
>  
>  	conn_flag(c, conn, ACK_FROM_TAP_DUE);

-- 
David Gibson			| I'll have my music baroque, and my code
david AT gibson.dropbear.id.au	| minimalist, thank you.  NOT _the_ _other_
				| _way_ _around_!
http://www.ozlabs.org/~dgibson

[-- Attachment #2: signature.asc --]
[-- Type: application/pgp-signature, Size: 833 bytes --]