From d24729693d97d505e63d789e43a70b16759ddd51 Mon Sep 17 00:00:00 2001 From: Victor Boivie Date: Mon, 10 May 2021 20:21:17 +0200 Subject: [PATCH] dcsctp: Disable TCP style slow start Due to a limit socket send buffer, it's quite easy to fill it up when using exponential slow start, which results in dropping a lot of packets and having to retransmit those. Disabling this, to align it to how SCTP normally behaves, and then try to stabilize it later. With SCTP slow start, it will increase with one MTU for each RTT when there is no packet loss. Even this mode will experience packet loss, but not as much will be lost, and it will stabilize quicker. Bug: webrtc:12614 Change-Id: Ibc484b19b7e708fe5bd837bbef178a2f69b7211f Reviewed-on: https://webrtc-review.googlesource.com/c/src/+/218203 Reviewed-by: Florent Castelli Commit-Queue: Victor Boivie Cr-Commit-Position: refs/heads/master@{#33969} --- net/dcsctp/public/dcsctp_options.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/dcsctp/public/dcsctp_options.h b/net/dcsctp/public/dcsctp_options.h index 692bed3bee..08893fda29 100644 --- a/net/dcsctp/public/dcsctp_options.h +++ b/net/dcsctp/public/dcsctp_options.h @@ -115,7 +115,7 @@ struct DcSctpOptions { DurationMs delayed_ack_max_timeout = DurationMs(200); // Do slow start as TCP - double cwnd instead of increasing it by MTU. - bool slow_start_tcp_style = true; + bool slow_start_tcp_style = false; // The initial congestion window size, in number of MTUs. // See https://tools.ietf.org/html/rfc4960#section-7.2.1 which defaults at ~3