diff options
| author | Luke Hoersten <[email protected]> | 2026-06-20 10:39:28 -0500 |
|---|---|---|
| committer | Luke Hoersten <[email protected]> | 2026-06-20 10:39:28 -0500 |
| commit | 6ceebe21c5271c4603493329f4496becbc388ef5 (patch) | |
| tree | 82b7a5349d5727c2da4a08fff117299193b094d6 | |
| parent | 6e36cbc14a06b8c0e15bfe78afb8adb43f8909ba (diff) | |
Revert "firmware: revert lwIP window bump — broke the stream accept path"
This reverts commit 6e36cbc14a06b8c0e15bfe78afb8adb43f8909ba.
| -rw-r--r-- | sdkconfig.defaults | 20 |
1 files changed, 12 insertions, 8 deletions
diff --git a/sdkconfig.defaults b/sdkconfig.defaults index 9e8c9e8..1ba8375 100644 --- a/sdkconfig.defaults +++ b/sdkconfig.defaults @@ -29,14 +29,18 @@ CONFIG_LWIP_IPV4=y CONFIG_LWIP_IPV6=y CONFIG_MDNS_MAX_INTERFACES=1 -# TCP tuning attempted (WND=64k, SND_BUF=64k, RECVMBOX=16, SACK on) -# after the streaming pivot landed. The accept path then silently -# failed — Scrypted's SYN was acked but no client-connected log -# fired, and the stream never moved a byte. Almost certainly lwIP's -# PBUF / MEMP pools weren't scaled to back the larger windows on -# multiple concurrent sockets (httpd has 4, stream has 1). Revisit -# with PBUF_POOL_SIZE + MEMP_NUM_TCP_PCB bumps next time, but for -# now ride the lwIP defaults which sustain ~5.3 MB/s ingest. +# TCP receive-window + buffer tuning. Earlier attempt under HTTP +# regressed because every /frame opened a fresh socket and we ate +# the slow-start cost repeatedly. Under the streaming pivot the +# socket is long-lived: slow-start happens once, then we run with +# the full window for the rest of the session — which is exactly +# the workload these knobs are designed for. Larger WND lets the +# sender keep more bytes in flight per ACK and pushes our recv +# throughput ceiling up from ~5.3 MB/s. +CONFIG_LWIP_TCP_WND_DEFAULT=65535 +CONFIG_LWIP_TCP_SND_BUF_DEFAULT=65535 +CONFIG_LWIP_TCP_RECVMBOX_SIZE=16 +CONFIG_LWIP_TCP_SACK_OUT=y # HTTP server CONFIG_HTTPD_MAX_REQ_HDR_LEN=1024 |
