260 Commits

Author	SHA1	Message	Date
Neil Alexander	14d48597da	Fix openbsd and netbsd	2018-07-07 12:18:03 +01:00
Neil Alexander	36c89da848	Stick with tcp://localhost:9001 as default for now	2018-07-07 12:16:55 +01:00
Neil Alexander	1692bd98fd	Centralise platform defaults into the 'defaults' package	2018-07-07 12:08:52 +01:00
Arceliar	ba4047b51a	correctly update buffer sizs when buffers overflow, and returned freed packets to the byte store	2018-07-06 17:27:04 -05:00
Arceliar	ad5dc9ea87	Drop 1 packet instead of a whole queue when overflowing	2018-07-06 00:55:00 -05:00
Arceliar	e6a47f705d	when dropping a queue, select one at random based on queue size in bytes	2018-07-06 00:11:36 -05:00
Arceliar	1a65c065d0	prioritize sending from small queues that have been blocked for a long time	2018-07-05 23:56:37 -05:00
Arceliar	7da4967f5e	Limit maximum queue size to 4 MB	2018-07-05 23:39:41 -05:00
Arceliar	a7c8be4d69	base backpressure decisions on queue size in bytes, instead of packet counts	2018-07-05 23:07:01 -05:00
Arceliar	b63b534fa7	drop packets that have been queued for longer than some timeout (currently 25ms) instead of using fixed length queues	2018-06-25 18:12:18 -05:00
Arceliar	7695a3fcbf	try using a simpler FIFO order for each backpressure buffer, since there are other mechanisms to penalize the flooding node, leads to better TCP throughput without affecting traffic between other nodes (does affect traffic in the same session, but there's hypothetically workarounds to that)	2018-06-24 20:20:07 -05:00
Arceliar	4ad2446557	cleanup	2018-06-24 18:21:00 -05:00
Arceliar	03949dcf3f	fix my terrible bug, I have no idea why the old one even worked	2018-06-24 18:05:00 -05:00
Arceliar	9c028e1d0d	switch to a separate queue per stream of traffic, FIXME for some reason this makes distance calculations more expensive in handleIdle?	2018-06-24 17:39:43 -05:00
Arceliar	189628b381	cleanup	2018-06-23 23:55:27 -05:00
Arceliar	0ad801bcfe	more work on backpressure, but still needs more testing	2018-06-23 23:33:03 -05:00
Arceliar	4b83efa218	more backpressure work, still needs testing	2018-06-23 21:51:32 -05:00
Arceliar	52a0027aea	switch refactoring, setup for a better approximation of local backpressure	2018-06-23 20:59:26 -05:00
Arceliar	988f4ad265	add a dedicated switch worker and start using it for lookups	2018-06-23 19:08:32 -05:00
Arceliar	2ae213c255	I'll try sorting, that's a good trick	2018-06-23 01:10:18 -05:00
Arceliar	cceecf4b1a	larger out queue size, make sure linkOut packets always get sent first	2018-06-22 23:46:42 -05:00
Arceliar	0021f3463f	slightly better way for the tcp sender goroutine(s) to block waiting for work	2018-06-22 20:39:57 -05:00
Neil Alexander	f68f779bee	Change box_pub_key to key in admin API	2018-06-22 22:26:17 +01:00
Arceliar	5dfa01a0e8	periodically clean up timed-out sessions and old signatures, instead of trying to do it when creating new sessions or adding new signatures	2018-06-21 20:31:30 -05:00
Arceliar	254be42614	gofmt	2018-06-21 10:39:43 -05:00
Arceliar	19014a198e	randomize the delay after tcp disconnects, to prevent synchronization issues	2018-06-21 10:38:31 -05:00
Arceliar	f599a1a2c1	start the pprof based on an env variable in debug builds, otherwise remove the flag/release.go stuff	2018-06-21 10:32:16 -05:00
Arceliar	496dc94f02	possibly mitigate livelock bug where lossy links lead to constant connect/disconnect cycles due to disagreement about which of the two duplicate autoconnection attempts to use	2018-06-16 15:31:25 -05:00
Arceliar	7fe038f87e	prevent parent nodes from forcing coord oscillation, have dht.handleRes clean up the old request info immediately	2018-06-14 12:32:18 -05:00
Neil Alexander	6c556da05e	Merge pull request #125 from Arceliar/cleanup ... Cleanup	2018-06-14 15:26:34 +01:00
Arceliar	d9c9787611	avoid the proxy.SOCK5 connection attempt unless we're actually going to use the dialer	2018-06-14 09:21:35 -05:00
Arceliar	e8eaabf0c8	comment	2018-06-14 09:12:58 -05:00
Arceliar	57837057b7	tcp/socks cleanup	2018-06-14 09:11:34 -05:00
Arceliar	f7a7f601a0	cleanup old ugly session MTU code that only mattered with lossy UDP fragments	2018-06-14 08:38:43 -05:00
Arceliar	93ffc0b876	macos	2018-06-14 08:00:57 -05:00
Arceliar	e7fca66655	fix address/prefix code, platform specific parts still need testing	2018-06-14 07:58:07 -05:00
Arceliar	330175889e	switch address range from fd00::/8 to the deprecated 0200::/7 range	2018-06-14 07:08:48 -05:00
Arceliar	cd514799da	recover if p.doSend is closed due to a race between peers.doSendSwitchMsgs and peers.removePeer	2018-06-13 00:24:12 -05:00
Arceliar	b006748da4	code cleanup	2018-06-12 17:50:08 -05:00
Arceliar	9ce428af66	Merge pull request #112 from neilalexander/documentation ... Adds more comments to ICMPv6 and TUN/TAP.	2018-06-12 17:11:24 -05:00
Neil Alexander	8e2c2aa977	Document ICMPv6 and TUN/TAP	2018-06-12 22:45:53 +01:00
Arceliar	24228bd381	disable unused configuration Net field and clean up comments to remove mention of UDP where no longer applicable	2018-06-12 14:00:04 -05:00
Arceliar	359af66d0d	exponential dht throttle backoff, and make it based on when packets were sent as part of bootstrapping/maintenance, not when arbitrary packets were received	2018-06-12 03:16:10 -05:00
Arceliar	56802d569e	minor documentation updates, code comments, and a couple of bugfixes that I noticed when going through the code to comment it	2018-06-10 18:03:28 -05:00
Arceliar	038a51fd13	it helps to add new files	2018-06-09 18:44:59 -05:00
Arceliar	72cca4ea43	version check/warning adjustments	2018-06-09 18:38:30 -05:00
Arceliar	076350f963	remove old tcp key exchange code	2018-06-09 17:49:02 -05:00
Arceliar	8733099516	add version metadata to key exchange at the start of connections	2018-06-09 17:46:19 -05:00
Arceliar	f5c850f098	better way to do wire signed ints (no negative zero, remove conditionals)	2018-06-09 16:36:13 -05:00
Arceliar	e5eb6de1f6	add inner crypto to linkProtoTraffic, using ephemeral keys, to prevent replay attacks from spoofing peer connections	2018-06-08 18:42:56 -05:00