continuum - P2P replicated document storage service

	Commit message (Collapse)	Author	Age	Files	Lines
...
*	push changes experiment	tv	8 days	1	-16/+78
\|
*	suspect paths	tv	8 days	1	-0/+5
\|
*	last chunks from two	tv	8 days	1	-1/+55
\|
*	unreached sources hand over	tv	8 days	1	-1/+26
\|
*	chunk timeout adapts	tv	8 days	1	-6/+74
\|
*	manifests asked at once	tv	8 days	1	-45/+57
\|
*	measure deflated chunks	tv	8 days	2	-8/+28
\|
*	deflate blob chunks	tv	8 days	2	-5/+29
\|
*	deflate blob chunks	tv	8 days	2	-5/+44
\|
*	epoch tag in sync	tv	8 days	2	-9/+34
\|
*	no swarm ID in sync	tv	8 days	2	-24/+9
\|
*	announce only to those behind	tv	8 days	2	-12/+31
\|
*	measure sync envelopes	tv	8 days	2	-0/+24
\|
*	dashboard: swarm-wide epoch shine	tv	8 days	1	-8/+31
\|
*	asked known elsewhere	tv	8 days	3	-2/+23
\|
*	predecessors go along	tv	8 days	1	-3/+18
\|
*	covered neighbours have it	tv	8 days	3	-16/+54
\|
*	new changes per message	tv	8 days	2	-1/+10
\|
*	neigbours by transport	tv	8 days	1	-1/+21
\|
*	own tree shape	tv	8 days	1	-10/+136
\|
*	drop full mesh stat	tv	8 days	1	-3/+7
\|
*	delta from held heads	tv	8 days	1	-1/+4
\|
*	offer again ungenerated	tv	8 days	1	-32/+53
\|
*	stale delta offers	tv	8 days	1	-0/+19
\|
*	blob window grows	tv	8 days	1	-5/+10
\|
*	delta known to sender	tv	8 days	1	-1/+7
\|
*	delta propagation	tv	8 days	2	-2/+18
\|
*	one delta at a time	tv	8 days	2	-9/+53
\|
*	time blob messages	tv	8 days	4	-4/+46
\|
*	log why a delta	tv	8 days	1	-0/+6
\|
*	offered deltas lapse	tv	8 days	1	-4/+14
\|
*	throughput from delivered message	tv	8 days	2	-2/+59
\|
*	hop delays	tv	8 days	4	-2/+128
\|
*	benchmark delays by path	tv	8 days	2	-0/+15
\|
*	fix: change publisher stops with the runtime	tv	8 days	1	-3/+8
\|
*	benchmark what sync bytes are	tv	8 days	2	-3/+30
\|
*	changes from a peer never go back	tv	8 days	1	-0/+4
\|
*	older delivered messages leave us level	tv	8 days	1	-1/+3
\|
*	benchmark where twice comes from	tv	8 days	2	-4/+11
\|
*	resend only what is needed	tv	8 days	1	-1/+1
\|
*	benchmark delivered and twice	tv	8 days	2	-0/+30
\|
*	any message taken as delivered	tv	8 days	2	-13/+23
\|
*	slow round back off	tv	8 days	2	-5/+86
\|
*	tree messages need no answer	tv	8 days	3	-6/+40
\|
*	hello again when heard from	tv	8 days	2	-2/+19
\| \| \| \| \| \|	While we wait for a peer's HELLO_REPLY, anything else that comes from it makes our HELLO go again at once, at most once a second, instead of when the backoff says.
*	unanswered pull frees the slot	tv	9 days	2	-1/+23
\| \| \| \| \| \|	When the answer to a pull is overdue (the sync reply timeout: 1 s in the simtests, 10 s in production), the pull gives up the slot, and the next waiting neighbour is pulled at once.
*	overdue sync asked after from then	tv	9 days	2	-4/+4
\|
*	pull after grace	tv	9 days	2	-4/+33
\| \| \| \| \| \| \| \|	Before pulling, a node waits one measured round trip to the announcer (1 s at most) and pulls only what is still missing. If the round trip isn't known yet, it pulls at once, as now. On the clean benchmark links the round trip is a few milliseconds, so those scenarios shouldn't change.
*	announcements answered when lacking	tv	9 days	4	-10/+34
\| \| \| \| \| \| \|	A neighbour now answers an announcement only if it lacks some of the announced heads. Heads that merely differ are no longer enough, since they do while writes go on. The check reads the document, so it runs off the message consumer, as the pull check already does.
*	unanswered members not reached	tv	10 days	2	-14/+43
\|