aboutsummaryrefslogtreecommitdiffstats
path: root/docs
Commit message (Collapse)AuthorAgeFilesLines
* predecessors go alongtv3 days1-1/+5
|
* covered neighbours have ittv3 days1-0/+8
|
* asked again countertv3 days2-1/+5
|
* neigbours by transporttv3 days2-1/+7
|
* own tree shapetv3 days2-2/+25
|
* drop full mesh stattv3 days2-4/+1
|
* bench mycelium round tripstv3 days1-2/+3
|
* delta from held headstv3 days1-2/+3
|
* offer again ungeneratedtv3 days1-1/+2
|
* stale delta offerstv3 days1-0/+3
|
* delta known to sendertv3 days1-1/+2
|
* delta propagationtv3 days1-1/+2
|
* benchmark bridge fast linktv3 days1-2/+3
|
* benchmark bridge slow linktv3 days1-1/+2
|
* benchmark bridgetv3 days1-1/+4
|
* one delta at a timetv3 days1-1/+5
|
* time blob messagestv3 days3-4/+4
|
* dashboard: hop delaystv3 days1-0/+1
|
* throughput from delivered messagetv3 days1-1/+1
|
* hop delaystv3 days2-0/+33
|
* benchmark members joiningtv3 days1-3/+3
|
* document messages that overtaketv3 days1-4/+20
|
* any message taken as deliveredtv3 days1-7/+9
|
* slow round back offtv3 days2-5/+10
|
* tree messages need no answertv3 days1-3/+10
|
* hello again when heard fromtv3 days1-1/+4
| | | | | | 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 slottv3 days1-3/+4
| | | | | | 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.
* no heal while both move ontv4 days2-2/+2
| | | | | | | The heal clock now also restarts when our heads and the peer's have both changed since the last STATUS that showed them differing. While writes go on, two neighbours's heads differ because of changes still on their way, and that alone no longer leads to a heal.
* pull after gracetv4 days1-1/+3
| | | | | | | | 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 lackingtv4 days2-3/+4
| | | | | | | 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 reachedtv4 days2-6/+11
|
* add member away benchmarktv4 days1-1/+2
|
* dashboard: show reach settv4 days1-0/+1
|
* dashboard: show writer treestv4 days2-0/+44
|
* update architecture doctv4 days1-4/+7
|
* writers from authorstv4 days1-5/+7
|
* reach set for the sessiontv5 days2-3/+5
|
* tree changes had alreadytv5 days1-1/+3
|
* announcement round counterstv5 days2-1/+7
|
* docs after treestv5 days1-1/+1
|
* announce what trees misstv5 days1-1/+6
|
* parallel propagation benchmarktv5 days1-1/+3
|
* quicker propagation benchmarktv5 days1-1/+2
|
* order members by distancetv5 days1-4/+6
|
* replace eager links by treestv5 days5-32/+13
|
* add writer treestv5 days1-0/+16
|
* add writer tree benchmarktv5 days1-1/+4
|
* measure 2-hop neighbourhoodtv5 days2-1/+20
|
* add propagation benchmarktv5 days1-0/+8
|
* dashboard: show eager links on the maptv5 days2-4/+9
|