aboutsummaryrefslogtreecommitdiffstats
path: root/src/swarm
Commit message (Collapse)AuthorAgeFilesLines
* benchmark where twice comes fromtv3 days2-4/+11
|
* resend only what is neededtv3 days1-1/+1
|
* benchmark delivered and twicetv3 days2-0/+30
|
* any message taken as deliveredtv3 days2-13/+23
|
* slow round back offtv3 days2-5/+86
|
* tree messages need no answertv3 days3-6/+40
|
* hello again when heard fromtv3 days2-2/+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 slottv4 days2-1/+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 thentv4 days2-4/+4
|
* pull after gracetv4 days2-4/+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 lackingtv4 days4-10/+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 reachedtv5 days2-14/+43
|
* links: only news pass ontv5 days1-6/+12
|
* dashboard: show writer treestv5 days1-26/+70
|
* writers from authorstv5 days3-27/+46
|
* reach set for the sessiontv5 days2-16/+10
|
* tree changes had alreadytv5 days1-4/+14
|
* announcement round counterstv5 days2-8/+23
|
* docs after treestv5 days1-5/+6
|
* announce what trees misstv5 days2-35/+115
|
* order members by distancetv5 days2-26/+59
|
* replace eager links by treestv5 days6-137/+35
|
* add writer treestv5 days5-27/+266
|
* add writer tree benchmarktv5 days1-0/+148
|
* measure 2-hop neighbourhoodtv5 days7-8/+136
|
* dashboard: show eager links on the maptv5 days1-5/+19
|
* add eager link counterstv5 days2-0/+21
|
* introduce eager linkstv5 days3-21/+100
|
* skip neighbours with our headstv5 days2-15/+37
|
* announcements answered only if heads differtv5 days4-7/+30
|
* retry new peers before probingtv5 days1-1/+1
|
* probe list memberstv5 days3-6/+17
|
* links: add failovertv5 days1-14/+129
|
* swarm: links by whom we reachtv5 days2-12/+25
|
* always announce new headstv5 days2-45/+9
|
* links: when asking for a lot relays, do chunktv5 days1-17/+72
|
* add budget for relayed LINKStv5 days1-1/+29
|
* add links relay testtv5 days1-0/+33
|
* swarm: relay links messagestv5 days2-24/+434
|
* swarm: announce to whom writers can't reachtv5 days2-28/+75
|
* dashboard: double-click opens peer dashboardtv5 days1-4/+61
|
* add per-node traffic countstv5 days1-1/+9
|
* probe when reachabletv6 days2-1/+26
|
* probe wakes peer workertv6 days1-2/+3
|
* document: introduce patch logtv6 days2-5/+5
|
* large messages over slow links are deltastv6 days2-7/+40
|
* links: wait for subscriber instead of tickertv6 days1-6/+16
|
* peer worker forget records on changetv6 days4-4/+28
|
* peer worker sleeps until deadline, not fixed timetv6 days7-14/+109
|
* bootstrap: replace pull by progress notifytv6 days2-2/+15
|