aboutsummaryrefslogtreecommitdiffstats
path: root/src/swarm
Commit message (Collapse)AuthorAgeFilesLines
...
* changes from a peer never go backtv14 days1-0/+4
|
* older delivered messages leave us leveltv14 days1-1/+3
|
* benchmark where twice comes fromtv14 days2-4/+11
|
* resend only what is neededtv14 days1-1/+1
|
* benchmark delivered and twicetv14 days2-0/+30
|
* any message taken as deliveredtv14 days2-13/+23
|
* slow round back offtv14 days2-5/+86
|
* tree messages need no answertv14 days3-6/+40
|
* hello again when heard fromtv14 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 slottv2026-11-042-1/+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 thentv2026-11-042-4/+4
|
* pull after gracetv2026-11-042-4/+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 lackingtv2026-11-044-10/+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 reachedtv2026-11-032-14/+43
|
* links: only news pass ontv2026-11-031-6/+12
|
* dashboard: show writer treestv2026-11-031-26/+70
|
* writers from authorstv2026-11-033-27/+46
|
* reach set for the sessiontv2026-11-032-16/+10
|
* tree changes had alreadytv2026-11-031-4/+14
|
* announcement round counterstv2026-11-032-8/+23
|
* docs after treestv2026-11-031-5/+6
|
* announce what trees misstv2026-11-032-35/+115
|
* order members by distancetv2026-11-032-26/+59
|
* replace eager links by treestv2026-11-036-137/+35
|
* add writer treestv2026-11-035-27/+266
|
* add writer tree benchmarktv2026-11-031-0/+148
|
* measure 2-hop neighbourhoodtv2026-11-037-8/+136
|
* dashboard: show eager links on the maptv2026-11-031-5/+19
|
* add eager link counterstv2026-11-032-0/+21
|
* introduce eager linkstv2026-11-033-21/+100
|
* skip neighbours with our headstv2026-11-032-15/+37
|
* announcements answered only if heads differtv2026-11-034-7/+30
|
* retry new peers before probingtv2026-11-031-1/+1
|
* probe list memberstv2026-11-033-6/+17
|
* links: add failovertv2026-11-031-14/+129
|
* swarm: links by whom we reachtv2026-11-032-12/+25
|
* always announce new headstv2026-11-032-45/+9
|
* links: when asking for a lot relays, do chunktv2026-11-031-17/+72
|
* add budget for relayed LINKStv2026-11-031-1/+29
|
* add links relay testtv2026-11-021-0/+33
|
* swarm: relay links messagestv2026-11-022-24/+434
|
* swarm: announce to whom writers can't reachtv2026-11-022-28/+75
|
* dashboard: double-click opens peer dashboardtv2026-11-021-4/+61
|
* add per-node traffic countstv2026-11-021-1/+9
|
* probe when reachabletv2026-11-012-1/+26
|
* probe wakes peer workertv2026-11-011-2/+3
|
* document: introduce patch logtv2026-11-012-5/+5
|
* large messages over slow links are deltastv2026-11-012-7/+40
|
* links: wait for subscriber instead of tickertv2026-11-011-6/+16
|
* peer worker forget records on changetv2026-11-014-4/+28
|