aboutsummaryrefslogtreecommitdiffstats
path: root/docs/peers.md
Commit message (Collapse)AuthorAgeFilesLines
* substitutes held longertv5 days1-2/+3
|
* indirect probestv5 days1-2/+10
|
* unlisted members forgottontv5 days1-1/+3
|
* fix doc (working links measured)tv5 days1-1/+2
|
* trees over working linkstv5 days1-3/+5
|
* working links recordedtv6 days1-0/+10
|
* suspend detectedtv6 days1-0/+7
|
* views documentedtv6 days1-0/+11
|
* swarm neighbourstv6 days1-2/+7
|
* slow link a hop moretv6 days1-1/+3
|
* heal is lasttv6 days1-0/+6
|
* offer answerstv6 days1-1/+2
|
* round trips in treestv6 days1-3/+6
|
* suspect pathstv7 days1-1/+4
|
* deflate blob chunkstv7 days1-2/+3
|
* deflate blob chunkstv7 days1-0/+5
|
* epoch tag in synctv7 days1-1/+4
|
* no swarm ID in synctv7 days1-1/+2
|
* announce only to those behindtv7 days1-1/+2
|
* predecessors go alongtv7 days1-1/+5
|
* covered neighbours have ittv7 days1-0/+8
|
* delta from held headstv7 days1-2/+3
|
* offer again ungeneratedtv7 days1-1/+2
|
* stale delta offerstv7 days1-0/+3
|
* delta known to sendertv7 days1-1/+2
|
* one delta at a timetv7 days1-1/+5
|
* document messages that overtaketv7 days1-4/+20
|
* any message taken as deliveredtv7 days1-7/+9
|
* slow round back offtv7 days1-4/+8
|
* tree messages need no answertv7 days1-3/+10
|
* hello again when heard fromtv7 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 slottv7 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 ontv7 days1-1/+1
| | | | | | | 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 gracetv8 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 lackingtv8 days1-2/+3
| | | | | | | 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 reachedtv8 days1-5/+10
|
* writers from authorstv8 days1-5/+7
|
* reach set for the sessiontv8 days1-2/+4
|
* tree changes had alreadytv8 days1-1/+3
|
* announce what trees misstv8 days1-1/+6
|
* order members by distancetv8 days1-4/+6
|
* replace eager links by treestv9 days1-9/+2
|
* add writer treestv9 days1-0/+16
|
* measure 2-hop neighbourhoodtv9 days1-0/+9
|
* introduce eager linkstv9 days1-1/+9
|
* skip neighbours with our headstv9 days1-1/+4
|
* announcements answered only if heads differtv9 days1-2/+3
|
* retry new peers before probingtv9 days1-1/+3
|
* probe list memberstv9 days1-1/+3
|
* always announce new headstv9 days1-5/+4
|