summaryrefslogtreecommitdiff
AgeCommit message (Expand)Author
2 daysMake the mainloop behave like every worker by claiming and releasing a socket being worked onDirk Engling
2 daysMake tcp worker multithreaded, tooDirk Engling
3 daysRefactor all tcp specific code into the ot_tcp module to prepare for multiple concurrent workersDirk Engling
3 daysAdd test for new config paramsDirk Engling
3 daysAdd config parsers for multiple tcp socket readers and a helper to see if we can offer it on the platformDirk Engling
3 daysIntroduce a fast path assuming that a tcp connection's payload already has arrived at accept timeDirk Engling
3 daysStart documenting design decisions and measurmentsDirk Engling
3 daysRemove references that you need libowfat to build opentrackerDirk Engling
3 daysgit ignore the poll flavor of the runner, tooDirk Engling
3 daysFix idle tests in presence of an accept filterDirk Engling
3 daysRemove stale xcode build fileDirk Engling
3 daysFix expiry tests under the new accept filtersDirk Engling
3 daysUse accept filter dataready instead of httpready on FreeBSDDirk Engling
3 daysDefer accepts until some data actually is thereDirk Engling
3 daysEnforce the invariant that each socket is only ever expected to be read from or written to, never bothDirk Engling
3 daysDon't treat a full send buffer as an error when sending http. Retry laterDirk Engling
4 daysReduce syscalls and add helper to count themDirk Engling
4 daysAdd an http load generatorDirk Engling
4 daysReduce number of per connection sys callsDirk Engling
4 daysCheck for free port in the udp integration test, also speed it up by a bitDirk Engling
4 daysConsolidate all tcp/http tear down into a single http_close function to prevent a rare UAF for expiring connectionsDirk Engling
5 daysBuild everything in one sweep, without intermediate object filesDirk Engling
5 daysadd wake-up tester that helped figuring out how to tickle hanging udp readersDirk Engling
5 daysRevert last wake-up experiment. Having each udp worker wake up once a second to check if the tracker stops is wastefulDirk Engling
5 daysFix a test that would over-report success rate when losing the race for cycles to the test targetDirk Engling
5 daysLivesync now also gets proper deinit codeDirk Engling
5 daysWith more workers blockingly waiting on udp sockets, we need to keep track of all sockets to shut them down on exitDirk Engling
5 daysDefault udp workers to 1, as it is the most sane choice everywhere, also reflect the new udp parallelism in the man pagesDirk Engling
5 daysLet the load tester log losses to better gauge performanceDirk Engling
5 daysAdd load tests to sanitize check the trackerlogic, based on udp requestsDirk Engling
5 daysPerformance improvement, where it works: Let different udp worker threads have their own socketDirk Engling
6 daysThe main event loop(s) now also catch an EINTR and return instead of blockingDirk Engling
6 daysAdd concurrency testDirk Engling
6 daysMake global torrent counter atomic and fix the setter and getterDirk Engling
6 daysPlug in the new per-thread stats counter, also make sure that the ot_clean sleep does not stall tracker exitDirk Engling
6 daysSecond half of moving the stat enum defines to trackerlogicDirk Engling
6 daysPrepare having each thread keep their own stats to avoid data racesDirk Engling
6 daysTurn malloc+memset into callocDirk Engling
6 daysSome more g_now_seconds occurrencesDirk Engling
6 daysForgot some g_now_seconds occurencesDirk Engling
6 daysAll OSes now do have a cheap monotonic clock, so no caching thread is needed. Also add some relative time helpersDirk Engling
6 daysWhile we're at it with the dynamic analyzers, add a tsanDirk Engling
7 daysAdd test for the revived keep aliveDirk Engling
7 daysFix some tests to match retired stats modes and wrong config file orderingDirk Engling
7 daysAdd test for the correct order of partial scrapesDirk Engling
7 daysAdd test for the error packet when a hash is blacklisted (the part I forgot in last commit)Dirk Engling
7 daysAdd test for the error packet when a hash is blacklistedDirk Engling
7 daysRemove enum for a retired stats modeDirk Engling
7 daysClean build artefacts on macos, tooDirk Engling
7 daysAdd DWANT_KEEPALIVE to integration test flags to test the whole sub systemDirk Engling