* generate .pb.go
* health checker conf
* check logic
* implement ping
* fix check interval
* improve check results
* health check on add outbounds
* fix tests
* fix ping handler
* fix min rtt < 0
* random alive
* fix check all on add outbounds
* least load strategy
* conf codes optimize
* improve least load strategy
* improve health check on AddOutboundHandler
* cleanup results with scheduler
code optimize
* health ping timeout default 5s
* remove config of health ping round
round 1 seems to be good enough
* fix TestSimpleBalancer
* add TestLeastLoadBalancer
* add todos
* lint and test fix
* balancer fallback
* api health stats command
* add hc cmd to perform health checks
* rename 'health stats' cmd to hci
* many code optimizations
* fix typo
* select none if no match for baselines only config
> prev 'select 1' behavior can achieved by baselines+expected=1
* add LeastLoadStrategy tests
* don't select alive on no match, go to fallback
* api hci refactor
* more detailed info
* ready for future new strategies
* apply lint style
* refactor: strategies don't need ref of balancer
* change check interval unit to seconds
> to reduce influence caused by what is described by new added FIXME
* fix test
* RouterService->RoutingService
* Revert "generate .pb.go"
This reverts commit 0e6fa1be889470d0ad9692f7279da45c030e1919.
* make checks distributed
> but `api hc` is the exception
* BalancingStrategy interface optimize
* fix random selects unchecked
* upgrade cmd hci to bi & rename hc to bc
* bi shows all balancers, while hci shows only heath-check-enabled ones
* shows more info
* fix test
* api bi sort output
* update according to review
* remove checks on add outbound
* refactor: move health checker inside to strategy
* enables rounds setting for health ping
* restore the random behavior, no ping, no pick alive
> if future strategy based on HealthPing, just embed it like what LeastLoad does
* apply lint style
* code optimize
* fix typo
* update desc of bc bi
* ping with head
code optimize
* force rouds to 1 if checks not distributed
* leatload: select by standard deviations
* health ping refactor
* continuously applying results
* config is easier to understand
* checker interfaces simplifying
* add maxRTT config to filter away high delay nodes
* apply lint
* cost for leastload
* api bo to override balancer selecting
* fix health ping statistics & fix test
* check connectivity if ping fail
* add tolerance setting & more detailed bi output
* fix connectivity check
* optimize bi output
* should not put results when network is down
* fixes @_@
* mux optimize
* remove pause option of selecting overriding
> it causes data racing
* update bo desc
* fix potential racing
* simplify locking
* switch sync.Mutex to avoid potential racing
* add more tests
* code optimize
* code optimize
* fix connectivity check when url not set
loyalsoldier
Shelikhoo
JebbsandGitHub
Vigilans
vcptr
Darien Raymond