chrislu
32dbb6a2ce
Merge branch 'master' into mq
2024-06-14 11:42:05 -07:00
vadimartynov
8aae82dd71
Added context for the MasterClient's methods to avoid endless loops ( #5628 )
...
* Added context for the MasterClient's methods to avoid endless loops
* Returned WithClient function. Added WithClientCustomGetMaster function
* Hid unused ctx arguments
* Using a common context for the KeepConnectedToMaster and WaitUntilConnected functions
* Changed the context termination check in the tryConnectToMaster function
* Added a child context to the tryConnectToMaster function
* Added a common context for KeepConnectedToMaster and WaitUntilConnected functions in benchmark
2024-06-14 11:40:34 -07:00
chrislu
25b2850e7d
refactor out FilerClientAccessor
2024-06-06 19:44:19 -07:00
chrislu
edc87c16f9
balance subscribers
...
need to ensure the offsets are persisted
2024-05-27 17:30:16 -07:00
chrislu
cdeaaf95b4
go fmt
2024-05-23 08:25:53 -07:00
chrislu
554ae09f82
rename
2024-05-21 10:02:07 -07:00
chrislu
67e6051585
rename Coordinator to SubCoordinator
2024-05-21 09:57:45 -07:00
chrislu
d5abffa42c
rename Balancer to PubBalancer
2024-05-21 09:56:30 -07:00
chrislu
3622196881
go fmt
2024-05-20 11:05:18 -07:00
chrislu
972e9faaa2
move initial assignment to rebalance logic
2024-05-14 09:09:36 -07:00
chrislu
6e5075e14e
move read write topic config into filer client accessor
2024-05-14 08:50:17 -07:00
chrislu
e7823ee967
retry connecting to broker leader
2024-03-09 12:56:49 -08:00
chrislu
62397f2371
adjust error
2024-03-07 10:47:50 -08:00
Chris Lu
4dc6681833
proxy requests to lock owner
2024-02-05 16:46:40 -08:00
Chris Lu
f9131de43f
fix lock TTL
2024-02-04 12:47:21 -08:00
Chris Lu
0a12301b3d
avoid too large expiration time
2024-02-04 09:20:21 -08:00
chrislu
d41792461c
lock returns host and owner
2024-02-02 15:54:57 -08:00
chrislu
d30150dde1
use a short-lived lock
2024-02-01 23:01:44 -08:00
chrislu
ac50d8a822
re-lock if the lock owner is not found
2024-01-29 22:46:23 -08:00
chrislu
34839237ab
refactor
2024-01-20 12:16:40 -08:00
chrislu
2828ccbb30
refactor
2024-01-20 11:41:11 -08:00
chrislu
bc8d2a01cc
create local topic partition from config on filer
2024-01-17 00:15:52 -08:00
chrislu
ba73199174
reuse local partition
2024-01-15 21:22:41 -08:00
chrislu
d51efddf5c
flush to disk
...
Need to do: read from disk
2024-01-08 23:27:02 -08:00
chrislu
35869b5c80
subscriber can be notified of the assignment change when topic is just configured
...
Next: Subscriber needs to read by the timestamp offset.
2024-01-03 13:30:30 -08:00
Chris Lu
580940bf82
Merge accumulated changes related to message queue ( #5098 )
...
* balance partitions on brokers
* prepare topic partition first and then publish, move partition
* purge unused APIs
* clean up
* adjust logs
* add BalanceTopics() grpc API
* configure topic
* configure topic command
* refactor
* repair missing partitions
* sequence of operations to ensure ordering
* proto to close publishers and consumers
* rename file
* topic partition versioned by unixTimeNs
* create local topic partition
* close publishers
* randomize the client name
* wait until no publishers
* logs
* close stop publisher channel
* send last ack
* comments
* comment
* comments
* support list of brokers
* add cli options
* Update .gitignore
* logs
* return io.eof directly
* refactor
* optionally create topic
* refactoring
* detect consumer disconnection
* sub client wait for more messages
* subscribe by time stamp
* rename
* rename to sub_balancer
* rename
* adjust comments
* rename
* fix compilation
* rename
* rename
* SubscriberToSubCoordinator
* sticky rebalance
* go fmt
* add tests
* balance partitions on brokers
* prepare topic partition first and then publish, move partition
* purge unused APIs
* clean up
* adjust logs
* add BalanceTopics() grpc API
* configure topic
* configure topic command
* refactor
* repair missing partitions
* sequence of operations to ensure ordering
* proto to close publishers and consumers
* rename file
* topic partition versioned by unixTimeNs
* create local topic partition
* close publishers
* randomize the client name
* wait until no publishers
* logs
* close stop publisher channel
* send last ack
* comments
* comment
* comments
* support list of brokers
* add cli options
* Update .gitignore
* logs
* return io.eof directly
* refactor
* optionally create topic
* refactoring
* detect consumer disconnection
* sub client wait for more messages
* subscribe by time stamp
* rename
* rename to sub_balancer
* rename
* adjust comments
* rename
* fix compilation
* rename
* rename
* SubscriberToSubCoordinator
* sticky rebalance
* go fmt
* add tests
* tracking topic=>broker
* merge
* comment
2023-12-11 12:05:54 -08:00
chrislu
de0b969b36
Revert "rename"
...
This reverts commit 35b5264ab7
2023-10-12 20:28:11 -07:00
chrislu
35b5264ab7
rename
2023-10-11 21:44:56 -07:00
chrislu
0361c321b4
add CreateTopic API
2023-09-24 22:00:43 -07:00
chrislu
b18112ae10
fix compilation bugs during merge
2023-09-19 14:08:17 -07:00
chrislu
4827425146
balancer works
2023-09-16 15:05:38 -07:00
chrislu
436d99443b
receive broker stats
2023-09-14 23:49:05 -07:00
chrislu
b771fefa37
Merge branch 'master' into sub
2023-09-13 00:03:47 -07:00
chrislu
4d6c18d86f
pub sub initial tests
2023-08-27 17:50:59 -07:00
Nico D'Cotta
796b7508f3
Implement SRV lookups for filer ( #4767 )
2023-08-24 07:08:56 -07:00
chrislu
01d70c21f3
Squashed commit of the following:
...
commit 32f4b1a13057d56b6de487cdb80ff7c205af01a6
Author: chrislu <chris.lu@gmail.com>
Date: Sun Aug 20 22:52:19 2023 -0700
fix compilation
commit e77ad33b7ca0423138fbae26a4433b60923a9588
Author: chrislu <chris.lu@gmail.com>
Date: Sun Aug 20 22:46:44 2023 -0700
pub
commit f431f30cc7ca277ca299e3cd118c05537fb9f5c3
Author: chrislu <chris.lu@gmail.com>
Date: Sun Aug 20 13:27:39 2023 -0700
fix generic type
commit 4e9dcb18293fd1e3e306e2dceb995dfd67a35e1d
Merge: 30f942580 16e3f2d52
2023-08-20 22:53:05 -07:00
chrislu
81fdf3651b
grpc connection to filer add sw-client-id header
2023-01-20 01:48:12 -08:00
Konstantin Lebedev
e90ab4ac60
avoid race conditions for OnPeerUpdate ( #3525 )
...
https://github.com/seaweedfs/seaweedfs/issues/3524
2022-08-26 10:18:49 -07:00
askeipx
2e78a522ab
remove old raft servers if they don't answer to pings for too long ( #3398 )
...
* remove old raft servers if they don't answer to pings for too long
add ping durations as options
rename ping fields
fix some todos
get masters through masterclient
raft remove server from leader
use raft servers to ping them
CheckMastersAlive for hashicorp raft only
* prepare blocking ping
* pass waitForReady as param
* pass waitForReady through all functions
* waitForReady works
* refactor
* remove unneeded params
* rollback unneeded changes
* fix
2022-08-23 23:18:21 -07:00
Konstantin Lebedev
4d08393b7c
filer prefer volume server in same data center ( #3405 )
...
* initial prefer same data center
https://github.com/seaweedfs/seaweedfs/issues/3404
* GetDataCenter
* prefer same data center for ReplicationSource
* GetDataCenterId
* remove glog
2022-08-04 17:35:00 -07:00
chrislu
26dbc6c905
move to https://github.com/seaweedfs/seaweedfs
2022-07-29 00:17:28 -07:00
chrislu
aa4a22ad47
segment serde
2022-07-28 23:24:38 -07:00
chrislu
74f60f246f
dynamically connect to a filer
2022-07-28 23:24:38 -07:00
chrislu
9f479aab98
allocate brokers to serve segments
2022-07-28 23:24:38 -07:00
chrislu
8060fdcac5
remove old code
2022-07-28 23:24:38 -07:00
chrislu
f25e273e32
display data center and rack in cluster.ps
2022-07-28 23:22:52 -07:00
chrislu
68065128b8
add dc and rack
2022-07-28 23:22:51 -07:00
chrislu
87ccef72db
cluster.ps can list brokers
2022-07-28 23:22:07 -07:00
chrislu
ac66227798
renaming
2022-07-28 23:22:07 -07:00
chrislu
21b6b07dd8
renaming
2022-07-28 23:22:06 -07:00
