aboutsummaryrefslogtreecommitdiff
path: root/go/topology
AgeCommit message (Collapse)AuthorFilesLines
2016-06-02directory structure change to work with glideChris Lu19-2000/+0
glide has its own requirements. My previous workaround caused me some code checkin errors. Need to fix this.
2016-05-30rwlock concurrent read mapChris Lu5-13/+11
2016-05-19lock node.childrenChris Lu1-3/+20
2016-05-19lock dn.volumesChris Lu4-4/+21
2016-05-09do not forget to vacuum if cluster changesChris Lu1-2/+2
2016-05-05return nil if no errorChris Lu1-0/+3
fix https://github.com/chrislusf/seaweedfs/issues/299
2016-04-28use detailed map of errors for distributed operationsChris Lu1-21/+42
2016-04-14make VolumeLayout thread safechrislusf1-3/+15
2016-04-11[MOD] fix a bug.if node is nil will get an panic.张远浩1-1/+1
2016-02-27Fix chunk manifest replicate upload errortnextday1-2/+19
Escape the redirect url in volume read handler
2015-12-30adjust print out when errorchrislusf1-4/+3
2015-12-28Update store_replicate.gohxiaodon1-0/+7
replication operations should be equal to volume's replication setting
2015-11-29add chunk file helper to support large filetnextday1-0/+1
2015-07-11add loggingchrislusf1-0/+3
2015-05-23Adjust log messagechrislusf1-1/+1
2015-05-17Adjust admin url patternchrislusf1-3/+3
2015-05-03break away from code.google.comchrislusf2-2/+2
2015-04-16Change all chrislusf/weed-fs links to point to chrislu/seaweedfsStuart P. Bentley12-31/+31
2015-04-06change count to uint64 to fix #109chrislusf2-2/+2
fix https://github.com/chrislusf/weed-fs/issues/109
2015-03-10follow golint suggestionschrislusf4-27/+25
2015-03-09Add read only public port on volume serverchrislusf5-20/+9
Add read only public port on volume server
2015-03-09Avoid wrong way to delete on replication failurechrislusf1-10/+0
Avoid wrong way to delete on replication failure. This deletion has bug to write. The better fix is not to use the deletion on failure at all.
2015-02-25display admin url on /dir/statuschrislusf1-0/+1
2015-02-25adjust debug messagechrislusf1-1/+1
2015-02-20Show returned content when can not parse sonchrislusf1-1/+2
2015-02-07merge conflictsChris Lu1-5/+21
2015-01-18Fix compilation error.Chris Lu1-1/+1
2015-01-18Add optional admin port to volume server, to seperate admin operations from ↵Chris Lu6-11/+23
normal file operations.
2015-01-14Resolve ConflictsChris Lu1-1/+1
2015-01-13Cleanup error printing.Chris Lu2-2/+2
2015-01-13fix some typosLei Xue1-1/+1
2015-01-08add some String() to make codes easier to read and debugyanyiwu5-0/+28
2014-12-08Add read-write lock to guard topology changes on new collections and ttls.chrislusf4-34/+37
2014-10-26formatting code by: goimports -w=true .Chris Lu13-27/+31
2014-10-25adjust visibilityChris Lu1-1/+1
2014-10-25fix typoChris Lu1-1/+1
2014-09-25use github.com/chrislusf instead of github.com/aszxqwwyy12-28/+28
2014-09-25use github.com/aszxqw instead of code.google.com/pwyy12-28/+28
2014-09-20add TTL supportChris Lu9-31/+61
The volume TTL and file TTL are not necessarily the same. as long as file TTL is smaller than volume TTL, it'll be fine. volume TTL is used when assigning file id, e.g. http://.../dir/assign?ttl=3h file TTL is used when uploading
2014-07-20fix old tests that's found not working during travis integration.Chris Lu2-108/+8
2014-05-19rename to _vacuum.goChris Lu1-0/+0
2014-04-21Change to protocol buffer for volume-join-masster messageChris Lu1-6/+15
Reduced size to about 1/5 of the previous json format message
2014-04-171. v0.54Chris Lu1-1/+0
2. go vet found many printing format errors
2014-04-161. volume server now sends master server its max file key, so thatChris Lu1-4/+5
master server does not need to store the sequence on disk any more 2. fix raft server's failure to init cluster during bootstrapping
2014-04-13Correct logic to allocate volume slotsChris Lu1-12/+25
2014-04-13correct assign logic for rack level. Still need to fix data centerChris Lu1-9/+19
level.
2014-04-13mostly working correctly, but may have failed volume growing attemptsChris Lu1-0/+13
when slots are tight.
2014-04-131. refactoring, merge "replication" logic into "topology" packageChris Lu8-20/+464
2. when growing volumes, additional preferred "rack" and "dataNode" paraemters are also provided. Previously only "dataCenter" paraemter is provided.
2014-04-11Add retrying logic to wait for other peers during cluster bootstrapping.Chris Lu1-4/+9
2014-03-30working filer server!Chris Lu2-2/+2