Commit Graph

  • 9653a54766 added typed join result Chris Lu 2014-04-16 17:29:58 -0700
  • da0480ad72 adjust to upgraded Raft library Chris Lu 2014-04-15 17:56:47 -0700
  • 4ecf5956d7 Add types to uploading Chris Lu 2014-04-15 10:01:13 -0700
  • 7ad6cd35e8 Use type ClusterStatusResult for writing and reading results Chris Lu 2014-04-15 09:30:08 -0700
  • cb56322937 minor textual change Chris Lu 2014-04-15 09:20:28 -0700
  • 68021c6fc3 Use type AssignResult when writing and reading result. Chris Lu 2014-04-15 09:20:04 -0700
  • cbc5a76e80 Added batch file deleting. Chris Lu 2014-04-15 09:09:40 -0700
  • b771f060f1 rename variable name Chris Lu 2014-04-14 01:07:11 -0700
  • 2eb9014606 rename file from lookup_volume_id.go to lookup.go Chris Lu 2014-04-14 01:05:57 -0700
  • 56a3d30e75 batch delete on volume servers Chris Lu 2014-04-14 01:00:09 -0700
  • 460923f094 use fileId as the official name for the file identifier Chris Lu 2014-04-14 00:28:48 -0700
  • 85894160c6 refactor: split master handler into 2 files Chris Lu 2014-04-14 00:23:52 -0700
  • 7337c29b90 refactor: split volume handlers into 3 files Chris Lu 2014-04-14 00:13:18 -0700
  • 5878f7c3a1 refactor lookup result types into package "operation" Chris Lu 2014-04-13 23:56:15 -0700
  • f20ef922fd 1. add batched volume lookup handler 2. working-in-progress batch delete Chris Lu 2014-04-13 23:41:34 -0700
  • 161526555f remove unused code additional functions for glog Chris Lu 2014-04-13 10:20:43 -0700
  • 963023898e adding instructions on how to use logging Chris Lu 2014-04-13 10:18:10 -0700
  • 931bf2a50a releasing 0.53, and then move to 0.54 beta Chris Lu 2014-04-13 03:10:59 -0700
  • 0abd809663 Correct logic to allocate volume slots Chris Lu 2014-04-13 03:06:58 -0700
  • 6084e7670a fix bug when reading back the replica settings! Chris Lu 2014-04-13 03:06:15 -0700
  • 47620bb27a correct assign logic for rack level. Still need to fix data center level. Chris Lu 2014-04-13 02:26:22 -0700
  • ae2ef6e41d mostly working correctly, but may have failed volume growing attempts when slots are tight. Chris Lu 2014-04-13 02:16:45 -0700
  • f7f582ec86 1. refactoring, merge "replication" logic into "topology" package 2. when growing volumes, additional preferred "rack" and "dataNode" paraemters are also provided. Previously only "dataCenter" paraemter is provided. Chris Lu 2014-04-13 01:29:52 -0700
  • 008aee0dc1 Add retrying logic to wait for other peers during cluster bootstrapping. Chris Lu 2014-04-11 16:23:58 -0700
  • 7c82e2316b starting 0.53 beta Chris Lu 2014-04-10 13:47:39 -0700
  • 79142614ea 0.52 version Chris Lu 2014-04-10 13:47:12 -0700
  • 5f4dc11409 1. root dir has id of 0 2. only delete empty folders 3. correct listing files under a folder Chris Lu 2014-04-09 21:01:48 -0700
  • abde40377c a correct implementation of filer Chris Lu 2014-04-09 09:44:58 -0700
  • 67be8a5af8 adding filer!!! Chris Lu 2014-03-30 20:57:25 -0700
  • d6aa6239de fix to avoid empty sub directory Chris Lu 2014-03-30 13:32:24 -0700
  • 51fafdb525 more robust filer Chris Lu 2014-03-30 13:26:44 -0700
  • 2861275fb6 working filer server! Chris Lu 2014-03-30 11:28:04 -0700
  • 259c7d66f7 all in progress version will just be beta Chris Lu 2014-03-28 12:19:11 -0700
  • 25a3c47def Issue 65: weed-fs 0.51 does not compile under windows Chris Lu 2014-03-28 12:18:01 -0700
  • 59f6a13609 adding lots of different stats Chris Lu 2014-03-26 13:22:27 -0700
  • 39b774a131 1. adding statistics reporting 2. refactor version to util package Chris Lu 2014-03-25 13:46:59 -0700
  • 6e0601a73b 0.51 Chris Lu 2014-03-24 10:06:23 -0700
  • a0955aa4dd refactor functions Chris Lu 2014-03-23 21:57:10 -0700
  • b1f083cb60 fix delayed deletion Chris Lu 2014-03-23 21:56:24 -0700
  • 5c6a166761 better delayed deletion Chris Lu 2014-03-20 13:58:56 -0700
  • 7251e357e7 enhance deletion operation Chris Lu 2014-03-20 13:30:34 -0700
  • 7c5c94785c switch to idle timeout instead of read timeout Chris Lu 2014-03-20 11:07:15 -0700
  • c22e5c1c51 now the volume compaction bug is fixed. Chris Lu 2014-03-19 04:48:58 -0700
  • 0563773944 switch to ReadAt() for thread-safe read fix bugs during volume compaction Chris Lu 2014-03-19 04:48:13 -0700
  • 463589da01 adjusting logs Chris Lu 2014-03-19 04:46:42 -0700
  • 96b67a7c35 adjusting logs Chris Lu 2014-03-19 04:45:25 -0700
  • 252e553ef2 add deletion during benchmarking Chris Lu 2014-03-19 04:44:59 -0700
  • b2e8bfb54e adjusting logs Chris Lu 2014-03-19 04:43:21 -0700
  • 76bf72e8ef adjust log level Chris Lu 2014-03-19 04:42:57 -0700
  • 37dd41ab91 print out log message Chris Lu 2014-03-19 04:41:41 -0700
  • 3dbebfd1e1 Thread-safe fixes: 1. avoid sharing []byte 2. switch to use ReadAt() Chris Lu 2014-03-19 04:38:10 -0700
  • e5e6eeda83 found bugs with 0.50, backing off for now Chris Lu 2014-03-19 01:30:53 -0700
  • d8bc540130 Last important fix is version-bump-up-worthy: prevent heartbeat lost when vacuuming Chris Lu 2014-03-18 23:50:03 -0700
  • af32b52727 1. no locks for all read operations! Switching to pread for all reads. 2. prevent heartbeat lost when vacuuming, by removing locks on Size() function Chris Lu 2014-03-18 23:48:01 -0700
  • 2841d59fb0 randomize the file size a little bit Chris Lu 2014-03-18 23:45:02 -0700
  • 3fec41b911 remove unnecessary code Chris Lu 2014-03-18 22:32:29 -0700
  • 92afbb858a adjusting volumeSizeLimitMB default value and descriptions Chris Lu 2014-03-17 15:10:12 -0700
  • 988f9d60d5 so many bug fixes, well worth an version bump Chris Lu 2014-03-16 13:51:32 -0700
  • f8b1d48f82 deal with empty learder() cases Chris Lu 2014-03-16 13:50:46 -0700
  • 1040761ab6 avoid herding effect by double checking Chris Lu 2014-03-16 13:50:20 -0700
  • 1c044280d6 reusing http connections in raft server Chris Lu 2014-03-16 13:49:49 -0700
  • 41143b3b78 toughen weedfs clustering, adding synchronizing max volume id among peers in order to avoid the same volume id being assigned twice 1. moving raft.Server to topology 2. adding max volume id command for raft Chris Lu 2014-03-15 23:03:49 -0700
  • fb75fe852c ignore "-peers" option if cluster is already bootstrapped Chris Lu 2014-03-15 00:36:51 -0700
  • 6cedaf4356 fix glog format Chris Lu 2014-03-15 00:34:21 -0700
  • 0c42c69e94 less greedy concurrency level, reducing open files Chris Lu 2014-03-14 01:53:47 -0700
  • eec67d6008 fix bug on volume growing failure where free space equals what's required. more meaningful volume allocation errors Chris Lu 2014-03-13 12:13:39 -0700
  • 946aa6d1e7 error message change Chris Lu 2014-03-13 12:11:50 -0700
  • 7621b9b8a9 help content textual changes Chris Lu 2014-03-13 12:11:26 -0700
  • 7a8bc2e19e avoid sharing same err variable Chris Lu 2014-03-12 15:17:23 -0700
  • 097aac2328 adjusting default read time out Chris Lu 2014-03-12 15:05:07 -0700
  • 24cc55b444 1. increase default concurrency level 2. efficient stats collection and calculation 3. accurate error count Chris Lu 2014-03-12 14:10:28 -0700
  • d30052ce85 adjusting error message Chris Lu 2014-03-12 14:08:57 -0700
  • ff0560ee03 adjust error message Chris Lu 2014-03-12 14:07:30 -0700
  • c3ce024fc1 reusing http connections Chris Lu 2014-03-12 14:07:01 -0700
  • 054374c765 in progress, trying to make benchmark working better to reuse http connections. Chris Lu 2014-03-12 10:30:57 -0700
  • 466a55b06d fix error message Chris Lu 2014-03-12 10:25:05 -0700
  • 6f2d590617 fix error message Chris Lu 2014-03-12 06:23:07 -0700
  • c169429c33 fix https://code.google.com/p/weed-fs/issues/detail?id=64 Chris Lu 2014-03-12 06:19:30 -0700
  • c81f85e16d add percentage of benchmark progress plan to release v0.48 Chris Lu 2014-03-10 13:34:06 -0700
  • 45757b8b55 minor output format change Chris Lu 2014-03-10 13:22:08 -0700
  • 1f0a564e43 adding progress report during benchmarking Chris Lu 2014-03-10 13:21:21 -0700
  • cd10c277b2 can now delete a collection! Is this a dangerous feature? Only enabling deleting "benchmark" collections for now. Chris Lu 2014-03-10 11:43:54 -0700
  • a121453188 benchmarking writing data to a specific collection Chris Lu 2014-03-09 23:54:07 -0700
  • eac9c4d86b better benchmarking statistics Chris Lu 2014-03-09 23:12:05 -0700
  • 86b17e8972 a kind of working benchmark Chris Lu 2014-03-09 19:42:50 -0700
  • c830b60f36 refactoring Chris Lu 2014-03-09 18:50:45 -0700
  • e6e85a6b2c truncate file content during creating Chris Lu 2014-03-09 18:50:09 -0700
  • 7283d68e32 fixed redirection error Chris Lu 2014-03-03 08:20:46 -0800
  • ab9206c38e spelling error with parameter name! Chris Lu 2014-03-02 23:32:54 -0800
  • 27c74a7e66 Major: change replication_type to ReplicaPlacement, hopefully cleaner code works for 9 possible ReplicaPlacement xyz x : number of copies on other data centers y : number of copies on other racks z : number of copies on current rack x y z each can be 0,1,2 Chris Lu 2014-03-02 22:16:54 -0800
  • edae676913 1. volume server auto detect clustered master nodes 2. remove operation package dependency on storage Chris Lu 2014-02-14 17:10:49 -0800
  • ef4c2c0d1e cleaner cluster messages Chris Lu 2014-02-09 23:37:29 -0800
  • 67125688ed Avoid creating *.dat file when reading and it does not exist Chris Lu 2014-02-06 17:32:06 -0800
  • 91829057c5 set to 400 Bad Request when failed to parse file id, recommended by claudiu Chris Lu 2014-02-06 12:03:25 -0800
  • f68e15da89 set to 404 when failed to read file id Chris Lu 2014-02-06 12:00:58 -0800
  • d0147a16a9 avoid index out of range exception Chris Lu 2014-02-06 11:44:54 -0800
  • 59b9fd26fc fix replication type parameter name Chris Lu 2014-02-06 11:44:18 -0800
  • 6d7556b31f help message adjustment Chris Lu 2014-02-05 11:47:26 -0800
  • 69a7de1ad8 optimize for submission from clustered master nodes Chris Lu 2014-02-05 10:49:05 -0800
  • 0e5c4e432d report when size is closing to the volume limit fix error Chris Lu 2014-02-05 10:36:37 -0800