3357 Commits (b4e4846e9f17ed9a45c6f815a5e37c0685b8ac47)

 

All Branches   

Search

Author	SHA1	Message	Date
Krishna Srinivas	b4e4846e9f	PutObject: object layer now returns ObjectInfo instead of md5sum to avoid extra GetObjectInfo call. (#2599) ... From the S3 layer after PutObject we were calling GetObjectInfo for bucket notification. This can be avoided if PutObjectInfo returns ObjectInfo. fixes #2567	8 years ago
Krishna Srinivas	92e49eab5a	FS/Multipart: Do not rename append files to another tmp file as the append files are already in tmp location. (#2612)	8 years ago
Harshavardhana	c4a7b950a0	fs: Fix asynchronous multipart bug. ... Construct part path properly.	8 years ago
Karthic Rao	1ce339abeb	Fixing ineffssaign errors (#2608)	8 years ago
Aditya Manthramurthy	a1f922315b	Add docker-compose file to run Minio in distributed mode (#2606) ... Serves as a starting point to run a Minio cluster using Docker. The file can be used as configuration for the docker-compose tool to start 4 Minio servers in distributed mode. * Add a docker-compose.yml file to run 4 minio server instances in distributed mode * Update Docker.md with command to use the file	8 years ago
Anis Elleuch	3e284162d7	Add global flags to all commands and subcommands (#2605)	8 years ago
Anis Elleuch	ff99392102	Enhance minio server help template (#2603)	8 years ago
Krishna Srinivas	9358ee011b	logging: Print stack trace in case of errors. ... fixes #1827	8 years ago
Harshavardhana	37cbcae6ba	xl: Remove an unecessary lock with isBucketExist() (#2593) ... Fixes #2566	8 years ago
Harshavardhana	ae64b7fac8	XL: Handle object layer initialization properly. ... Initialization when disk was down the network disk reported an incorrect error rather than errDiskNotFound. This resulted in incorrect error handling during prepInitStorage() stage. Fixes #2577	8 years ago
Anis Elleuch	d936ed90ae	Avoid testing on system errors strings in posix (#2583)	8 years ago
Krishna Srinivas	7cc77eba45	XL/Healing: errDiskNotFound is the only pardonable error in xlShouldHeal. (#2586) ... This is so that we try to heal a file for all the "bad" cases except when the disk is down.	8 years ago
Karthic Rao	07d232c7b4	instrumentation: instrumentation for locks. (#2584) ... - Instrumentation for locks. - Detailed test coverage. - Adding RPC control handler to fetch lock instrumentation. - RPC control handlers suite tests with a test RPC server.	8 years ago
Krishnan Parthasarathi	de67bca211	Move formatting of disks out of object layer initialization (#2572)	8 years ago
Anis Elleuch	5c4dbc966f	Add Howto setup minio distributed with Docker	8 years ago
Harshavardhana	bca1385683	lock: Fix support single node XL locking as well.	8 years ago
Harshavardhana	f655592ff5	vendorize new dsync with new changes of logging.	8 years ago
Harshavardhana	cbe87cb2ed	Fix fd-leak in rpcClient close it pro-actively.	8 years ago
Anis Elleuch	0513b3ed07	Add Heal Disk Metadata RPC API + tests (#2556)	8 years ago
Frank	7f92165c79	Single use DRWMutex, RPCClient refactor and added missing cases to lock-rpc-server (#2560) ... This PR contains various fixes for the distributed release: - Use DRWMutex in namespace-lock only for a single Lock()/RLock() call in conformance to server-side rw-locking as implemented in minio/dsync - Implement missing cases in lock-rpc-server to catch Unlock() for active read locks and RUnlock() for an active write lock - Refactor RPCClient to release local mutex while making actual RPC.Call()	8 years ago
Harshavardhana	780ccc26f7	server: Validate server arguments for duplicates. (#2554) ... - Validates invalid format inputs. - Validates duplicate entries. - Validates sufficient amount of disks. Partially fixes #2502	8 years ago
Harshavardhana	339425fd52	server: Fetch StorageInfo() from underlying disks transparently. (#2549) ... Fixes #2511	8 years ago
Harshavardhana	fa6e9540a8	server: We shouldn't exit the server in lazy init. (#2548) ... Avoid fatalIf instead these are non-critical errors, continue running the server. - initializing bucket notifications - initializing bucket policies. - migrating bucket policies failure. Fixes #2547	8 years ago
Harshavardhana	9605fde04d	controller/auth: Implement JWT based authorization for controller. (#2544) ... Fixes #2474	8 years ago
Anis Elleuch	200d327737	List only objects that need healing (#2546)	8 years ago
Harshavardhana	e1b0985b5b	rpc: Refactor authentication and login changes. (#2543) ... - Cache login requests. - Converge validating distributed setup.	8 years ago
Krishnan Parthasarathi	c8dfc4cda4	auth-rpc: Reset token on disconnect (#2542)	8 years ago
Bala FA	7922a54c9a	rpc-client: remove unwanted nil check of rpcClient. (#2538)	8 years ago
Krishnan Parthasarathi	bda6bcd5be	Layered rpc-client implementation (#2512)	8 years ago
Harshavardhana	7e3e24b394	rpc: client login should ignore server versions.	8 years ago
Harshavardhana	bb0466f4ce	control: Fix controller CLI handling with distributed server object layer. ... Object layer initialization is done lazily fix it.	8 years ago
Harshavardhana	8797952409	server: Add server command line for running in distributed mode	8 years ago
Krishnan Parthasarathi	c33d1b8ee6	Vendorize minio/dsync for server-side read lock (#2484) ... - Prevention of stale lock accumulation. - Removal of dead code.	8 years ago
Krishnan Parthasarathi	1f67c18222	Lock/Rlock rpc reply was incorrect (#2479)	8 years ago
Krishnan Parthasarathi	a4691611a7	Move initGracefulShutdown before objectLayer initialization (#2468)	8 years ago
awwalker	7c7eb1475d	splitNetPath: Add support for windows paths including volumeNames e.g ip:C:\network\path	8 years ago
Harshavardhana	0bce3d6d63	Fix web handler initialize with distributed lazy init.	8 years ago
Krishnan Parthasarathi	804d91ef61	storage/rpc-client: Reconnect on network disconnect (#2436)	8 years ago
Krishnan Parthasarathi	229600ce9b	Implement RLock, RUnlock rpc handlers (#2437) ... This would make it simplify dsync.RWMutex's algorithm to acquire a distributed read lock and be tolerant to N/2-1 failures.	8 years ago
Harshavardhana	43098df9d8	rpc: Re-factor ReadFile behavior client <--> server. ... Current code did not marshal/unmarshal buffers properly from the server, The reason being buffers have to be allocated and sent properly back to client to be consumable.	8 years ago
Harshavardhana	6908a0dcd4	Extract rpc server wrapped errors and translate to storage error.	8 years ago
Harshavardhana	cae5761f16	rpc/client: Add missing rpcTokens for each rpc calls.	8 years ago
Harshavardhana	83074ed57e	Add missing rpc-client.go - missing in previous commit.	8 years ago
Krishnan Parthasarathi	64a7e6992e	Vendorize rpc reconnect changes from minio/dsync (#2405)	8 years ago
Harshavardhana	61af764f8a	Add rpc layer authentication.	8 years ago
Harshavardhana	b4172ad3c8	Rename rpc-{client,server} storage-rpc-{client,server}	8 years ago
Harshavardhana	4917038f55	Move the ObjectAPI() resource to be beginning of each handlers. ... We should return back proper errors so that the clients can retry until server has been initialized.	8 years ago
Krishnan Parthasarathi	b0f3f94163	unify single-node and distributed namespace locking (#2401)	8 years ago
Krishnan Parthasarathi	b7c169d71d	object layer initialization using distributed locking (#2397) ... * vendorized latest minio/dsync * wip - object layer initialization using distributed locking	8 years ago
Frank	3939c75345	Added distributed RWMutex (#2369)	8 years ago