MyFavMirrors
/
minio
mirror of https://github.com/minio/minio.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity
2,030 Commits 5 Branches 503 Tags 186 MiB
Commit Graph

63 Commits

Author SHA1 Message Date
Harshavardhana b938e40fb5 Move atomic package to the top and simplify its tests 2015-09-20 13:51:38 -07:00
Harshavardhana 45d8898019 Merge branch 'parallel-read2' of https://github.com/krishnasrinivas/minio into krishnasrinivas-parallel-read2 
Make few more changes and rebased with current master
 2015-09-15 17:33:33 -07:00
Harshavardhana 1e2c010174 Avoid shadowing variables and enable checks to avoid them during build 2015-09-09 15:14:55 -07:00
Harshavardhana 988d39a5b6 Migrate to golang1.5 release with GO15VENDOREXPERIMENT=1 enabled 2015-08-22 18:35:37 -07:00
Anand Babu (AB) Periasamy cdf93e534c simplify probe APIs 2015-08-18 19:30:17 -07:00
Harshavardhana 61175ef091 Migrate to govendor to avoid limitations of godep 
- over the course of a project history every maintainer needs to update
  its dependency packages, the problem essentially with godep is manipulating
  GOPATH - this manipulation leads to static objects created at different locations
  which end up conflicting with the overall functionality of golang.

  This also leads to broken builds. There is no easier way out of this other than
  asking developers to do 'godep restore' all the time. Which perhaps as a practice
  doesn't sound like a clean solution. On the other hand 'godep restore' has its own
  set of problems.

- govendor is a right tool but a stop gap tool until we wait for golangs official
  1.5 version which fixes this vendoring issue once and for all.

- govendor provides consistency in terms of how import paths should be handled unlike
  manipulation GOPATH.

  This has advantages
    - no more compiled objects being referenced in GOPATH and build time GOPATH
      manging which leads to conflicts.
    - proper import paths referencing the exact package a project is dependent on.

 govendor is simple and provides the minimal necessary tooling to achieve this.

 For now this is the right solution.
 2015-08-12 19:24:57 -07:00
Harshavardhana 45b59b8456 Probe revamped to provide for a new WrappedError struct to wrap probes as error interface 
This convenience was necessary to be used for golang library functions like io.Copy and io.Pipe
where we shouldn't be writing proxies and alternatives returning *probe.Error

This change also brings more changes across code base for clear separation regarding where an error
interface should be passed encapsulating *probe.Error and where it should be used as is.
 2015-08-08 00:16:38 -07:00
Harshavardhana f8141493bd use command not found helper 2015-08-03 18:06:19 -07:00
Harshavardhana d09fd8b0a1 Migrate from iodine to probe 2015-08-03 16:33:44 -07:00
Krishna Srinivas ee4432bc40 rename disk.OpenFile to Open which will do os.Open (which will be read-only). disk.OpenFile will do os.OpenFile (which can be rw, append) 2015-08-02 17:34:29 +05:30
Krishna Srinivas fdd2c22fa5 Do go fmt on bucket.go 2015-07-29 23:49:25 +05:30
Krishna Srinivas ae8089c9b6 when signature is not available there is no need to compute sha256 2015-07-29 21:09:02 +05:30
Krishna Srinivas bdc00624fd get erros from buffered channel. Return error during object read only if we have readers < k 2015-07-29 19:36:41 +05:30
Harshavardhana d346250f1c Collapse GetPartialObject() into GetObject() 2015-07-28 19:33:56 -07:00
Krishna Srinivas e1280779ed Read from the disks in parallel during object read 2015-07-28 18:04:17 +05:30
Harshavardhana b0ea64a04f Strip off quotes from ETag for verifying complete multipart upload 2015-07-25 16:10:05 -07:00
Harshavardhana e082f26e10 Improving EncoderStream to return error only upon non io.EOF. 
io.EOF is okay since io.ReadFull will not have read any bytes at all.

Also making error channel receive only for go routine.
 2015-07-25 15:57:30 -07:00
Krishna Srinivas bcfaa12a4d Encoder now directly reads from the object stream. Using split.Stream() was causing lot of redundant memory operations. 2015-07-26 03:54:39 +05:30
Harshavardhana d6a0e0cc55 Rename more 2015-07-24 18:09:53 -07:00
Harshavardhana 63c9cf0c4b Move from Minimalist Object Storage to Minio Cloud Storage 2015-07-24 17:51:40 -07:00
Harshavardhana 43c908d5b9 ListObjects now considers multipart objects, also move to upstream check.v1 2015-07-18 15:49:41 -07:00
Harshavardhana 966786c78e remove unnecessary updateAt() 2015-07-17 19:48:09 -07:00
Harshavardhana c1da10a207 Donut multipart support no get, listobjects() support yet 2015-07-17 16:23:51 -07:00
Harshavardhana 5507a39840 Heal buckets upon init if needed, adding new disks and HUP works 2015-07-16 09:59:05 -07:00
Harshavardhana 6baf45e360 Fix a crash during listObjects() populating NextMarker 2015-07-15 10:04:15 -07:00
Harshavardhana 2553654e24 Add initial version of heal, remove rebalance 2015-07-14 22:56:41 -07:00
Harshavardhana e37c5315ec Live multiple disk removal works properly 2015-07-14 20:46:14 -07:00
Harshavardhana e1e4908515 Wire up sha512 matching inside donut along with md5sum 2015-07-14 19:47:50 -07:00
Harshavardhana e885259584 Handle removal of disks - getObject() now reads if disks are missing underneath, add initial stub healing code 2015-07-14 18:53:00 -07:00
Harshavardhana da8b9fd112 Remove global custom config path variables, use get/set methods instead 2015-07-14 11:56:15 -07:00
Harshavardhana c4cf7635bf Read req.Body for PutBucket() if any 2015-07-14 09:30:10 -07:00
Harshavardhana 45ddec925c Fix an ugly multipart bug 2015-07-13 21:38:01 -07:00
Harshavardhana 7ae60a6d10 For missing parts reply back as InvalidPart{} 2015-07-13 19:31:01 -07:00
Harshavardhana 634f70f3b0 WriteObject() encoded data in go routine, fix another multipart issue 2015-07-13 15:56:54 -07:00
Anand Babu (AB) Periasamy 8af5933b07 Merge pull request #743 from flandr/fix-osx 
Fix OS X build
 2015-07-13 10:15:53 -07:00
Nate Rosenblum ec347f96fd Fix OS X build 
- Explicitly cast statfs_t members to int64 (this structure is
   platform-specific)
 - Add pass-through New methods to Darwin SHA package
 - Move scsi pkg types to common translation unit (package was empty)
 - Add stub implementations mount/disk ops for OS X
 2015-07-13 10:06:55 -07:00
Harshavardhana 55e4d0c6a5 mkdonut now creates a donut processing cli args 2015-07-12 21:21:31 -07:00
Harshavardhana 97d4a27c7e Do not reply on ignoredHeaders for server, rely on SignedHeaders sent as part of Authorization header 2015-07-10 19:37:22 -07:00
Harshavardhana 53f5d2c32b nodejs http library sends Connection header during HTTP request, this clobbers up the signature handling ignore it 2015-07-10 15:44:47 -07:00
Harshavardhana 29838bb851 Cleanup temporary writers upon errors during putObject(), all metadata() write operations 2015-07-10 14:11:04 -07:00
Harshavardhana 15dd0df187 Support signature v4 at rest 2015-07-10 11:49:27 -07:00
Harshavardhana e5006c738d Handle both space and non-space characters, in signature v4 - add errors for all API's 2015-07-09 21:49:58 -07:00
Harshavardhana 84f427f14a All other API's now support signature v4 2015-07-09 19:45:56 -07:00
Harshavardhana 00890c254e CompleteMultipartUpload and CreateObjectPart now fully support signature v4 2015-07-09 19:01:15 -07:00
Harshavardhana 89c1215194 PutObject handler gets initial support for signature v4, working 2015-07-09 16:44:38 -07:00
Harshavardhana 375860077d HTTP header Content-Length signifies body length of the request, if its smaller reply appropriately 
This patch also handles large individual part sizes > 5MB by using less memory copies.
 2015-07-08 20:56:41 -07:00
Harshavardhana ec33d79d57 Add server side signaturev4 check, not wired up to the readers yet. 2015-07-08 16:57:03 -07:00
Harshavardhana d1deda3a96 Add API tests for both donut on disk and donut cache 2015-07-07 19:39:46 -07:00
Harshavardhana 8abb96c030 If NodeDisks are not empty do not impose cache maxSize restriction 2015-07-07 16:41:40 -07:00
Harshavardhana 11b893804c Moving os.MkdirAll() inside atomic for auto parent directory creates 2015-07-07 12:35:57 -07:00