Commit graph

45 commits

Author SHA1 Message Date
Anis Elleuch 14cefd352c Heal corrupted formats of disks already containing objects (#2297) 2016-07-28 16:49:58 -07:00
Harshavardhana f503ac3db8 XL/Erasure: Make bit-rot verification based on xl.json algo. (#2299)
Currently `xl.json` saves algorithm information for bit-rot
verification. Since the bit-rot algo's can change in the
future make sure the erasureReadFile doesn't default to
a particular algo. Instead use the checkSumInfo.
2016-07-28 02:20:34 -07:00
Harshavardhana 1e3d80552f XL: format.json healing should cater for mismatching order. (#2285)
Fresh disks can be provided in any order, we need to make sure
to preserve existing disk order and populate the fresh disks
in new positions.

Thanks for Anis Elleuch <vadmeste@gmail.com> for finding this issue.
2016-07-26 03:18:47 -07:00
Harshavardhana cef26fd6ea XL: Refactor usage of reduceErrs and consistent behavior. (#2240)
This refactor is also needed in lieu of our quorum
requirement change for the newly understood logic behind
klauspost/reedsolom implementation.
2016-07-19 19:24:32 -07:00
Harshavardhana bdff0848ed server: Implement --ignore-disks for ignoring disks from healing. (#2158)
By default server heals/creates missing directories and re-populates
`format.json`, in some scenarios when disk is down for maintainenance
it would be beneficial for users to ignore such disks rather than
mistakenly using `root` partition.

Fixes #2128
2016-07-10 14:38:15 -07:00
Harshavardhana c0c8a8430e XL/PutObject: Add single putObject and multipart caching. (#2115)
- Additionally adds test cases as well for object cache.
- Adds auto-expiry with expiration and cleanup time interval.

Fixes #2080
Fixes #2091
2016-07-08 20:34:27 -07:00
Harshavardhana d2557bb538 XL: GetObject caching implemented for XL. (#2017)
The object cache implementation is XL cache, which defaults
to 8GB worth of read cache. Currently GetObject() transparently
writes to this cache upon first client read and then subsequently
serves reads from the same cache.

Currently expiration is not implemented.
2016-07-03 17:15:38 -07:00
Harshavardhana d64c3fd464 posix: Return errDiskNotWritable during disk initialization. (#2048)
It can happen that minio server might not have
writable permissions on the export paths command line.

Fixes #2035
2016-07-02 01:59:28 -07:00
Harshavardhana 0e3907072c XL/fs: Initialize export paths supplied on command line (#2020)
Fixes #2013
2016-06-29 03:13:44 -07:00
Harshavardhana ae936a0147 XL: Relax write quorum further to N/2 + 1. (#2018)
This changes behavior in some parts of the code
as well address it.

Fixes #2016
2016-06-29 02:10:40 -07:00
Harshavardhana 3ac39ff107 XL: Change minimum disks supported to 6 now. (#2023)
This change co-incides with another patch set which
reduces the writeQuorum requirement. With the
write quorum change it is now possible to support
6 disk configuration.
2016-06-29 02:05:29 -07:00
Harshavardhana 0d3a9c9438 XL: Add tests for checkSufficientDisks, storageInfo. (#1988) 2016-06-26 19:48:02 -07:00
Harshavardhana f4830162a4 XL: Format heal should re-allocate new UUIDs not reuse. (#1953)
This patch also supports writing to a temporary file and renaming
rather than appending to an existing file. This helps in avoiding
inconsistent files.
2016-06-22 17:18:31 -07:00
Harshavardhana 23c88ffb1d XL/format: Fix a bug in checkDisksConsistency. (#1894) 2016-06-14 01:12:15 -07:00
Bala FA f2765d98a8 XL: set write quorum (no. of disk / 2) + 2 (#1876)
Previously write quorum was set to (no. of disk / 2) + 3.  As per new
change, the write quorum is set to (no. of disk / 2) + 2.  This helps
to accommodate one more failure of disk.
2016-06-08 22:12:36 -07:00
Krishna Srinivas acc393ba8b XL/tree-walk: Added comments, changed variable names and structure fields to improve code readability. (#1856) 2016-06-05 11:55:45 -07:00
Harshavardhana 1cf1532ca3 XL: Implement ListObjects channel and pool management. 2016-06-03 12:17:54 -07:00
Harshavardhana fb95c1fad3 XL: Bring in some modularity into format verification and healing. (#1832) 2016-06-02 16:34:15 -07:00
Harshavardhana de21126f7e XL: Re-align the code again. 2016-06-02 01:54:06 -07:00
Harshavardhana ae311aa53b XL: Cleanup, comments and all the updated functions. (#1830) 2016-06-01 16:43:31 -07:00
Harshavardhana 445dc22118 XL: Cleanup and add more comments. (#1807) 2016-05-30 16:51:59 -07:00
Harshavardhana 34e9ad24aa XL: Introduce new API StorageInfo. (#1770)
This is necessary for calculating the total storage
capacity from object layer. This value is also needed for
browser UI.

Buckets used to carry this information, this patch
deprecates this feature.
2016-05-28 15:15:53 -07:00
Harshavardhana 553fdb9211 XL: Bring in support for object versions written during writeQuorum. (#1762)
Erasure is initialized as needed depending on the quorum and onlineDisks.
This way we can manage the quorum at the object layer.
2016-05-28 15:15:53 -07:00
Harshavardhana 293d246f95 XL/FS: Rewrite in new format. 2016-05-28 15:15:53 -07:00
Harshavardhana 4e34e03dd4 xl/fs: Split object layer into interface. (#1415) 2016-04-29 14:24:10 -07:00
Krishna Srinivas 7066ce5160 XL/Multipart: rename the parts instead of concatenating. (#1416) 2016-04-29 12:17:48 -07:00
Harshavardhana 984903cce1 server: Add global namespace lock. (#1398)
Fixes #1393
2016-04-29 01:29:09 -07:00
Harshavardhana a1a667ae5d xl: Change fileMetadata to xlMetadata. (#1404)
Finalized backend format

```
{
    "version": "1.0.0",
    "stat": {
        "size": 24256,
        "modTime": "2016-04-28T00:11:37.843Z"
    },
    "erasure": {
        "data": 5,
        "parity": 5,
        "blockSize": 4194304
    ],
    "minio": {
        "release": "RELEASE.2016-04-28T00-09-47Z"
    }
}
```
2016-04-28 19:27:02 -07:00
Harshavardhana 41b35cff7b xl: Fixes a bug in read quorum ListFiles() (#1412)
Fixes a bug in #1406
2016-04-28 17:32:46 -07:00
Harshavardhana 2ac10209cc xl: ListFiles - return sorted files. (#1408)
Fixes #1407
2016-04-28 01:48:57 -07:00
Bala FA 5bd6b0b510 xl: check read quorum for ListFiles() (#1406)
Fixes #1364
2016-04-27 21:09:26 -07:00
Harshavardhana 5fffd558d0 xl/heal: Make healFile non-blocking for StatFile and ReadFile. (#1399)
Fixes #1355
2016-04-27 15:10:19 -07:00
Harshavardhana 90987df9b4 objectapi: Simplify ListMultipart combine recursive and non-recursive. (#1390)
Fixes #1365
2016-04-26 17:57:16 -07:00
Harshavardhana ad1abc4486 xl-v1/Cleanup: use listOnlineDisks instead of getReadableDisks. (#1389)
Remove usage of getFileVersionQuorumMap, instead use listFileVersions
to get the version list and extract higherVersion.

Fixes #1379
Fixes #1378
Fixes #1377
2016-04-26 13:03:37 -07:00
Krishna Srinivas 4333e529e6 xl/ListFiles: return as many objects as requested. (#1383)
* xl/ListFiles: return as many objects as requested and take care of eof (#1361)

* xl/ListFiles: fix review comments.

* xl/ListFiles: Add windows filepath translation.

* xl/ListFiles: Use slashSeparator instead of "/". Remove filepath.FromSlash() as golang-windows takes care of it automatically.
2016-04-26 10:35:39 -07:00
Harshavardhana 8bce699dae xl: Add logging. (#1372) 2016-04-25 12:47:31 -07:00
Harshavardhana cab6805f09 xl: Enable a subset of tests for XL branch. (#1359) 2016-04-25 12:47:31 -07:00
Krishna Srinivas becc814531 Xl layer selfheal quorum2
* xl/selfheal: selfheal based on read quorum on GET

* xl: getReadableDisks() also returns whether self-heal is needed so that this info can be used by ReadFile/SelfHeal/StatFile.

* xl: trigger selfheal from StatFile.
2016-04-25 12:47:31 -07:00
Harshavardhana 9bd9441107 xl: Simplify reading metadata and add a new fileMetadata type. (#1346) 2016-04-25 12:47:31 -07:00
Harshavardhana f3784d1087 xl: Handle read quorum for StatVol, ListVols 2016-04-25 12:47:31 -07:00
Harshavardhana c7bf471c9e list/xl: Fix the way marker is handled in leafDirectory verification. 2016-04-25 12:47:31 -07:00
Krishna Srinivas c302875774 selfheal: implement self-heal. Heals the missing parts. (#1335) 2016-04-25 12:47:31 -07:00
Harshavardhana b76f3f1d62 xl: Add more fixes and cleanup.
Simplify cleanup of temporary files during createFile operations.
2016-04-25 12:47:31 -07:00
Bala FA ada0f82b9a xl: add quorum support for read file and name space locking. (#1333) 2016-04-25 12:47:31 -07:00
Harshavardhana a98a7fb1ad Implement XL layer - preliminary work. 2016-04-25 12:47:31 -07:00