Commit Graph

20 Commits

Author SHA1 Message Date
Harshavardhana d45a8784fc
Fix hash order to generate more even distribution (#5247)
The problem in existing code was the following line

```
start := int(keyCrc%uint32(cardinality)) | 1
```

A given a value of N cardinality the ending result
because of the the bitwise '|' would lead to always
higher affinity to odd sequences.

As can be seen from the test cases that this can
lead to many objects being allocated the same set
of disks or atleast the first disk is an odd disk
always.  This introduces a performance problem
for majority of the objects under concurrent load.

Remove `| 1` to provide a more cleaner distribution
and the new code will be.
```
start := int(keyCrc % uint32(cardinality))
```

Thanks to Krishna Srinivas for pointing out the bitwise
situation here.
2017-11-30 12:57:03 -08:00
Harshavardhana 8efa82126b
Convert errors tracer into a separate package (#5221) 2017-11-25 11:58:29 -08:00
Harshavardhana 0b546ddfd4 Return errors in PutObject()/PutObjectPart() if input size is -1. (#5015)
Amazon S3 API expects all incoming stream has a content-length
set it was superflous for us to support object layer which supports
unknown sized stream as well, this PR removes such requirements
and explicitly error out if input stream is less than zero.
2017-10-06 09:38:01 -07:00
Bala FA 88938340b3 remove all dead codes (#5019)
Fixes #5012
2017-10-05 12:25:45 -07:00
Andreas Auernhammer 85fcee1919 erasure: simplify XL backend operations (#4649) (#4758)
This change provides new implementations of the XL backend operations:
 - create file
 - read   file
 - heal   file
Further this change adds table based tests for all three operations.

This affects also the bitrot algorithm integration. Algorithms are now
integrated in an idiomatic way (like crypto.Hash).
Fixes #4696
Fixes #4649
Fixes #4359
2017-08-14 18:08:42 -07:00
Anis Elleuch af8071c86a xl: Fix rare freeze after many disk/network errors (#4438)
xl.storageDisks is sometimes passed to some low-level XL functions. Some disks in
xl.storageDisks are set to nil when they encounter some errors. This means all
elements in xl.storageDisks will be nil after some time which lead to an unusable XL.
2017-06-14 17:14:27 -07:00
Aditya Manthramurthy 8975da4e84 Add new ReadFileWithVerify storage-layer API (#4349)
This is an enhancement to the XL/distributed-XL mode. FS mode is
unaffected.

The ReadFileWithVerify storage-layer call is similar to ReadFile with
the additional functionality of performing bit-rot checking. It
accepts additional parameters for a hashing algorithm to use and the
expected hex-encoded hash string.

This patch provides significant performance improvement because:

1. combines the step of reading the file (during
erasure-decoding/reconstruction) with bit-rot verification;

2. limits the number of file-reads; and

3. avoids transferring the file over the network for bit-rot
verification.

ReadFile API is implemented as ReadFileWithVerify with empty hashing
arguments.

Credits to AB and Harsha for the algorithmic improvement.

Fixes #4236.
2017-05-16 14:21:52 -07:00
Bala FA de204a0a52 Add extensive endpoints validation (#4019) 2017-04-11 15:44:27 -07:00
Krishnan Parthasarathi 417ec0df56 HealObject should succeed when only N/2 disks have data (#3952) 2017-03-22 10:15:16 -07:00
Bala FA 1c97dcb10a Add UTCNow() function. (#3931)
This patch adds UTCNow() function which returns current UTC time.

This is equivalent of UTCNow() == time.Now().UTC()
2017-03-18 11:28:41 -07:00
Harshavardhana bcc5b6e1ef xl: Rename getOrderedDisks as shuffleDisks appropriately. (#3796)
This PR is for readability cleanup

- getOrderedDisks as shuffleDisks
- getOrderedPartsMetadata as shufflePartsMetadata

Distribution is now a second argument instead being the
primary input argument for brevity.

Also change the usage of type casted int64(0), instead
rely on direct type reference as `var variable int64` everywhere.
2017-02-24 09:20:40 -08:00
Harshavardhana 1b30a3be2b xl/utils: getPartSizeFromIdx should return error. (#3669) 2017-01-31 15:34:49 -08:00
Anis Elleuch e9394dc22d xl PutObject: Split object into parts (#3651)
For faster time-to-first-byte when we try to download a big object
2017-01-30 15:44:42 -08:00
Harshavardhana 62f8343879 Add constants for commonly used values. (#3588)
This is a consolidation effort, avoiding usage
of naked strings in codebase. Whenever possible
use constants which can be repurposed elsewhere.

This also fixes `goconst ./...` reported issues.
2017-01-18 12:24:34 -08:00
Harshavardhana 5197649081 utils: reduceErrs returns and validates quorum errors. (#3300)
This is needed as explained by @krisis

Lets say we have following errors.

```
[]error{nil, errFileNotFound, errDiskAccessDenied, errDiskAccesDenied}
```

Since the last two errors are filtered, the maximum is nil,
depending on map order.

Let's say we get nil from reduceErr. Clearly at this point
we don't have quorum nodes agreeing about the data and since
GetObject only requires N/2 (Read quorum) and isDiskQuorum
would have returned true. This is problematic and can lead to
undersiable consequences.

Fixes #3298
2016-11-21 01:47:26 -08:00
Harshavardhana 39331b6b4e xl: GetCheckSumInfo() shouldn't fail if hash not available. (#2984)
In a multipart upload scenario disks going down and coming backup
can lead to certain parts missing on the disk/server which was
going down. This is a valid case since these blocks can be
missing and should be healed through heal operation. But we are
not supposed to fail prematurely since we have enough data on
the other disks as well within read-quorum.

This fix relaxes previous assumption, fixes a major corruption
issue reproduced by @vadmeste.

Fixes #2976
2016-10-18 11:13:25 -07:00
Harshavardhana 9216981262 tests: Add test for diskCount. (#2717)
Fixes #2312
2016-09-16 13:44:52 -07:00
Karthic Rao 8bd78fbdfb performance: gjson parsing for readXLMeta, listParts, getObjectInfo. (#2631)
- Using gjson for constructing xlMetaV1{} in realXLMeta.
- Test for parsing constructing xlMetaV1{} using gjson.
- Changes made since benchmarks showed 30-40% improvement in speed.
- Follow up comments in issue https://github.com/minio/minio/issues/2208
  for more details.
- gjson parsing of parts from xl.json for listParts.
- gjson parsing of statInfo from xl.json for getObjectInfo.
- Vendorizing gjson dependency.
2016-09-13 21:18:30 -07:00
Krishna Srinivas 9358ee011b logging: Print stack trace in case of errors.
fixes #1827
2016-09-13 21:18:30 -07:00
Harshavardhana bccf549463 server: Move all the top level files into cmd folder. (#2490)
This change brings a change which was done for the 'mc'
package to allow for clean repo and have a cleaner
github drop in experience.
2016-08-18 16:23:42 -07:00