All Versions
79
Latest Version
Avg Release Cycle
70 days
Latest Release
1423 days ago
Changelog History
Page 7
Changelog History
Page 7
-
v0.14.3 Changes
June 21, 2013π Improved
- Improved redundant-manager's performance when retrieving redundancies by up to 20%
- Changed method of retrieving redundancies from ets to worker-processes
- Make a parameter of consumption of queue's message interval into the application config
- Replace obsolete functions crypto:sha|md5 with crypto:hash
- Improved redundant-manager's performance when retrieving redundancies by up to 20%
π Fixed Bugs
- Manager
- Some problem with bucket names format
- Storage
- The number of queue messages can be wrong value
- Needed to call bitcask:merge/1 after relaunch the storage process
- Compaction-function can fail - "did not match data" when a target file is corrupted
- The number of queue messages can be wrong value
- Manager
π Used libraries
- Leo Project
- leo_backend-db v0.12.16
- leo_cache v0.4.8
- leo_commons v0.14.3
- leo_dcerl v0.2.3
- leo_logger v0.10.11
- leo_mcerl v0.2.3
- leo_mq v0.12.17
- leo_object_storage v0.14.4
- leo_ordning_reda v0.8.14
- leo_redundant_manager v1.0.1
- leo_s3_libs v0.12.13
- leo_statistics v0.14.3
- leo_gateway v0.14.5
- leo_manager v0.14.3
- leo_storage v0.14.3
- Others
- bitcask v1.6.2
- cowboy v0.8.6
- folsom
- jiffy
- lz4 v0.1.1 - forked from szktty/erlang-lz4
- Leo Project
-
v0.14.2 Changes
June 07, 2013π New Features
- Supported rack-awareness replica placement
π Improved
- Gateway
- Improved cache-libs, which are mem-cache and disc-cache.
- Refactoring codes - Getting rid of duplicate codes to "libcutil"
- Using file:sendfile/2 when retrieving an object from disk cache(dcerl)
- Improve S3-API's compatibility
- Supported "Range request API" for a large object
- Supported retrieving object-list
- Upgrade Cowboy to v0.8.5
- Improved cache-libs, which are mem-cache and disc-cache.
- Storage
- Improved data-compaction
- Performance tuning
- Avoid polluting OS page caches during compaction
- Modified the launch process
- Able to retry connection with manager(s)
- Improved data-compaction
- Manager
- Supported to Able to remove gateway-node from manager's console when the state of specified node is βstopβ
- Supported system-data backup/restore (mnesia)
- Supported taking over manager(s) for affected hardware failure
- Supported taking over storage-node when having attach/detach nodes in operation
- Able to take over from detach-node's files to attach-node
- Gateway
π Fixed Bugs
- Gateway
- Reply empty response unintentionally when using some s3-clients
- Gateway
π Used libraries
- Leo Project
- leo_backend-db v0.12.14
- leo_cache v0.4.7
- leo_commons v0.14.1
- leo_dcerl v0.2.2
- leo_logger v0.10.10
- leo_mcerl v0.2.2
- leo_mq v0.12.15
- leo_object_storage v0.14.3
- leo_ordning_reda v0.8.13
- leo_redundant_manager v0.14.2
- leo_s3_libs v0.12.10
- leo_statistics v0.14.2
- leo_gateway v0.14.4
- leo_manager v0.14.2
- leo_storage v0.14.2
- Others
- bitcask v1.6.2
- cowboy v0.8.5
- folsom
- jiffy
- lz4 v0.1.1 - forked from szktty/erlang-lz4
- Leo Project
-
v0.14.1 Changes
April 15, 2013- π Improved
- Gateway
- Commonize request-handler for easily creating APIs
- Improve cache-controller which was replaced from ecache to leo_cache
- Improve performance
- Upgrade Ranch and Cowboy to latest version
- Storage
- Improved phased data-compaction
- To realize non-blocking data-compaction
- before: Making compaction per an "object-storage-file"
- after: Making compaction per an object
- To realize non-blocking data-compaction
- Improved phased data-compaction
- Manager/Storage
- Implement judgment of precondition in rebalance-comamnd
- Implemented
recover-command
in Manager- To realize:
- synchronize a file:
recover file ${file-path}
- recover a target-node files:
recover node ${storage-node}
- recover target-node RING:
recover ring ${storage-node}
- synchronize a file:
- To realize:
- Gateway
π Fix Bugs
- NOT worked
s3cmd
by degraded - Stored wrong file-path with REST-API by degraded
- NOT worked
π Used libraries
- Leo Project
- leo_cache v0.4.4
- leo_commons v0.12.12
- leo_backend-db v0.12.11
- leo_object_storage v0.14.1
- leo_mq v0.12.12
- leo_ordning_reda v0.8.11
- leo_redundant_manager v0.12.19
- leo_s3_libs v0.12.8
- leo_statistics v0.10.11
- leo_logger v0.10.8
- leo_gateway v0.14.1
- leo_manager v0.14.1
- leo_storage v0.14.1
- cherly v0.12.5
- dcerl v0.4.1
- Others
- bitcask
- cowboy v0.8.3
- folsom
- jiffy
- lz4 v0.1.1 - forked from szktty/erlang-lz4
- Leo Project
- π Improved
-
v0.14.1-1 Changes
May 08, 2013- π Improved
- Gateway
- Upgrade Ranch and Cowboy to latest version
- Gateway
- π Fix Bugs
- Gateway
- Reply empty response unintentionally when using some s3 clients
- "leo_gateway" stored a "0-byte length object" into the cache when put an large-object(over 5MB) from clients. So We supported to remove a registered object from the cache.
- Reply empty response unintentionally when using some s3 clients
- Gateway
- π Improved
-
v0.14.0 Changes
March 20, 2013π Improved
- Upgrade Cowboy from 0.6.2(foked/add patches) to 0.8.2(original)
- Improved put/get large-object performance
- Support recovery of manager-status-monitor after network partition occured
- Upgrade Cowboy from 0.6.2(foked/add patches) to 0.8.2(original)
π Fix bugs
- Recovery objects (Storage)
- Ignore
detach-status
from replication-message
- Ignore
- Not handle
compaction-start command
invalid argument on Manager-console
- Recovery objects (Storage)
π Used libraries
- Leo Project
- Others
- bitcask
- cowboy v0.8.2
- folsom
- jiffy
- lz4 v0.1.1 - forked from szktty/erlang-lz4
-
v0.14.0-RC2 Changes
March 14, 2013π Improved
- Improved cache-mechanism (Gateway)
- Support Layered Cache, First cache-layer is RAM and Secondary cache-layer is SSD (or HDD)
- This version realized that cache-destination is decided by object-size
- Need to set gateway's configuration
- Improved cache-mechanism (Gateway)
π Fix bugs
- Incorrect judgement of active storage-node
- Possibility of including node(s) of
attached (status)
- Possibility of including node(s) of
- Incorrect judgement of active storage-node
π Used libraries
- Leo Project
- leo_commons v0.12.11
- leo_backend-db v0.12.10
- leo_object_storage v0.12.29
- leo_mq v0.12.11
- leo_ordning_reda v0.8.10
- leo_redundant_manager v0.12.17
- leo_s3_libs v0.12.7
- leo_statistics v0.10.10
- leo_logger v0.10.7
- leo_gateway v0.14.0-RC2
- leo_manager v0.14.0-RC2
- leo_storage v0.14.0-RC2
- ecache v0.10.14
- cherly v0.12.4
- Others
- bitcask
- cowboy v0.6.2 - forked from extend/cowboy
- folsom
- jiffy
- lz4 v0.1.1 - forked from szktty/erlang-lz4
- Leo Project
-
v0.14.0-RC1 Changes
March 05, 2013π Improved
- Improved cache-mechanism (Gateway)
- According to improving efficiency of object-cache-pool, LeoFS-Gateway was able to store an object up to 8MB into the RAM
- Improved data-compaction related processes (Storage, Manager)
- Realized compact a part of data-storage, which called "phased data-compaction"
- Realized
suspend
andresume
data-compaction, also able to comfirm status of processes
- Supported recovery from temporally network unlink #1 (Storage, Manager)
- Automatically recovered target-node(s), which status transition from
stop
torunning
- Automatically recovered target-node(s), which status transition from
- Improved cache-mechanism (Gateway)
π Fix bugs
- Cannot consume queueing-message(s) when storage cluster has a detached node
- Resolved that messages of a detached node ignored
- Cannot consume queueing-message(s) when storage cluster has a detached node
π Used libraries
- Leo Project
- leo_commons v0.12.10
- leo_backend-db v0.12.9
- leo_object_storage v0.12.28
- leo_mq v0.12.9
- leo_ordning_reda v0.8.9
- leo_redundant_manager v0.12.15
- leo_s3_libs v0.12.6
- leo_statistics v0.10.9
- leo_logger v0.10.6
- leo_gateway v0.14.0-RC1
- leo_manager v0.14.0-RC1
- leo_storage v0.14.0-RC1
- ecache v0.10.8
- cherly v0.12.4
- Others
- bitcask
- cowboy v0.6.2 - forked from extend/cowboy
- folsom
- jiffy
- lz4 v0.1.1 - forked from szktty/erlang-lz4
- Leo Project
-
v0.12.7 Changes
December 26, 2012- π Improve performances
- Storage Performance Tuning#6
- Related libs: [leo_storage, leo_object_storage]
- Reduced compaction-cost
- Able to execution of parallel comaction
- Get maximum performance by setting a appropriate number corresponding with number of cores.
- Able to execution of parallel comaction
- Storage Performance Tuning#6
- π Improve
- Gateway:
- The optimal timeout according to file size set up.
- Modified default cache mode from 'http' to 'inner'
- Storage:
- Modified completion of storage for restriction of file destruction
- When shutting down storage, in charge of storage-process close files
- Refactor message-queue functions
- Unified read-failure's queue and write-failure's queue
- Modified completion of storage for restriction of file destruction
- Gateway:
π Fix bugs
- Storage:
- Overwrite an object during rebalance
- Always check the version(clock) of object
- Fix haystacks reopen correctly when failing compaction
- Overwrite an object during rebalance
- Manager-Console
- Crush get-endpoints when no-records
- Crush get-users when no-records
- Storage:
π Used libraries
- Leo Project
- Others
- bitcask
- cowboy v0.6.2 - forked from extend/cowboy
- folsom
- jiffy
- lz4 v0.1.1 - forked from szktty/erlang-lz4
- π Improve performances
-
v0.12.5 Changes
December 07, 2012- π Improve performances
- Storage Performance Tuning#5
- Related libs: [leo_storage, leo_object_storage]
- Reduced using spawn/1 in replicator #2
- Storage Performance Tuning#5
- π Improve
- Able to monitor VM-values on Leo Manager's console
- Deprecate parameterized module in leo_object_storage
- Reference: http://www.erlang.org/news/35
- Modified re-launch storage process
- When regularly stop the storage-process, It writes current status in a file. Then it restarts the storage-process when reading the file.
- Able to post a large part of an object to LeoFS with multipart-upload API.
π Fix bugs
- Respond invalid "Etag" from the gateway when using multipart-upload API.
- Possibility of file-destruction
- Termination of storages for the restriction of file-destruction
- Related libs: [leo_storage, leo_object_storage]
- Termination of storages for the restriction of file-destruction
π Used libraries
- Leo Project
- Others
- bitcask
- cowboy v0.6.2 - forked from extend/cowboy
- folsom
- jiffy
- lz4 v0.1.1 - forked from szktty/erlang-lz4
- π Improve performances
-
v0.12.4 Changes
November 21, 2012- π Improve performances
- Storage Performance Tuning#4
- Target libs: [leo_storage, leo_object_storage]
- Reduced using spawn/1 in replicator #1
- Used rpc:cast/4 for async-replication
- Storage Performance Tuning#4
- π Improve
- Able to retrieve leofs-uesrs from manager-console
- NOT allow duplication registration of a user-account into the s3-credential
π Fix bugs
- Fail rebalance and compaction when exists chunked objects in the storage
- Manager-console crashed when inputed invalid parameter(s)
π Used libraries
- Leo Project
- Others
- bitcask
- cowboy v0.6.2 - forked from extend/cowboy
- folsom
- jiffy
- lz4 v0.1.1 - forked from szktty/erlang-lz4
- π Improve performances