1
0
mirror of https://github.com/gluster/glusterd2.git synced 2026-02-06 06:45:35 +01:00

Commit Graph

  • 54ce5f6f7a blockvolume: Code re-org to fix race condition and cleanup bhv master Poornima G 2019-03-09 12:25:00 +05:30
  • 9054f74a6b added method for acquiring txn Lock with retry mechanism Oshank Kumar 2019-03-13 15:28:39 +05:30
  • 00652479ad Downgrade lvm2, disable lvmetad and dmevent Kotresh HR 2019-03-09 14:09:06 +05:30
  • 568322a4b7 Fix function comments based on best practices from Effective Go CodeLingo Bot 2019-03-15 13:17:28 +13:00
  • 82e1c185aa Add gluster-rsyslog Alpine container Sridhar Seshasayee 2019-03-11 19:21:49 +05:30
  • dc3d7e054a nightly-contaienr: Switch glusterfs release-6 nightly rpms Kaushal M 2019-03-08 16:15:32 +05:30
  • 73f5bbdeef Check aliveness of all nodes in a single etcd query Oshank Kumar 2019-03-05 16:57:29 +05:30
  • 994aaa0489 broadcast an event on election of cleanup leader Oshank Kumar 2019-02-28 12:48:54 +05:30
  • 829f22ac31 transaction: adding txns under pending-transaction/transaction/ key Oshank Kumar 2019-02-22 22:33:42 +05:30
  • 9093acb370 expose all txn related timeouts as expvars Oshank Kumar 2019-01-22 15:11:37 +05:30
  • c82180e979 BlockVolume: Reduce the number of clusterlocks Poornima G 2019-02-19 11:22:42 +05:30
  • 2869f88344 BlockVolume: Input block host volume properties in block create request Poornima G 2019-01-25 14:35:28 +05:30
  • a94bec26fc tracing: refactor tracing code in transaction Oshank Kumar 2019-02-14 20:55:08 +05:30
  • f46dee66ce fixed Merge conflicts and added a middleware in txn Executor to record trace information Oshank Kumar 2019-02-12 10:32:05 +05:30
  • 698448f229 transaction: refactor txn.Do() method Oshank Kumar 2019-01-10 20:12:34 +05:30
  • c3b0cc3f1e transaction: resume txn if a peer restarts Oshank Kumar 2019-01-08 17:26:32 +05:30
  • 17bc6f49cc Added max limit for loopback brick size Aravinda VK 2019-02-12 12:25:32 +05:30
  • bebbc65052 Support for loopback bricks Aravinda VK 2019-01-10 09:22:45 +05:30
  • 830c8c9ff0 Tracing: Generate new endpoints.md with new tracing endpoints. Sridhar Seshasayee 2019-02-12 00:26:00 +05:30
  • ec25ca6619 Tracing: Implement glustercli command to disable the trace configuration Sridhar Seshasayee 2019-01-14 01:37:35 +05:30
  • 219ce69b48 Tracing: Implement glustercli command to update the trace configuration Sridhar Seshasayee 2019-01-12 00:24:49 +05:30
  • 4c65b6f95a Tracing: Implement glustercli command to get current tracing status Sridhar Seshasayee 2019-01-11 11:54:11 +05:30
  • 6158f4a040 Tracing: Implement glustercli command to enable tracing Sridhar Seshasayee 2019-01-10 10:58:24 +05:30
  • 2a5df76893 Tracing: Apply trace config from store if present on GD2 start-up Sridhar Seshasayee 2018-12-24 23:43:52 +05:30
  • fc9596d555 Tracing: Implement Undo step for trace enable transaction. Sridhar Seshasayee 2019-01-10 13:01:19 +05:30
  • 76a5a9f928 Tracing: Implement gd2 plugin that enables tracing across the cluster. Sridhar Seshasayee 2018-12-20 14:59:13 +05:30
  • 3e4f7a1b07 Tracing: Introduce new Jaeger trace config options and management logic. Sridhar Seshasayee 2018-11-23 21:19:14 +05:30
  • 520305c9f0 Tracing: Include span info in transactionv2 Txn structure. Sridhar Seshasayee 2019-01-09 00:27:26 +05:30
  • 31c7e8a065 Tracing: Remove hardcoded option to always sample traces in ocgrpc handlers Sridhar Seshasayee 2018-11-28 12:18:13 +05:30
  • 9aed7a59a5 Gluster-virtblock: Improve the GET/DELETE blocks api performance Poornima G 2019-01-23 12:12:27 +05:30
  • df3f7a764c Fix auto creation of block host volume Poornima G 2019-01-28 11:03:16 +05:30
  • a37193deab Initialize config and logging before main() starts to execute Oshank Kumar 2019-01-14 18:32:45 +05:30
  • 9c6ee47f50 blockvolume: change log level from info to debug in RegisterProvider func closes #1475 Oshank Kumar 2019-01-11 18:49:42 +05:30
  • fff7c211e7 xlators default orders and volume default options Aravinda VK 2019-01-23 11:25:17 +05:30
  • ca3d113915 use cluster-options for host volume configuration Oshank Kumar 2019-01-23 15:23:08 +05:30
  • 13757cfa33 Fix thin arbiter Option name Aravinda VK 2019-01-24 11:34:33 +05:30
  • 445cdb9256 Fixing volume set options functionality Fixes:#1445 rishubhjain 2019-01-21 06:27:56 -05:00
  • f4692484ae Fix restclient api gluster virtblock Kotresh HR 2019-01-21 09:50:55 +05:30
  • d51f60b084 gluster-virtblock: Rename to virtual block Kotresh HR 2019-01-17 15:52:58 +05:30
  • 4103a89b66 Add resclient api for block volume Poornima G 2019-01-10 12:35:57 +05:30
  • 8034fbdd10 Add loopback block provider Poornima G 2018-12-25 15:23:15 +05:30
  • 5800472c20 Skip local bricks path validation if auto provisioned volume Aravinda VK 2019-01-12 20:40:54 +05:30
  • 1353b0e79f Set options metadata-self-heal, entry-self-heal and data-self-heal in glustershd e2e tests to successfully heal. Change introduced in https://review.gluster.org/#/c/glusterfs/+/21938/. The above three options are not set to off by default in glustershd volfile. Vishal Pandey 2019-01-15 15:47:26 +05:30
  • dfb24628dc Improve brick mux e2e test suite. Handle cases causing spurious failures in brickmux tests. Increase waiting time for bricks to sign in and add sleep whereever a new gd2 instance is respawned to give enough time to bricks to sign in properly and multiplex. Vishal Pandey 2019-01-03 00:46:49 +05:30
  • 79d998788e transaction: increase timeout fot transaction Oshank Kumar 2019-01-04 16:18:10 +05:30
  • c896a94589 Skip lvs command during thinpool delete Aravinda VK 2019-01-07 10:58:23 +05:30
  • 8ef2e187de block volume: added a common function for updating available hosting volume size Oshank Kumar 2019-01-03 17:17:12 +05:30
  • 9bd5bc9173 block volume: Fix Merge conflicts in volume-start.go Oshank Kumar 2019-01-03 13:57:08 +05:30
  • cf94e9f39c update dependencies using dep ensure Oshank Kumar 2018-12-21 18:22:03 +05:30
  • 12aef05756 block-volume: change size type from int64 to uint64 Oshank Kumar 2018-12-21 11:31:58 +05:30
  • 6cedc1082f block-volume: added a interface for host volume management. Oshank Kumar 2018-12-18 18:07:42 +05:30
  • 6b4ba1037f block-volume: moved common code to a utils package Oshank Kumar 2018-12-18 14:43:36 +05:30
  • 9b6e78fe05 gd2 plugin: added a plugin for block volume management Oshank Kumar 2018-11-30 15:15:34 +05:30
  • 0839909c62 Removed redundant log messages Aravinda VK 2019-01-04 11:19:14 +05:30
  • 5dd12549da check connectivity to peer before sending join cluster request. Oshank Kumar 2018-12-26 20:56:08 +05:30
  • a6fc33c2b1 txn Lock: acquire cluster locks while creating a txn Oshank Kumar 2019-01-02 21:31:34 +05:30
  • 922ec7f3d6 Migrate volume operations(start,stop,del) to new txn framework Oshank Kumar 2019-01-02 19:25:45 +05:30
  • 0a30ce1f4c txn Engine: refactor code and fix a minor issue in step synchronization Oshank Kumar 2018-12-30 20:47:22 +05:30
  • 601ba61cea Issue - Vishal Pandey 2018-12-24 16:31:28 +05:30
  • d4ca2cb0b6 Add online status to peer add response Madhu Rajanna 2018-12-24 10:40:15 +05:30
  • 4d140ab8b5 add prune to Gopkg.toml file Madhu Rajanna 2018-12-21 12:57:29 +05:30
  • 27859b48fe cluster-lock: fix getting cluster wide etcd lock Oshank Kumar 2018-12-19 16:41:50 +05:30
  • 0827c74916 Do not allocate memory manually while creating RPC buffer Aravinda VK 2018-12-18 18:09:49 +05:30
  • 500e5912a1 minimum brick size validation during Volume create Hari Gowtham 2018-12-17 13:36:07 +05:30
  • ea22407fc9 Avoid using lvm lock while using readonly commands Aravinda VK 2018-12-18 10:58:19 +05:30
  • 18c0b006be Add device info cli command Madhu Rajanna 2018-12-16 15:04:30 +05:30
  • 140393c6fa Add logging if there is an error in CLI Madhu Rajanna 2018-12-17 10:36:21 +05:30
  • c198e1173b add regex for different volume size format Madhu Rajanna 2018-12-17 11:07:04 +05:30
  • e432ed380d Add total and used field to device response Madhu Rajanna 2018-12-17 10:15:39 +05:30
  • 9bfa47103e print volume capacity,used and free size in human readable format Madhu Rajanna 2018-12-16 15:53:58 +05:30
  • 0358340132 Fix spelling mistake Madhu Rajanna 2018-12-16 15:53:12 +05:30
  • 5814720454 Implement max-bricks-per-process option for brick multiplexing. The implementation is an extension to brick-multiplexing. The max-bricks-per-process is being monitored by using entries in pmap corresponding to a particular port. So, If a brick needs to be multiplexed following are the series of steps that needs to be followed. The following are the genralised sets of steps - - look into all started volumes with same options as the current volume(one by one) - traverse through all local bricks of taregtVolume - find the port of the local brick by using its path - look for number of entries in pmap corresponding to particular port No. and count num of bricks already attached to that port - If the number of bricks attached to a port is less that max-bricks-per-process constraint - Then we have our target brick or repeat from step 1 until all targetVolumes are covered. - Since current volume is not considered into started volumes list, so if we don't have any target brick yet from any of the started volumes then - look for any target brick in the current volume - If even the current volume doesn't have any target brick then - start seperate glusterfsd. Vishal Pandey 2018-12-06 23:55:51 +05:30
  • 5f8ec37832 Profiling: to implement go profiling in glusterd2 Hari Gowtham 2018-11-27 17:42:40 +05:30
  • 0c5d70f231 Fix misspelled English words Madhu Rajanna 2018-12-14 10:42:58 +05:30
  • de2e950e1c Fix ineffectual assignments in Go code Madhu Rajanna 2018-12-14 10:38:17 +05:30
  • 752b408bb5 Fix golint issues Madhu Rajanna 2018-12-14 10:27:42 +05:30
  • 2bf5b53cb2 Fix xlator .so read failure if no options Aravinda VK 2018-12-14 17:50:40 +05:30
  • 040c63d8a8 Fix error message Madhu Rajanna 2018-12-13 11:27:24 +05:30
  • 4b2888c485 volume stop: return error if volume is not in started state Madhu Rajanna 2018-12-12 17:59:38 +05:30
  • 56dc388f64 Auto distribute count based on Max brick size Aravinda VK 2018-12-12 12:55:03 +05:30
  • 05fee9fdbc Volume Create: Add a check to validate if volume exists Madhu Rajanna 2018-12-13 16:46:37 +05:30
  • ee2fb7f89a Normalize the xlator name when stored in Volinfo Aravinda VK 2018-12-13 12:34:17 +05:30
  • 74924d58db Removing volume stop from replace-brick e2e test case rishubhjain 2018-12-12 08:32:30 -05:00
  • 5f889176c9 Update transactions to use Sync Kaushal M 2018-12-11 16:24:12 +05:30
  • 744704d231 transaction: restore logs of txn lock Oshank Kumar 2018-11-21 16:02:16 +05:30
  • c6e4d23e42 transaction: removed duplicate code Oshank Kumar 2018-11-14 19:03:12 +05:30
  • ed884b2af4 transaction: used etcd Election to elect cleanup leader Oshank Kumar 2018-10-31 19:16:31 +05:30
  • b7e1f6040b transaction: Implemented Txn Engine Oshank Kumar 2018-09-07 17:21:58 +05:30
  • 0a44716619 doc: Add a design document for the transaction framework Kaushal M 2018-07-11 21:09:24 +05:30
  • 9361638cfc Default Options for new Volumes Aravinda VK 2018-12-07 16:22:35 +05:30
  • 755eff7f5f build: Use random build id Kaushal M 2018-12-10 22:32:32 +05:30
  • cf00bdf93a nightly-rpms: Use golang from EPEL on EL7 Kaushal M 2018-12-10 11:55:02 +05:30
  • a9044cb33d logging: log in UTC timezone Madhu Rajanna 2018-12-11 09:38:51 +05:30
  • aeffd41917 Replacing afr to replicate as xlator option rishubhjain 2018-12-10 11:33:07 -05:00
  • bc57805ca2 Fix go vet issues Madhu Rajanna 2018-12-10 12:17:07 +05:30
  • 8a52b23d84 Replace brick api rishubhjain 2018-12-07 08:19:18 -05:00
  • a84850d37a Improved test suite for self heal feature Vishal Pandey 2018-12-04 13:16:36 +05:30
  • 8de2a9ee49 Fix Option names in group profile and add db profile Aravinda VK 2018-12-06 18:06:17 +05:30
  • b73370c553 Fix #1321: acceptLoop keeps a list of all sessions, and each session keeps a reference to the memory block allocated as a read buffer. This reference is there even if the session closes, so as long as acceptLoop runs, memory keeps growing. This should fix it by doing two things: 1) When session closes, remove the reference to the buffer. But that will still continue to leak sessions, because nothing removes elements from the session list. So, 2) remove the logic that keep track of sessions, instead, run two goroutines for each session, one to keep the session and run the server, and the other to terminate the first one when needed. Burak Serdar 2018-12-06 09:36:22 -07:00
  • 119cbb6823 ISSUE - MountLocalBricks() and MountVolumeBricks() are called during GD2 startup. Both these methods are responsible for mounting bricks for all the volumes in the store. MountLocalBricks() exits as soon as there is some issue with mounting any volume's localBricks because of which other volumes' localBricks(which are yet to be processed) are skipped for mounting. MountVolumeBricks() exits as soon as any one of the brick of that volume is unable to be mounted because of which other localBricks of that volume(which are yet to be processed), are skipped for mounting. Vishal Pandey 2018-11-23 16:00:39 +05:30