These commits are when the Protocol Buffers files have changed: (only the last 100 relevant commits are shown)
| Commit: | 96c5f72 | |
|---|---|---|
| Author: | Ahmet Uyar | |
handled job master restarting properly
The documentation is generated from this commit.
| Commit: | fa70e41 | |
|---|---|---|
| Author: | Ahmet Uyar | |
implemented common logic for event sending out from jm
| Commit: | 9ea949e | |
|---|---|---|
| Author: | Ahmet Uyar | |
implemented barriers with common logic at job master
| Commit: | 7e4eb32 | |
|---|---|---|
| Author: | Ahmet Uyar | |
implemented job failure based on restarts and re-executes
| Commit: | 9755efa | |
|---|---|---|
| Author: | Ahmet Uyar | |
implemented init barrier on JMWorkerController
| Commit: | f399e08 | |
|---|---|---|
| Author: | Ahmet Uyar | |
implemented init barrier with zookeeper
| Commit: | 4b64c8c | |
|---|---|---|
| Author: | Ahmet Uyar | |
Merge branch 'ahmet/fault-tolerance' of https://github.com/DSC-SPIDAL/twister2 into ahmet/fault-tolerance
| Commit: | b549de0 | |
|---|---|---|
| Author: | Ahmet Uyar | |
added worker restartCount
| Commit: | f44522c | |
|---|---|---|
| Author: | Chathura Widanage | |
Returning the response immediately during a cluster instability
| Commit: | df951fb | |
|---|---|---|
| Author: | Ahmet Uyar | |
added KILLED state to worker states
| Commit: | dd312fd | |
|---|---|---|
| Author: | Ahmet Uyar | |
added job status to zookeeper job znode
| Commit: | 484f2b2 | |
|---|---|---|
| Author: | Ahmet Uyar | |
improved performance of listWorkers message
| Commit: | bcaeaf2 | |
|---|---|---|
| Author: | pulasthi | |
updating proto
| Commit: | 1aafa77 | |
|---|---|---|
| Author: | pulasthi | |
refacoring for driver move to api and adding way to return job state for submit
| Commit: | 99396bf | |
|---|---|---|
| Author: | Ahmet Uyar | |
removed Pinger
| Commit: | e92e519 | |
|---|---|---|
| Author: | Ahmet Uyar | |
added job master restarted event
| Commit: | e0a285d | |
|---|---|---|
| Author: | Ahmet Uyar | |
implemented restarting for Job Master after failure
| Commit: | f003a1b | |
|---|---|---|
| Author: | Ahmet Uyar | |
implemented barrier with event queue on zk
| Commit: | 77a068f | |
|---|---|---|
| Author: | Ahmet Uyar | |
implemented scaling with zk based event queue
| Commit: | 70e8033 | |
|---|---|---|
| Author: | Ahmet Uyar | |
zk based event queue implemented with allJoined, failed, restarted events
| Commit: | 18ef410 | |
|---|---|---|
| Author: | Ahmet Uyar | |
removed RUNNING from WorkerState
| Commit: | 1b82c03 | |
|---|---|---|
| Author: | Supun Kamburugamuve | |
| Committer: | GitHub | |
Merge pull request #671 from DSC-SPIDAL/ahmet/fault-tolerance Ahmet/fault tolerance
| Commit: | f511d29 | |
|---|---|---|
| Author: | Ahmet Uyar | |
removed Recover message from jobmaster proto
| Commit: | 4cd108b | |
|---|---|---|
| Author: | Ahmet Uyar | |
removed pingMessage from proto
| Commit: | ac00a7c | |
|---|---|---|
| Author: | Ahmet Uyar | |
added job master to zk based worker controller and discovery
| Commit: | ac3f518 | |
|---|---|---|
| Author: | Ahmet Uyar | |
IWorkerFailureListener interface added and implemented for ZooKeeper
| Commit: | acf96ff | |
|---|---|---|
| Author: | Ahmet Uyar | |
jobId added to job object
| Commit: | d099c0e | |
|---|---|---|
| Author: | Supun Kamburugamuve | |
| Committer: | GitHub | |
Merge pull request #640 from DSC-SPIDAL/python-support Python support
| Commit: | 1a8ef6a | |
|---|---|---|
| Author: | kannang83 | |
renaming the class
| Commit: | db626b6 | |
|---|---|---|
| Author: | Ahmet Uyar | |
scalable field of ComputeResource made required
| Commit: | 5e4800c | |
|---|---|---|
| Author: | kannang83 | |
adding iteration to the connected dataflow
| Commit: | 46df6b1 | |
|---|---|---|
| Author: | kannang83 | |
adding iteration to the connected dataflow
| Commit: | 8763d5d | |
|---|---|---|
| Author: | Chathura Widanage | |
Fixed proto cpp build
| Commit: | df44212 | |
|---|---|---|
| Author: | kannang83 | |
connected dataflow example update for iterative
| Commit: | 90a93de | |
|---|---|---|
| Author: | kannang83 | |
updates to the connected dataflow
| Commit: | 0816b32 | |
|---|---|---|
| Author: | supunkamburugamuve | |
adding support for zip jobs
| Commit: | ae7b469 | |
|---|---|---|
| Author: | kannang83 | |
connected dataflow k-means example update
| Commit: | ec5ef8c | |
|---|---|---|
| Author: | kannang83 | |
updates to the connected dataflow
| Commit: | 515f7d7 | |
|---|---|---|
| Author: | Gurhan Gunduz | |
job master fault tolerance initial implementation
| Commit: | 03cabe0 | |
|---|---|---|
| Author: | Chathura Widanage | |
Adding init protobuf message
| Commit: | f464f33 | |
|---|---|---|
| Author: | Chathura Widanage | |
Changing checkpoint family name from enum to string
| Commit: | 48be0f3 | |
|---|---|---|
| Author: | Chathura Widanage | |
Adding new proto messages
| Commit: | 4f11f67 | |
|---|---|---|
| Author: | Chathura Widanage | |
Merging master to checkpoints code by UoM
| Commit: | dfff8ef | |
|---|---|---|
| Author: | Tharmarajasingam Thuvarakan | |
Merge branch 'master' into uomfyp
| Commit: | 225b332 | |
|---|---|---|
| Author: | kannang83 | |
Pull Request #193 update.
| Commit: | eef58ff | |
|---|---|---|
| Author: | kannang83 | |
CDFW Scheduler improvements with jobmaster driver.
| Commit: | 54646fd | |
|---|---|---|
| Author: | kannang83 | |
CDFW Scheduler integration update with jobmaster driver.
| Commit: | bbcacce | |
|---|---|---|
| Author: | kannang83 | |
CDFW Scheduler integration with jobmaster driver.
| Commit: | d352744 | |
|---|---|---|
| Author: | supunkamburugamuve | |
refactoring htg to cdfw
| Commit: | b56306f | |
|---|---|---|
| Author: | supunkamburugamuve | |
Merge remote-tracking branch 'upstream/master' into driver-workflow Conflicts: twister2/resource-scheduler/src/java/edu/iu/dsc/tws/rsched/schedulers/standalone/MPILauncher.java
| Commit: | 4097cdf | |
|---|---|---|
| Author: | Ahmet Uyar | |
Driver implemented on Job Master
| Commit: | 4478a10 | |
|---|---|---|
| Author: | kannang83 | |
Connected Dataflow Scheduler Update.
| Commit: | 903990c | |
|---|---|---|
| Author: | supunkamburugamuve | |
adding more to connected dataflow
| Commit: | f10c016 | |
|---|---|---|
| Author: | niranda perera | |
reverting supuns commits
| Commit: | 72e2c88 | |
|---|---|---|
| Author: | supunkamburugamuve | |
using a new model for htg execution
| Commit: | a07ae61 | |
|---|---|---|
| Author: | niranda perera | |
Merge branch 'ahmet/implementing-workers-joined-events' of https://github.com/DSC-SPIDAL/twister2 into htg-new-temp
| Commit: | d0630d3 | |
|---|---|---|
| Author: | Ahmet Uyar | |
RegisterDriver message added
| Commit: | 6c04b33 | |
|---|---|---|
| Author: | Ahmet Uyar | |
allWorkersJoined method added to IWorker and IDriver
| Commit: | 80b0fc2 | |
|---|---|---|
| Author: | niranda perera | |
adding htgtask executor
| Commit: | 3468cae | |
|---|---|---|
| Author: | kannang83 | |
HTG Update after merge.
| Commit: | e4cbe3c | |
|---|---|---|
| Author: | Ahmet Uyar | |
worker to the driver messaging added
| Commit: | b636674 | |
|---|---|---|
| Author: | Ahmet Uyar | |
driver broadcast message type changed to protocol buffer message
| Commit: | c4648cf | |
|---|---|---|
| Author: | Ahmet Uyar | |
DriverListener and example usage added
| Commit: | fdcb959 | |
|---|---|---|
| Author: | Ahmet Uyar | |
ScaledComputeResource renamed to WorkersScaled
| Commit: | ab380d2 | |
|---|---|---|
| Author: | Ahmet Uyar | |
broadcast messaging implemented in JobMaster
| Commit: | 4665560 | |
|---|---|---|
| Author: | Ahmet Uyar | |
broadcast messaging added to K8SDriverController and related classes
| Commit: | aff753e | |
|---|---|---|
| Author: | kannang83 | |
Merge branch 'htg' of https://github.com/DSC-SPIDAL/twister2 into htg # Conflicts: # twister2/api/src/java/edu/iu/dsc/tws/api/htgjob/Twister2HTGClient.java # twister2/common/src/java/BUILD # twister2/common/src/java/edu/iu/dsc/tws/common/net/tcp/request/RRServer.java # twister2/examples/src/java/edu/iu/dsc/tws/examples/batch/htg/HTGExample.java # twister2/examples/src/java/edu/iu/dsc/tws/examples/internal/jobmaster/JobMasterClientExample.java # twister2/master/src/java/edu/iu/dsc/tws/master/WorkerMonitor.java # twister2/master/src/java/edu/iu/dsc/tws/master/worker/JobMasterClient.java
| Commit: | fabd0f1 | |
|---|---|---|
| Author: | niranda perera | |
Merge branch 'master' into htg_master_merge # Conflicts: # twister2/api/src/java/edu/iu/dsc/tws/api/job/Twister2Job.java
| Commit: | bfb7ef1 | |
|---|---|---|
| Author: | Ahmet Uyar | |
scale message renamed to scaled
| Commit: | 44c8202 | |
|---|---|---|
| Author: | Ahmet Uyar | |
scaling up/down compute resource in Kubernetes implemented
| Commit: | fe17946 | |
|---|---|---|
| Author: | nirandaperera | |
Merge branch 'master' into up_htg # Conflicts: # tools/rules/twister2_client.bzl # twister2/api/src/java/BUILD # twister2/api/src/java/edu/iu/dsc/tws/api/task/ComputeConnection.java # twister2/examples/src/java/edu/iu/dsc/tws/examples/batch/htg/HTGExample.java # twister2/proto/BUILD # twister2/proto/jobmaster.proto
| Commit: | 5b1f06c | |
|---|---|---|
| Author: | Ahmet Uyar | |
scalable added to ComputeResource definition
| Commit: | 7affdb0 | |
|---|---|---|
| Author: | Ahmet Uyar | |
scale compute resource message implemented
| Commit: | 419e37e | |
|---|---|---|
| Author: | kannang83 | |
HTG Client Monitor Initial Code
| Commit: | 11a7c35 | |
|---|---|---|
| Author: | kannang83 | |
HTG Job Master Client (Initial Version)
| Commit: | e1ed258 | |
|---|---|---|
| Author: | Ahmet Uyar | |
register worker message added to job master, workerID bug fixed
| Commit: | b4033ee | |
|---|---|---|
| Author: | kannang83 | |
HTG Metagraph update.
| Commit: | 5ccd4f5 | |
|---|---|---|
| Author: | Ahmet Uyar | |
additional ports implemented in WorkerInfo and Kubernetes
| Commit: | cd8889b | |
|---|---|---|
| Author: | kannang83 | |
HTG Metagraph update.
| Commit: | 4813bbd | |
|---|---|---|
| Author: | kannang83 | |
| Committer: | kannang83 | |
HTG Proto
| Commit: | 9aa11cc | |
|---|---|---|
| Author: | kannang83 | |
| Committer: | kannang83 | |
HTG Update
| Commit: | e247ea3 | |
|---|---|---|
| Author: | Ahmet Uyar | |
renamed numberOfWorkers to instances in ComputeResource in job.proto
| Commit: | 366f8bc | |
|---|---|---|
| Author: | Arunan Sugunakumar | |
accept changes from origin/master
| Commit: | d83dddf | |
|---|---|---|
| Author: | kannang83 | |
HTG Update
| Commit: | df0d0f5 | |
|---|---|---|
| Author: | Ahmet Uyar | |
job master support added for ComputeResource in WorkerInfo
| Commit: | 0d476b2 | |
|---|---|---|
| Author: | kannang83 | |
Refactoring@HTG
| Commit: | f96248e | |
|---|---|---|
| Author: | Ahmet Uyar | |
added index to ComputeResource in job proto
| Commit: | 6e453ec | |
|---|---|---|
| Author: | Ahmet Uyar | |
separated oneofs for message fields
| Commit: | 9882c9a | |
|---|---|---|
| Author: | Ahmet Uyar | |
improving JobMaster log messages
| Commit: | 915625a | |
|---|---|---|
| Author: | Ahmet Uyar | |
JobResources message removed from job proto
| Commit: | 8c35d2a | |
|---|---|---|
| Author: | Ahmet Uyar | |
ram and disk are renamed in job proto
| Commit: | f7b811e | |
|---|---|---|
| Author: | Ahmet Uyar | |
job.proto class and variable renamings
| Commit: | bd58c8f | |
|---|---|---|
| Author: | Arunan Sugunakumar | |
add sink ID in barrier complete message
| Commit: | 3f0be90 | |
|---|---|---|
| Author: | Arunan Sugunakumar | |
implement message from sink task to checkpoint manager
| Commit: | fd24949 | |
|---|---|---|
| Author: | Arunan Sugunakumar | |
implement response messages from the checkpoint manager to the source tasks
| Commit: | 3008b73 | |
|---|---|---|
| Author: | Arunan Sugunakumar | |
introduce parallelism parameter in task discovery message
| Commit: | a99581d | |
|---|---|---|
| Author: | Arunan Sugunakumar | |
define barriersync and barriersend protobuf message
| Commit: | e239520 | |
|---|---|---|
| Author: | Ahmet Uyar | |
JobFormatType modified
| Commit: | c42cdaf | |
|---|---|---|
| Author: | Ahmet Uyar | |
WorkerResourceUtils.getWorkersPerNode method added
| Commit: | 05f2713 | |
|---|---|---|
| Author: | Ahmet Uyar | |
unused proto files deleted