[jira] [Comment Edited] (HDDS-3254) Datanode memory increase so much

[ https://issues.apache.org/jira/browse/HDDS-3254?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=17067371#comment-17067371 ] runzhiwang edited comment on HDDS-3254 at 3/26/20, 6:06 AM: [~shashikant] I

[jira] [Commented] (HDDS-3254) Datanode memory increase so much

[ https://issues.apache.org/jira/browse/HDDS-3254?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=17067371#comment-17067371 ] runzhiwang commented on HDDS-3254: -- [~shashikant] I have stop send request to s3gateway for one day, but

[jira] [Updated] (HDDS-3240) Improve write efficiency by creating container in parallel.

[ https://issues.apache.org/jira/browse/HDDS-3240?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] runzhiwang updated HDDS-3240: - Attachment: screenshot-2.png > Improve write efficiency by creating container in parallel. >

[jira] [Updated] (HDDS-3240) Improve write efficiency by creating container in parallel.

[ https://issues.apache.org/jira/browse/HDDS-3240?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] runzhiwang updated HDDS-3240: - Description: Now follower cannot create container until leader finish creating container. But follower

[jira] [Updated] (HDDS-3240) Improve write efficiency by creating container in parallel.

[ https://issues.apache.org/jira/browse/HDDS-3240?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] runzhiwang updated HDDS-3240: - Description: Now follower cannot create container until leader finish creating container. But follower

[jira] [Commented] (HDDS-3240) Improve write efficiency by creating container in parallel.

[ https://issues.apache.org/jira/browse/HDDS-3240?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=17067325#comment-17067325 ] runzhiwang commented on HDDS-3240: -- I'm working on it > Improve write efficiency by creating container

[jira] [Updated] (HDDS-3240) Improve write efficiency by creating container in parallel.

[ https://issues.apache.org/jira/browse/HDDS-3240?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] runzhiwang updated HDDS-3240: - Description: Now follower cannot create container until leader finish creating container. But follower

[jira] [Updated] (HDDS-3240) Improve write efficiency by creating container in parallel.

[ https://issues.apache.org/jira/browse/HDDS-3240?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] runzhiwang updated HDDS-3240: - Description: Now follower cannot create container until leader finish creating container. But follower

[jira] [Updated] (HDDS-3240) Improve write efficiency by creating container in parallel.

[ https://issues.apache.org/jira/browse/HDDS-3240?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] runzhiwang updated HDDS-3240: - Description: Now follower cannot create container until leader finish creating container. But follower

[jira] [Reopened] (HDDS-3240) Improve write efficiency by creating container in parallel.

[ https://issues.apache.org/jira/browse/HDDS-3240?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] runzhiwang reopened HDDS-3240: -- > Improve write efficiency by creating container in parallel. >

[jira] [Issue Comment Deleted] (HDDS-3240) Improve write efficiency by creating container in parallel.

[ https://issues.apache.org/jira/browse/HDDS-3240?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] runzhiwang updated HDDS-3240: - Comment: was deleted (was: duplicated with https://jira.apache.org/jira/browse/HDDS-3244) > Improve

[jira] [Updated] (HDDS-3283) Improve write efficiency by improving RocksDB writeBatch

[ https://issues.apache.org/jira/browse/HDDS-3283?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] runzhiwang updated HDDS-3283: - Description: >From the image, you can find the whole write cost 140ms, but RocksDB

[jira] [Commented] (HDDS-3283) Improve write efficiency by improving RocksDB writeBatch

[ https://issues.apache.org/jira/browse/HDDS-3283?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=17067287#comment-17067287 ] runzhiwang commented on HDDS-3283: -- I'm working on it. > Improve write efficiency by improving RocksDB

[jira] [Updated] (HDDS-3283) Improve write efficiency by improving RocksDB writeBatch

[ https://issues.apache.org/jira/browse/HDDS-3283?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] runzhiwang updated HDDS-3283: - Description: >From the image, you can find the whole write cost 140ms, but RocksDB >writeBatch of two OM

[jira] [Updated] (HDDS-3283) Improve write efficiency by improving RocksDB writeBatch

[ https://issues.apache.org/jira/browse/HDDS-3283?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] runzhiwang updated HDDS-3283: - Attachment: screenshot-1.png > Improve write efficiency by improving RocksDB writeBatch >

[jira] [Assigned] (HDDS-3283) Improve write efficiency by improving RocksDB writeBatch

[ https://issues.apache.org/jira/browse/HDDS-3283?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] runzhiwang reassigned HDDS-3283: Assignee: runzhiwang > Improve write efficiency by improving RocksDB writeBatch >

[jira] [Created] (HDDS-3283) Improve write efficiency by improving RocksDB writeBatch

runzhiwang created HDDS-3283: Summary: Improve write efficiency by improving RocksDB writeBatch Key: HDDS-3283 URL: https://issues.apache.org/jira/browse/HDDS-3283 Project: Hadoop Distributed Data Store

[jira] [Updated] (HDDS-3254) Datanode memory increase so much

[ https://issues.apache.org/jira/browse/HDDS-3254?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] runzhiwang updated HDDS-3254: - Summary: Datanode memory increase so much (was: Memory leak of datanode) > Datanode memory increase so

[jira] [Comment Edited] (HDDS-3254) Memory leak of datanode

[ https://issues.apache.org/jira/browse/HDDS-3254?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=17065422#comment-17065422 ] runzhiwang edited comment on HDDS-3254 at 3/24/20, 8:33 AM: [~shashikant]I

[jira] [Comment Edited] (HDDS-3254) Memory leak of datanode

[ https://issues.apache.org/jira/browse/HDDS-3254?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=17065422#comment-17065422 ] runzhiwang edited comment on HDDS-3254 at 3/24/20, 8:33 AM: [~shashikant]I

[jira] [Comment Edited] (HDDS-3254) Memory leak of datanode

[ https://issues.apache.org/jira/browse/HDDS-3254?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=17065422#comment-17065422 ] runzhiwang edited comment on HDDS-3254 at 3/24/20, 8:32 AM: [~shashikant]I

[jira] [Comment Edited] (HDDS-3254) Memory leak of datanode

[ https://issues.apache.org/jira/browse/HDDS-3254?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=17065422#comment-17065422 ] runzhiwang edited comment on HDDS-3254 at 3/24/20, 8:30 AM: [~shashikant]I

[jira] [Comment Edited] (HDDS-3254) Memory leak of datanode

[ https://issues.apache.org/jira/browse/HDDS-3254?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=17065422#comment-17065422 ] runzhiwang edited comment on HDDS-3254 at 3/24/20, 8:30 AM: [~shashikant]I

[jira] [Commented] (HDDS-3254) Memory leak of datanode

[ https://issues.apache.org/jira/browse/HDDS-3254?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=17065422#comment-17065422 ] runzhiwang commented on HDDS-3254: -- I deploy 550 datanodes and 30 s3gateways on k8s. Python client starts

[jira] [Comment Edited] (HDDS-3122) Fail to destroy pipeline in k8s when redeploy DataNode

[ https://issues.apache.org/jira/browse/HDDS-3122?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=17049841#comment-17049841 ] runzhiwang edited comment on HDDS-3122 at 3/24/20, 6:34 AM: duplicated with

[jira] [Resolved] (HDDS-3122) Fail to destroy pipeline in k8s when redeploy DataNode

[ https://issues.apache.org/jira/browse/HDDS-3122?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] runzhiwang resolved HDDS-3122. -- Resolution: Duplicate > Fail to destroy pipeline in k8s when redeploy DataNode >

[jira] [Resolved] (HDDS-3125) Can not make full use of all datanodes.

[ https://issues.apache.org/jira/browse/HDDS-3125?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] runzhiwang resolved HDDS-3125. -- Resolution: Duplicate > Can not make full use of all datanodes. >

[jira] [Comment Edited] (HDDS-3125) Can not make full use of all datanodes.

[ https://issues.apache.org/jira/browse/HDDS-3125?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=17050718#comment-17050718 ] runzhiwang edited comment on HDDS-3125 at 3/24/20, 6:32 AM: 100% datanode cpu

[jira] [Resolved] (HDDS-3240) Improve write efficiency by creating container in parallel.

[ https://issues.apache.org/jira/browse/HDDS-3240?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] runzhiwang resolved HDDS-3240. -- Resolution: Duplicate > Improve write efficiency by creating container in parallel. >

[jira] [Comment Edited] (HDDS-3240) Improve write efficiency by creating container in parallel.

[ https://issues.apache.org/jira/browse/HDDS-3240?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=17063324#comment-17063324 ] runzhiwang edited comment on HDDS-3240 at 3/24/20, 6:24 AM: duplicated with

[jira] [Updated] (HDDS-3254) Memory leak of datanode

[ https://issues.apache.org/jira/browse/HDDS-3254?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] runzhiwang updated HDDS-3254: - Description: As the image shows, the physical memory of datanode increase to 11.2GB, and then crash. I

[jira] [Assigned] (HDDS-3254) Memory leak of datanode

[ https://issues.apache.org/jira/browse/HDDS-3254?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] runzhiwang reassigned HDDS-3254: Assignee: runzhiwang > Memory leak of datanode > --- > > Key:

[jira] [Commented] (HDDS-3254) Memory leak of datanode

[ https://issues.apache.org/jira/browse/HDDS-3254?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=17065244#comment-17065244 ] runzhiwang commented on HDDS-3254: -- I'm working on it. > Memory leak of datanode >

[jira] [Created] (HDDS-3254) Memory leak of datanode

runzhiwang created HDDS-3254: Summary: Memory leak of datanode Key: HDDS-3254 URL: https://issues.apache.org/jira/browse/HDDS-3254 Project: Hadoop Distributed Data Store Issue Type: Bug

[jira] [Updated] (HDDS-3244) Improve write efficiency by opening RocksDB only once

[ https://issues.apache.org/jira/browse/HDDS-3244?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] runzhiwang updated HDDS-3244: - Description: when datanode create each container, a new RocksDB instance will be

[jira] [Updated] (HDDS-3244) Improve write efficiency by opening RocksDB only once

[ https://issues.apache.org/jira/browse/HDDS-3244?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] runzhiwang updated HDDS-3244: - Summary: Improve write efficiency by opening RocksDB only once (was: Improve write efficiency by

[jira] [Updated] (HDDS-3244) Improve write efficiency by optimizing RocksDB.open

[ https://issues.apache.org/jira/browse/HDDS-3244?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] runzhiwang updated HDDS-3244: - Description: when datanode create each container, a new RocksDB instance will be

[jira] [Updated] (HDDS-3244) Improve write efficiency by optimizing RocksDB.open

[ https://issues.apache.org/jira/browse/HDDS-3244?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] runzhiwang updated HDDS-3244: - Description: when datanode create each container, a new RocksDB instance will be

[jira] [Updated] (HDDS-3244) Improve write efficiency by optimizing RocksDB.open

[ https://issues.apache.org/jira/browse/HDDS-3244?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] runzhiwang updated HDDS-3244: - Description: when datanode create each container, a new RocksDB instance will be

[jira] [Updated] (HDDS-3244) Improve write efficiency by optimizing RocksDB.open

[ https://issues.apache.org/jira/browse/HDDS-3244?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] runzhiwang updated HDDS-3244: - Description: when datanode create each container, a RocksDB instance will be

[jira] [Updated] (HDDS-3244) Improve write efficiency by optimizing RocksDB.open

[ https://issues.apache.org/jira/browse/HDDS-3244?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] runzhiwang updated HDDS-3244: - Description: when datanode create each container, a RocksDB instance will be

[jira] [Updated] (HDDS-3244) Improve write efficiency by optimizing RocksDB.open

[ https://issues.apache.org/jira/browse/HDDS-3244?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] runzhiwang updated HDDS-3244: - Description: when datanode create each container, a RocksDB instance will be created, but

[jira] [Updated] (HDDS-3244) Improve write efficiency by optimizing RocksDB.open

[ https://issues.apache.org/jira/browse/HDDS-3244?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] runzhiwang updated HDDS-3244: - Description: when create each container, a RocksDB instance will be created, but

[jira] [Issue Comment Deleted] (HDDS-3244) Improve write efficiency by optimizing RocksDB.open

[ https://issues.apache.org/jira/browse/HDDS-3244?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] runzhiwang updated HDDS-3244: - Comment: was deleted (was: [~bharat] Hi, when create each container in datanode, it will create an

[jira] [Comment Edited] (HDDS-3244) Improve write efficiency by optimizing RocksDB.open

[ https://issues.apache.org/jira/browse/HDDS-3244?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=17064149#comment-17064149 ] runzhiwang edited comment on HDDS-3244 at 3/22/20, 2:40 AM: [~bharat] Hi, when

[jira] [Commented] (HDDS-3244) Improve write efficiency by optimizing RocksDB.open

[ https://issues.apache.org/jira/browse/HDDS-3244?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=17064149#comment-17064149 ] runzhiwang commented on HDDS-3244: -- [~bharat] Hi, when create each container in datanode, it will create

[jira] [Updated] (HDDS-3244) Improve write efficiency by optimizing RocksDB.open

[ https://issues.apache.org/jira/browse/HDDS-3244?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] runzhiwang updated HDDS-3244: - Description:

[jira] [Updated] (HDDS-3244) Improve write efficiency by optimizing RocksDB.open

[ https://issues.apache.org/jira/browse/HDDS-3244?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] runzhiwang updated HDDS-3244: - Description:

[jira] [Commented] (HDDS-3244) Improve write efficiency by optimizing RocksDB.open

[ https://issues.apache.org/jira/browse/HDDS-3244?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=17064148#comment-17064148 ] runzhiwang commented on HDDS-3244: -- I'm working on it. > Improve write efficiency by optimizing

[jira] [Assigned] (HDDS-3244) Improve write efficiency by optimizing RocksDB.open

[ https://issues.apache.org/jira/browse/HDDS-3244?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] runzhiwang reassigned HDDS-3244: Assignee: runzhiwang > Improve write efficiency by optimizing RocksDB.open >

[jira] [Created] (HDDS-3244) Improve write efficiency by optimizing RocksDB.open

runzhiwang created HDDS-3244: Summary: Improve write efficiency by optimizing RocksDB.open Key: HDDS-3244 URL: https://issues.apache.org/jira/browse/HDDS-3244 Project: Hadoop Distributed Data Store

[jira] [Updated] (HDDS-3240) Improve write efficiency by creating container in parallel.

[ https://issues.apache.org/jira/browse/HDDS-3240?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] runzhiwang updated HDDS-3240: - Summary: Improve write efficiency by creating container in parallel. (was: Improve write efficiency by

[jira] [Updated] (HDDS-3240) Improve write efficiency by creating container parallel.

[ https://issues.apache.org/jira/browse/HDDS-3240?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] runzhiwang updated HDDS-3240: - Description: 1. As the image shows, when stage is DispatcherContext.WriteChunkStage.WRITE_DATA, the

[jira] [Updated] (HDDS-3240) Improve write efficiency by creating container parallel.

[ https://issues.apache.org/jira/browse/HDDS-3240?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] runzhiwang updated HDDS-3240: - Description: 1. As the image shows, when stage is DispatcherContext.WriteChunkStage.WRITE_DATA, the

[jira] [Updated] (HDDS-3240) Improve write efficiency by creating container parallel.

[ https://issues.apache.org/jira/browse/HDDS-3240?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] runzhiwang updated HDDS-3240: - Description: 1.As the image shows, when stage is DispatcherContext.WriteChunkStage.WRITE_DATA, the

[jira] [Commented] (HDDS-3240) Improve write efficiency by creating container parallel.

[ https://issues.apache.org/jira/browse/HDDS-3240?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=17063324#comment-17063324 ] runzhiwang commented on HDDS-3240: -- I'm working on it. > Improve write efficiency by creating container

[jira] [Updated] (HDDS-3240) Improve write efficiency by creating container parallel.

[ https://issues.apache.org/jira/browse/HDDS-3240?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] runzhiwang updated HDDS-3240: - Description: As the image shows, when write data, the leader datanode execute two steps:

[jira] [Updated] (HDDS-3240) Improve write efficiency by creating container parallel.

[ https://issues.apache.org/jira/browse/HDDS-3240?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] runzhiwang updated HDDS-3240: - Description: 1.As the image shows, when write data, the leader datanode execute two steps:

[jira] [Assigned] (HDDS-3240) Improve write efficiency by creating container parallel.

[ https://issues.apache.org/jira/browse/HDDS-3240?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] runzhiwang reassigned HDDS-3240: Assignee: runzhiwang > Improve write efficiency by creating container parallel. >

[jira] [Updated] (HDDS-3240) Improve write efficiency by creating container parallel.

[ https://issues.apache.org/jira/browse/HDDS-3240?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] runzhiwang updated HDDS-3240: - Description: !screenshot-1.png! was: !screenshot-1.png! > Improve write efficiency by creating

[jira] [Updated] (HDDS-3240) Improve write efficiency by creating container parallel.

[ https://issues.apache.org/jira/browse/HDDS-3240?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] runzhiwang updated HDDS-3240: - Description: !screenshot-1.png! > Improve write efficiency by creating container parallel. >

[jira] [Created] (HDDS-3240) Improve write efficiency by creating container parallel.

runzhiwang created HDDS-3240: Summary: Improve write efficiency by creating container parallel. Key: HDDS-3240 URL: https://issues.apache.org/jira/browse/HDDS-3240 Project: Hadoop Distributed Data Store

[jira] [Updated] (HDDS-3240) Improve write efficiency by creating container parallel.

[ https://issues.apache.org/jira/browse/HDDS-3240?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] runzhiwang updated HDDS-3240: - Attachment: screenshot-1.png > Improve write efficiency by creating container parallel. >

[jira] [Comment Edited] (HDDS-3223) Read a big object cost 2 times more than write it by s3g

[ https://issues.apache.org/jira/browse/HDDS-3223?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=17060612#comment-17060612 ] runzhiwang edited comment on HDDS-3223 at 3/18/20, 12:54 PM: - I think it's

[jira] [Comment Edited] (HDDS-3223) Read a big object cost 2 times more than write it by s3g

[ https://issues.apache.org/jira/browse/HDDS-3223?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=17060612#comment-17060612 ] runzhiwang edited comment on HDDS-3223 at 3/18/20, 12:46 PM: - I think it's

[jira] [Resolved] (HDDS-3223) Read a big object cost 2 times more than write it by s3g

[ https://issues.apache.org/jira/browse/HDDS-3223?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] runzhiwang resolved HDDS-3223. -- Resolution: Fixed > Read a big object cost 2 times more than write it by s3g >

[jira] [Comment Edited] (HDDS-3223) Read a big object cost 2 times more than write it by s3g

[ https://issues.apache.org/jira/browse/HDDS-3223?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=17060612#comment-17060612 ] runzhiwang edited comment on HDDS-3223 at 3/18/20, 12:39 PM: - I think it's

[jira] [Updated] (HDDS-3168) Improve read efficiency by merging a lot of RPC call getContainerWithPipeline into one

[ https://issues.apache.org/jira/browse/HDDS-3168?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] runzhiwang updated HDDS-3168: - Summary: Improve read efficiency by merging a lot of RPC call getContainerWithPipeline into one (was:

[jira] [Updated] (HDDS-3223) Read a big object cost 2 times more than write it by s3g

[ https://issues.apache.org/jira/browse/HDDS-3223?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] runzhiwang updated HDDS-3223: - Description: By s3gateway, write a 187MB file cost 5 seconds, but read it cost 17 seconds. Both write

[jira] [Updated] (HDDS-3223) Read a big object cost 2 times more than write it by s3g

[ https://issues.apache.org/jira/browse/HDDS-3223?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] runzhiwang updated HDDS-3223: - Description: By s3gateway, write a 187MB file cost 5 seconds, but read it cost 17 seconds. Both write

[jira] [Updated] (HDDS-3223) Read a big object cost 2 times more than write it by s3g

[ https://issues.apache.org/jira/browse/HDDS-3223?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] runzhiwang updated HDDS-3223: - Description: By s3gateway, write a 187MB file cost 5 seconds, but read it cost 17 seconds. Both write

[jira] [Updated] (HDDS-3223) Read a big object cost 2 times more than write it by s3g

[ https://issues.apache.org/jira/browse/HDDS-3223?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] runzhiwang updated HDDS-3223: - Description: By s3gateway, write a 187MB file cost 5 seconds, but read it cost 17 seconds. Both write

[jira] [Updated] (HDDS-3223) Read a big object cost 2 times more than write it by s3g

[ https://issues.apache.org/jira/browse/HDDS-3223?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] runzhiwang updated HDDS-3223: - Attachment: screenshot-5.png > Read a big object cost 2 times more than write it by s3g >

[jira] [Updated] (HDDS-3223) Read a big object cost 2 times more than write it by s3g

[ https://issues.apache.org/jira/browse/HDDS-3223?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] runzhiwang updated HDDS-3223: - Attachment: (was: screenshot-4.png) > Read a big object cost 2 times more than write it by s3g >

[jira] [Updated] (HDDS-3223) Read a big object cost 2 times more than write it by s3g

[ https://issues.apache.org/jira/browse/HDDS-3223?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] runzhiwang updated HDDS-3223: - Description: By s3gateway, write a 187MB file cost 5 seconds, but read it cost 17 seconds. Both write

[jira] [Updated] (HDDS-3223) Read a big object cost 2 times more than write it by s3g

[ https://issues.apache.org/jira/browse/HDDS-3223?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] runzhiwang updated HDDS-3223: - Attachment: screenshot-4.png > Read a big object cost 2 times more than write it by s3g >

[jira] [Updated] (HDDS-3223) Read a big object cost 2 times more than write it by s3g

[ https://issues.apache.org/jira/browse/HDDS-3223?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] runzhiwang updated HDDS-3223: - Attachment: (was: screenshot-2.png) > Read a big object cost 2 times more than write it by s3g >

[jira] [Updated] (HDDS-3223) Read a big object cost 2 times more than write it by s3g

[ https://issues.apache.org/jira/browse/HDDS-3223?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] runzhiwang updated HDDS-3223: - Description: By s3gateway, write a 187MB file cost 5 seconds, but read it cost 17 seconds. Both write

[jira] [Updated] (HDDS-3223) Read a big object cost 2 times more than write it by s3g

[ https://issues.apache.org/jira/browse/HDDS-3223?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] runzhiwang updated HDDS-3223: - Attachment: (was: screenshot-1.png) > Read a big object cost 2 times more than write it by s3g >

[jira] [Updated] (HDDS-3223) Read a big object cost 2 times more than write it by s3g

[ https://issues.apache.org/jira/browse/HDDS-3223?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] runzhiwang updated HDDS-3223: - Description: By s3gateway, write a 187MB file cost 5 seconds, but read it cost 17 seconds. Both write

[jira] [Updated] (HDDS-3223) Read a big object cost 2 times more than write it by s3g

[ https://issues.apache.org/jira/browse/HDDS-3223?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] runzhiwang updated HDDS-3223: - Description: By s3gateway, write a 187MB file cost 5 seconds, but read it cost 17 seconds. I use

[jira] [Updated] (HDDS-3223) Read a big object cost 2 times more than write it by s3g

[ https://issues.apache.org/jira/browse/HDDS-3223?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] runzhiwang updated HDDS-3223: - Description: By s3gateway, write a 187MB file cost 5 seconds, but read it cost 17 seconds. I use

[jira] [Updated] (HDDS-3223) Read a big object cost 2 times more than write it by s3g

[ https://issues.apache.org/jira/browse/HDDS-3223?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] runzhiwang updated HDDS-3223: - Description: By s3gateway, write a 187MB file cost 5 seconds, but read it cost 17 seconds. I use tcpdump

[jira] [Updated] (HDDS-3223) Read a big object cost 2 times more than write it by s3g

[ https://issues.apache.org/jira/browse/HDDS-3223?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] runzhiwang updated HDDS-3223: - Description: By s3gateway, write a 187MB file cost 5 seconds, but read it cost 17 seconds. I use tcpdump

[jira] [Updated] (HDDS-3223) Read a big object cost 2 times more than write it by s3g

[ https://issues.apache.org/jira/browse/HDDS-3223?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] runzhiwang updated HDDS-3223: - Description: By s3gateway, write a 187MB file cost 5 seconds, but read it cost 17 seconds. I use tcpdump

[jira] [Updated] (HDDS-3223) Read a big object cost 2 times more than write it by s3g

[ https://issues.apache.org/jira/browse/HDDS-3223?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] runzhiwang updated HDDS-3223: - Attachment: screenshot-3.png > Read a big object cost 2 times more than write it by s3g >

[jira] [Updated] (HDDS-3223) Read a big object cost 2 times more than write it by s3g

[ https://issues.apache.org/jira/browse/HDDS-3223?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] runzhiwang updated HDDS-3223: - Description: By s3gateway, write a 187MB file cost 5 seconds, but read it cost 17 seconds. I use tcpdump

[jira] [Updated] (HDDS-3223) Read a big object cost 2 times more than write it by s3g

[ https://issues.apache.org/jira/browse/HDDS-3223?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] runzhiwang updated HDDS-3223: - Description: By s3gateway, write a 187MB file cost 5 seconds, but read it cost 17 seconds. I use tcpdump

[jira] [Updated] (HDDS-3223) Read a big object cost 2 times more than write it by s3g

[ https://issues.apache.org/jira/browse/HDDS-3223?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] runzhiwang updated HDDS-3223: - Description: By s3gateway, write a 187MB file cost 5 seconds, but read it cost 17 seconds. I use tcpdump

[jira] [Updated] (HDDS-3223) Read a big object cost 2 times more than write it by s3g

[ https://issues.apache.org/jira/browse/HDDS-3223?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] runzhiwang updated HDDS-3223: - Description: By s3gateway, write a 187MB file cost 5 seconds, but read it cost 17 seconds. I use tcpdump

[jira] [Updated] (HDDS-3223) Read a big object cost 2 times more than write it by s3g

[ https://issues.apache.org/jira/browse/HDDS-3223?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] runzhiwang updated HDDS-3223: - Description: By s3gateway, write a 187MB file cost 5 seconds, but read it cost 17 seconds.

[jira] [Updated] (HDDS-3223) Read a big object cost 2 times more than write it by s3g

[ https://issues.apache.org/jira/browse/HDDS-3223?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] runzhiwang updated HDDS-3223: - Attachment: screenshot-1.png > Read a big object cost 2 times more than write it by s3g >

[jira] [Updated] (HDDS-3223) Read a big object cost 2 times more than write it by s3g

[ https://issues.apache.org/jira/browse/HDDS-3223?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] runzhiwang updated HDDS-3223: - Attachment: screenshot-2.png > Read a big object cost 2 times more than write it by s3g >

[jira] [Updated] (HDDS-3223) Read a big object cost 2 times more than write it by s3g

[ https://issues.apache.org/jira/browse/HDDS-3223?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] runzhiwang updated HDDS-3223: - Description: By s3gateway, write a 187MB file cost 5 seconds, but read it cost 17 seconds. The write and

[jira] [Commented] (HDDS-3223) Read a big object cost 2 times more than write it by s3g

[ https://issues.apache.org/jira/browse/HDDS-3223?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=17060612#comment-17060612 ] runzhiwang commented on HDDS-3223: -- I'm working on it. > Read a big object cost 2 times more than write

[jira] [Assigned] (HDDS-3223) Read a big object cost 2 times more than write it by s3g

[ https://issues.apache.org/jira/browse/HDDS-3223?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] runzhiwang reassigned HDDS-3223: Assignee: runzhiwang > Read a big object cost 2 times more than write it by s3g >

[jira] [Updated] (HDDS-3223) Read a big object cost 2 times more than write it by s3g

[ https://issues.apache.org/jira/browse/HDDS-3223?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] runzhiwang updated HDDS-3223: - Description: By s3gateway, write a 187MB file cost 5 seconds, but read it cost 17 seconds. The write and

[jira] [Updated] (HDDS-3223) Read a big object cost 2 times more than write it by s3g

[ https://issues.apache.org/jira/browse/HDDS-3223?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] runzhiwang updated HDDS-3223: - Summary: Read a big object cost 2 times more than write it by s3g (was: Improve the read efficiency of

[jira] [Updated] (HDDS-3223) Improve the read efficiency of big object in s3g

[ https://issues.apache.org/jira/browse/HDDS-3223?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] runzhiwang updated HDDS-3223: - Description: By s3gateway, write a 187MB file cost 5 seconds, but read it cost 17 seconds. The write and

[jira] [Updated] (HDDS-3223) Improve the read efficiency of big object in s3g

[ https://issues.apache.org/jira/browse/HDDS-3223?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] runzhiwang updated HDDS-3223: - Description: By s3gateway, write a 200MB file cost 5 seconds, but read it cost 17 seconds. And >

<    1   2   3   4   5   6   7   >