[jira] [Updated] (HBASE-10497) Add standard handling for swallowed InterruptedException thrown by Thread.sleep under HBase-Client/HBase-Server folders systematically

[ https://issues.apache.org/jira/browse/HBASE-10497?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Feng Honghua updated HBASE-10497: - Summary: Add standard handling for swallowed InterruptedException thrown by Thread.sleep under

[jira] [Updated] (HBASE-10497) Add standard handling for swallowed InterruptedException thrown by Thread.sleep under HBase-Client/HBase-Server folders systematically

[ https://issues.apache.org/jira/browse/HBASE-10497?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Feng Honghua updated HBASE-10497: - Attachment: HBASE-10497-trunk_v2.patch Patch attached per [~nkeywal]'s review feedback, and

[jira] [Commented] (HBASE-10497) Add standard handling for swallowed InterruptedException thrown by Thread.sleep under HBase-Client/HBase-Server folders systematically

[ https://issues.apache.org/jira/browse/HBASE-10497?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanelfocusedCommentId=13897827#comment-13897827 ] Feng Honghua commented on HBASE-10497: -- Thanks [~nkeywal] for the prompt review!

[jira] [Updated] (HBASE-10487) Avoid allocating new KeyValue and according bytes-copying for appended kvs which don't have existing values

[ https://issues.apache.org/jira/browse/HBASE-10487?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Feng Honghua updated HBASE-10487: - Attachment: HBASE-10487-0.98_v1.patch Patch for 0.98 attached, thanks [~yuzhih...@gmail.com]

[jira] [Commented] (HBASE-10487) Avoid allocating new KeyValue and according bytes-copying for appended kvs which don't have existing values

[ https://issues.apache.org/jira/browse/HBASE-10487?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanelfocusedCommentId=13898744#comment-13898744 ] Feng Honghua commented on HBASE-10487: -- bq.-1 overall. Here are the results of

[jira] [Commented] (HBASE-10497) Add standard handling for swallowed InterruptedException thrown by Thread.sleep under HBase-Client/HBase-Server folders systematically

[ https://issues.apache.org/jira/browse/HBASE-10497?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanelfocusedCommentId=13898762#comment-13898762 ] Feng Honghua commented on HBASE-10497: -- The helper method Threads.sleep is

[jira] [Commented] (HBASE-10487) Avoid allocating new KeyValue and according bytes-copying for appended kvs which don't have existing values

[ https://issues.apache.org/jira/browse/HBASE-10487?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanelfocusedCommentId=13898764#comment-13898764 ] Feng Honghua commented on HBASE-10487: -- Got it, thanks Ted. Avoid allocating new

[jira] [Commented] (HBASE-10252) Don't write back to WAL/memstore when Increment amount is zero (mostly for query rather than update intention)

[ https://issues.apache.org/jira/browse/HBASE-10252?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanelfocusedCommentId=13898896#comment-13898896 ] Feng Honghua commented on HBASE-10252: -- bq.The test presumes that even though the

[jira] [Commented] (HBASE-10487) Avoid allocating new KeyValue and according bytes-copying for appended kvs which don't have existing(old) values

[ https://issues.apache.org/jira/browse/HBASE-10487?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanelfocusedCommentId=13896142#comment-13896142 ] Feng Honghua commented on HBASE-10487: -- Thanks all bq.Is that a common scenario,

[jira] [Created] (HBASE-10487) Avoid allocating new KeyValue for appended kvs which don't have existing(old) values

Feng Honghua created HBASE-10487: Summary: Avoid allocating new KeyValue for appended kvs which don't have existing(old) values Key: HBASE-10487 URL: https://issues.apache.org/jira/browse/HBASE-10487

[jira] [Updated] (HBASE-10487) Avoid allocating new KeyValue for appended kvs which don't have existing(old) values

[ https://issues.apache.org/jira/browse/HBASE-10487?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Feng Honghua updated HBASE-10487: - Attachment: HBASE-10487-trunk_v1.patch patch attached Avoid allocating new KeyValue for

[jira] [Updated] (HBASE-10487) Avoid allocating new KeyValue and bytes-copying for appended kvs which don't have existing(old) values

[ https://issues.apache.org/jira/browse/HBASE-10487?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Feng Honghua updated HBASE-10487: - Description: in HRegion.append, a new KeyValue will be allocated no matter there is existing kv

[jira] [Updated] (HBASE-10487) Avoid allocating new KeyValue and according bytes-copying for appended kvs which don't have existing(old) values

[ https://issues.apache.org/jira/browse/HBASE-10487?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Feng Honghua updated HBASE-10487: - Summary: Avoid allocating new KeyValue and according bytes-copying for appended kvs which don't

[jira] [Updated] (HBASE-10487) Avoid allocating new KeyValue and according bytes-copying for appended kvs which don't have existing(old) values

[ https://issues.apache.org/jira/browse/HBASE-10487?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Feng Honghua updated HBASE-10487: - Description: in HRegion.append, new KeyValues will be allocated and do according bytes-copying

[jira] [Updated] (HBASE-9501) Provide throttling for replication

[ https://issues.apache.org/jira/browse/HBASE-9501?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Feng Honghua updated HBASE-9501: Attachment: HBASE-9501-trunk_v3.patch new patch per [~jdcryans]'s review feedback, thanks

[jira] [Commented] (HBASE-9501) Provide throttling for replication

[ https://issues.apache.org/jira/browse/HBASE-9501?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanelfocusedCommentId=13894317#comment-13894317 ] Feng Honghua commented on HBASE-9501: - bq.How do you feel about using a class instead

[jira] [Commented] (HBASE-8751) Enable peer cluster to choose/change the ColumnFamilies/Tables it really want to replicate from a source cluster

[ https://issues.apache.org/jira/browse/HBASE-8751?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanelfocusedCommentId=13894318#comment-13894318 ] Feng Honghua commented on HBASE-8751: - Ping [~andrew.purt...@gmail.com] :-) Enable

[jira] [Commented] (HBASE-10296) Replace ZK with a consensus lib(paxos,zab or raft) running within master processes to provide better master failover performance and state consistency

[ https://issues.apache.org/jira/browse/HBASE-10296?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanelfocusedCommentId=13894362#comment-13894362 ] Feng Honghua commented on HBASE-10296: -- bq.The only thing is that, this would

[jira] [Commented] (HBASE-9501) Provide throttling for replication

[ https://issues.apache.org/jira/browse/HBASE-9501?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanelfocusedCommentId=13895337#comment-13895337 ] Feng Honghua commented on HBASE-9501: - bq.If you're ok with those changes I'll just

[jira] [Commented] (HBASE-10296) Replace ZK with a consensus lib(paxos,zab or raft) running within master processes to provide better master failover performance and state consistency

[ https://issues.apache.org/jira/browse/HBASE-10296?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanelfocusedCommentId=13895363#comment-13895363 ] Feng Honghua commented on HBASE-10296: -- bq.There has been at least 3 proposals so

[jira] [Updated] (HBASE-9501) Provide throttling for replication

[ https://issues.apache.org/jira/browse/HBASE-9501?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Feng Honghua updated HBASE-9501: Attachment: HBASE-9501-trunk_v2.patch [~jdcryans] : Thanks very much for the review. New patch

[jira] [Commented] (HBASE-8751) Enable peer cluster to choose/change the ColumnFamilies/Tables it really want to replicate from a source cluster

[ https://issues.apache.org/jira/browse/HBASE-8751?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanelfocusedCommentId=13887812#comment-13887812 ] Feng Honghua commented on HBASE-8751: - Thanks [~jdcryans] for the review :-) Enable

[jira] [Commented] (HBASE-10296) Replace ZK with a consensus lib(paxos,zab or raft) running within master processes to provide better master failover performance and state consistency

[ https://issues.apache.org/jira/browse/HBASE-10296?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanelfocusedCommentId=13887841#comment-13887841 ] Feng Honghua commented on HBASE-10296: -- bq. Varying group membership and compacting

[jira] [Commented] (HBASE-10296) Replace ZK with a consensus lib(paxos,zab or raft) running within master processes to provide better master failover performance and state consistency

[ https://issues.apache.org/jira/browse/HBASE-10296?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanelfocusedCommentId=13885002#comment-13885002 ] Feng Honghua commented on HBASE-10296: -- bq.Speaking of RAFT implementation, we, the

[jira] [Updated] (HBASE-8751) Enable peer cluster to choose/change the ColumnFamilies/Tables it really want to replicate from a source cluster

[ https://issues.apache.org/jira/browse/HBASE-8751?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Feng Honghua updated HBASE-8751: Attachment: HBASE-8751-trunk_v2.patch New patch attached removing lines longer than 100;

[jira] [Updated] (HBASE-8751) Enable peer cluster to choose/change the ColumnFamilies/Tables it really want to replicate from a source cluster

[ https://issues.apache.org/jira/browse/HBASE-8751?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Feng Honghua updated HBASE-8751: Attachment: HBASE-8751-trunk_v3.patch New patch removing javadoc warnings and lines longer than

[jira] [Commented] (HBASE-10296) Replace ZK with a paxos running within master processes to provide better master failover performance and state consistency

[ https://issues.apache.org/jira/browse/HBASE-10296?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanelfocusedCommentId=13882237#comment-13882237 ] Feng Honghua commented on HBASE-10296: -- sorry for the late reply :-) [~lhofhansl],

[jira] [Updated] (HBASE-10296) Replace ZK with a consensus lib(paxos,zab or raft) running within master processes to provide better master failover performance and state consistency

[ https://issues.apache.org/jira/browse/HBASE-10296?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Feng Honghua updated HBASE-10296: - Summary: Replace ZK with a consensus lib(paxos,zab or raft) running within master processes to

[jira] [Commented] (HBASE-10295) Refactor the replication implementation to eliminate permanent zk node

[ https://issues.apache.org/jira/browse/HBASE-10295?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanelfocusedCommentId=13882245#comment-13882245 ] Feng Honghua commented on HBASE-10295: -- a long-term item and need more discussion

[jira] [Updated] (HBASE-10295) Refactor the replication implementation to eliminate permanent zk node

[ https://issues.apache.org/jira/browse/HBASE-10295?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Feng Honghua updated HBASE-10295: - Assignee: (was: Feng Honghua) Refactor the replication implementation to eliminate

[jira] [Commented] (HBASE-1755) Putting 'Meta' table into ZooKeeper

[ https://issues.apache.org/jira/browse/HBASE-1755?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanelfocusedCommentId=13882497#comment-13882497 ] Feng Honghua commented on HBASE-1755: - I agree with [~lhofhansl] in some sense. ZK is

[jira] [Commented] (HBASE-8751) Enable peer cluster to choose/change the ColumnFamilies/Tables it really want to replicate from a source cluster

[ https://issues.apache.org/jira/browse/HBASE-8751?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanelfocusedCommentId=13882143#comment-13882143 ] Feng Honghua commented on HBASE-8751: - [~jdcryans], thanks very much for the review,

[jira] [Updated] (HBASE-8751) Enable peer cluster to choose/change the ColumnFamilies/Tables it really want to replicate from a source cluster

[ https://issues.apache.org/jira/browse/HBASE-8751?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Feng Honghua updated HBASE-8751: Attachment: HBASE-8751-trunk_v1.patch new trunk patch attached per [~jdcryans]'s comments, thanks

[jira] [Commented] (HBASE-8751) Enable peer cluster to choose/change the ColumnFamilies/Tables it really want to replicate from a source cluster

[ https://issues.apache.org/jira/browse/HBASE-8751?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanelfocusedCommentId=13882190#comment-13882190 ] Feng Honghua commented on HBASE-8751: - bq.This should be part of setUpBeforeClass and

[jira] [Updated] (HBASE-9501) No throttling for replication

[ https://issues.apache.org/jira/browse/HBASE-9501?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Feng Honghua updated HBASE-9501: Attachment: HBASE-9501-trunk_v1.patch as this jira's description says, this feature is to prevent

[jira] [Updated] (HBASE-9501) Provide throttling for replication

[ https://issues.apache.org/jira/browse/HBASE-9501?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Feng Honghua updated HBASE-9501: Release Note: A new configuration replication.source.per.peer.node.bandwidth is added by this

[jira] [Commented] (HBASE-10213) Add read log size per second metrics for replication source

[ https://issues.apache.org/jira/browse/HBASE-10213?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanelfocusedCommentId=13877435#comment-13877435 ] Feng Honghua commented on HBASE-10213: -- bq.However, it is not clear enough to know

[jira] [Updated] (HBASE-9501) No throttling for replication

[ https://issues.apache.org/jira/browse/HBASE-9501?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Feng Honghua updated HBASE-9501: Attachment: HBASE-9501-trunk_v0.patch trunk patch attached No throttling for replication

[jira] [Commented] (HBASE-9004) Fix Documentation around Minor compaction and ttl

[ https://issues.apache.org/jira/browse/HBASE-9004?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanelfocusedCommentId=13877069#comment-13877069 ] Feng Honghua commented on HBASE-9004: - bq.In my understanding, whole hfile is deleted

[jira] [Updated] (HBASE-8751) Enable peer cluster to choose/change the ColumnFamilies/Tables it really want to replicate from a source cluster

[ https://issues.apache.org/jira/browse/HBASE-8751?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Feng Honghua updated HBASE-8751: Attachment: HBASE-8751-trunk_v0.patch trunk patch attached Enable peer cluster to choose/change

[jira] [Commented] (HBASE-8751) Enable peer cluster to choose/change the ColumnFamilies/Tables it really want to replicate from a source cluster

[ https://issues.apache.org/jira/browse/HBASE-8751?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanelfocusedCommentId=13877215#comment-13877215 ] Feng Honghua commented on HBASE-8751: - bq.We can't introduce new functionality on 0.94

[jira] [Updated] (HBASE-9469) Synchronous replication

[ https://issues.apache.org/jira/browse/HBASE-9469?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Feng Honghua updated HBASE-9469: Assignee: (was: Feng Honghua) Synchronous replication ---

[jira] [Commented] (HBASE-9469) Synchronous replication

[ https://issues.apache.org/jira/browse/HBASE-9469?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanelfocusedCommentId=13877226#comment-13877226 ] Feng Honghua commented on HBASE-9469: - after some rethought, I think this feature has

[jira] [Commented] (HBASE-9004) Fix Documentation around Minor compaction and ttl

[ https://issues.apache.org/jira/browse/HBASE-9004?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanelfocusedCommentId=13876169#comment-13876169 ] Feng Honghua commented on HBASE-9004: - minor compaction *will* delete expired cells,

[jira] [Created] (HBASE-10344) Improve writer performance by ignoring sync to hdfs when an asyncer's writes have been synced by other asyncer

Feng Honghua created HBASE-10344: Summary: Improve writer performance by ignoring sync to hdfs when an asyncer's writes have been synced by other asyncer Key: HBASE-10344 URL:

[jira] [Updated] (HBASE-10344) Improve writer performance by ignoring sync to hdfs when an asyncer's writes have been synced by other asyncer

[ https://issues.apache.org/jira/browse/HBASE-10344?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Feng Honghua updated HBASE-10344: - Attachment: HBASE-10344-trunk_v0.patch patch attached. thanks [~yuzhih...@gmail.com] for

[jira] [Updated] (HBASE-10344) Improve writer performance by ignoring sync to hdfs when an asyncer's writes have been synced by other asyncer

[ https://issues.apache.org/jira/browse/HBASE-10344?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Feng Honghua updated HBASE-10344: - Description: By fixing [HBASE-10329|https://issues.apache.org/jira/browse/HBASE-10329], we

[jira] [Updated] (HBASE-10344) Improve write performance by ignoring sync to hdfs when an asyncer's writes have been synced by other asyncer

[ https://issues.apache.org/jira/browse/HBASE-10344?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Feng Honghua updated HBASE-10344: - Summary: Improve write performance by ignoring sync to hdfs when an asyncer's writes have been

[jira] [Commented] (HBASE-10344) Improve write performance by ignoring sync to hdfs when an asyncer's writes have been synced by other asyncer

[ https://issues.apache.org/jira/browse/HBASE-10344?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanelfocusedCommentId=13872820#comment-13872820 ] Feng Honghua commented on HBASE-10344: -- [~apurtell] : should be the last one in this

[jira] [Commented] (HBASE-10227) When a region is opened, its mvcc isn't correctly recovered when there are split hlogs to replay

[ https://issues.apache.org/jira/browse/HBASE-10227?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanelfocusedCommentId=13870650#comment-13870650 ] Feng Honghua commented on HBASE-10227: -- thanks [~sershe] for the review bq.Storing

[jira] [Commented] (HBASE-10324) refactor deferred-log-flush/Durability related interface/code/naming to align with changed semantic of the new write thread model

[ https://issues.apache.org/jira/browse/HBASE-10324?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanelfocusedCommentId=13870653#comment-13870653 ] Feng Honghua commented on HBASE-10324: -- sorry I was out of office today, thanks

[jira] [Updated] (HBASE-10329) Fail the writes rather than proceeding silently to prevent data loss when AsyncSyncer encounters null writer and its writes aren't synced by other Asyncer

[ https://issues.apache.org/jira/browse/HBASE-10329?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Feng Honghua updated HBASE-10329: - Attachment: HBASE-10329-trunk_v2.patch A further improvement can be done here inspired by the

[jira] [Commented] (HBASE-10329) Fail the writes rather than proceeding silently to prevent data loss when AsyncSyncer encounters null writer and its writes aren't synced by other Asyncer

[ https://issues.apache.org/jira/browse/HBASE-10329?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanelfocusedCommentId=13871743#comment-13871743 ] Feng Honghua commented on HBASE-10329: -- v2 patch is based on v0 since v0 has already

[jira] [Updated] (HBASE-10227) When a region is opened, its mvcc isn't correctly recovered when there are split hlogs to replay

[ https://issues.apache.org/jira/browse/HBASE-10227?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Feng Honghua updated HBASE-10227: - Attachment: HBASE-10227-trunk_v0.patch the fix is as below: 1. persist mvcc in HLog (in

[jira] [Created] (HBASE-10329) Fail the writes rather than proceeding silently to prevent data loss when AsyncSyncer encounters null writer and its writes aren't synced by other Asyncer

Feng Honghua created HBASE-10329: Summary: Fail the writes rather than proceeding silently to prevent data loss when AsyncSyncer encounters null writer and its writes aren't synced by other Asyncer Key: HBASE-10329

[jira] [Updated] (HBASE-10329) Fail the writes rather than proceeding silently to prevent data loss when AsyncSyncer encounters null writer and its writes aren't synced by other Asyncer

[ https://issues.apache.org/jira/browse/HBASE-10329?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Feng Honghua updated HBASE-10329: - Description: Last month after I introduced multiple AsyncSyncer threads to improve the

[jira] [Updated] (HBASE-10329) Fail the writes rather than proceeding silently to prevent data loss when AsyncSyncer encounters null writer and its writes aren't synced by other Asyncer

[ https://issues.apache.org/jira/browse/HBASE-10329?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Feng Honghua updated HBASE-10329: - Attachment: HBASE-10329-trunk_v0.patch patch is attached and ping [~stack] :-) Fail the

[jira] [Updated] (HBASE-10329) Fail the writes rather than proceeding silently to prevent data loss when AsyncSyncer encounters null writer and its writes aren't synced by other Asyncer

[ https://issues.apache.org/jira/browse/HBASE-10329?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Feng Honghua updated HBASE-10329: - Description: Last month after I introduced multiple AsyncSyncer threads to improve the

[jira] [Created] (HBASE-10324) refactor deferred-log-flush/Durability related interface/code/naming to align with changed semantic by the new write thread model

Feng Honghua created HBASE-10324: Summary: refactor deferred-log-flush/Durability related interface/code/naming to align with changed semantic by the new write thread model Key: HBASE-10324 URL:

[jira] [Updated] (HBASE-10324) refactor deferred-log-flush/Durability related interface/code/naming to align with changed semantic by the new write thread model

[ https://issues.apache.org/jira/browse/HBASE-10324?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Feng Honghua updated HBASE-10324: - Attachment: HBASE-10324-trunk_v0.patch thanks [~anoop.hbase] for reminding me that there are

[jira] [Updated] (HBASE-10324) refactor deferred-log-flush/Durability related interface/code/naming to align with changed semantic of the new write thread model

[ https://issues.apache.org/jira/browse/HBASE-10324?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Feng Honghua updated HBASE-10324: - Summary: refactor deferred-log-flush/Durability related interface/code/naming to align with

[jira] [Commented] (HBASE-10296) Replace ZK with a paxos running within master processes to provide better master failover performance and state consistency

[ https://issues.apache.org/jira/browse/HBASE-10296?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanelfocusedCommentId=13868984#comment-13868984 ] Feng Honghua commented on HBASE-10296: -- bq.I always thought that having processes

[jira] [Assigned] (HBASE-10227) When a region is opened, its mvcc isn't correctly recovered when there are split hlogs to replay

[ https://issues.apache.org/jira/browse/HBASE-10227?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Feng Honghua reassigned HBASE-10227: Assignee: Feng Honghua (was: Gustavo Anatoly) When a region is opened, its mvcc isn't

[jira] [Commented] (HBASE-10227) When a region is opened, its mvcc isn't correctly recovered when there are split hlogs to replay

[ https://issues.apache.org/jira/browse/HBASE-10227?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanelfocusedCommentId=13868994#comment-13868994 ] Feng Honghua commented on HBASE-10227: -- [~gustavoanatoly] : nothing at all, please

[jira] [Commented] (HBASE-10324) refactor deferred-log-flush/Durability related interface/code/naming to align with changed semantic of the new write thread model

[ https://issues.apache.org/jira/browse/HBASE-10324?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanelfocusedCommentId=13869225#comment-13869225 ] Feng Honghua commented on HBASE-10324: -- Thanks [~yuzhih...@gmail.com]'s review :-)

[jira] [Updated] (HBASE-10324) refactor deferred-log-flush/Durability related interface/code/naming to align with changed semantic of the new write thread model

[ https://issues.apache.org/jira/browse/HBASE-10324?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Feng Honghua updated HBASE-10324: - Attachment: HBASE-10324-trunk_v1.patch new patch with naming correction per

[jira] [Updated] (HBASE-10324) refactor deferred-log-flush/Durability related interface/code/naming to align with changed semantic of the new write thread model

[ https://issues.apache.org/jira/browse/HBASE-10324?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Feng Honghua updated HBASE-10324: - Description: By the new write thread model introduced by

[jira] [Commented] (HBASE-10324) refactor deferred-log-flush/Durability related interface/code/naming to align with changed semantic of the new write thread model

[ https://issues.apache.org/jira/browse/HBASE-10324?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanelfocusedCommentId=13869228#comment-13869228 ] Feng Honghua commented on HBASE-10324: -- the failed unit-test

[jira] [Updated] (HBASE-10324) refactor deferred-log-flush/Durability related interface/code/naming to align with changed semantic of the new write thread model

[ https://issues.apache.org/jira/browse/HBASE-10324?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Feng Honghua updated HBASE-10324: - Attachment: HBASE-10324-trunk_v2.patch new patch attached per [~yuzhih...@gmail.com]'s review

[jira] [Commented] (HBASE-10324) refactor deferred-log-flush/Durability related interface/code/naming to align with changed semantic of the new write thread model

[ https://issues.apache.org/jira/browse/HBASE-10324?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanelfocusedCommentId=13869235#comment-13869235 ] Feng Honghua commented on HBASE-10324: -- bq. You should lower the number of booleans,

[jira] [Commented] (HBASE-10263) make LruBlockCache single/multi/in-memory ratio user-configurable and provide preemptive mode for in-memory type block

[ https://issues.apache.org/jira/browse/HBASE-10263?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanelfocusedCommentId=13869242#comment-13869242 ] Feng Honghua commented on HBASE-10263: -- [~vrodionov] : bq.I have always thought

[jira] [Commented] (HBASE-6581) Build with hadoop.profile=3.0

[ https://issues.apache.org/jira/browse/HBASE-6581?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanelfocusedCommentId=13869262#comment-13869262 ] Feng Honghua commented on HBASE-6581: - {code} +// public boolean remove(K key, V

[jira] [Commented] (HBASE-10296) Replace ZK with a paxos running within master processes to provide better master failover performance and state consistency

[ https://issues.apache.org/jira/browse/HBASE-10296?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanelfocusedCommentId=13868787#comment-13868787 ] Feng Honghua commented on HBASE-10296: -- bq.but that ZK path is used to find the

[jira] [Commented] (HBASE-10296) Replace ZK with a paxos running within master processes to provide better master failover performance and state consistency

[ https://issues.apache.org/jira/browse/HBASE-10296?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanelfocusedCommentId=13868792#comment-13868792 ] Feng Honghua commented on HBASE-10296: -- bq.One aspect of ZK that is worth

[jira] [Commented] (HBASE-10296) Replace ZK with a paxos running within master processes to provide better master failover performance and state consistency

[ https://issues.apache.org/jira/browse/HBASE-10296?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanelfocusedCommentId=13868800#comment-13868800 ] Feng Honghua commented on HBASE-10296: -- bq.The google chubby paper goes into some

[jira] [Commented] (HBASE-10296) Replace ZK with a paxos running within master processes to provide better master failover performance and state consistency

[ https://issues.apache.org/jira/browse/HBASE-10296?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanelfocusedCommentId=13868802#comment-13868802 ] Feng Honghua commented on HBASE-10296: -- [~lhofhansl] / [~apurtell] /

[jira] [Commented] (HBASE-10296) Replace ZK with a paxos running within master processes to provide better master failover performance and state consistency

[ https://issues.apache.org/jira/browse/HBASE-10296?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanelfocusedCommentId=13868803#comment-13868803 ] Feng Honghua commented on HBASE-10296: -- thanks all guys for the

[jira] [Commented] (HBASE-10295) Refactor the replication implementation to eliminate permanent zk node

[ https://issues.apache.org/jira/browse/HBASE-10295?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanelfocusedCommentId=13868811#comment-13868811 ] Feng Honghua commented on HBASE-10295: -- [~stack] Yes, sound feasible, thanks :-)

[jira] [Commented] (HBASE-10227) When a region is opened, its mvcc isn't correctly recovered when there are split hlogs to replay

[ https://issues.apache.org/jira/browse/HBASE-10227?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanelfocusedCommentId=13868961#comment-13868961 ] Feng Honghua commented on HBASE-10227: -- ping [~gustavoanatoly] : any update? :-)

[jira] [Commented] (HBASE-10263) make LruBlockCache single/multi/in-memory ratio user-configurable and provide preemptive mode for in-memory type block

[ https://issues.apache.org/jira/browse/HBASE-10263?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanelfocusedCommentId=13866270#comment-13866270 ] Feng Honghua commented on HBASE-10263: -- [~yuzhih...@gmail.com]: you mean to fix the

[jira] [Updated] (HBASE-10263) make LruBlockCache single/multi/in-memory ratio user-configurable and provide preemptive mode for in-memory type block

[ https://issues.apache.org/jira/browse/HBASE-10263?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Feng Honghua updated HBASE-10263: - Release Note: 4 new configurations are introduced: hbase.lru.blockcache.single.percentage /

[jira] [Commented] (HBASE-10263) make LruBlockCache single/multi/in-memory ratio user-configurable and provide preemptive mode for in-memory type block

[ https://issues.apache.org/jira/browse/HBASE-10263?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanelfocusedCommentId=13866285#comment-13866285 ] Feng Honghua commented on HBASE-10263: -- [~yuzhih...@gmail.com] : done, thanks very

[jira] [Commented] (HBASE-10156) Fix up the HBASE-8755 slowdown when low contention

[ https://issues.apache.org/jira/browse/HBASE-10156?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanelfocusedCommentId=13866361#comment-13866361 ] Feng Honghua commented on HBASE-10156: -- [~stack] : really amazing improvement for =

[jira] [Commented] (HBASE-10263) make LruBlockCache single/multi/in-memory ratio user-configurable and provide preemptive mode for in-memory type block

[ https://issues.apache.org/jira/browse/HBASE-10263?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanelfocusedCommentId=13866379#comment-13866379 ] Feng Honghua commented on HBASE-10263: -- thanks [~xieliang007] :-) make

[jira] [Commented] (HBASE-8751) Enable peer cluster to choose/change the ColumnFamilies/Tables it really want to replicate from a source cluster

[ https://issues.apache.org/jira/browse/HBASE-8751?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanelfocusedCommentId=13864975#comment-13864975 ] Feng Honghua commented on HBASE-8751: - bq.I think that is a bug and we should fix it.

[jira] [Created] (HBASE-10295) Refactor the implementation of replication peer to eliminate permanent peer-state ZKNode

Feng Honghua created HBASE-10295: Summary: Refactor the implementation of replication peer to eliminate permanent peer-state ZKNode Key: HBASE-10295 URL: https://issues.apache.org/jira/browse/HBASE-10295

[jira] [Commented] (HBASE-8751) Enable peer cluster to choose/change the ColumnFamilies/Tables it really want to replicate from a source cluster

[ https://issues.apache.org/jira/browse/HBASE-8751?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanelfocusedCommentId=13864979#comment-13864979 ] Feng Honghua commented on HBASE-8751: - A new jira

[jira] [Commented] (HBASE-10263) make LruBlockCache single/multi/in-memory ratio user-configurable and provide preemptive mode for in-memory type block

[ https://issues.apache.org/jira/browse/HBASE-10263?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanelfocusedCommentId=13864982#comment-13864982 ] Feng Honghua commented on HBASE-10263: -- bq.Any chance you can post some more

[jira] [Commented] (HBASE-10263) make LruBlockCache single/multi/in-memory ratio user-configurable and provide preemptive mode for in-memory type block

[ https://issues.apache.org/jira/browse/HBASE-10263?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanelfocusedCommentId=13865002#comment-13865002 ] Feng Honghua commented on HBASE-10263: -- Performance result: 1. create 2 tables: TA,

[jira] [Commented] (HBASE-8751) Enable peer cluster to choose/change the ColumnFamilies/Tables it really want to replicate from a source cluster

[ https://issues.apache.org/jira/browse/HBASE-8751?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanelfocusedCommentId=13865007#comment-13865007 ] Feng Honghua commented on HBASE-8751: - I agree, but is there any plan to fix the

[jira] [Updated] (HBASE-10295) Refactor the implementation of replication to eliminate permanent zk node

[ https://issues.apache.org/jira/browse/HBASE-10295?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Feng Honghua updated HBASE-10295: - Description: Though this is a more broader and bigger change, it original motivation derives

[jira] [Updated] (HBASE-10295) Refactor the replication implementation to eliminate permanent zk node

[ https://issues.apache.org/jira/browse/HBASE-10295?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Feng Honghua updated HBASE-10295: - Summary: Refactor the replication implementation to eliminate permanent zk node (was:

[jira] [Updated] (HBASE-10295) Refactor the replication implementation to eliminate permanent zk node

[ https://issues.apache.org/jira/browse/HBASE-10295?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Feng Honghua updated HBASE-10295: - Description: Though this is a broader and bigger change, it original motivation derives from

[jira] [Commented] (HBASE-10295) Refactor the replication implementation to eliminate permanent zk node

[ https://issues.apache.org/jira/browse/HBASE-10295?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanelfocusedCommentId=13865038#comment-13865038 ] Feng Honghua commented on HBASE-10295: -- Another HBase internal system table (similar

[jira] [Created] (HBASE-10296) Replace ZK with a paxos running within master processes to provide better master failover performance and state consistency

Feng Honghua created HBASE-10296: Summary: Replace ZK with a paxos running within master processes to provide better master failover performance and state consistency Key: HBASE-10296 URL:

[jira] [Commented] (HBASE-10263) make LruBlockCache single/multi/in-memory ratio user-configurable and provide preemptive mode for in-memory type block

[ https://issues.apache.org/jira/browse/HBASE-10263?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanelfocusedCommentId=13865119#comment-13865119 ] Feng Honghua commented on HBASE-10263: -- Before this jira, a rough performance

[jira] [Commented] (HBASE-10263) make LruBlockCache single/multi/in-memory ratio user-configurable and provide preemptive mode for in-memory type block

[ https://issues.apache.org/jira/browse/HBASE-10263?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanelfocusedCommentId=13863838#comment-13863838 ] Feng Honghua commented on HBASE-10263: -- Thanks [~ndimiduk] for the careful review

[jira] [Updated] (HBASE-10263) make LruBlockCache single/multi/in-memory ratio user-configurable and provide preemptive mode for in-memory type block

[ https://issues.apache.org/jira/browse/HBASE-10263?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Feng Honghua updated HBASE-10263: - Attachment: HBASE-10263-trunk_v2.patch new patch attached which adds hbase.lru.blockcache

[jira] [Commented] (HBASE-8751) Enable peer cluster to choose/change the ColumnFamilies/Tables it really want to replicate from a source cluster

[ https://issues.apache.org/jira/browse/HBASE-8751?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanelfocusedCommentId=13861354#comment-13861354 ] Feng Honghua commented on HBASE-8751: - I'll try to make a patch for trunk... Enable

[jira] [Commented] (HBASE-10263) make LruBlockCache single/multi/in-memory ratio user-configurable and provide preemptive mode for in-memory type block

[ https://issues.apache.org/jira/browse/HBASE-10263?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanelfocusedCommentId=13861358#comment-13861358 ] Feng Honghua commented on HBASE-10263: -- I re-run unit tests several times locally

<    1   2   3   4   5   6   >