[jira] [Commented] (ZOOKEEPER-2846) Leader follower sync with on disk txns can possibly leads to data inconsistency

[ https://issues.apache.org/jira/browse/ZOOKEEPER-2846?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=17485092#comment-17485092 ] Fangmin Lv commented on ZOOKEEPER-2846: --- > In the long term, we have finished adding a real

[jira] [Created] (ZOOKEEPER-3870) Avoid out of order response and txns created with ReadOnlyZooKeeperServer

Fangmin Lv created ZOOKEEPER-3870: - Summary: Avoid out of order response and txns created with ReadOnlyZooKeeperServer Key: ZOOKEEPER-3870 URL: https://issues.apache.org/jira/browse/ZOOKEEPER-3870

[jira] [Resolved] (ZOOKEEPER-3805) NIOServerCnxnFactory static block has no used code

[ https://issues.apache.org/jira/browse/ZOOKEEPER-3805?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Fangmin Lv resolved ZOOKEEPER-3805. --- Fix Version/s: 3.7.0 Resolution: Fixed Resolved in PR 

[jira] [Updated] (ZOOKEEPER-3783) Build ZooKeeper based on RocksDB

[ https://issues.apache.org/jira/browse/ZOOKEEPER-3783?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Fangmin Lv updated ZOOKEEPER-3783: -- Attachment: 0001-Use-RocksDB-for-taking-a-snapshot.patch > Build ZooKeeper based on

[jira] [Created] (ZOOKEEPER-3783) Build ZooKeeper based on RocksDB

Fangmin Lv created ZOOKEEPER-3783: - Summary: Build ZooKeeper based on RocksDB Key: ZOOKEEPER-3783 URL: https://issues.apache.org/jira/browse/ZOOKEEPER-3783 Project: ZooKeeper Issue Type:

[jira] [Resolved] (ZOOKEEPER-3682) Stop initializing new SSL connection if ZK server is shutting down

[ https://issues.apache.org/jira/browse/ZOOKEEPER-3682?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Fangmin Lv resolved ZOOKEEPER-3682. --- Resolution: Fixed Issue resolved by pull request 1210

[jira] [Resolved] (ZOOKEEPER-3575) Moving sending packets in Learner to a separate thread

[ https://issues.apache.org/jira/browse/ZOOKEEPER-3575?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Fangmin Lv resolved ZOOKEEPER-3575. --- Fix Version/s: 3.7.0 Resolution: Fixed Issue resolved by pull request 1116

[jira] [Assigned] (ZOOKEEPER-3642) Data inconsistency when the leader crashes right after sending SNAP sync

[ https://issues.apache.org/jira/browse/ZOOKEEPER-3642?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Fangmin Lv reassigned ZOOKEEPER-3642: - Assignee: Fangmin Lv > Data inconsistency when the leader crashes right after

[jira] [Updated] (ZOOKEEPER-3642) Data inconsistency when the leader crashes right after sending SNAP sync

[ https://issues.apache.org/jira/browse/ZOOKEEPER-3642?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Fangmin Lv updated ZOOKEEPER-3642: -- Affects Version/s: 3.7.0 3.6.0 > Data inconsistency when the leader

[jira] [Resolved] (ZOOKEEPER-3694) Use Map computeIfAbsent in AvgMinMaxCounterSet Class

[ https://issues.apache.org/jira/browse/ZOOKEEPER-3694?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Fangmin Lv resolved ZOOKEEPER-3694. --- Fix Version/s: 3.7.0 Resolution: Fixed Issue resolved by pull request 1218

[jira] [Resolved] (ZOOKEEPER-3658) Potential data inconsistency due to txns gap in committedLog when ZkDB not fully shutdown

[ https://issues.apache.org/jira/browse/ZOOKEEPER-3658?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Fangmin Lv resolved ZOOKEEPER-3658. --- Resolution: Invalid Different from our internal code, txns received before NEWLEADER

[jira] [Created] (ZOOKEEPER-3690) Improving leader efficiency via not processing learner's requests in commit processor

Fangmin Lv created ZOOKEEPER-3690: - Summary: Improving leader efficiency via not processing learner's requests in commit processor Key: ZOOKEEPER-3690 URL: https://issues.apache.org/jira/browse/ZOOKEEPER-3690

[jira] [Resolved] (ZOOKEEPER-3656) SyncRequestProcessor doesn't update lastFlushTime correctly on observers

[ https://issues.apache.org/jira/browse/ZOOKEEPER-3656?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Fangmin Lv resolved ZOOKEEPER-3656. --- Fix Version/s: 3.7.0 Resolution: Fixed Issue resolved by pull request 1189

[jira] [Commented] (ZOOKEEPER-3642) Data inconsistency when the leader crashes right after sending SNAP sync

[ https://issues.apache.org/jira/browse/ZOOKEEPER-3642?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=17001155#comment-17001155 ] Fangmin Lv commented on ZOOKEEPER-3642: --- [~mirg] thanks for reporting this, always taking

[jira] [Commented] (ZOOKEEPER-3591) Inconsistent resync with dynamic reconfig

[ https://issues.apache.org/jira/browse/ZOOKEEPER-3591?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=17001154#comment-17001154 ] Fangmin Lv commented on ZOOKEEPER-3591: --- [~mirg] it doesn't seem to be related to reconfig, is

[jira] [Commented] (ZOOKEEPER-3562) PKV Games atau Situs PokerV Online Indonesia

[ https://issues.apache.org/jira/browse/ZOOKEEPER-3562?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=17001047#comment-17001047 ] Fangmin Lv commented on ZOOKEEPER-3562: --- Looks like a spam? > PKV Games atau Situs PokerV

[jira] [Commented] (ZOOKEEPER-3573) Dealing with long TLS connection closing time without SO_LINGER option

[ https://issues.apache.org/jira/browse/ZOOKEEPER-3573?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=17001034#comment-17001034 ] Fangmin Lv commented on ZOOKEEPER-3573: --- Recently, we found without SO_LINGER it might cause

[jira] [Commented] (ZOOKEEPER-3586) Write Log To Multiple Drives

[ https://issues.apache.org/jira/browse/ZOOKEEPER-3586?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=17001014#comment-17001014 ] Fangmin Lv commented on ZOOKEEPER-3586: --- [~belugabehr] thanks for proposing this, can you also

[jira] [Commented] (ZOOKEEPER-3607) Potential data inconsistency due to the inconsistency between ZKDatabase.committedLog and dataTree in Trunc sync.

[ https://issues.apache.org/jira/browse/ZOOKEEPER-3607?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=17000717#comment-17000717 ] Fangmin Lv commented on ZOOKEEPER-3607: --- [~jiangjiafu] in the step 10, when zk3 tries to sync

[jira] [Created] (ZOOKEEPER-3658) Potential data inconsistency due to txns gap in committedLog when ZkDB not fully shutdown

Fangmin Lv created ZOOKEEPER-3658: - Summary: Potential data inconsistency due to txns gap in committedLog when ZkDB not fully shutdown Key: ZOOKEEPER-3658 URL: https://issues.apache.org/jira/browse/ZOOKEEPER-3658

[jira] [Commented] (ZOOKEEPER-3619) Implement server side semaphore API to improve the efficiency and throughput of coordination

[ https://issues.apache.org/jira/browse/ZOOKEEPER-3619?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=17000695#comment-17000695 ] Fangmin Lv commented on ZOOKEEPER-3619: --- Thanks [~randgalt], we'll add you as reviewer when

[jira] [Commented] (ZOOKEEPER-3634) why zookeeper huge snapshot cause waitEpockAck timeout?

[ https://issues.apache.org/jira/browse/ZOOKEEPER-3634?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=17000692#comment-17000692 ] Fangmin Lv commented on ZOOKEEPER-3634: --- [~ghostssd] Do you see things like full GC issue? >

[jira] [Commented] (ZOOKEEPER-3657) Implementing snapshot schedule to avoid high latency issue due to disk contention

[ https://issues.apache.org/jira/browse/ZOOKEEPER-3657?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=17000575#comment-17000575 ] Fangmin Lv commented on ZOOKEEPER-3657: ---  [~eolivelli] I've removed the 3.6.0 tag, thanks for

[jira] [Updated] (ZOOKEEPER-3657) Implementing snapshot schedule to avoid high latency issue due to disk contention

[ https://issues.apache.org/jira/browse/ZOOKEEPER-3657?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Fangmin Lv updated ZOOKEEPER-3657: -- Fix Version/s: (was: 3.6.0) > Implementing snapshot schedule to avoid high latency

[jira] [Updated] (ZOOKEEPER-3657) Implementing snapshot schedule to avoid high latency issue due to disk contention

[ https://issues.apache.org/jira/browse/ZOOKEEPER-3657?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Fangmin Lv updated ZOOKEEPER-3657: -- Description: If ZK server is running a machine with single disk driver, the snapshot and

[jira] [Updated] (ZOOKEEPER-3657) Implementing snapshot schedule to avoid high latency issue due to disk contention

[ https://issues.apache.org/jira/browse/ZOOKEEPER-3657?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Fangmin Lv updated ZOOKEEPER-3657: -- Description: If ZK server is running a machine with single disk driver, the snapshot and

[jira] [Created] (ZOOKEEPER-3657) Implementing snapshot schedule to avoid high latency issue due to disk contention

Fangmin Lv created ZOOKEEPER-3657: - Summary: Implementing snapshot schedule to avoid high latency issue due to disk contention Key: ZOOKEEPER-3657 URL: https://issues.apache.org/jira/browse/ZOOKEEPER-3657

[jira] [Resolved] (ZOOKEEPER-3595) Fsync parameter for serialize method is ingnored

[ https://issues.apache.org/jira/browse/ZOOKEEPER-3595?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Fangmin Lv resolved ZOOKEEPER-3595. --- Fix Version/s: 3.6.0 Resolution: Fixed Issue resolved by pull request 1146

[jira] [Commented] (ZOOKEEPER-3619) Implement server side semaphore API to improve the efficiency and throughput of coordination

[ https://issues.apache.org/jira/browse/ZOOKEEPER-3619?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=16982207#comment-16982207 ] Fangmin Lv commented on ZOOKEEPER-3619: --- [~randgalt] we're working on the implementation, will

[jira] [Updated] (ZOOKEEPER-3618) Send batch quorum Ack and Commit packets to improve the efficiency and throughput of ZK

[ https://issues.apache.org/jira/browse/ZOOKEEPER-3618?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Fangmin Lv updated ZOOKEEPER-3618: -- Summary: Send batch quorum Ack and Commit packets to improve the efficiency and throughput

[jira] [Created] (ZOOKEEPER-3619) Implement server side semaphore API to improve the efficiency and throughput of coordination

Fangmin Lv created ZOOKEEPER-3619: - Summary: Implement server side semaphore API to improve the efficiency and throughput of coordination Key: ZOOKEEPER-3619 URL:

[jira] [Created] (ZOOKEEPER-3618) Send batch quorum Ack and Commit packets to improve the efficiency and throughput of Zeus

Fangmin Lv created ZOOKEEPER-3618: - Summary: Send batch quorum Ack and Commit packets to improve the efficiency and throughput of Zeus Key: ZOOKEEPER-3618 URL: https://issues.apache.org/jira/browse/ZOOKEEPER-3618

[jira] [Commented] (ZOOKEEPER-3594) Ability to skip proposing requests with error transactions

[ https://issues.apache.org/jira/browse/ZOOKEEPER-3594?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=16971779#comment-16971779 ] Fangmin Lv commented on ZOOKEEPER-3594: --- [~hanm] this is the skip error txn feature I mentioned

[jira] [Created] (ZOOKEEPER-3598) Fix potential data inconsistency issue due to CommitProcessor not gracefully shutdown

Fangmin Lv created ZOOKEEPER-3598: - Summary: Fix potential data inconsistency issue due to CommitProcessor not gracefully shutdown Key: ZOOKEEPER-3598 URL: https://issues.apache.org/jira/browse/ZOOKEEPER-3598

[jira] [Created] (ZOOKEEPER-3540) Client port unavailable after binding the same client port during reconfig

Fangmin Lv created ZOOKEEPER-3540: - Summary: Client port unavailable after binding the same client port during reconfig Key: ZOOKEEPER-3540 URL: https://issues.apache.org/jira/browse/ZOOKEEPER-3540

[jira] [Commented] (ZOOKEEPER-3496) Transaction larger than jute.maxbuffer makes ZooKeeper unavailable

[ https://issues.apache.org/jira/browse/ZOOKEEPER-3496?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=16922851#comment-16922851 ] Fangmin Lv commented on ZOOKEEPER-3496: --- [~arshad.mohammad] thanks for reporting the issue and

[jira] [Commented] (ZOOKEEPER-3531) Synchronization on ACLCache cause cluster to hang when network/disk issues happen during datatree serialization

[ https://issues.apache.org/jira/browse/ZOOKEEPER-3531?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=16922835#comment-16922835 ] Fangmin Lv commented on ZOOKEEPER-3531: --- Thanks [~chlou] for reporting the issue, I've

[jira] [Commented] (ZOOKEEPER-3534) Non-stop communication between participants and observers.

[ https://issues.apache.org/jira/browse/ZOOKEEPER-3534?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=16922824#comment-16922824 ] Fangmin Lv commented on ZOOKEEPER-3534: --- [~karolos] thanks for reporting the issue, if there

[jira] [Updated] (ZOOKEEPER-3512) Real time data integrity check during broadcast time

[ https://issues.apache.org/jira/browse/ZOOKEEPER-3512?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Fangmin Lv updated ZOOKEEPER-3512: -- Parent: ZOOKEEPER-3114 Issue Type: Sub-task (was: New Feature) > Real time data

[jira] [Created] (ZOOKEEPER-3512) Real time data integrity check during broadcast time

Fangmin Lv created ZOOKEEPER-3512: - Summary: Real time data integrity check during broadcast time Key: ZOOKEEPER-3512 URL: https://issues.apache.org/jira/browse/ZOOKEEPER-3512 Project: ZooKeeper

[jira] [Commented] (ZOOKEEPER-3500) Improving the ZAB UPTODATE semantic to only issue it to learner when there is limited lagging

[ https://issues.apache.org/jira/browse/ZOOKEEPER-3500?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=16903178#comment-16903178 ] Fangmin Lv commented on ZOOKEEPER-3500: --- This is the basic idea we're trying to have

[jira] [Created] (ZOOKEEPER-3500) Improving the ZAB UPTODATE semantic to only issue it to learner when there is limited lagging

Fangmin Lv created ZOOKEEPER-3500: - Summary: Improving the ZAB UPTODATE semantic to only issue it to learner when there is limited lagging Key: ZOOKEEPER-3500 URL:

[jira] [Commented] (ZOOKEEPER-3480) Flaky test CommitProcessorMetricsTest.testConcurrentRequestProcessingInCommitProcessor

[ https://issues.apache.org/jira/browse/ZOOKEEPER-3480?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=16899394#comment-16899394 ] Fangmin Lv commented on ZOOKEEPER-3480: --- [~maoling] yes, I've provided a PR to fix this. >

[jira] [Created] (ZOOKEEPER-3480) Flaky test CommitProcessorMetricsTest.testConcurrentRequestProcessingInCommitProcessor

Fangmin Lv created ZOOKEEPER-3480: - Summary: Flaky test CommitProcessorMetricsTest.testConcurrentRequestProcessingInCommitProcessor Key: ZOOKEEPER-3480 URL: https://issues.apache.org/jira/browse/ZOOKEEPER-3480

[jira] [Created] (ZOOKEEPER-3473) Improving successful TLS handshake throughput with concurrent control

Fangmin Lv created ZOOKEEPER-3473: - Summary: Improving successful TLS handshake throughput with concurrent control Key: ZOOKEEPER-3473 URL: https://issues.apache.org/jira/browse/ZOOKEEPER-3473

[jira] [Updated] (ZOOKEEPER-3472) Treat check request as a write request which needs to wait for the check txn commit from leader

[ https://issues.apache.org/jira/browse/ZOOKEEPER-3472?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Fangmin Lv updated ZOOKEEPER-3472: -- Description: Check op is usually used as a sub op in multi, but from the ZooKeeper server

[jira] [Created] (ZOOKEEPER-3472) Treat check request as a write request which needs to wait for the check txn commit from leader

Fangmin Lv created ZOOKEEPER-3472: - Summary: Treat check request as a write request which needs to wait for the check txn commit from leader Key: ZOOKEEPER-3472 URL:

[jira] [Commented] (ZOOKEEPER-3418) Improve quorum throughput through eager ACL checks of requests on local servers

[ https://issues.apache.org/jira/browse/ZOOKEEPER-3418?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=16873664#comment-16873664 ] Fangmin Lv commented on ZOOKEEPER-3418: --- Yes, that's the protocol change I mentioned, we need

[jira] [Commented] (ZOOKEEPER-3418) Improve quorum throughput through eager ACL checks of requests on local servers

[ https://issues.apache.org/jira/browse/ZOOKEEPER-3418?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=16863328#comment-16863328 ] Fangmin Lv commented on ZOOKEEPER-3418: --- [~hanm] we're thinking of optimizing other throughput

[jira] [Resolved] (ZOOKEEPER-3321) Add metrics for Leader

[ https://issues.apache.org/jira/browse/ZOOKEEPER-3321?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Fangmin Lv resolved ZOOKEEPER-3321. --- Resolution: Fixed Issue resolved by pull request 858

[jira] [Resolved] (ZOOKEEPER-3309) Add sync processor metrics

[ https://issues.apache.org/jira/browse/ZOOKEEPER-3309?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Fangmin Lv resolved ZOOKEEPER-3309. --- Resolution: Fixed Issue resolved by pull request 850