[jira] [Updated] (HDFS-7980) Incremental BlockReport will dramatically slow down the startup of a namenode
[ https://issues.apache.org/jira/browse/HDFS-7980?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Junping Du updated HDFS-7980: - Fix Version/s: 2.8.0 > Incremental BlockReport will dramatically slow down the startup of a namenode > -- > > Key: HDFS-7980 > URL: https://issues.apache.org/jira/browse/HDFS-7980 > Project: Hadoop HDFS > Issue Type: Bug >Reporter: Hui Zheng >Assignee: Walter Su > Labels: 2.6.1-candidate > Fix For: 2.6.1, 2.8.0, 2.7.1, 3.0.0-alpha1 > > Attachments: HDFS-7980-branch-2.6.1.txt, HDFS-7980.001.patch, > HDFS-7980.002.patch, HDFS-7980.003.patch, HDFS-7980.004.patch, > HDFS-7980.004.repost.patch > > > In the current implementation the datanode will call the > reportReceivedDeletedBlocks() method that is a IncrementalBlockReport before > calling the bpNamenode.blockReport() method. So in a large(several thousands > of datanodes) and busy cluster it will slow down(more than one hour) the > startup of namenode. > {code} > List blockReport() throws IOException { > // send block report if timer has expired. > final long startTime = now(); > if (startTime - lastBlockReport <= dnConf.blockReportInterval) { > return null; > } > final ArrayList cmds = new ArrayList(); > // Flush any block information that precedes the block report. Otherwise > // we have a chance that we will miss the delHint information > // or we will report an RBW replica after the BlockReport already reports > // a FINALIZED one. > reportReceivedDeletedBlocks(); > lastDeletedReport = startTime; > . > // Send the reports to the NN. > int numReportsSent = 0; > int numRPCs = 0; > boolean success = false; > long brSendStartTime = now(); > try { > if (totalBlockCount < dnConf.blockReportSplitThreshold) { > // Below split threshold, send all reports in a single message. > DatanodeCommand cmd = bpNamenode.blockReport( > bpRegistration, bpos.getBlockPoolId(), reports); > {code} -- This message was sent by Atlassian JIRA (v6.3.4#6332) - To unsubscribe, e-mail: hdfs-issues-unsubscr...@hadoop.apache.org For additional commands, e-mail: hdfs-issues-h...@hadoop.apache.org
[jira] [Updated] (HDFS-7980) Incremental BlockReport will dramatically slow down the startup of a namenode
[ https://issues.apache.org/jira/browse/HDFS-7980?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Vinod Kumar Vavilapalli updated HDFS-7980: -- Fix Version/s: 2.6.1 Pulled this into 2.6.1. Made minor code changes (usage of the non-absent AddBlockResult with a boolean), dropped java-7'isms and edited the test to not use the non-absent BlockListAsLongs.Builder. Ran compilation and TestBlockManager before the push. > Incremental BlockReport will dramatically slow down the startup of a namenode > -- > > Key: HDFS-7980 > URL: https://issues.apache.org/jira/browse/HDFS-7980 > Project: Hadoop HDFS > Issue Type: Bug >Reporter: Hui Zheng >Assignee: Walter Su > Labels: 2.6.1-candidate > Fix For: 2.6.1, 2.7.1 > > Attachments: HDFS-7980-branch-2.6.1.txt, HDFS-7980.001.patch, > HDFS-7980.002.patch, HDFS-7980.003.patch, HDFS-7980.004.patch, > HDFS-7980.004.repost.patch > > > In the current implementation the datanode will call the > reportReceivedDeletedBlocks() method that is a IncrementalBlockReport before > calling the bpNamenode.blockReport() method. So in a large(several thousands > of datanodes) and busy cluster it will slow down(more than one hour) the > startup of namenode. > {code} > List blockReport() throws IOException { > // send block report if timer has expired. > final long startTime = now(); > if (startTime - lastBlockReport <= dnConf.blockReportInterval) { > return null; > } > final ArrayList cmds = new ArrayList(); > // Flush any block information that precedes the block report. Otherwise > // we have a chance that we will miss the delHint information > // or we will report an RBW replica after the BlockReport already reports > // a FINALIZED one. > reportReceivedDeletedBlocks(); > lastDeletedReport = startTime; > . > // Send the reports to the NN. > int numReportsSent = 0; > int numRPCs = 0; > boolean success = false; > long brSendStartTime = now(); > try { > if (totalBlockCount < dnConf.blockReportSplitThreshold) { > // Below split threshold, send all reports in a single message. > DatanodeCommand cmd = bpNamenode.blockReport( > bpRegistration, bpos.getBlockPoolId(), reports); > {code} -- This message was sent by Atlassian JIRA (v6.3.4#6332)
[jira] [Updated] (HDFS-7980) Incremental BlockReport will dramatically slow down the startup of a namenode
[ https://issues.apache.org/jira/browse/HDFS-7980?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Vinod Kumar Vavilapalli updated HDFS-7980: -- Attachment: HDFS-7980-branch-2.6.1.txt Attaching the patch that I committed to 2.6.1. > Incremental BlockReport will dramatically slow down the startup of a namenode > -- > > Key: HDFS-7980 > URL: https://issues.apache.org/jira/browse/HDFS-7980 > Project: Hadoop HDFS > Issue Type: Bug >Reporter: Hui Zheng >Assignee: Walter Su > Labels: 2.6.1-candidate > Fix For: 2.6.1, 2.7.1 > > Attachments: HDFS-7980-branch-2.6.1.txt, HDFS-7980.001.patch, > HDFS-7980.002.patch, HDFS-7980.003.patch, HDFS-7980.004.patch, > HDFS-7980.004.repost.patch > > > In the current implementation the datanode will call the > reportReceivedDeletedBlocks() method that is a IncrementalBlockReport before > calling the bpNamenode.blockReport() method. So in a large(several thousands > of datanodes) and busy cluster it will slow down(more than one hour) the > startup of namenode. > {code} > List blockReport() throws IOException { > // send block report if timer has expired. > final long startTime = now(); > if (startTime - lastBlockReport <= dnConf.blockReportInterval) { > return null; > } > final ArrayList cmds = new ArrayList(); > // Flush any block information that precedes the block report. Otherwise > // we have a chance that we will miss the delHint information > // or we will report an RBW replica after the BlockReport already reports > // a FINALIZED one. > reportReceivedDeletedBlocks(); > lastDeletedReport = startTime; > . > // Send the reports to the NN. > int numReportsSent = 0; > int numRPCs = 0; > boolean success = false; > long brSendStartTime = now(); > try { > if (totalBlockCount < dnConf.blockReportSplitThreshold) { > // Below split threshold, send all reports in a single message. > DatanodeCommand cmd = bpNamenode.blockReport( > bpRegistration, bpos.getBlockPoolId(), reports); > {code} -- This message was sent by Atlassian JIRA (v6.3.4#6332)
[jira] [Updated] (HDFS-7980) Incremental BlockReport will dramatically slow down the startup of a namenode
[ https://issues.apache.org/jira/browse/HDFS-7980?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Zhihua Deng updated HDFS-7980: -- Attachment: hadoop-241.patch Incremental BlockReport will dramatically slow down the startup of a namenode -- Key: HDFS-7980 URL: https://issues.apache.org/jira/browse/HDFS-7980 Project: Hadoop HDFS Issue Type: Bug Reporter: Hui Zheng Assignee: Walter Su Labels: 2.6.1-candidate Fix For: 2.7.1 Attachments: HDFS-7980.001.patch, HDFS-7980.002.patch, HDFS-7980.003.patch, HDFS-7980.004.patch, HDFS-7980.004.repost.patch, hadoop-241.patch In the current implementation the datanode will call the reportReceivedDeletedBlocks() method that is a IncrementalBlockReport before calling the bpNamenode.blockReport() method. So in a large(several thousands of datanodes) and busy cluster it will slow down(more than one hour) the startup of namenode. {code} ListDatanodeCommand blockReport() throws IOException { // send block report if timer has expired. final long startTime = now(); if (startTime - lastBlockReport = dnConf.blockReportInterval) { return null; } final ArrayListDatanodeCommand cmds = new ArrayListDatanodeCommand(); // Flush any block information that precedes the block report. Otherwise // we have a chance that we will miss the delHint information // or we will report an RBW replica after the BlockReport already reports // a FINALIZED one. reportReceivedDeletedBlocks(); lastDeletedReport = startTime; . // Send the reports to the NN. int numReportsSent = 0; int numRPCs = 0; boolean success = false; long brSendStartTime = now(); try { if (totalBlockCount dnConf.blockReportSplitThreshold) { // Below split threshold, send all reports in a single message. DatanodeCommand cmd = bpNamenode.blockReport( bpRegistration, bpos.getBlockPoolId(), reports); {code} -- This message was sent by Atlassian JIRA (v6.3.4#6332)
[jira] [Updated] (HDFS-7980) Incremental BlockReport will dramatically slow down the startup of a namenode
[ https://issues.apache.org/jira/browse/HDFS-7980?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Zhihua Deng updated HDFS-7980: -- Attachment: (was: hadoop-241.patch) Incremental BlockReport will dramatically slow down the startup of a namenode -- Key: HDFS-7980 URL: https://issues.apache.org/jira/browse/HDFS-7980 Project: Hadoop HDFS Issue Type: Bug Reporter: Hui Zheng Assignee: Walter Su Labels: 2.6.1-candidate Fix For: 2.7.1 Attachments: HDFS-7980.001.patch, HDFS-7980.002.patch, HDFS-7980.003.patch, HDFS-7980.004.patch, HDFS-7980.004.repost.patch In the current implementation the datanode will call the reportReceivedDeletedBlocks() method that is a IncrementalBlockReport before calling the bpNamenode.blockReport() method. So in a large(several thousands of datanodes) and busy cluster it will slow down(more than one hour) the startup of namenode. {code} ListDatanodeCommand blockReport() throws IOException { // send block report if timer has expired. final long startTime = now(); if (startTime - lastBlockReport = dnConf.blockReportInterval) { return null; } final ArrayListDatanodeCommand cmds = new ArrayListDatanodeCommand(); // Flush any block information that precedes the block report. Otherwise // we have a chance that we will miss the delHint information // or we will report an RBW replica after the BlockReport already reports // a FINALIZED one. reportReceivedDeletedBlocks(); lastDeletedReport = startTime; . // Send the reports to the NN. int numReportsSent = 0; int numRPCs = 0; boolean success = false; long brSendStartTime = now(); try { if (totalBlockCount dnConf.blockReportSplitThreshold) { // Below split threshold, send all reports in a single message. DatanodeCommand cmd = bpNamenode.blockReport( bpRegistration, bpos.getBlockPoolId(), reports); {code} -- This message was sent by Atlassian JIRA (v6.3.4#6332)
[jira] [Updated] (HDFS-7980) Incremental BlockReport will dramatically slow down the startup of a namenode
[ https://issues.apache.org/jira/browse/HDFS-7980?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Chris Trezzo updated HDFS-7980: --- Labels: 2.6.1-candidate (was: ) Incremental BlockReport will dramatically slow down the startup of a namenode -- Key: HDFS-7980 URL: https://issues.apache.org/jira/browse/HDFS-7980 Project: Hadoop HDFS Issue Type: Bug Reporter: Hui Zheng Assignee: Walter Su Labels: 2.6.1-candidate Fix For: 2.7.1 Attachments: HDFS-7980.001.patch, HDFS-7980.002.patch, HDFS-7980.003.patch, HDFS-7980.004.patch, HDFS-7980.004.repost.patch In the current implementation the datanode will call the reportReceivedDeletedBlocks() method that is a IncrementalBlockReport before calling the bpNamenode.blockReport() method. So in a large(several thousands of datanodes) and busy cluster it will slow down(more than one hour) the startup of namenode. {code} ListDatanodeCommand blockReport() throws IOException { // send block report if timer has expired. final long startTime = now(); if (startTime - lastBlockReport = dnConf.blockReportInterval) { return null; } final ArrayListDatanodeCommand cmds = new ArrayListDatanodeCommand(); // Flush any block information that precedes the block report. Otherwise // we have a chance that we will miss the delHint information // or we will report an RBW replica after the BlockReport already reports // a FINALIZED one. reportReceivedDeletedBlocks(); lastDeletedReport = startTime; . // Send the reports to the NN. int numReportsSent = 0; int numRPCs = 0; boolean success = false; long brSendStartTime = now(); try { if (totalBlockCount dnConf.blockReportSplitThreshold) { // Below split threshold, send all reports in a single message. DatanodeCommand cmd = bpNamenode.blockReport( bpRegistration, bpos.getBlockPoolId(), reports); {code} -- This message was sent by Atlassian JIRA (v6.3.4#6332)
[jira] [Updated] (HDFS-7980) Incremental BlockReport will dramatically slow down the startup of a namenode
[ https://issues.apache.org/jira/browse/HDFS-7980?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Priyank Rastogi updated HDFS-7980: -- Labels: (was: BB2015-05-TBR) Incremental BlockReport will dramatically slow down the startup of a namenode -- Key: HDFS-7980 URL: https://issues.apache.org/jira/browse/HDFS-7980 Project: Hadoop HDFS Issue Type: Bug Reporter: Hui Zheng Assignee: Walter Su Fix For: 2.7.1 Attachments: HDFS-7980.001.patch, HDFS-7980.002.patch, HDFS-7980.003.patch, HDFS-7980.004.patch, HDFS-7980.004.repost.patch In the current implementation the datanode will call the reportReceivedDeletedBlocks() method that is a IncrementalBlockReport before calling the bpNamenode.blockReport() method. So in a large(several thousands of datanodes) and busy cluster it will slow down(more than one hour) the startup of namenode. {code} ListDatanodeCommand blockReport() throws IOException { // send block report if timer has expired. final long startTime = now(); if (startTime - lastBlockReport = dnConf.blockReportInterval) { return null; } final ArrayListDatanodeCommand cmds = new ArrayListDatanodeCommand(); // Flush any block information that precedes the block report. Otherwise // we have a chance that we will miss the delHint information // or we will report an RBW replica after the BlockReport already reports // a FINALIZED one. reportReceivedDeletedBlocks(); lastDeletedReport = startTime; . // Send the reports to the NN. int numReportsSent = 0; int numRPCs = 0; boolean success = false; long brSendStartTime = now(); try { if (totalBlockCount dnConf.blockReportSplitThreshold) { // Below split threshold, send all reports in a single message. DatanodeCommand cmd = bpNamenode.blockReport( bpRegistration, bpos.getBlockPoolId(), reports); {code} -- This message was sent by Atlassian JIRA (v6.3.4#6332)
[jira] [Updated] (HDFS-7980) Incremental BlockReport will dramatically slow down the startup of a namenode
[ https://issues.apache.org/jira/browse/HDFS-7980?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Tsz Wo Nicholas Sze updated HDFS-7980: -- Resolution: Fixed Fix Version/s: 2.7.1 Hadoop Flags: Reviewed Status: Resolved (was: Patch Available) Thanks for explaining it. +1 patch looks good. I have committed this. Thanks, Walter! Incremental BlockReport will dramatically slow down the startup of a namenode -- Key: HDFS-7980 URL: https://issues.apache.org/jira/browse/HDFS-7980 Project: Hadoop HDFS Issue Type: Bug Reporter: Hui Zheng Assignee: Walter Su Labels: BB2015-05-TBR Fix For: 2.7.1 Attachments: HDFS-7980.001.patch, HDFS-7980.002.patch, HDFS-7980.003.patch, HDFS-7980.004.patch, HDFS-7980.004.repost.patch In the current implementation the datanode will call the reportReceivedDeletedBlocks() method that is a IncrementalBlockReport before calling the bpNamenode.blockReport() method. So in a large(several thousands of datanodes) and busy cluster it will slow down(more than one hour) the startup of namenode. {code} ListDatanodeCommand blockReport() throws IOException { // send block report if timer has expired. final long startTime = now(); if (startTime - lastBlockReport = dnConf.blockReportInterval) { return null; } final ArrayListDatanodeCommand cmds = new ArrayListDatanodeCommand(); // Flush any block information that precedes the block report. Otherwise // we have a chance that we will miss the delHint information // or we will report an RBW replica after the BlockReport already reports // a FINALIZED one. reportReceivedDeletedBlocks(); lastDeletedReport = startTime; . // Send the reports to the NN. int numReportsSent = 0; int numRPCs = 0; boolean success = false; long brSendStartTime = now(); try { if (totalBlockCount dnConf.blockReportSplitThreshold) { // Below split threshold, send all reports in a single message. DatanodeCommand cmd = bpNamenode.blockReport( bpRegistration, bpos.getBlockPoolId(), reports); {code} -- This message was sent by Atlassian JIRA (v6.3.4#6332)
[jira] [Updated] (HDFS-7980) Incremental BlockReport will dramatically slow down the startup of a namenode
[ https://issues.apache.org/jira/browse/HDFS-7980?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Walter Su updated HDFS-7980: Attachment: HDFS-7980.004.repost.patch Incremental BlockReport will dramatically slow down the startup of a namenode -- Key: HDFS-7980 URL: https://issues.apache.org/jira/browse/HDFS-7980 Project: Hadoop HDFS Issue Type: Bug Reporter: Hui Zheng Assignee: Walter Su Labels: BB2015-05-TBR Attachments: HDFS-7980.001.patch, HDFS-7980.002.patch, HDFS-7980.003.patch, HDFS-7980.004.patch, HDFS-7980.004.repost.patch In the current implementation the datanode will call the reportReceivedDeletedBlocks() method that is a IncrementalBlockReport before calling the bpNamenode.blockReport() method. So in a large(several thousands of datanodes) and busy cluster it will slow down(more than one hour) the startup of namenode. {code} ListDatanodeCommand blockReport() throws IOException { // send block report if timer has expired. final long startTime = now(); if (startTime - lastBlockReport = dnConf.blockReportInterval) { return null; } final ArrayListDatanodeCommand cmds = new ArrayListDatanodeCommand(); // Flush any block information that precedes the block report. Otherwise // we have a chance that we will miss the delHint information // or we will report an RBW replica after the BlockReport already reports // a FINALIZED one. reportReceivedDeletedBlocks(); lastDeletedReport = startTime; . // Send the reports to the NN. int numReportsSent = 0; int numRPCs = 0; boolean success = false; long brSendStartTime = now(); try { if (totalBlockCount dnConf.blockReportSplitThreshold) { // Below split threshold, send all reports in a single message. DatanodeCommand cmd = bpNamenode.blockReport( bpRegistration, bpos.getBlockPoolId(), reports); {code} -- This message was sent by Atlassian JIRA (v6.3.4#6332)
[jira] [Updated] (HDFS-7980) Incremental BlockReport will dramatically slow down the startup of a namenode
[ https://issues.apache.org/jira/browse/HDFS-7980?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Allen Wittenauer updated HDFS-7980: --- Labels: BB2015-05-TBR (was: ) Incremental BlockReport will dramatically slow down the startup of a namenode -- Key: HDFS-7980 URL: https://issues.apache.org/jira/browse/HDFS-7980 Project: Hadoop HDFS Issue Type: Bug Reporter: Hui Zheng Assignee: Walter Su Labels: BB2015-05-TBR Attachments: HDFS-7980.001.patch, HDFS-7980.002.patch, HDFS-7980.003.patch, HDFS-7980.004.patch In the current implementation the datanode will call the reportReceivedDeletedBlocks() method that is a IncrementalBlockReport before calling the bpNamenode.blockReport() method. So in a large(several thousands of datanodes) and busy cluster it will slow down(more than one hour) the startup of namenode. {code} ListDatanodeCommand blockReport() throws IOException { // send block report if timer has expired. final long startTime = now(); if (startTime - lastBlockReport = dnConf.blockReportInterval) { return null; } final ArrayListDatanodeCommand cmds = new ArrayListDatanodeCommand(); // Flush any block information that precedes the block report. Otherwise // we have a chance that we will miss the delHint information // or we will report an RBW replica after the BlockReport already reports // a FINALIZED one. reportReceivedDeletedBlocks(); lastDeletedReport = startTime; . // Send the reports to the NN. int numReportsSent = 0; int numRPCs = 0; boolean success = false; long brSendStartTime = now(); try { if (totalBlockCount dnConf.blockReportSplitThreshold) { // Below split threshold, send all reports in a single message. DatanodeCommand cmd = bpNamenode.blockReport( bpRegistration, bpos.getBlockPoolId(), reports); {code} -- This message was sent by Atlassian JIRA (v6.3.4#6332)
[jira] [Updated] (HDFS-7980) Incremental BlockReport will dramatically slow down the startup of a namenode
[ https://issues.apache.org/jira/browse/HDFS-7980?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Walter Su updated HDFS-7980: Attachment: HDFS-7980.004.patch Incremental BlockReport will dramatically slow down the startup of a namenode -- Key: HDFS-7980 URL: https://issues.apache.org/jira/browse/HDFS-7980 Project: Hadoop HDFS Issue Type: Bug Reporter: Hui Zheng Assignee: Walter Su Attachments: HDFS-7980.001.patch, HDFS-7980.002.patch, HDFS-7980.003.patch, HDFS-7980.004.patch In the current implementation the datanode will call the reportReceivedDeletedBlocks() method that is a IncrementalBlockReport before calling the bpNamenode.blockReport() method. So in a large(several thousands of datanodes) and busy cluster it will slow down(more than one hour) the startup of namenode. {code} ListDatanodeCommand blockReport() throws IOException { // send block report if timer has expired. final long startTime = now(); if (startTime - lastBlockReport = dnConf.blockReportInterval) { return null; } final ArrayListDatanodeCommand cmds = new ArrayListDatanodeCommand(); // Flush any block information that precedes the block report. Otherwise // we have a chance that we will miss the delHint information // or we will report an RBW replica after the BlockReport already reports // a FINALIZED one. reportReceivedDeletedBlocks(); lastDeletedReport = startTime; . // Send the reports to the NN. int numReportsSent = 0; int numRPCs = 0; boolean success = false; long brSendStartTime = now(); try { if (totalBlockCount dnConf.blockReportSplitThreshold) { // Below split threshold, send all reports in a single message. DatanodeCommand cmd = bpNamenode.blockReport( bpRegistration, bpos.getBlockPoolId(), reports); {code} -- This message was sent by Atlassian JIRA (v6.3.4#6332)
[jira] [Updated] (HDFS-7980) Incremental BlockReport will dramatically slow down the startup of a namenode
[ https://issues.apache.org/jira/browse/HDFS-7980?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Walter Su updated HDFS-7980: Attachment: HDFS-7980.003.patch Incremental BlockReport will dramatically slow down the startup of a namenode -- Key: HDFS-7980 URL: https://issues.apache.org/jira/browse/HDFS-7980 Project: Hadoop HDFS Issue Type: Bug Reporter: Hui Zheng Assignee: Walter Su Attachments: HDFS-7980.001.patch, HDFS-7980.002.patch, HDFS-7980.003.patch In the current implementation the datanode will call the reportReceivedDeletedBlocks() method that is a IncrementalBlockReport before calling the bpNamenode.blockReport() method. So in a large(several thousands of datanodes) and busy cluster it will slow down(more than one hour) the startup of namenode. {code} ListDatanodeCommand blockReport() throws IOException { // send block report if timer has expired. final long startTime = now(); if (startTime - lastBlockReport = dnConf.blockReportInterval) { return null; } final ArrayListDatanodeCommand cmds = new ArrayListDatanodeCommand(); // Flush any block information that precedes the block report. Otherwise // we have a chance that we will miss the delHint information // or we will report an RBW replica after the BlockReport already reports // a FINALIZED one. reportReceivedDeletedBlocks(); lastDeletedReport = startTime; . // Send the reports to the NN. int numReportsSent = 0; int numRPCs = 0; boolean success = false; long brSendStartTime = now(); try { if (totalBlockCount dnConf.blockReportSplitThreshold) { // Below split threshold, send all reports in a single message. DatanodeCommand cmd = bpNamenode.blockReport( bpRegistration, bpos.getBlockPoolId(), reports); {code} -- This message was sent by Atlassian JIRA (v6.3.4#6332)
[jira] [Updated] (HDFS-7980) Incremental BlockReport will dramatically slow down the startup of a namenode
[ https://issues.apache.org/jira/browse/HDFS-7980?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Walter Su updated HDFS-7980: Status: Patch Available (was: Open) Incremental BlockReport will dramatically slow down the startup of a namenode -- Key: HDFS-7980 URL: https://issues.apache.org/jira/browse/HDFS-7980 Project: Hadoop HDFS Issue Type: Bug Reporter: Hui Zheng Assignee: Walter Su Attachments: HDFS-7980.001.patch, HDFS-7980.002.patch, HDFS-7980.003.patch In the current implementation the datanode will call the reportReceivedDeletedBlocks() method that is a IncrementalBlockReport before calling the bpNamenode.blockReport() method. So in a large(several thousands of datanodes) and busy cluster it will slow down(more than one hour) the startup of namenode. {code} ListDatanodeCommand blockReport() throws IOException { // send block report if timer has expired. final long startTime = now(); if (startTime - lastBlockReport = dnConf.blockReportInterval) { return null; } final ArrayListDatanodeCommand cmds = new ArrayListDatanodeCommand(); // Flush any block information that precedes the block report. Otherwise // we have a chance that we will miss the delHint information // or we will report an RBW replica after the BlockReport already reports // a FINALIZED one. reportReceivedDeletedBlocks(); lastDeletedReport = startTime; . // Send the reports to the NN. int numReportsSent = 0; int numRPCs = 0; boolean success = false; long brSendStartTime = now(); try { if (totalBlockCount dnConf.blockReportSplitThreshold) { // Below split threshold, send all reports in a single message. DatanodeCommand cmd = bpNamenode.blockReport( bpRegistration, bpos.getBlockPoolId(), reports); {code} -- This message was sent by Atlassian JIRA (v6.3.4#6332)
[jira] [Updated] (HDFS-7980) Incremental BlockReport will dramatically slow down the startup of a namenode
[ https://issues.apache.org/jira/browse/HDFS-7980?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Walter Su updated HDFS-7980: Attachment: HDFS-7980.002.patch Incremental BlockReport will dramatically slow down the startup of a namenode -- Key: HDFS-7980 URL: https://issues.apache.org/jira/browse/HDFS-7980 Project: Hadoop HDFS Issue Type: Bug Reporter: Hui Zheng Assignee: Walter Su Attachments: HDFS-7980.001.patch, HDFS-7980.002.patch In the current implementation the datanode will call the reportReceivedDeletedBlocks() method that is a IncrementalBlockReport before calling the bpNamenode.blockReport() method. So in a large(several thousands of datanodes) and busy cluster it will slow down(more than one hour) the startup of namenode. {code} ListDatanodeCommand blockReport() throws IOException { // send block report if timer has expired. final long startTime = now(); if (startTime - lastBlockReport = dnConf.blockReportInterval) { return null; } final ArrayListDatanodeCommand cmds = new ArrayListDatanodeCommand(); // Flush any block information that precedes the block report. Otherwise // we have a chance that we will miss the delHint information // or we will report an RBW replica after the BlockReport already reports // a FINALIZED one. reportReceivedDeletedBlocks(); lastDeletedReport = startTime; . // Send the reports to the NN. int numReportsSent = 0; int numRPCs = 0; boolean success = false; long brSendStartTime = now(); try { if (totalBlockCount dnConf.blockReportSplitThreshold) { // Below split threshold, send all reports in a single message. DatanodeCommand cmd = bpNamenode.blockReport( bpRegistration, bpos.getBlockPoolId(), reports); {code} -- This message was sent by Atlassian JIRA (v6.3.4#6332)
[jira] [Updated] (HDFS-7980) Incremental BlockReport will dramatically slow down the startup of a namenode
[ https://issues.apache.org/jira/browse/HDFS-7980?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Walter Su updated HDFS-7980: Attachment: (was: HDFS-7980.002.patch) Incremental BlockReport will dramatically slow down the startup of a namenode -- Key: HDFS-7980 URL: https://issues.apache.org/jira/browse/HDFS-7980 Project: Hadoop HDFS Issue Type: Bug Reporter: Hui Zheng Assignee: Walter Su Attachments: HDFS-7980.001.patch In the current implementation the datanode will call the reportReceivedDeletedBlocks() method that is a IncrementalBlockReport before calling the bpNamenode.blockReport() method. So in a large(several thousands of datanodes) and busy cluster it will slow down(more than one hour) the startup of namenode. {code} ListDatanodeCommand blockReport() throws IOException { // send block report if timer has expired. final long startTime = now(); if (startTime - lastBlockReport = dnConf.blockReportInterval) { return null; } final ArrayListDatanodeCommand cmds = new ArrayListDatanodeCommand(); // Flush any block information that precedes the block report. Otherwise // we have a chance that we will miss the delHint information // or we will report an RBW replica after the BlockReport already reports // a FINALIZED one. reportReceivedDeletedBlocks(); lastDeletedReport = startTime; . // Send the reports to the NN. int numReportsSent = 0; int numRPCs = 0; boolean success = false; long brSendStartTime = now(); try { if (totalBlockCount dnConf.blockReportSplitThreshold) { // Below split threshold, send all reports in a single message. DatanodeCommand cmd = bpNamenode.blockReport( bpRegistration, bpos.getBlockPoolId(), reports); {code} -- This message was sent by Atlassian JIRA (v6.3.4#6332)
[jira] [Updated] (HDFS-7980) Incremental BlockReport will dramatically slow down the startup of a namenode
[ https://issues.apache.org/jira/browse/HDFS-7980?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Walter Su updated HDFS-7980: Attachment: HDFS-7980.002.patch Incremental BlockReport will dramatically slow down the startup of a namenode -- Key: HDFS-7980 URL: https://issues.apache.org/jira/browse/HDFS-7980 Project: Hadoop HDFS Issue Type: Bug Reporter: Hui Zheng Assignee: Walter Su Attachments: HDFS-7980.001.patch, HDFS-7980.002.patch In the current implementation the datanode will call the reportReceivedDeletedBlocks() method that is a IncrementalBlockReport before calling the bpNamenode.blockReport() method. So in a large(several thousands of datanodes) and busy cluster it will slow down(more than one hour) the startup of namenode. {code} ListDatanodeCommand blockReport() throws IOException { // send block report if timer has expired. final long startTime = now(); if (startTime - lastBlockReport = dnConf.blockReportInterval) { return null; } final ArrayListDatanodeCommand cmds = new ArrayListDatanodeCommand(); // Flush any block information that precedes the block report. Otherwise // we have a chance that we will miss the delHint information // or we will report an RBW replica after the BlockReport already reports // a FINALIZED one. reportReceivedDeletedBlocks(); lastDeletedReport = startTime; . // Send the reports to the NN. int numReportsSent = 0; int numRPCs = 0; boolean success = false; long brSendStartTime = now(); try { if (totalBlockCount dnConf.blockReportSplitThreshold) { // Below split threshold, send all reports in a single message. DatanodeCommand cmd = bpNamenode.blockReport( bpRegistration, bpos.getBlockPoolId(), reports); {code} -- This message was sent by Atlassian JIRA (v6.3.4#6332)
[jira] [Updated] (HDFS-7980) Incremental BlockReport will dramatically slow down the startup of a namenode
[ https://issues.apache.org/jira/browse/HDFS-7980?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Walter Su updated HDFS-7980: Attachment: (was: HDFS-7980.002.patch) Incremental BlockReport will dramatically slow down the startup of a namenode -- Key: HDFS-7980 URL: https://issues.apache.org/jira/browse/HDFS-7980 Project: Hadoop HDFS Issue Type: Bug Reporter: Hui Zheng Assignee: Walter Su Attachments: HDFS-7980.001.patch In the current implementation the datanode will call the reportReceivedDeletedBlocks() method that is a IncrementalBlockReport before calling the bpNamenode.blockReport() method. So in a large(several thousands of datanodes) and busy cluster it will slow down(more than one hour) the startup of namenode. {code} ListDatanodeCommand blockReport() throws IOException { // send block report if timer has expired. final long startTime = now(); if (startTime - lastBlockReport = dnConf.blockReportInterval) { return null; } final ArrayListDatanodeCommand cmds = new ArrayListDatanodeCommand(); // Flush any block information that precedes the block report. Otherwise // we have a chance that we will miss the delHint information // or we will report an RBW replica after the BlockReport already reports // a FINALIZED one. reportReceivedDeletedBlocks(); lastDeletedReport = startTime; . // Send the reports to the NN. int numReportsSent = 0; int numRPCs = 0; boolean success = false; long brSendStartTime = now(); try { if (totalBlockCount dnConf.blockReportSplitThreshold) { // Below split threshold, send all reports in a single message. DatanodeCommand cmd = bpNamenode.blockReport( bpRegistration, bpos.getBlockPoolId(), reports); {code} -- This message was sent by Atlassian JIRA (v6.3.4#6332)
[jira] [Updated] (HDFS-7980) Incremental BlockReport will dramatically slow down the startup of a namenode
[ https://issues.apache.org/jira/browse/HDFS-7980?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Walter Su updated HDFS-7980: Attachment: HDFS-7980.002.patch Incremental BlockReport will dramatically slow down the startup of a namenode -- Key: HDFS-7980 URL: https://issues.apache.org/jira/browse/HDFS-7980 Project: Hadoop HDFS Issue Type: Bug Reporter: Hui Zheng Assignee: Walter Su Attachments: HDFS-7980.001.patch, HDFS-7980.002.patch In the current implementation the datanode will call the reportReceivedDeletedBlocks() method that is a IncrementalBlockReport before calling the bpNamenode.blockReport() method. So in a large(several thousands of datanodes) and busy cluster it will slow down(more than one hour) the startup of namenode. {code} ListDatanodeCommand blockReport() throws IOException { // send block report if timer has expired. final long startTime = now(); if (startTime - lastBlockReport = dnConf.blockReportInterval) { return null; } final ArrayListDatanodeCommand cmds = new ArrayListDatanodeCommand(); // Flush any block information that precedes the block report. Otherwise // we have a chance that we will miss the delHint information // or we will report an RBW replica after the BlockReport already reports // a FINALIZED one. reportReceivedDeletedBlocks(); lastDeletedReport = startTime; . // Send the reports to the NN. int numReportsSent = 0; int numRPCs = 0; boolean success = false; long brSendStartTime = now(); try { if (totalBlockCount dnConf.blockReportSplitThreshold) { // Below split threshold, send all reports in a single message. DatanodeCommand cmd = bpNamenode.blockReport( bpRegistration, bpos.getBlockPoolId(), reports); {code} -- This message was sent by Atlassian JIRA (v6.3.4#6332)
[jira] [Updated] (HDFS-7980) Incremental BlockReport will dramatically slow down the startup of a namenode
[ https://issues.apache.org/jira/browse/HDFS-7980?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Walter Su updated HDFS-7980: Attachment: HDFS-7980.001.patch Incremental BlockReport will dramatically slow down the startup of a namenode -- Key: HDFS-7980 URL: https://issues.apache.org/jira/browse/HDFS-7980 Project: Hadoop HDFS Issue Type: Bug Reporter: Hui Zheng Assignee: Walter Su Attachments: HDFS-7980.001.patch In the current implementation the datanode will call the reportReceivedDeletedBlocks() method that is a IncrementalBlockReport before calling the bpNamenode.blockReport() method. So in a large(several thousands of datanodes) and busy cluster it will slow down(more than one hour) the startup of namenode. {code} ListDatanodeCommand blockReport() throws IOException { // send block report if timer has expired. final long startTime = now(); if (startTime - lastBlockReport = dnConf.blockReportInterval) { return null; } final ArrayListDatanodeCommand cmds = new ArrayListDatanodeCommand(); // Flush any block information that precedes the block report. Otherwise // we have a chance that we will miss the delHint information // or we will report an RBW replica after the BlockReport already reports // a FINALIZED one. reportReceivedDeletedBlocks(); lastDeletedReport = startTime; . // Send the reports to the NN. int numReportsSent = 0; int numRPCs = 0; boolean success = false; long brSendStartTime = now(); try { if (totalBlockCount dnConf.blockReportSplitThreshold) { // Below split threshold, send all reports in a single message. DatanodeCommand cmd = bpNamenode.blockReport( bpRegistration, bpos.getBlockPoolId(), reports); {code} -- This message was sent by Atlassian JIRA (v6.3.4#6332)