[jira] [Commented] (HDFS-3564) Make the replication policy pluggable to allow custom replication policies
[ https://issues.apache.org/jira/browse/HDFS-3564?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanelfocusedCommentId=13413155#comment-13413155 ] Harsh J commented on HDFS-3564: --- bq. I will re-purpose this JIRA to suggest enhancements to the existing abstraction. Given that HDFS-3649 was just opened for backport work, can you at least re-title the JIRA to fit this re-purpose goal? Avoids confusion for some of us. Thanks! :) Make the replication policy pluggable to allow custom replication policies -- Key: HDFS-3564 URL: https://issues.apache.org/jira/browse/HDFS-3564 Project: Hadoop HDFS Issue Type: Improvement Components: name-node Reporter: Sumadhur Reddy Bolli Original Estimate: 24h Remaining Estimate: 24h ReplicationTargetChooser currently determines the placement of replicas in hadoop. Making the replication policy pluggable would help in having custom replication policies that suit the environment. Eg1: Enabling placing replicas across different datacenters(not just racks) Eg2: Enabling placing replicas across multiple(more than 2) racks Eg3: Cloud environments like azure have logical concepts like fault and upgrade domains. Each fault domain spans multiple upgrade domains and each upgrade domain spans multiple fault domains. Machines are spread typically evenly across both fault and upgrade domains. Fault domain failures are typically catastrophic/unplanned failures and data loss possibility is high. An upgrade domain can be taken down by azure for maintenance periodically. Each time an upgrade domain is taken down a small percentage of machines in the upgrade domain(typically 1-2%) are replaced due to disk failures, thus losing data. Assuming the default replication factor 3, any 3 data nodes going down at the same time would mean potential data loss. So, it is important to have a policy that spreads replicas across both fault and upgrade domains to ensure practically no data loss. The problem here is two dimensional and the default policy in hadoop is one-dimensional. Custom policies to address issues like these can be written if we make the policy pluggable. -- This message is automatically generated by JIRA. If you think it was sent incorrectly, please contact your JIRA administrators: https://issues.apache.org/jira/secure/ContactAdministrators!default.jspa For more information on JIRA, see: http://www.atlassian.com/software/jira
[jira] [Commented] (HDFS-3564) Make the replication policy pluggable to allow custom replication policies
[ https://issues.apache.org/jira/browse/HDFS-3564?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanelfocusedCommentId=13412463#comment-13412463 ] Sumadhur Reddy Bolli commented on HDFS-3564: Making the policy pluggable should be sufficent. I will re-purpose this JIRA to suggest enhancements to the existing abstraction. Network topology is not known to the users in azure and it is not strictly hierarichical in nature as fault domains span upgrade domains and upgrade domains can span fault domains. However, I do not see much value in changing the internal abstractions for topology as we do not know the underlying physical topology in azure. I will post a document with the details on the JIRA 3566 to explain this better. Make the replication policy pluggable to allow custom replication policies -- Key: HDFS-3564 URL: https://issues.apache.org/jira/browse/HDFS-3564 Project: Hadoop HDFS Issue Type: Improvement Components: name-node Reporter: Sumadhur Reddy Bolli Original Estimate: 24h Remaining Estimate: 24h ReplicationTargetChooser currently determines the placement of replicas in hadoop. Making the replication policy pluggable would help in having custom replication policies that suit the environment. Eg1: Enabling placing replicas across different datacenters(not just racks) Eg2: Enabling placing replicas across multiple(more than 2) racks Eg3: Cloud environments like azure have logical concepts like fault and upgrade domains. Each fault domain spans multiple upgrade domains and each upgrade domain spans multiple fault domains. Machines are spread typically evenly across both fault and upgrade domains. Fault domain failures are typically catastrophic/unplanned failures and data loss possibility is high. An upgrade domain can be taken down by azure for maintenance periodically. Each time an upgrade domain is taken down a small percentage of machines in the upgrade domain(typically 1-2%) are replaced due to disk failures, thus losing data. Assuming the default replication factor 3, any 3 data nodes going down at the same time would mean potential data loss. So, it is important to have a policy that spreads replicas across both fault and upgrade domains to ensure practically no data loss. The problem here is two dimensional and the default policy in hadoop is one-dimensional. Custom policies to address issues like these can be written if we make the policy pluggable. -- This message is automatically generated by JIRA. If you think it was sent incorrectly, please contact your JIRA administrators: https://issues.apache.org/jira/secure/ContactAdministrators!default.jspa For more information on JIRA, see: http://www.atlassian.com/software/jira
[jira] [Commented] (HDFS-3564) Make the replication policy pluggable to allow custom replication policies
[ https://issues.apache.org/jira/browse/HDFS-3564?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanelfocusedCommentId=13403453#comment-13403453 ] Sanjay Radia commented on HDFS-3564: HDFS has assumed that the hierarchical network shows both distance and fault-domains. The rack represented a group of machines that are close to each other and also within a fault domain. For VMs we simply needed to generalize the network topology to more levels to address both distance and faults with vm-hosts. This jira suggests that the notion of fault domains can be orthogonal to the topology. Do we need to change some internal abstractions or is it sufficient to make the placement policy pluggable? Not sure. Make the replication policy pluggable to allow custom replication policies -- Key: HDFS-3564 URL: https://issues.apache.org/jira/browse/HDFS-3564 Project: Hadoop HDFS Issue Type: Improvement Components: name-node Reporter: Sumadhur Reddy Bolli Original Estimate: 24h Remaining Estimate: 24h ReplicationTargetChooser currently determines the placement of replicas in hadoop. Making the replication policy pluggable would help in having custom replication policies that suit the environment. Eg1: Enabling placing replicas across different datacenters(not just racks) Eg2: Enabling placing replicas across multiple(more than 2) racks Eg3: Cloud environments like azure have logical concepts like fault and upgrade domains. Each fault domain spans multiple upgrade domains and each upgrade domain spans multiple fault domains. Machines are spread typically evenly across both fault and upgrade domains. Fault domain failures are typically catastrophic/unplanned failures and data loss possibility is high. An upgrade domain can be taken down by azure for maintenance periodically. Each time an upgrade domain is taken down a small percentage of machines in the upgrade domain(typically 1-2%) are replaced due to disk failures, thus losing data. Assuming the default replication factor 3, any 3 data nodes going down at the same time would mean potential data loss. So, it is important to have a policy that spreads replicas across both fault and upgrade domains to ensure practically no data loss. The problem here is two dimensional and the default policy in hadoop is one-dimensional. Custom policies to address issues like these can be written if we make the policy pluggable. -- This message is automatically generated by JIRA. If you think it was sent incorrectly, please contact your JIRA administrators: https://issues.apache.org/jira/secure/ContactAdministrators!default.jspa For more information on JIRA, see: http://www.atlassian.com/software/jira
[jira] [Commented] (HDFS-3564) Make the replication policy pluggable to allow custom replication policies
[ https://issues.apache.org/jira/browse/HDFS-3564?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanelfocusedCommentId=13401595#comment-13401595 ] Harsh J commented on HDFS-3564: --- We've already made replication policies pluggable via an experimental API. See https://issues.apache.org/jira/browse/HDFS-385. This is available in the 2.0.x, 0.23.x and 0.22.x releases already today. If that suffices, please close this out as a dupe? Make the replication policy pluggable to allow custom replication policies -- Key: HDFS-3564 URL: https://issues.apache.org/jira/browse/HDFS-3564 Project: Hadoop HDFS Issue Type: Improvement Components: name-node Reporter: Sumadhur Reddy Bolli Original Estimate: 24h Remaining Estimate: 24h ReplicationTargetChooser currently determines the placement of replicas in hadoop. Making the replication policy pluggable would help in having custom replication policies that suit the environment. Eg1: Enabling placing replicas across different datacenters(not just racks) Eg2: Enabling placing replicas across multiple(more than 2) racks Eg3: Cloud environments like azure have logical concepts like fault and upgrade domains. Each fault domain spans multiple upgrade domains and each upgrade domain spans multiple fault domains. Machines are spread typically evenly across both fault and upgrade domains. Fault domain failures are typically catastrophic/unplanned failures and data loss possibility is high. An upgrade domain can be taken down by azure for maintenance periodically. Each time an upgrade domain is taken down a small percentage of machines in the upgrade domain(typically 1-2%) are replaced due to disk failures, thus losing data. Assuming the default replication factor 3, any 3 data nodes going down at the same time would mean potential data loss. So, it is important to have a policy that spreads replicas across both fault and upgrade domains to ensure practically no data loss. The problem here is two dimensional and the default policy in hadoop is one-dimensional. Custom policies to address issues like these can be written if we make the policy pluggable. -- This message is automatically generated by JIRA. If you think it was sent incorrectly, please contact your JIRA administrators: https://issues.apache.org/jira/secure/ContactAdministrators!default.jspa For more information on JIRA, see: http://www.atlassian.com/software/jira
[jira] [Commented] (HDFS-3564) Make the replication policy pluggable to allow custom replication policies
[ https://issues.apache.org/jira/browse/HDFS-3564?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanelfocusedCommentId=13401856#comment-13401856 ] Tsz Wo (Nicholas), SZE commented on HDFS-3564: -- Harsh, this is not a dupe since this is for branch-1/branch-1-win. We probably should first backport HDFS-385. BTW, there is a an ongoing work on supporting different failure and locality topologies; see HADOOP-8468. Make the replication policy pluggable to allow custom replication policies -- Key: HDFS-3564 URL: https://issues.apache.org/jira/browse/HDFS-3564 Project: Hadoop HDFS Issue Type: Improvement Components: name-node Reporter: Sumadhur Reddy Bolli Original Estimate: 24h Remaining Estimate: 24h ReplicationTargetChooser currently determines the placement of replicas in hadoop. Making the replication policy pluggable would help in having custom replication policies that suit the environment. Eg1: Enabling placing replicas across different datacenters(not just racks) Eg2: Enabling placing replicas across multiple(more than 2) racks Eg3: Cloud environments like azure have logical concepts like fault and upgrade domains. Each fault domain spans multiple upgrade domains and each upgrade domain spans multiple fault domains. Machines are spread typically evenly across both fault and upgrade domains. Fault domain failures are typically catastrophic/unplanned failures and data loss possibility is high. An upgrade domain can be taken down by azure for maintenance periodically. Each time an upgrade domain is taken down a small percentage of machines in the upgrade domain(typically 1-2%) are replaced due to disk failures, thus losing data. Assuming the default replication factor 3, any 3 data nodes going down at the same time would mean potential data loss. So, it is important to have a policy that spreads replicas across both fault and upgrade domains to ensure practically no data loss. The problem here is two dimensional and the default policy in hadoop is one-dimensional. Custom policies to address issues like these can be written if we make the policy pluggable. -- This message is automatically generated by JIRA. If you think it was sent incorrectly, please contact your JIRA administrators: https://issues.apache.org/jira/secure/ContactAdministrators!default.jspa For more information on JIRA, see: http://www.atlassian.com/software/jira
[jira] [Commented] (HDFS-3564) Make the replication policy pluggable to allow custom replication policies
[ https://issues.apache.org/jira/browse/HDFS-3564?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanelfocusedCommentId=13401954#comment-13401954 ] Harsh J commented on HDFS-3564: --- Nicholas, Understood from target list that this is for branch-1 (which is also why I didn't close it, but just asked). Thank you for clarifying! :) Make the replication policy pluggable to allow custom replication policies -- Key: HDFS-3564 URL: https://issues.apache.org/jira/browse/HDFS-3564 Project: Hadoop HDFS Issue Type: Improvement Components: name-node Reporter: Sumadhur Reddy Bolli Original Estimate: 24h Remaining Estimate: 24h ReplicationTargetChooser currently determines the placement of replicas in hadoop. Making the replication policy pluggable would help in having custom replication policies that suit the environment. Eg1: Enabling placing replicas across different datacenters(not just racks) Eg2: Enabling placing replicas across multiple(more than 2) racks Eg3: Cloud environments like azure have logical concepts like fault and upgrade domains. Each fault domain spans multiple upgrade domains and each upgrade domain spans multiple fault domains. Machines are spread typically evenly across both fault and upgrade domains. Fault domain failures are typically catastrophic/unplanned failures and data loss possibility is high. An upgrade domain can be taken down by azure for maintenance periodically. Each time an upgrade domain is taken down a small percentage of machines in the upgrade domain(typically 1-2%) are replaced due to disk failures, thus losing data. Assuming the default replication factor 3, any 3 data nodes going down at the same time would mean potential data loss. So, it is important to have a policy that spreads replicas across both fault and upgrade domains to ensure practically no data loss. The problem here is two dimensional and the default policy in hadoop is one-dimensional. Custom policies to address issues like these can be written if we make the policy pluggable. -- This message is automatically generated by JIRA. If you think it was sent incorrectly, please contact your JIRA administrators: https://issues.apache.org/jira/secure/ContactAdministrators!default.jspa For more information on JIRA, see: http://www.atlassian.com/software/jira