[
https://issues.apache.org/jira/browse/HDFS-8578?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]
Raju Bairishetti updated HDFS-8578:
-----------------------------------
Description:
Right now, during upgrades datanode is processing all the storage dirs
sequentially. Assume it takes ~20 mins to process a single storage dir then
datanode which has ~10 disks will take around 3hours to come up.
{code}
for (int idx = 0; idx < getNumStorageDirs(); idx++) {
doTransition(datanode, getStorageDir(idx), nsInfo, startOpt);
assert getCTime() == nsInfo.getCTime()
: "Data-node and name-node CTimes must be the same.";
}
{code}
Can we make datanode to process all the storage dirs parallelly? This saves
lots of time during upgrades.
was:
Right now, during upgrades datanode is processing all the storage dirs
sequentially. Assume it takes ~20 mins to process a single storage dir then
datanode which has ~10 disks will take around 3hours to come up.
{code}
for (int idx = 0; idx < getNumStorageDirs(); idx++) {
doTransition(datanode, getStorageDir(idx), nsInfo, startOpt);
assert getCTime() == nsInfo.getCTime()
: "Data-node and name-node CTimes must be the same.";
}
{code}
Can we make datanode to process all the staorage dirs parallelly? This saves
lots of time during upgrades.
> On upgrade, Datanode should process all storage/data dirs in parallel
> ---------------------------------------------------------------------
>
> Key: HDFS-8578
> URL: https://issues.apache.org/jira/browse/HDFS-8578
> Project: Hadoop HDFS
> Issue Type: Bug
> Components: datanode
> Reporter: Raju Bairishetti
> Priority: Critical
>
> Right now, during upgrades datanode is processing all the storage dirs
> sequentially. Assume it takes ~20 mins to process a single storage dir then
> datanode which has ~10 disks will take around 3hours to come up.
> {code}
> for (int idx = 0; idx < getNumStorageDirs(); idx++) {
> doTransition(datanode, getStorageDir(idx), nsInfo, startOpt);
> assert getCTime() == nsInfo.getCTime()
> : "Data-node and name-node CTimes must be the same.";
> }
> {code}
> Can we make datanode to process all the storage dirs parallelly? This saves
> lots of time during upgrades.
--
This message was sent by Atlassian JIRA
(v6.3.4#6332)
