[
https://issues.apache.org/jira/browse/HDFS-8863?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=14681087#comment-14681087
]
Yi Liu commented on HDFS-8863:
------------------------------
The patch looks good, thanks Kihwal.
Agree to check the maximum remaining of storage instead of summing all
remaining spaces, since we can split a block to multiple storage.
One question is: should we still keep {{getRemaining(StorageType t)}} there? No
place to call it, so can remove it?
Nits in the test:
{code}
DatanodeStorageInfo si = new DatanodeStorageInfo(
storages[5].getDatanodeDescriptor(), extraStorage);
{code}
It's unused and can be removed.
{code}
// No available space in the extra storage of dn0
updateHeartbeatForExtraStorage(0L, 0L, 0L, 0L);
{code}
typo in comment: dn0 should be dn5
It's better to set no available space in the extra storage at the end of
{{testChooseNodeWithMultipleStorages}}:
{code}
updateHeartbeatForExtraStorage(0L, 0L, 0L, 0L);
{code}
> The remiaing space check in BlockPlacementPolicyDefault is flawed
> -----------------------------------------------------------------
>
> Key: HDFS-8863
> URL: https://issues.apache.org/jira/browse/HDFS-8863
> Project: Hadoop HDFS
> Issue Type: Bug
> Affects Versions: 2.6.0
> Reporter: Kihwal Lee
> Assignee: Kihwal Lee
> Priority: Critical
> Labels: 2.6.1-candidate
> Attachments: HDFS-8863.patch
>
>
> The block placement policy calls
> {{DatanodeDescriptor#getRemaining(StorageType}}}} to check whether the block
> is going to fit. Since the method is adding up all remaining spaces, namenode
> can allocate a new block on a full node. This causes pipeline construction
> failure and {{abandonBlock}}. If the cluster is nearly full, the client might
> hit this multiple times and the write can fail permanently.
--
This message was sent by Atlassian JIRA
(v6.3.4#6332)
