[
https://issues.apache.org/jira/browse/HDFS-10587?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15376368#comment-15376368
]
Vinayakumar B commented on HDFS-10587:
--------------------------------------
bq. (5) The last chunk (512 bytes) was not a full chunk, but the destination
still reserved the whole chunk in its buffer, and wrote the entire buffer to
disk, therefore some written data is garbage.
Since the sender have more onDisk data than ack'ed, it can send extra bytes
during transfer. That doesnt mean that extra data sent is garbage. Its valid
data, but not sent the ack upstream, possibly due to waiting for the ack from
downstream.
So in current case, extra bytes sent to make up to chunk end, should be valid
data, along with the checksum available at the sender.
Client, anyway will send the unack'ed packets again. These packets should
recalculate the checksum if these are appending data to same chunk.
If the onDisk data is at the chunk boundary, that chunk will be skipped and
next chunk will be written for the packet.
If the packet starting in between the chunk, then it should contain only data
to fill up the chunk.
So in this case, since the ondisk length is at the chunk boundary, then next
packet(which is starting in middle of the chunk) will be skipped.
Another question is, whats the exact sequence of events? VolumeScanner can scan
only completed blocks. Whether this block was closed and re-opened for append?
Whether client reading the data found any corruption later?
It would be helpful, if more logs are shared for both datanodes.
> Incorrect offset/length calculation in pipeline recovery causes block
> corruption
> --------------------------------------------------------------------------------
>
> Key: HDFS-10587
> URL: https://issues.apache.org/jira/browse/HDFS-10587
> Project: Hadoop HDFS
> Issue Type: Bug
> Components: datanode
> Reporter: Wei-Chiu Chuang
> Assignee: Wei-Chiu Chuang
> Attachments: HDFS-10587.001.patch
>
>
> We found incorrect offset and length calculation in pipeline recovery may
> cause block corruption and results in missing blocks under a very unfortunate
> scenario.
> (1) A client established pipeline and started writing data to the pipeline.
> (2) One of the data node in the pipeline restarted, closing the socket, and
> some written data were unacknowledged.
> (3) Client replaced the failed data node with a new one, initiating block
> transfer to copy existing data in the block to the new datanode.
> (4) The block is transferred to the new node. Crucially, the entire block,
> including the unacknowledged data, was transferred.
> (5) The last chunk (512 bytes) was not a full chunk, but the destination
> still reserved the whole chunk in its buffer, and wrote the entire buffer to
> disk, therefore some written data is garbage.
> (6) When the transfer was done, the destination data node converted the
> replica from temporary to rbw, which made its visible length as the length of
> bytes on disk. That is to say, it thought whatever was transferred was
> acknowledged. However, the visible length of the replica is different (round
> up to the next multiple of 512) than the source of transfer. [1]
> (7) Client then truncated the block in the attempt to remove unacknowledged
> data. However, because the visible length is equivalent of the bytes on disk,
> it did not truncate unacknowledged data.
> (8) When new data was appended to the destination, it skipped the bytes
> already on disk. Therefore, whatever was written as garbage was not replaced.
> (9) the volume scanner detected corrupt replica, but due to HDFS-10512, it
> wouldn’t tell NameNode to mark the replica as corrupt, so the client
> continued to form a pipeline using the corrupt replica.
> (10) Finally the DN that had the only healthy replica was restarted. NameNode
> then update the pipeline to only contain the corrupt replica.
> (11) Client continue to write to the corrupt replica, because neither client
> nor the data node itself knows the replica is corrupt. When the restarted
> datanodes comes back, their replica are stale, despite they are not corrupt.
> Therefore, none of the replica is good and up to date.
> The sequence of events was reconstructed based on DataNode/NameNode log and
> my understanding of code.
> Incidentally, we have observed the same sequence of events on two independent
> clusters.
> [1]
> The sender has the replica as follows:
> 2016-04-15 22:03:05,066 INFO
> org.apache.hadoop.hdfs.server.datanode.fsdataset.impl.FsDatasetImpl:
> Recovering ReplicaBeingWritten, blk_1556997324_1100153495099, RBW
> getNumBytes() = 41381376
> getBytesOnDisk() = 41381376
> getVisibleLength()= 41186444
> getVolume() = /hadoop-i/data/current
> getBlockFile() =
> /hadoop-i/data/current/BP-1043567091-10.216.26.120-1343682168507/current/rbw/blk_1556997324
> bytesAcked=41186444
> bytesOnDisk=41381376
> while the receiver has the replica as follows:
> 2016-04-15 22:03:05,068 INFO
> org.apache.hadoop.hdfs.server.datanode.fsdataset.impl.FsDatasetImpl:
> Recovering ReplicaBeingWritten, blk_1556997324_1100153495099, RBW
> getNumBytes() = 41186816
> getBytesOnDisk() = 41186816
> getVisibleLength()= 41186816
> getVolume() = /hadoop-g/data/current
> getBlockFile() =
> /hadoop-g/data/current/BP-1043567091-10.216.26.120-1343682168507/current/rbw/blk_1556997324
> bytesAcked=41186816
> bytesOnDisk=41186816
--
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
