hadoop-hdfs-issues mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From "Dennis Huo (JIRA)" <j...@apache.org>
Subject [jira] [Commented] (HDFS-13056) Expose file-level composite CRCs in HDFS which are comparable across different instances/layouts
Date Fri, 09 Mar 2018 00:40:00 GMT

    [ https://issues.apache.org/jira/browse/HDFS-13056?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=16392176#comment-16392176
] 

Dennis Huo commented on HDFS-13056:
-----------------------------------

Variable-sized blocks within a file are indeed supported (though in your examples there are
still uniform blocksizes within a file except for last file); in addition to your three examples,
the following would also return the same value as another example:
 # [1, 3, 2, 1]

This is implemented by FileChecksumHelper always using block.getBlockSize() as the data length
for each block rather than assuming what the block size should be, except for the last block,
where I don't trust block.getBlockSize(). In the last block, it turned out that some flows
modified the reported block-size in-place and others didn't so I just made sure to manually
compute the correct number of bytes associated with the last block.

There are constraints on chunk and cell sizes, but these are based on inherent constraints
in the system rather than assumptions in my algorithm; cell size must be uniform within a
block group (but can vary in different block groups within a single file), which is already
a fundamental assumption in striped reader anyways, and chunk size must be uniform within
a block (which is also fundamental because block metadata doesn't have any way to indicate
changes of bytes-per-crc midway through the block).

> Expose file-level composite CRCs in HDFS which are comparable across different instances/layouts
> ------------------------------------------------------------------------------------------------
>
>                 Key: HDFS-13056
>                 URL: https://issues.apache.org/jira/browse/HDFS-13056
>             Project: Hadoop HDFS
>          Issue Type: New Feature
>          Components: datanode, distcp, erasure-coding, federation, hdfs
>    Affects Versions: 3.0.0
>            Reporter: Dennis Huo
>            Assignee: Dennis Huo
>            Priority: Major
>         Attachments: HDFS-13056-branch-2.8.001.patch, HDFS-13056-branch-2.8.002.patch,
HDFS-13056-branch-2.8.003.patch, HDFS-13056-branch-2.8.004.patch, HDFS-13056-branch-2.8.005.patch,
HDFS-13056-branch-2.8.poc1.patch, HDFS-13056.001.patch, HDFS-13056.002.patch, HDFS-13056.003.patch,
HDFS-13056.003.patch, HDFS-13056.004.patch, HDFS-13056.005.patch, HDFS-13056.006.patch, HDFS-13056.007.patch,
HDFS-13056.008.patch, Reference_only_zhen_PPOC_hadoop2.6.X.diff, hdfs-file-composite-crc32-v1.pdf,
hdfs-file-composite-crc32-v2.pdf, hdfs-file-composite-crc32-v3.pdf
>
>
> FileChecksum was first introduced in [https://issues-test.apache.org/jira/browse/HADOOP-3981] and
ever since then has remained defined as MD5-of-MD5-of-CRC, where per-512-byte chunk CRCs are
already stored as part of datanode metadata, and the MD5 approach is used to compute an aggregate
value in a distributed manner, with individual datanodes computing the MD5-of-CRCs per-block
in parallel, and the HDFS client computing the second-level MD5.
>  
> A shortcoming of this approach which is often brought up is the fact that this FileChecksum
is sensitive to the internal block-size and chunk-size configuration, and thus different
HDFS files with different block/chunk settings cannot be compared. More commonly, one might
have different HDFS clusters which use different block sizes, in which case any data migration
won't be able to use the FileChecksum for distcp's rsync functionality or for verifying end-to-end
data integrity (on top of low-level data integrity checks applied at data transfer time).
>  
> This was also revisited in https://issues.apache.org/jira/browse/HDFS-8430 during the
addition of checksum support for striped erasure-coded files; while there was some discussion
of using CRC composability, it still ultimately settled on hierarchical MD5 approach, which also adds
the problem that checksums of basic replicated files are not comparable to striped files.
>  
> This feature proposes to add a "COMPOSITE-CRC" FileChecksum type which uses CRC composition
to remain completely chunk/block agnostic, and allows comparison between striped vs replicated
files, between different HDFS instances, and possible even between HDFS and other external
storage systems. This feature can also be added in-place to be compatible with existing block
metadata, and doesn't need to change the normal path of chunk verification, so is minimally
invasive. This also means even large preexisting HDFS deployments could adopt this feature
to retroactively sync data. A detailed design document can be found here: https://storage.googleapis.com/dennishuo/hdfs-file-composite-crc32-v1.pdf



--
This message was sent by Atlassian JIRA
(v7.6.3#76005)

---------------------------------------------------------------------
To unsubscribe, e-mail: hdfs-issues-unsubscribe@hadoop.apache.org
For additional commands, e-mail: hdfs-issues-help@hadoop.apache.org


Mime
View raw message