hadoop-common-issues mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From "Niels Basjes (Commented) (JIRA)" <j...@apache.org>
Subject [jira] [Commented] (HADOOP-7909) Implement Splittable Gzip based on a signature in a gzip header field
Date Mon, 12 Dec 2011 12:32:30 GMT

    [ https://issues.apache.org/jira/browse/HADOOP-7909?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=13167474#comment-13167474
] 

Niels Basjes commented on HADOOP-7909:
--------------------------------------

Tim,

I think that both of those questions are hard because of the fact that Hadoop MapReduce does
roughly these steps in this order:
1. Look at the input filename and filesize
2. Determine codec and if it is splittable
3. Create the split definitions
4. Distribute these split definitions over many tasks / nodes on your cluster
5. Each task opens a file and tries to process the indicated split.

If you find around 5. that you cannot split correctly, then you cannot go back to 3. to redefine
the splits.
Also I expect that trying the HADOOP-7076 way afterwards is hard: What if the first split
succeeds and the second one doesn't (which run on completely separate nodes)?

Niels
                
> Implement Splittable Gzip based on a signature in a gzip header field
> ---------------------------------------------------------------------
>
>                 Key: HADOOP-7909
>                 URL: https://issues.apache.org/jira/browse/HADOOP-7909
>             Project: Hadoop Common
>          Issue Type: New Feature
>          Components: io
>            Reporter: Tim Broberg
>            Priority: Minor
>   Original Estimate: 672h
>  Remaining Estimate: 672h
>
> I propose to take the suggestion of PIG-42 extend it to
>  - add a more robust header such that false matches are vanishingly unlikely
>  - repeat initial bytes of the header for very fast split searching
>  - break down the stream into modest size chunks (~64k?) for rapid parallel encode and
decode
>  - provide length information on the blocks in advance to make block decode possible
in hardware
> An optional extra header would be added to the gzip header, adding 36 bytes.
> <sh> := <version><signature><uncompressedDataLength><compressedRecordLength>
> <version> := 1 byte version field allowing us to later adjust the deader definition
> <signature> := 23 byte signature of the form aaaaaaabcdefghijklmnopr where each
letter represents a randomly generated byte
> <uncompressedDataLength> := 32-bit length of the data compressed into this record
> <compressedRecordLength> := 32-bit length of this record as compressed, including
all headers, trailers
> If multiple extra headers are present and the split header is not the first header, the
initial implementation will not recognize the split.
> Input streams would be broken down into blocks which are appended, much as BlockCompressorStream
does. Non-split-aware decoders will ignore this header and decode the appended blocks without
ever noticing the difference.
> The signature has >= 132 bits of entropy which is sufficient for 80+ years of Moore's
law before collisions become a significant concern.
> The first 7 bytes are repeated for speed. When splitting, the signature search will look
for the 32-bit value aaaa every 4 bytes until a hit is found, then the next 4 bytes identify
the alignment of the header mod 4 to identify a potential header match, then the whole header
is validated at that offset. So, there is a load, compare, branch, and increment per 4 bytes
searched.
> The existing gzip implementations do not provide access to the optional header fields
(nor comment nor filename), so the entire gzip header will have to be reimplemented and compression
will need to be done using the raw deflate options of the native library / built in deflater.
> There will be some degradation when using splittable gzip:
>  - The gzip headers will each be 36 bytes larger. (4 byte extra header header, 32 byte
extra header)
>  - There will be one gzip header per block.
>  - History will have to be reset with each block to allow starting from scratch at that
offset resulting in some uncompressed bytes that would otherwise have been strings.
> Issues to consider:
>  - Is the searching fast enough without the repeating 7 bytes in the signature?
>  - Should this be a patch to the existing gzip classes to add a switch, or should this
be a whole new class?
>  - Which level does this belong at? CompressionStream? Compressor?
>  - Is it more advantageous to encode the signature into the less dense comment field?
>  - Optimum block size? Smaller splits faster and may conserve memory, larger provides
slightly better compression ratio.

--
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

        

Mime
View raw message