[ 
https://issues.apache.org/jira/browse/HBASE-4218?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=13179945#comment-13179945
 ] 

Mikhail Bautin commented on HBASE-4218:
---------------------------------------

I think that with an 8K line patch we probably should not try to put more 
complexity into the first version of delta encoding. We can always make things 
more complicated later. I like the two-parameter setup: DATA_BLOCK_ENCODING 
sets the encoding type (on-disk and in-cache by default) and ENCODE_ON_DISK 
(true by default) allows to use in-cache-only encoding (when explicitly setting 
ENCODE_ON_DISK=false) and get the benefit of encoding in cache even before we 
are 100% sure that our encoding algorithms and encoded scanners are stable. If 
everyone agrees with that, I will finish the patch by (1) adding a unit test 
for switching data block encoding column family settings; (2) including 
encoding type in the cache key; and (3) simplifying the HFileDataBlockEncoder 
interface, since we assume that the "in-memory format" (used by scanners) is 
always the same as the in-cache format and don't need methods such as 
afterReadFromDiskAndPuttingInCache anymore.
                
> Data Block Encoding of KeyValues  (aka delta encoding / prefix compression)
> ---------------------------------------------------------------------------
>
>                 Key: HBASE-4218
>                 URL: https://issues.apache.org/jira/browse/HBASE-4218
>             Project: HBase
>          Issue Type: Improvement
>          Components: io
>    Affects Versions: 0.94.0
>            Reporter: Jacek Migdal
>            Assignee: Mikhail Bautin
>              Labels: compression
>             Fix For: 0.94.0
>
>         Attachments: 0001-Delta-encoding-fixed-encoded-scanners.patch, 
> 0001-Delta-encoding.patch, 4218-v16.txt, 4218.txt, D447.1.patch, 
> D447.10.patch, D447.11.patch, D447.12.patch, D447.13.patch, D447.14.patch, 
> D447.15.patch, D447.16.patch, D447.17.patch, D447.2.patch, D447.3.patch, 
> D447.4.patch, D447.5.patch, D447.6.patch, D447.7.patch, D447.8.patch, 
> D447.9.patch, Data-block-encoding-2011-12-23.patch, 
> Delta-encoding.patch-2011-12-22_11_52_07.patch, 
> Delta_encoding_with_memstore_TS.patch, open-source.diff
>
>
> A compression for keys. Keys are sorted in HFile and they are usually very 
> similar. Because of that, it is possible to design better compression than 
> general purpose algorithms,
> It is an additional step designed to be used in memory. It aims to save 
> memory in cache as well as speeding seeks within HFileBlocks. It should 
> improve performance a lot, if key lengths are larger than value lengths. For 
> example, it makes a lot of sense to use it when value is a counter.
> Initial tests on real data (key length = ~ 90 bytes , value length = 8 bytes) 
> shows that I could achieve decent level of compression:
>  key compression ratio: 92%
>  total compression ratio: 85%
>  LZO on the same data: 85%
>  LZO after delta encoding: 91%
> While having much better performance (20-80% faster decompression ratio than 
> LZO). Moreover, it should allow far more efficient seeking which should 
> improve performance a bit.
> It seems that a simple compression algorithms are good enough. Most of the 
> savings are due to prefix compression, int128 encoding, timestamp diffs and 
> bitfields to avoid duplication. That way, comparisons of compressed data can 
> be much faster than a byte comparator (thanks to prefix compression and 
> bitfields).
> In order to implement it in HBase two important changes in design will be 
> needed:
> -solidify interface to HFileBlock / HFileReader Scanner to provide seeking 
> and iterating; access to uncompressed buffer in HFileBlock will have bad 
> performance
> -extend comparators to support comparison assuming that N first bytes are 
> equal (or some fields are equal)
> Link to a discussion about something similar:
> http://search-hadoop.com/m/5aqGXJEnaD1/hbase+windows&subj=Re+prefix+compression

--
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

        

Reply via email to