Difference between revisions of "User:StefanoZacchiroli/Content deduplication"

From Software Heritage Wiki
Jump to navigation Jump to search
Line 52: Line 52:
 
* average chunk size (effective): 1.72 KB
 
* average chunk size (effective): 1.72 KB
 
* dedup chunk size (uncompressed): '''6.49 GB (11.60%)'''
 
* dedup chunk size (uncompressed): '''6.49 GB (11.60%)'''
 +
 +
=== test 4 ===
 +
 +
TODO
 +
 +
contents: 4111582
 +
chunks: 164052312
 +
average chunk size: 1597.60
 +
total content size: 308154402601
 +
total chunk size: 262090652269 (85.05%)
 +
 +
real 22m20,334s
 +
user 15m56,586s
 +
sys 2m49,606s
  
 
== References ==
 
== References ==

Revision as of 21:43, 16 January 2018

Some experiments on deduplicating contents at sub-file granularity.

Datasets

Linux kernel, Git repo

  • origin: git.kernel.org, on 2018-01-06
  • 1.653.941 content blobs, for a total of 19 GB (compressed)
  • original size (uncompressed): 55.89 GB

Rabin fingerprint chunking

test 1

Dataset: linux.git

Rabin fingerprint parameters:

  • prime: 3
  • window_size: 48 KB
  • chunk size (min/avg/max): 2 KB / 8 KB / 64 KB

Results:

  • average chunk size (effective): 9.37 KB
  • dedup chunk size (uncompressed): 19.87 GB (35.55%)

test 2

Dataset: linux.git

Rabin fingerprint parameters:

  • prime: 3
  • window_size: 48 KB
  • chunk size (min/avg/max): 512 B / 2 KB / 8 KB

Results:

  • average chunk size (effective): 2.86 KB
  • dedup chunk size (uncompressed): 9.09 GB (16.26%)

test 3

Dataset: linux.git

Rabin fingerprint parameters:

  • prime: 3
  • window_size: 48 KB
  • chunk size (min/avg/max): 512 B / 1 KB / 8 KB

Results:

  • average chunk size (effective): 1.72 KB
  • dedup chunk size (uncompressed): 6.49 GB (11.60%)

test 4

TODO

contents: 4111582 chunks: 164052312 average chunk size: 1597.60 total content size: 308154402601 total chunk size: 262090652269 (85.05%)

real 22m20,334s user 15m56,586s sys 2m49,606s

References