Skip to content

Instantly share code, notes, and snippets.

@sorentwo
Created March 7, 2014 03:51
Show Gist options
  • Select an option

  • Save sorentwo/9404956 to your computer and use it in GitHub Desktop.

Select an option

Save sorentwo/9404956 to your computer and use it in GitHub Desktop.
Comparison of different perforated cache backends.
The first pass writes and the second pass reads.
10_000 Objects:
user system total real
memory-1 1.240000 0.010000 1.250000 ( 1.252629)
memory-2 0.110000 0.000000 0.110000 ( 0.114169)
redis-1 1.930000 0.230000 2.160000 ( 2.300067)
redis-2 0.210000 0.010000 0.220000 ( 0.222959)
dalli-1 1.470000 0.090000 1.560000 ( 1.574031)
dalli-2 0.200000 0.010000 0.210000 ( 0.204826)
20_000 Objects
user system total real
memory-1 2.440000 0.020000 2.460000 ( 2.457315)
memory-2 0.230000 0.000000 0.230000 ( 0.228092)
redis-1 3.870000 0.450000 4.320000 ( 4.613556)
redis-2 0.400000 0.030000 0.430000 ( 0.435164)
dalli-1 2.900000 0.190000 3.090000 ( 3.117383)
dalli-2 0.420000 0.010000 0.430000 ( 0.970062)
# Redis read times: 0.223, 0.435 (1.95x)
# Dalli read times: 0.205, 0.970 (4.73x)
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment