Skip to main content

Table 6 The runtime of sampling (128 MB) on WordCount, Sort and Inverted index

From: Estimating runtime of a job in Hadoop MapReduce

Information of sampling

Average map

time(s)

Average shuffle time(s)

Average merge time(s)

Average reduce time(s)

Average total time(s)

selm

selr

WordCount

18

16.4

7.3

1.66

43.36

8.61

1

TeraSort

9.7

10.09

3.7

4.8

28.29

7.71

1.6

Inverted index

32.3

30.9

10.21

17.07

90.48

15.59

3.68