1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
|
smoke-test:
description: Run an Apache Bigtop smoke test.
mrbench:
description: Mapreduce benchmark for small jobs
params:
basedir:
description: DFS working directory
type: string
default: "/benchmarks/MRBench"
numruns:
description: Number of times to run the job
type: integer
default: 1
maps:
description: number of maps for each run
type: integer
default: 2
reduces:
description: number of reduces for each run
type: integer
default: 1
inputlines:
description: number of input lines to generate
type: integer
default: 1
inputtype:
description: 'Type of input to generate, one of [ascending, descending, random]'
type: string
default: "ascending"
enum: [ascending,descending,random]
nnbench:
description: Load test the NameNode hardware and configuration
params:
maps:
description: number of map jobs
type: integer
default: 12
reduces:
description: number of reduces
type: integer
default: 6
blocksize:
description: block size
type: integer
default: 1
bytes:
description: bytes to write
type: integer
default: 0
numfiles:
description: number of files
type: integer
default: 0
repfactor:
description: replication factor per file
type: integer
default: 3
basedir:
description: DFS working directory
type: string
default: "/benchmarks/NNBench"
testdfsio:
description: DFS IO Testing
params:
mode:
description: read or write IO test
type: string
default: "write"
enum: [read,write]
numfiles:
description: number of files
type: integer
default: 10
filesize:
description: filesize in MB
type: integer
default: 1000
resfile:
description: Results file name
type: string
default: "/tmp/TestDFSIO_results.log"
buffersize:
description: Buffer size in bytes
type: integer
default: 1000000
teragen:
description: Generate data with teragen
params:
size:
description: The number of 100 byte rows, default to 1GB of data to generate
type: integer
default: 10000000
indir:
description: HDFS directory where generated data is stored
type: string
default: 'tera_demo_in'
terasort:
description: Runs teragen to generate sample data, and then runs terasort to sort that data
params:
indir:
description: HDFS directory where generated data is stored
type: string
default: 'tera_demo_in'
outdir:
description: HDFS directory where sorted data is stored
type: string
default: 'tera_demo_out'
size:
description: The number of 100 byte rows, default to 1GB of data to generate and sort
type: integer
default: 10000000
maps:
description: The default number of map tasks per job. 1-20
type: integer
default: 1
reduces:
description: The default number of reduce tasks per job. Typically set to 99% of the cluster's reduce capacity, so that if a node fails the reduces can still be executed in a single wave. Try 1-20
type: integer
default: 1
numtasks:
description: How many tasks to run per jvm. If set to -1, there is no limit.
type: integer
default: 1
compression:
description: >
Enable or Disable mapred output (intermediate) compression.
LocalDefault will run with your current local hadoop configuration.
Default means default hadoop deflate codec.
One of: Gzip, BZip2, Snappy, Lzo, Default, Disable, LocalDefault
These are all case sensitive.
type: string
default: "LocalDefault"
enum: [Gzip, BZip2, Snappy, Lzo, Default, Disable, LocalDefault]
|
