1
2ethfindgood(8)               EFSFFCLIRG (Man Page)              ethfindgood(8)
3
4
5

NAME

7       ethfindgood
8
9
10
11       Checks  for hosts that are able to be pinged, accessed via SSH, and ac‐
12       tive on the Intel(R) Ethernet Fabric. Produces a  list  of  good  hosts
13       meeting  all criteria. Typically used to identify good hosts to undergo
14       further testing and benchmarking during  initial  cluster  staging  and
15       startup.
16
17       The  resulting  good  file lists each good host exactly once and can be
18       used as input to create mpi_hosts files for running  mpi_apps  and  the
19       NIC-SW  cable test. The files alive, running, active, good, and bad are
20       created in the selected directory listing hosts passing each criteria.
21
22       This command  automatically  generates  the  file  FF_RESULT_DIR/punch‐
23       list.csv.  This file provides a concise summary of the bad hosts found.
24       This can be imported into Excel directly  as  a  *.csv  file.  Alterna‐
25       tively,  it  can be cut/pasted into Excel, and the Data/Text to Columns
26       toolbar can be used to separate the information into  multiple  columns
27       at the semicolons.
28
29       A sample generated output is:
30
31       # ethfindgood
32
33       3 hosts will be checked
34
35       2 hosts are pingable (alive)
36
37       2 hosts are ssh'able (running)
38
39       2 total hosts have RDMA active on one or more fabrics (active)
40
41       1 hosts are alive, running, active (good)
42
43       2 hosts are bad (bad)
44
45       Bad hosts have been added to /root/punchlist.csv
46
47       # cat /root/punchlist.csv
48
49       2015/10/09 14:36:48;phs1fnivd13u07n4;Doesn't ping
50
51       2015/10/09 14:36:48;phs1fnivd13u07n4;Can't ssh
52
53       2015/10/09 14:36:48;phs1fnivd13u07n3;No active RDMA port
54
55
56
57       For  a  given run, a line is generated for each failing host. Hosts are
58       reported exactly once for a given run. Therefore, a host that does  not
59       ping  is  NOT listed as can't ssh nor No active RDMA port. There may be
60       cases where ports could be active for hosts that do not ping.  However,
61       the lack of ping often implies there are other fundamental issues, such
62       as PXE boot or inability to access DNS or DHCP to get proper host  name
63       and  IP  address.  Therefore, reporting hosts that do not ping is typi‐
64       cally of limited value.
65

Syntax

67       ethfindgood [-R|-A] [-d  dir] [-f  hostfile] [-h  'hosts']  [-T   time‐
68       limit]
69

Options

71       --help
72
73                 Produces full help text.
74
75       -R
76
77                 Skips  the  running  test (SSH). Recommended if password-less
78                 SSH is not set up.
79
80       -A
81
82                 Skips the active test. Recommended if Intel(R) Ethernet  Fab‐
83                 ric Suite software or fabric is not up.
84
85       -d dir
86
87                 Specifies  the  directory  in  which to create alive, active,
88                 running, good, and bad files. Default is  /etc/eth-tools  di‐
89                 rectory.
90
91       -f hostfile
92
93                 Specifies   the  file  with  hosts  in  cluster.  Default  is
94                 /etc/eth-tools/hosts directory.
95
96       -h hosts
97
98                 Specifies the list of hosts to ping.
99
100       -T timelimit
101
102                 Specifies the time limit in seconds for host  to  respond  to
103                 SSH. Default is 20 seconds.
104
105

Environment Variables

107       The following environment variables are also used by this command:
108
109       HOSTS
110
111                 List of hosts, used if -h option not supplied.
112
113
114       HOSTS_FILE
115
116                 File containing list of hosts, used in absence of -f and -h.
117
118
119       FF_MAX_PARALLEL
120
121                 Maximum concurrent operations.
122
123

Examples

125       ethfindgood
126
127       ethfindgood -f allhosts
128
129       ethfindgood -h 'arwen elrond'
130
131       HOSTS='arwen elrond' ethfindgood
132
133       HOSTS_FILE=allhosts ethfindgood
134
135
136
137Copyright(C) 2020-2021         Intel Corporation                ethfindgood(8)