You can use strace on a specific pid to figure out what a specific process is doing, e.g.:
strace -fp <pid>
You might see something like:
select(9, [3 5 8], [], [], {0, 999999}) = 0 (Timeout)
#!/bin/bash | |
# | |
# MongoDB Backup Script | |
# VER. 0.1 | |
# Note, this is a lobotomized port of AutoMySQLBackup | |
# (http://sourceforge.net/projects/automysqlbackup/) for use with | |
# MongoDB. | |
# | |
# This program is free software; you can redistribute it and/or modify | |
# it under the terms of the GNU General Public License as published by |
package forma; | |
import forma.WholeFileInputFormat; | |
import cascading.scheme.Scheme; | |
import cascading.tap.Tap; | |
import cascading.tuple.Fields; | |
import cascading.tuple.Tuple; | |
import cascading.tuple.TupleEntry; | |
import java.io.IOException; | |
import org.apache.hadoop.mapred.JobConf; |
#Colo Server costs | |
set ServerTypes; | |
set InstanceTypes; | |
param CoreDemand; #How many cores do we need for a workload | |
param OurMoney; #The maximum upper-bound of what we're willing to spend | |
param ColoCostPerU; #How much are we paying per U of colocation | |
param Months; # How many months do we know we need this hardware |
# Requirements | |
#sudo apt-get install libcurl4-gnutls-dev # for RCurl on linux | |
#install.packages('RCurl') | |
#install.packages('RJSONIO') | |
library('RCurl') | |
library('RJSONIO') | |
query <- function(querystring) { | |
h = basicTextGatherer() |
pv_by_industry = GROUP profile_view by viewee_industry_id | |
pv_avg_by_industry = FOREACH pv_by_industry | |
GENERATE group as viewee_industry_id, AVG(profie_view) AS average_pv; |
# GNU Screen - main configuration file | |
# All other .screenrc files will source this file to inherit settings. | |
# Author: Christian Wills - [email protected] | |
# Allow bold colors - necessary for some reason | |
attrcolor b ".I" | |
# Tell screen how to set colors. AB = background, AF=foreground | |
termcapinfo xterm 'Co#256:AB=\E[48;5;%dm:AF=\E[38;5;%dm' |
package com.jteso.hadoop.contrib.inputformat; | |
import java.io.IOException; | |
import org.apache.hadoop.fs.Path; | |
import org.apache.hadoop.io.BytesWritable; | |
import org.apache.hadoop.io.Text; | |
import org.apache.hadoop.mapreduce.InputSplit; | |
import org.apache.hadoop.mapreduce.RecordReader; | |
import org.apache.hadoop.mapreduce.TaskAttemptContext; |
-- This is a Hive program. Hive is an SQL-like language that compiles | |
-- into Hadoop Map/Reduce jobs. It's very popular among analysts at | |
-- Facebook, because it allows them to query enormous Hadoop data | |
-- stores using a language much like SQL. | |
-- Our logs are stored on the Hadoop Distributed File System, in the | |
-- directory /logs/randomhacks.net/access. They're ordinary Apache | |
-- logs in *.gz format. | |
-- | |
-- We want to pretend that these gzipped log files are a database table, |
================================================================= | |
SETTING UP SSHD AS A SERVICE FOR RUNNING HADOOP DAEMONS ON WINDOWS 7 | |
================================================================= | |
Steps: | |
1. Download 'setup.exe' from Cygwin website | |
2. Right-click on 'setup.exe' | |
3. Leave settings as they are, click through until you come to the plugin selection window | |
3.1 - Make sure that the installation directory is 'C:\cygwin' |