meyarivan

#!/usr/bin/env python2

from __future__ import print_function

import os, sys
from kafka import KafkaConsumer

import avro.schema
from avro.datafile import DataFileReader, DataFileWriter
from avro.io import DatumReader, DatumWriter

meyarivan

# stdlib
import subprocess
import os
import sys
import re
import traceback

# project
from checks import AgentCheck
from utils.platform import Platform

meyarivan

#!/bin/bash

for DB in `hive -e "SHOW DATABASES;"`; do
    for tbl in `hive -e "USE ${DB}; SHOW TABLES"`; do
	hive -e "DESC FORMATTED ${DB}.${tbl};" > desc.${DB}.${tbl}
    done
done

meyarivan

Tunables:
  - mapreduce.input.fileinputformat.list-status.num-threads (hive-site.xml)
  - fs.s3a.block.size
  
JIRAs:
  - https://issues.apache.org/jira/browse/HADOOP-12810
  - https://issues.apache.org/jira/browse/HADOOP-9565
  - https://issues.apache.org/jira/browse/HADOOP-12878