sadikovi

#!/bin/bash

# Usage: ./gen.sh collected-stacks.txt

TMPSTACKS=/tmp/flamegraph-stacks-collapsed.txt
TMPPALETTE=/tmp/flamegraph-palette.map

./stackcollapse-jstack.pl $1 > $TMPSTACKS

# 1st run - hot: default

sadikovi

Java HotSpot(TM) 64-Bit Server VM 1.7.0_80-b15 on Mac OS X 10.12.4
Intel(R) Core(TM) i5-4258U CPU @ 2.40GHz
SQL project:                             Best/Avg Time(ms)    Rate(M/s)   Per Row(ns)   Relative
------------------------------------------------------------------------------------------------
Riff (all fields)                             1426 / 1459          0.7        1425.7       1.0X
Riff (1 field)                                 876 /  983          1.1         876.3       1.6X
Riff (3 fields)                                974 / 1021          1.0         974.1       1.5X
Riff (6 fields)                               1354 / 1477          0.7        1353.6       1.1X

sadikovi

import org.apache.spark.sql.Row
import org.apache.spark.sql.types._
import com.github.sadikovi.spark.riff._
def row(i: Int): Row = {
  Row(i, i, i.toLong, i.toLong, s"abc$i abc$i abc$i", s"abc$i abc$i abc$i", s"abc$i abc$i abc$i", s"abc$i abc$i abc$i")
}
val schema = StructType(
  StructField("col1", IntegerType) ::
  StructField("col2", IntegerType) ::
  StructField("col3", LongType) ::

sadikovi

#!/usr/bin/python

import json
import os
import time
import urllib2

# env vars that script requires
GITHUB_TOKEN="GITHUB_TOKEN"
GITHUB_USER="GITHUB_USER"

sadikovi

import java.net.URI
import org.apache.hadoop.conf.Configuration
import org.apache.hadoop.fs._
import org.apache.hadoop.hdfs.client._
import org.apache.hadoop.hdfs.inotify._

val url = new URI("hdfs://localhost:8020")
val conf = new Configuration(false)
val dfs = new HdfsAdmin(url, conf)
val stream = dfs.getInotifyEventStream()

sadikovi

public class Tree<T extends Comparable<T>> {
  static class TreeNode<T> {
    T value;
    int height;
    TreeNode<T> left;
    TreeNode<T> right;

    public TreeNode(T value) {
      this.value = value;
      this.height = 0;

sadikovi

Parquet tuning

https://www.slideshare.net/RyanBlue3/parquet-performance-tuning-the-missing-guide

sadikovi

package org.apache.spark.sql

import scala.language.implicitConversions
import scala.util.control.NonFatal

import org.apache.commons.io.IOUtils
import org.apache.hadoop.conf.Configuration
import org.apache.hadoop.fs.{FileStatus, FileSystem, Path}

import org.apache.spark.internal.Logging

sadikovi

import org.apache.spark.rdd.batch.implicits._

val rdd = sc.parallelize(0 until 1000, 100)
val res = rdd.batch(numPartitionsPerBatch = 20)
res.collect

val rdd = sc.parallelize(Seq("a", "b", "c", "d", "e", "f", "g", "h"), 10)
val res = rdd.batch(numPartitionsPerBatch = 4)
res.collect

sadikovi

##Google Interview Questions: Product Marketing Manager

• Why do you want to join Google? -- Because I want to create tools for others to learn, for free. I didn't have a lot of money when growing up so I didn't get access to the same books, computers and resources that others had which caused money, I want to help ensure that others can learn on the same playing field regardless of their families wealth status or location.
• What do you know about Google’s product and technology? -- A lot actually, I am a beta tester for numerous products, I use most of the Google tools such as: Search, Gmaill, Drive, Reader, Calendar, G+, YouTube, Web Master Tools, Keyword tools, Analytics etc.
• If you are Product Manager for Google’s Adwords, how do you plan to market this?
• What would you say during an AdWords or AdSense product seminar?
• Who are Google’s competitors, and how does Google compete with them? -- Google competes on numerous fields: --- Search: Baidu, Bing, Duck Duck Go