prelim_kill_hard

prelim_kill_hard.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## SUBPROCESS_KILL_HARD"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "from montecarlino import grouped_permutation_test"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {
    "collapsed": false,
    "scrolled": true
   },
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/home/hadoop/anaconda2/lib/python2.7/site-packages/matplotlib/font_manager.py:273: UserWarning: Matplotlib is building the font cache using fc-list. This may take a moment.\n",
      "  warnings.warn('Matplotlib is building the font cache using fc-list. This may take a moment.')\n",
      "WARNING: "
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Unable to parse whitelist (/home/hadoop/anaconda2/lib/python2.7/site-packages/moztelemetry/histogram-whitelists.json). Assuming all histograms are acceptable.\n",
      "Populating the interactive namespace from numpy and matplotlib\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "pylab import has clobbered these variables: ['Annotation', 'Figure']\n",
      "`%matplotlib` prevents importing * from pylab and numpy\n"
     ]
    }
   ],
   "source": [
    "import ujson as json\n",
    "import matplotlib.pyplot as plt\n",
    "import pandas as pd\n",
    "import numpy as np\n",
    "import plotly.plotly as py\n",
    "from plotly.graph_objs import *\n",
    "\n",
    "from moztelemetry import get_pings, get_pings_properties, get_one_ping_per_client, get_clients_history, get_records\n",
    "\n",
    "%pylab inline"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "640"
      ]
     },
     "execution_count": 3,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "sc.defaultParallelism"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "metadata": {
    "collapsed": false
   },
   "outputs": [],
   "source": [
    "pings = get_pings(sc, app=\"Firefox\", channel=\"beta\", version=\"47.0\", build_id=(\"20160505000000\", \"20160511999999\"), fraction=1)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "... and extract only the attributes we need from the Telemetry submissions:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "metadata": {
    "collapsed": false
   },
   "outputs": [],
   "source": [
    "subset = get_pings_properties(pings, [\"clientId\",\n",
    "                                      \"environment/settings/e10sCohort\",\n",
    "                                      \"payload/keyedHistograms/SUBPROCESS_CRASHES_WITH_DUMP\",\n",
    "                                      \"payload/keyedHistograms/SUBPROCESS_KILL_HARD\"], with_processes=True)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "subset = subset.filter(lambda p: p[\"environment/settings/e10sCohort\"] in [\"test\", \"control\"])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "subset = subset.filter(lambda p: p[\"payload/keyedHistograms/SUBPROCESS_CRASHES_WITH_DUMP\"] is not None)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "metadata": {
    "collapsed": false
   },
   "outputs": [],
   "source": [
    "subset = get_one_ping_per_client(subset)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "metadata": {
    "collapsed": false
   },
   "outputs": [],
   "source": [
    "cached = subset.cache()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 20,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "87430"
      ]
     },
     "execution_count": 20,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "cached.count()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 21,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "defaultdict(int, {u'control': 16683, u'test': 70747})"
      ]
     },
     "execution_count": 21,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "cached.map(lambda p: (p[\"environment/settings/e10sCohort\"], 1)).countByKey()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 22,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(65179L, 5568L)"
      ]
     },
     "execution_count": 22,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "def get_content_crashes(p):\n",
    "    crashes = p[\"payload/keyedHistograms/SUBPROCESS_CRASHES_WITH_DUMP\"]\n",
    "    if crashes is not None and crashes.get(\"content\", None) is not None:\n",
    "        return crashes[\"content\"]\n",
    "    return 0\n",
    "\n",
    "e10s_content_crashes = cached.filter(lambda p: p[\"environment/settings/e10sCohort\"] == \"test\").map(get_content_crashes).reduce(lambda a, b: a + b)\n",
    "none10s_content_crashes = cached.filter(lambda p: p[\"environment/settings/e10sCohort\"] == \"control\").map(get_content_crashes).reduce(lambda a, b: a + b)\n",
    "e10s_content_crashes, none10s_content_crashes"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 23,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(55751L, 5295L)"
      ]
     },
     "execution_count": 23,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "def get_shutdown_kills(p):\n",
    "    kill_hards = p[\"payload/keyedHistograms/SUBPROCESS_KILL_HARD\"]\n",
    "    if kill_hards is not None and kill_hards.get(\"ShutDownKill\", None) is not None:\n",
    "        return kill_hards[\"ShutDownKill\"]\n",
    "    return 0\n",
    "\n",
    "e10s_shutdown_kills = cached.filter(lambda p: p[\"environment/settings/e10sCohort\"] == \"test\").map(get_shutdown_kills).reduce(lambda a, b: a + b)\n",
    "none10s_shutdown_kills = cached.filter(lambda p: p[\"environment/settings/e10sCohort\"] == \"control\").map(get_shutdown_kills).reduce(lambda a, b: a + b)\n",
    "e10s_shutdown_kills, none10s_shutdown_kills"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 2",
   "language": "python",
   "name": "python2"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 2
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython2",
   "version": "2.7.11"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 0
}

prelim_kill_hard.py

# coding: utf-8

# ## SUBPROCESS_KILL_HARD

# In[1]:

from montecarlino import grouped_permutation_test


# In[2]:

import ujson as json
import matplotlib.pyplot as plt
import pandas as pd
import numpy as np
import plotly.plotly as py
from plotly.graph_objs import *

from moztelemetry import get_pings, get_pings_properties, get_one_ping_per_client, get_clients_history, get_records

get_ipython().magic(u'pylab inline')


# In[3]:

sc.defaultParallelism


# In[14]:

pings = get_pings(sc, app="Firefox", channel="beta", version="47.0", build_id=("20160505000000", "20160511999999"), fraction=1)


# ... and extract only the attributes we need from the Telemetry submissions:

# In[15]:

subset = get_pings_properties(pings, ["clientId",
                                      "environment/settings/e10sCohort",
                                      "payload/keyedHistograms/SUBPROCESS_CRASHES_WITH_DUMP",
                                      "payload/keyedHistograms/SUBPROCESS_KILL_HARD"], with_processes=True)


# In[16]:

subset = subset.filter(lambda p: p["environment/settings/e10sCohort"] in ["test", "control"])


# In[17]:

subset = subset.filter(lambda p: p["payload/keyedHistograms/SUBPROCESS_CRASHES_WITH_DUMP"] is not None)


# In[18]:

subset = get_one_ping_per_client(subset)


# In[19]:

cached = subset.cache()


# In[20]:

cached.count()


# In[21]:

cached.map(lambda p: (p["environment/settings/e10sCohort"], 1)).countByKey()


# In[22]:

def get_content_crashes(p):
    crashes = p["payload/keyedHistograms/SUBPROCESS_CRASHES_WITH_DUMP"]
    if crashes is not None and crashes.get("content", None) is not None:
        return crashes["content"]
    return 0

e10s_content_crashes = cached.filter(lambda p: p["environment/settings/e10sCohort"] == "test").map(get_content_crashes).reduce(lambda a, b: a + b)
none10s_content_crashes = cached.filter(lambda p: p["environment/settings/e10sCohort"] == "control").map(get_content_crashes).reduce(lambda a, b: a + b)
e10s_content_crashes, none10s_content_crashes


# In[23]:

def get_shutdown_kills(p):
    kill_hards = p["payload/keyedHistograms/SUBPROCESS_KILL_HARD"]
    if kill_hards is not None and kill_hards.get("ShutDownKill", None) is not None:
        return kill_hards["ShutDownKill"]
    return 0

e10s_shutdown_kills = cached.filter(lambda p: p["environment/settings/e10sCohort"] == "test").map(get_shutdown_kills).reduce(lambda a, b: a + b)
none10s_shutdown_kills = cached.filter(lambda p: p["environment/settings/e10sCohort"] == "control").map(get_shutdown_kills).reduce(lambda a, b: a + b)
e10s_shutdown_kills, none10s_shutdown_kills