204 lines
6.6 KiB
Python
Executable file
204 lines
6.6 KiB
Python
Executable file
#!/usr/bin/env python3
|
|
# coding: utf-8
|
|
|
|
import os
|
|
import json
|
|
import pandas as pd
|
|
import findspark
|
|
findspark.init()
|
|
import pyspark
|
|
import pyspark.sql
|
|
import sys
|
|
import gzip
|
|
from pyspark import AccumulatorParam
|
|
from pyspark.sql.functions import lit
|
|
from pyspark.sql import Window
|
|
from pyspark.sql.types import *
|
|
from decimal import *
|
|
|
|
CHECKDIR = "/home/claudio/google_2019/thesis_queries/figure_8/"
|
|
|
|
if len(sys.argv) is not 4:
|
|
print(sys.argv[0] + " {cluster} {tmpdir} {maxram}")
|
|
sys.exit()
|
|
|
|
cluster=sys.argv[1]
|
|
|
|
if os.path.exists(CHECKDIR + cluster + "_figure8cd.json"):
|
|
print("already computed")
|
|
sys.exit()
|
|
|
|
if os.path.exists(CHECKDIR + cluster + "_figure8cd_working"):
|
|
print("already in execution")
|
|
sys.exit()
|
|
|
|
os.system("touch " + CHECKDIR + cluster + "_figure8cd_working")
|
|
|
|
|
|
spark = pyspark.sql.SparkSession.builder \
|
|
.appName("task_slowdown") \
|
|
.config("spark.driver.maxResultSize", "128g") \
|
|
.config("spark.local.dir", sys.argv[2]) \
|
|
.config("spark.driver.memory", sys.argv[3]) \
|
|
.getOrCreate()
|
|
sc = spark.sparkContext
|
|
|
|
def tabid(x):
|
|
return Decimal(x.collection_id) + Decimal(x.instance_index) / Decimal(2**64)
|
|
|
|
#
|
|
# READING INSTANCE EVENTS DATA
|
|
#
|
|
dfepath = "/home/claudio/google_2019/instance_events/" + cluster + "/" + cluster + "_instance_events*.json.gz"
|
|
#dfepath = "/home/claudio/google_2019/instance_events/" + cluster + "/" + cluster + "_test.json"
|
|
df = spark.read.json(dfepath)
|
|
|
|
# READING MACHINE EVENTS DATA, sort them and save them as broadcast variable
|
|
print("Starting to read machine events...")
|
|
dfm = pd.read_csv("~/google_2019/machine_events/" + cluster + "_machine_events.csv", converters={
|
|
'time': lambda x: -1 if x == '' else int(x),
|
|
'machine_id': lambda x: str(x),
|
|
'capacity.cpus': lambda x: -1 if x == '' else Decimal(x),
|
|
'capacity.memory': lambda x: -1 if x == '' else Decimal(x)})
|
|
print("Dropping remove events...")
|
|
dfm = dfm[(dfm.type!=2)&(dfm.time!=-1)&(dfm["capacity.cpus"]!=-1)&(dfm["capacity.memory"]!=-1)]
|
|
print("Dropping missing data events...")
|
|
dfm = dfm[dfm.missing_data_reason.isnull()]
|
|
print("Projecting on useful columns...")
|
|
dfm = dfm[["time", "machine_id", "capacity.cpus", "capacity.memory"]]
|
|
print("Sorting by time...")
|
|
dfm = dfm.sort_values(by=["machine_id", "time"])
|
|
print("Converting to broadcast variable...")
|
|
dfm = sc.broadcast([tuple(r) for r in dfm.to_numpy()])
|
|
print("Done with machine events.")
|
|
|
|
df = df.rdd \
|
|
.filter(lambda x: x.time is not None and x.type is not None and x.machine_id is not None and
|
|
x.instance_index is not None and x.collection_id is not None and x.resource_request is not None and
|
|
x.resource_request.cpus is not None and x.resource_request.memory is not None) \
|
|
.map(lambda x: [tabid(x), int(x.time), int(x.type),
|
|
Decimal(x.resource_request.cpus), Decimal(x.resource_request.memory), x.machine_id]) \
|
|
.toDF(["id", "time", "type", "rcpu", "rram", "mid"])
|
|
|
|
|
|
def get_machine_time_resources(machine_id, time):
|
|
def aux(i, j):
|
|
if i == j:
|
|
return i if dfm.value[i][1] == machine_id else None
|
|
elif i + 1 == j:
|
|
if dfm.value[i][1] == machine_id:
|
|
return i
|
|
elif dfm.value[j][1] == machine_id:
|
|
return j
|
|
else:
|
|
return None
|
|
|
|
mid = (i + j) // 2
|
|
|
|
if dfm.value[mid][1] > machine_id:
|
|
return aux(i, mid - 1)
|
|
elif dfm.value[mid][1] < machine_id:
|
|
return aux(mid + 1, j)
|
|
elif dfm.value[mid][0] > time:
|
|
return aux(i, mid)
|
|
elif dfm.value[mid][0] < time:
|
|
return aux(mid, j)
|
|
else:
|
|
return mid
|
|
|
|
return aux(0, len(dfm.value)-1)
|
|
|
|
def increment_reserv_bucket(bucket, taskid, value):
|
|
if value < 0:
|
|
idx = 0
|
|
else:
|
|
idx = 40 if value >= 1 else (int(value * 40) + 1)
|
|
|
|
if taskid not in bucket:
|
|
bucket[taskid] = [0] * 41
|
|
bucket[taskid][idx] += 1
|
|
|
|
def bucket_sum_per_termination(bucket, last_term_by_id):
|
|
result = {-1: None, 4: None, 5: None, 6: None, 7: None, 8: None}
|
|
for tid, vs in bucket.items():
|
|
term = last_term_by_id[tid]
|
|
if result[term] is None:
|
|
result[term] = vs
|
|
else:
|
|
result[term] = [sum(x) for x in zip(result[term], vs)]
|
|
return result
|
|
|
|
def for_each_joined(x):
|
|
machine_id = x[0]
|
|
ts = x[1]
|
|
|
|
ts = sorted(ts, key=lambda x: x.time)
|
|
last_req_by_id = {} # map taskid -> last known req [cpu, ram] (data removed when task terminates)
|
|
|
|
cpu_reservs_by_id = {}
|
|
ram_reservs_by_id = {}
|
|
|
|
last_term_by_id = {} # map taskid -> last termination
|
|
start = get_machine_time_resources(machine_id, 0)
|
|
end = get_machine_time_resources(machine_id, 6_000_000_000_000)
|
|
machine_logs = None if start is None or end is None else dfm.value[start:(end+1)]
|
|
|
|
for i, t in enumerate(ts):
|
|
if machine_logs is not None and len(machine_logs) > 1 and machine_logs[1][0] >= t.time:
|
|
machine_logs.pop(0)
|
|
if t.id not in last_term_by_id:
|
|
last_term_by_id[t.id] = -1
|
|
if t.rcpu is not None and t.rram is not None:
|
|
last_req_by_id[t.id] = (t.rcpu, t.rram)
|
|
# 8b
|
|
tot_req = [sum(x) for x in zip(*last_req_by_id.values())]
|
|
if machine_logs is not None:
|
|
reserv_cpu = tot_req[0] / machine_logs[0][2]
|
|
reserv_ram = tot_req[1] / machine_logs[0][3]
|
|
else:
|
|
reserv_cpu = -1
|
|
reserv_ram = -1
|
|
increment_reserv_bucket(cpu_reservs_by_id, t.id, reserv_cpu)
|
|
increment_reserv_bucket(ram_reservs_by_id, t.id, reserv_ram)
|
|
if t.type >= 4 and t.type <= 8:
|
|
last_term_by_id[t.id] = t.type
|
|
|
|
resobj = {'rscpu': cpu_reservs_by_id, 'rsram': ram_reservs_by_id}
|
|
|
|
for k, v in resobj.items():
|
|
resobj[k] = bucket_sum_per_termination(v, last_term_by_id)
|
|
|
|
return resobj
|
|
|
|
def fold_resobjs(ro1, ro2):
|
|
if ro1 is None:
|
|
return ro2
|
|
elif ro2 is None:
|
|
return ro1
|
|
else:
|
|
for k in ro1.keys():
|
|
for kk in ro1[k].keys():
|
|
if ro1[k][kk] is None:
|
|
ro1[k][kk] = ro2[k][kk]
|
|
elif ro2[k][kk] is None:
|
|
continue
|
|
else:
|
|
ro1[k][kk] = [sum(x) for x in zip(ro1[k][kk], ro2[k][kk])]
|
|
return ro1
|
|
|
|
import random
|
|
|
|
result = df.rdd \
|
|
.groupBy(lambda x: x.mid) \
|
|
.partitionBy(1000, lambda x: random.randint(0, 1000-1)) \
|
|
.map(for_each_joined) \
|
|
.fold(None, fold_resobjs)
|
|
|
|
d = os.path.dirname(os.path.realpath(__file__))
|
|
|
|
with open(d + "/" + cluster + "_figure8cd.json", "w") as f:
|
|
json.dump(result, f)
|
|
|
|
os.system("rm " + CHECKDIR + cluster + "_figure8cd_working")
|
|
|
|
# vim: set ts=4 sw=4 et tw=120:
|