def test_parse_cust(self):
# run as user 0xcustomer to get access (with .json config and ssh key file specified)
importFolderPath = '/mnt/0xcustomer-datasets'
pollTimeoutSecs = 120
retryDelaySecs = 30
timeoutSecs = 300
(importResult, importPattern) = h2i.import_only(path=importFolderPath + "/*")
importFileList = importResult['files']
importFailList = importResult['fails']
importKeyList = importResult['keys']
importDelList = importResult['dels']
if len(importDelList)!=0:
raise Exception("import shouldn't have any deletes. importDelList: %s" % h2o.dump_json(importDelList))
if len(importFileList)<MINFILES:
raise Exception("Didn't import successfully. importFileList: %s" % h2o.dump_json(importFileList))
if len(importKeyList)<MINFILES:
raise Exception("Didn't import successfully. importKeyList: %s" % h2o.dump_json(importKeyList))
if len(importFailList)!=0:
raise Exception("Didn't import successfully. importFailList: %s" % h2o.dump_json(importFailList))
# only parse files with .csv or .tsv in their name (no dirs like that?)
goodKeyList = [key for key in importKeyList if ('.csv' in key or '.tsv' in key)]
trial = 0
# just do 1?
for i, importKey in enumerate(random.sample(goodKeyList,3)):
print "importKey:", importKey
trial +=1
start = time.time()
# some data has ,, in the header row. can't have multiple NAs. h2o doesn't like
# force header=0..should mean headers get treated as NAs
parseResult = h2i.parse_only(pattern=importKey, header=0,
timeoutSecs=timeoutSecs, retryDelaySecs=retryDelaySecs, pollTimeoutSecs=pollTimeoutSecs)
elapsed = time.time() - start
print "Parse #", trial, "completed in", "%6.2f" % elapsed, "seconds.", \
"%d pct. of timeout" % ((elapsed*100)/timeoutSecs)
print "Parse result['destination_key']:", parseResult['destination_key']
origKey = parseResult['destination_key']
inspect = h2o_cmd.runInspect(key=origKey)
h2o_cmd.infoFromInspect(inspect, origKey)
execExpr = 'newKey = '+origKey+'[1,1]'
h2e.exec_expr(h2o.nodes[0], execExpr, "a", timeoutSecs=30)
newParseKey = {'destination_key': 'newKey'}
h2o_cmd.checkKeyDistribution()
h2o.nodes[0].remove_key(key=origKey)
# a key isn't created for a scalar
# h2o.nodes[0].remove_key(key='newKey')
self.assertGreater(trial, MINDONE-1, msg="There should be more than %s parsed files" % MINDONE)
x = ",".join(map(str,x))
GLMkwargs = {'x': x, 'y': 378, 'case': 15, 'case_mode': '>',
'max_iter': 10, 'n_folds': 1, 'alpha': 0.2, 'lambda': 1e-5}
start = time.time()
glm = h2o_cmd.runGLMOnly(parseResult=parseResult, timeoutSecs=timeoutSecs, **GLMkwargs)
h2o_glm.simpleCheckGLM(self, glm, None, **GLMkwargs)
elapsed = time.time() - start
h2o.check_sandbox_for_errors()
l = '{:d} jvms, {:d}GB heap, {:s} {:s} GLM: {:6.2f} secs'.format(
len(h2o.nodes), h2o.nodes[0].java_heap_GB, csvFilepattern, csvFilename, elapsed)
print l
h2o.cloudPerfH2O.message(l)
#**********************************************************************************
h2o_cmd.checkKeyDistribution()
h2i.delete_keys_from_import_result(pattern=csvFilename, importResult=importResult)
### time.sleep(3600)
h2o.tear_down_cloud()
if not localhost:
print "Waiting 30 secs before building cloud again (sticky ports?)"
### time.sleep(30)
sys.stdout.write('.')
sys.stdout.flush()
if __name__ == '__main__':
h2o.unit_main()
def test_parse_nflx_loop_s3n_hdfs(self):
DO_GLM = True
DO_GLMGRID = False
USE_S3 = False
noPoll = False
benchmarkLogging = ['jstack','iostats']
benchmarkLogging = ['iostats']
benchmarkLogging = []
# typical size of the michal files
avgMichalSize = 116561140
avgSynSize = 4020000
synSize = 183
csvFilenameList = [
(["manyfiles-nflx-gz"], "*file_1[0-9][0-9].dat.gz", "file_100_A.dat.gz", 100 * avgMichalSize, 3600),
(["manyfiles-nflx-gz"], "*file_[1-2][0-5][0-9].dat.gz", "file_120_A.dat.gz", 120 * avgMichalSize, 3600),
(["manyfiles-nflx-gz"], "*file_[1-2][0-6][0-9].dat.gz", "file_140_A.dat.gz", 140 * avgMichalSize, 3600),
(["manyfiles-nflx-gz"], "*file_[1-2][0-7][0-9].dat.gz", "file_160_A.dat.gz", 160 * avgMichalSize, 3600),
(["manyfiles-nflx-gz"], "*file_[1-2][0-8][0-9].dat.gz", "file_180_A.dat.gz", 180 * avgMichalSize, 3600),
(["manyfiles-nflx-gz"], "*file_[12][0-9][0-9].dat.gz", "file_200_A.dat.gz", 200 * avgMichalSize, 3600),
(["manyfiles-nflx-gz"], "*file_[123][0-9][0-9].dat.gz", "file_300_A.dat.gz", 300 * avgMichalSize, 3600),
(["manyfiles-nflx-gz"], "*file_[123][0-9][0-9].dat.gz", "file_300_B.dat.gz", 300 * avgMichalSize, 3600),
(["manyfiles-nflx-gz"], "*file_[123][0-9][0-9].dat.gz", "file_300_C.dat.gz", 300 * avgMichalSize, 3600),
(["manyfiles-nflx-gz"], "*file_1.dat.gz", "file_1.dat.gz", 1 * avgMichalSize, 300),
(["manyfiles-nflx-gz"], "*file_[2][0-9].dat.gz", "file_10.dat.gz", 10 * avgMichalSize, 700),
(["manyfiles-nflx-gz"], "*file_[34][0-9].dat.gz", "file_20.dat.gz", 20 * avgMichalSize, 900),
(["manyfiles-nflx-gz"], "*file_[5-9][0-9].dat.gz", "file_50_A.dat.gz", 50 * avgMichalSize, 3600),
(["manyfiles-nflx-gz"], "*file_1[0-4][0-9].dat.gz", "file_50_B.dat.gz", 50 * avgMichalSize, 3600),
(["manyfiles-nflx-gz"], "*file_1[0-9][0-9].dat.gz", "file_100_A.dat.gz", 100 * avgMichalSize, 3600),
(["manyfiles-nflx-gz"], "*file_2[0-9][0-9].dat.gz", "file_100_B.dat.gz", 100 * avgMichalSize, 3600),
# beware: the files should be non-overlapping sequentially if noPoll is used, to avoid deleting keys in use
(["A-800-manyfiles-nflx-gz"],
"*file_[0-9]*.dat.gz", "file_A_200_x55.dat.gz", 200 * (avgMichalSize/2), 7200),
(["A-800-manyfiles-nflx-gz", "B-800-manyfiles-nflx-gz"],
"*file_[0-9]*.dat.gz", "file_A_400_x55.dat.gz", 400 * (avgMichalSize/2), 7200),
(["A-800-manyfiles-nflx-gz", "B-800-manyfiles-nflx-gz", "C-800-manyfiles-nflx-gz", "D-800-manyfiles-nflx-gz"],
"*file_[0-9]*.dat.gz", "file_A_800_x55.dat.gz", 800 * (avgMichalSize/2), 7200),
]
print "Using the -.gz files from s3"
# want just s3n://home-0xdiag-datasets/manyfiles-nflx-gz/file_1.dat.gz
# split out the pattern match and the filename used for the hex
trialMax = 1
pollTimeoutSecs = 180
retryDelaySecs = 10
# use i to forward reference in the list, so we can do multiple outstanding parses below
for i, (csvFolderList, csvFilepattern, csvFilename, totalBytes, timeoutSecs) in enumerate(csvFilenameList):
bucket = "home-0xdiag-datasets"
## for tryHeap in [54, 28]:
h2oPerNode = 1
# h1.4xlarge 60.5GB dram
for tryHeap in [28]:
if USE_S3:
protocol = "s3"
else:
protocol = "s3n"
print "\n", tryHeap,"GB heap,", h2oPerNode, "jvm per host, import", protocol, "then parse"
# jea = "-XX:+UseParNewGC -XX:+UseConcMarkSweepGC"
# jea = "-Dh2o.find-ByteBuffer-leaks=true"
h2o.init(h2oPerNode, java_heap_GB=tryHeap, enable_benchmark_log=True, timeoutSecs=120, retryDelaySecs=10)
# java_extra_args=jea,
# don't raise exception if we find something bad in h2o stdout/stderr?
h2o.nodes[0].sandboxIgnoreErrors = True
for trial in range(trialMax):
# import a list of folders, one at a time (hdfs import can't take pattern match
# want to be able to parse 800 files, but only 200 per folder. Don't want to import the full bucket
# too slow
for csvFolder in csvFolderList:
# since we delete the key, we have to re-import every iteration, to get it again
# s3n URI thru HDFS is not typical.
if USE_S3:
(importResult, importPattern) = h2i.import_only(
bucket=bucket, path=csvFolder + "/" + csvFilepattern, schema='s3')
else:
(importResult, importPattern) = h2i.import_only(
bucket=bucket, path=csvFolder + "/" + csvFilepattern, schema='hdfs')
foundKeys = 0
for s in importResult['succeeded']:
# just print the first tile
# if 'nflx' in key and 'file_1.dat.gz' in key:
if csvFilepattern in s['key']:
# should be s3n://home-0xdiag-datasets/manyfiles-nflx-gz/file_1.dat.gz
print "example file we'll use:", s['key']
break
else:
pass
foundKeys += 1
### print "s3nFullList:", h2o.dump_json(s3nFullList)
# error if none?
self.assertGreater(foundKeys,8,"Didn't see more than 8 files in s3n?")
src_key = csvFilepattern
hex_key = csvFilename + "_" + str(trial) + ".hex"
print "Loading", protocol, "key:", src_key, "to", hex_key
start = time.time()
parseResult = h2i.import_parse(bucket='home-0xdiag-datasets', path=csvFolder + "/" + csvFilepattern,
timeoutSecs=timeoutSecs,
retryDelaySecs=retryDelaySecs,
pollTimeoutSecs=pollTimeoutSecs,
noPoll=noPoll,
benchmarkLogging=benchmarkLogging)
if noPoll:
if (i+1) < len(csvFilenameList):
time.sleep(1)
h2o.check_sandbox_for_errors()
(csvFilepattern, csvFilename, totalBytes2, timeoutSecs) = csvFilenameList[i+1]
src_key = csvFilepattern
hex_key = csvFilename + "_" + str(trial) + ".hex"
print "Loading", protocol, "key:", src_key, "to", hex_key
parse2Result = h2i.import_parse(bucket='home-0xdiag-datasets', path=csvFolder + "/" + csvFilepattern,
timeoutSecs=timeoutSecs,
retryDelaySecs=retryDelaySecs,
pollTimeoutSecs=pollTimeoutSecs,
noPoll=noPoll,
benchmarkLogging=benchmarkLogging)
if (i+2) < len(csvFilenameList):
time.sleep(1)
h2o.check_sandbox_for_errors()
(csvFilepattern, csvFilename, totalBytes3, timeoutSecs) = csvFilenameList[i+2]
src_key = URI + csvFilepattern
hex_key = csvFilename + "_" + str(trial) + ".hex"
print "Loading", protocol, "key:", src_key, "to", hex_key
parse3Result = h2i.import_parse(bucket='home-0xdiag-datasets', path=importFolderPath + "/" + csvFilepattern,
timeoutSecs=timeoutSecs,
retryDelaySecs=retryDelaySecs,
pollTimeoutSecs=pollTimeoutSecs,
noPoll=noPoll,
benchmarkLogging=benchmarkLogging)
elapsed = time.time() - start
print "parse result:", parseResult['destination_key']
print "Parse #", trial, "completed in", "%6.2f" % elapsed, "seconds.", \
"%d pct. of timeout" % ((elapsed*100)/timeoutSecs)
# print stats on all three if noPoll
if noPoll:
# does it take a little while to show up in Jobs, from where we issued the parse?
time.sleep(2)
# FIX! use the last (biggest?) timeoutSecs? maybe should increase since parallel
h2o_jobs.pollWaitJobs(pattern=csvFilename,
timeoutSecs=timeoutSecs, benchmarkLogging=benchmarkLogging)
# for getting the MB/sec closer to 'right'
totalBytes += totalBytes2 + totalBytes3
elapsed = time.time() - start
h2o.check_sandbox_for_errors()
if totalBytes is not None:
fileMBS = (totalBytes/1e6)/elapsed
l = '{:d} jvms, {:d}GB heap, {:s} {:s} {:6.2f} MB/sec for {:6.2f} secs'.format(
len(h2o.nodes), tryHeap, csvFilepattern, csvFilename, fileMBS, elapsed)
print l
h2o.cloudPerfH2O.message(l)
y = 378
if not noPoll:
x = h2o_glm.goodXFromColumnInfo(y, key=parseResult['destination_key'], timeoutSecs=300)
#**********************************************************************************
# Do GLM too
# Argument case error: Value 0.0 is not between 12.0 and 9987.0 (inclusive)
if DO_GLM or DO_GLMGRID:
# these are all the columns that are enums in the dataset...too many for GLM!
x = range(542) # don't include the output column
# remove the output too! (378)
for i in [3, 4, 5, 6, 7, 8, 9, 10, 11, 14, 16, 17, 18, 19, 20, 424, 425, 426, 540, 541, y]:
x.remove(i)
x = ",".join(map(str,x))
if DO_GLM:
algo = 'GLM'
GLMkwargs = {'x': x, 'y': y, 'case': 15, 'case_mode': '>', 'family': 'binomial',
'max_iter': 10, 'n_folds': 1, 'alpha': 0.2, 'lambda': 1e-5}
start = time.time()
glm = h2o_cmd.runGLM(parseResult=parseResult,
timeoutSecs=timeoutSecs, retryDelaySecs=retryDelaySecs,
pollTimeoutSecs=pollTimeoutSecs,
benchmarkLogging=benchmarkLogging, **GLMkwargs)
elapsed = time.time() - start
h2o_glm.simpleCheckGLM(self, glm, None, **GLMkwargs)
else:
algo = 'GLMGrid'
GLMkwargs = {'x': x, 'y': y, 'case': 15, 'case_mode': '>', 'family': 'binomial',
'max_iter': 10, 'n_folds': 1, 'beta_epsilon': 1e-4,
'lambda': '1e-4',
'alpha': '0,0.5',
'thresholds': '0.5'
}
start = time.time()
glm = h2o_cmd.runGLMGrid(parseResult=parseResult,
timeoutSecs=timeoutSecs, retryDelaySecs=retryDelaySecs,
pollTimeoutSecs=pollTimeoutSecs,
benchmarkLogging=benchmarkLogging, **GLMkwargs)
elapsed = time.time() - start
h2o_glm.simpleCheckGLMGrid(self, glm, None, **GLMkwargs)
h2o.check_sandbox_for_errors()
l = '{:d} jvms, {:d}GB heap, {:s} {:s} {:s} {:6.2f} secs'.format(
len(h2o.nodes), tryHeap, algo, csvFilepattern, csvFilename, elapsed)
print l
h2o.cloudPerfH2O.message(l)
#**********************************************************************************
print "Deleting key in H2O so we get it from S3 (if ec2) or nfs again.", \
"Otherwise it would just parse the cached key."
### storeView = h2o.nodes[0].store_view()
### print "storeView:", h2o.dump_json(storeView)
# "key": "s3n://home-0xdiag-datasets/manyfiles-nflx-gz/file_84.dat.gz"
# have to do the pattern match ourself, to figure out what keys to delete
# we're deleting the keys in the initial import. We leave the keys we created
# by the parse. We use unique dest keys for those, so no worries.
# Leaving them is good because things fill up! (spill)
h2o_cmd.checkKeyDistribution()
h2i.delete_keys_from_import_result(pattern=csvFilename, importResult=importResult)
h2o.tear_down_cloud()
# sticky ports? wait a bit.
print "Waiting 30 secs before building cloud again (sticky ports?)"
time.sleep(30)
def sub_c3_fvec_long(self):
h2o.beta_features = True
# a kludge
h2o.setup_benchmark_log()
avgMichalSize = 116561140
bucket = "home-0xdiag-datasets"
### importFolderPath = 'more1_1200_link'
importFolderPath = "manyfiles-nflx-gz"
print "Using .gz'ed files in", importFolderPath
if len(h2o.nodes) == 1:
csvFilenameList = [("*[1][0][0-9].dat.gz", "file_10_A.dat.gz", 10 * avgMichalSize, 600)]
else:
csvFilenameList = [
("*[1][0-4][0-9].dat.gz", "file_50_A.dat.gz", 50 * avgMichalSize, 1800),
# ("*[1][0-9][0-9].dat.gz", "file_100_A.dat.gz", 100 * avgMichalSize, 1800),
]
if LOG_MACHINE_STATS:
benchmarkLogging = ["cpu", "disk", "network"]
else:
benchmarkLogging = []
pollTimeoutSecs = 120
retryDelaySecs = 10
for trial, (csvFilepattern, csvFilename, totalBytes, timeoutSecs) in enumerate(csvFilenameList):
csvPathname = importFolderPath + "/" + csvFilepattern
(importResult, importPattern) = h2i.import_only(bucket=bucket, path=csvPathname, schema="local")
importFullList = importResult["files"]
importFailList = importResult["fails"]
print "\n Problem if this is not empty: importFailList:", h2o.dump_json(importFailList)
# this accumulates performance stats into a benchmark log over multiple runs
# good for tracking whether we're getting slower or faster
h2o.cloudPerfH2O.change_logfile(csvFilename)
h2o.cloudPerfH2O.message("")
h2o.cloudPerfH2O.message("Parse " + csvFilename + " Start--------------------------------")
start = time.time()
parseResult = h2i.import_parse(
bucket=bucket,
path=csvPathname,
schema="local",
hex_key=csvFilename + ".hex",
timeoutSecs=timeoutSecs,
retryDelaySecs=retryDelaySecs,
pollTimeoutSecs=pollTimeoutSecs,
benchmarkLogging=benchmarkLogging,
)
elapsed = time.time() - start
print "Parse #", trial, "completed in", "%6.2f" % elapsed, "seconds.", "%d pct. of timeout" % (
(elapsed * 100) / timeoutSecs
)
print "Parse result['destination_key']:", parseResult["destination_key"]
h2o_cmd.columnInfoFromInspect(parseResult["destination_key"], exceptionOnMissingValues=False)
if totalBytes is not None:
fileMBS = (totalBytes / 1e6) / elapsed
msg = "{!s} jvms, {!s}GB heap, {:s} {:s} {:6.2f} MB/sec for {:.2f} secs".format(
len(h2o.nodes), h2o.nodes[0].java_heap_GB, csvFilepattern, csvFilename, fileMBS, elapsed
)
print msg
h2o.cloudPerfH2O.message(msg)
if DO_GLM:
# these are all the columns that are enums in the dataset...too many for GLM!
x = range(542) # don't include the output column
# remove the output too! (378)
ignore_x = []
for i in [3, 4, 5, 6, 7, 8, 9, 10, 11, 14, 16, 17, 18, 19, 20, 424, 425, 426, 540, 541]:
x.remove(i)
ignore_x.append(i)
x.remove(378)
# add one since we are no longer 0 based offset
x = ",".join(map(lambda x: "C" + str(x + 1), x))
ignore_x = ",".join(map(lambda x: "C" + str(x + 1), ignore_x))
GLMkwargs = {
"ignored_cols": ignore_x,
"response": "C379",
"max_iter": 4,
"n_folds": 1,
"family": "binomial",
"alpha": 0.2,
"lambda": 1e-5,
}
# convert to binomial
execExpr = "A.hex=%s" % parseResult["destination_key"]
h2e.exec_expr(execExpr=execExpr, timeoutSecs=60)
execExpr = "A.hex[,%s]=(A.hex[,%s]>%s)" % ("C379", "C379", 15)
h2e.exec_expr(execExpr=execExpr, timeoutSecs=60)
aHack = {"destination_key": "A.hex"}
start = time.time()
glm = h2o_cmd.runGLM(parseResult=aHack, timeoutSecs=timeoutSecs, **GLMkwargs)
elapsed = time.time() - start
h2o.check_sandbox_for_errors()
h2o_glm.simpleCheckGLM(self, glm, None, **GLMkwargs)
msg = "{:d} jvms, {:d}GB heap, {:s} {:s} GLM: {:6.2f} secs".format(
len(h2o.nodes), h2o.nodes[0].java_heap_GB, csvFilepattern, csvFilename, elapsed
)
print msg
h2o.cloudPerfH2O.message(msg)
h2o_cmd.checkKeyDistribution()
def sub_c3_nongz_fvec_long(self, csvFilenameList):
h2o.beta_features = True
# a kludge
h2o.setup_benchmark_log()
bucket = 'home-0xdiag-datasets'
importFolderPath = 'manyfiles-nflx'
print "Using nongz'ed files in", importFolderPath
if LOG_MACHINE_STATS:
benchmarkLogging = ['cpu', 'disk', 'network']
else:
benchmarkLogging = []
pollTimeoutSecs = 120
retryDelaySecs = 10
for trial, (csvFilepattern, csvFilename, totalBytes, timeoutSecs) in enumerate(csvFilenameList):
csvPathname = importFolderPath + "/" + csvFilepattern
if DO_DOUBLE_IMPORT:
(importResult, importPattern) = h2i.import_only(bucket=bucket, path=csvPathname, schema='local')
importFullList = importResult['files']
importFailList = importResult['fails']
print "\n Problem if this is not empty: importFailList:", h2o.dump_json(importFailList)
# this accumulates performance stats into a benchmark log over multiple runs
# good for tracking whether we're getting slower or faster
h2o.cloudPerfH2O.change_logfile(csvFilename)
h2o.cloudPerfH2O.message("")
h2o.cloudPerfH2O.message("Parse " + csvFilename + " Start--------------------------------")
start = time.time()
parseResult = h2i.import_parse(bucket=bucket, path=csvPathname, schema='local',
hex_key=csvFilename + ".hex", timeoutSecs=timeoutSecs,
retryDelaySecs=retryDelaySecs,
pollTimeoutSecs=pollTimeoutSecs,
benchmarkLogging=benchmarkLogging)
elapsed = time.time() - start
print "Parse #", trial, "completed in", "%6.2f" % elapsed, "seconds.", \
"%d pct. of timeout" % ((elapsed*100)/timeoutSecs)
print "Parse result['destination_key']:", parseResult['destination_key']
h2o_cmd.columnInfoFromInspect(parseResult['destination_key'], exceptionOnMissingValues=False)
if totalBytes is not None:
fileMBS = (totalBytes/1e6)/elapsed
msg = '{!s} jvms, {!s}GB heap, {:s} {:s} {:6.2f} MB/sec for {:.2f} secs'.format(
len(h2o.nodes), h2o.nodes[0].java_heap_GB, csvFilepattern, csvFilename, fileMBS, elapsed)
print msg
h2o.cloudPerfH2O.message(msg)
if DO_GLM:
# these are all the columns that are enums in the dataset...too many for GLM!
x = range(542) # don't include the output column
# remove the output too! (378)
ignore_x = []
for i in [3,4,5,6,7,8,9,10,11,14,16,17,18,19,20,424,425,426,540,541]:
x.remove(i)
ignore_x.append(i)
x.remove(378)
# add one since we are no longer 0 based offset
x = ",".join(map(lambda x: "C" + str(x+1), x))
ignore_x = ",".join(map(lambda x: "C" + str(x+1), ignore_x))
GLMkwargs = {
'ignored_cols': ignore_x,
'response': 'C379',
'max_iter': 4,
'n_folds': 1,
'family': 'binomial',
'alpha': 0.2,
'lambda': 1e-5
}
# convert to binomial
execExpr="A.hex=%s" % parseResult['destination_key']
h2e.exec_expr(execExpr=execExpr, timeoutSecs=60)
execExpr = 'A.hex[,378+1]=(A.hex[,378+1]>15)'
h2e.exec_expr(execExpr=execExpr, timeoutSecs=60)
aHack = {'destination_key': "A.hex"}
start = time.time()
glm = h2o_cmd.runGLM(parseResult=aHack, timeoutSecs=timeoutSecs, **GLMkwargs)
elapsed = time.time() - start
h2o.check_sandbox_for_errors()
h2o_glm.simpleCheckGLM(self, glm, None, **GLMkwargs)
msg = '{:d} jvms, {:d}GB heap, {:s} {:s} GLM: {:6.2f} secs'.format(
len(h2o.nodes), h2o.nodes[0].java_heap_GB, csvFilepattern, csvFilename, elapsed)
print msg
h2o.cloudPerfH2O.message(msg)
h2o_cmd.checkKeyDistribution()
def sub_c2_rel_long(self):
# a kludge
h2o.setup_benchmark_log()
avgMichalSize = 116561140
bucket = 'home-0xdiag-datasets'
### importFolderPath = 'more1_1200_link'
importFolderPath = 'manyfiles-nflx-gz'
print "Using .gz'ed files in", importFolderPath
if len(h2o.nodes)==1:
csvFilenameList= [
("*[1][0][0-9].dat.gz", "file_10_A.dat.gz", 10 * avgMichalSize, 600),
]
else:
csvFilenameList= [
("*[1][0-4][0-9].dat.gz", "file_50_A.dat.gz", 50 * avgMichalSize, 1800),
# ("*[1][0-9][0-9].dat.gz", "file_100_A.dat.gz", 100 * avgMichalSize, 3600),
]
if LOG_MACHINE_STATS:
benchmarkLogging = ['cpu', 'disk', 'network']
else:
benchmarkLogging = []
pollTimeoutSecs = 120
retryDelaySecs = 10
for trial, (csvFilepattern, csvFilename, totalBytes, timeoutSecs) in enumerate(csvFilenameList):
csvPathname = importFolderPath + "/" + csvFilepattern
(importResult, importPattern) = h2i.import_only(bucket=bucket, path=csvPathname, schema='local')
# this accumulates performance stats into a benchmark log over multiple runs
# good for tracking whether we're getting slower or faster
h2o.cloudPerfH2O.change_logfile(csvFilename)
h2o.cloudPerfH2O.message("")
h2o.cloudPerfH2O.message("Parse " + csvFilename + " Start--------------------------------")
start = time.time()
parseResult = h2i.import_parse(bucket=bucket, path=csvPathname, schema='local',
hex_key=csvFilename + ".hex", timeoutSecs=timeoutSecs,
retryDelaySecs=retryDelaySecs,
pollTimeoutSecs=pollTimeoutSecs,
benchmarkLogging=benchmarkLogging)
elapsed = time.time() - start
print "Parse #", trial, "completed in", "%6.2f" % elapsed, "seconds.", \
"%d pct. of timeout" % ((elapsed*100)/timeoutSecs)
print "Parse result['destination_key']:", parseResult['destination_key']
h2o_cmd.columnInfoFromInspect(parseResult['destination_key'], exceptionOnMissingValues=False)
if totalBytes is not None:
fileMBS = (totalBytes/1e6)/elapsed
msg = '{!s} jvms, {!s}GB heap, {:s} {:s} {:6.2f} MB/sec for {:.2f} secs'.format(
len(h2o.nodes), h2o.nodes[0].java_heap_GB, csvFilepattern, csvFilename, fileMBS, elapsed)
print msg
h2o.cloudPerfH2O.message(msg)
if DO_GLM:
# these are all the columns that are enums in the dataset...too many for GLM!
x = range(542) # don't include the output column
# remove the output too! (378)
ignore_x = []
# for i in [3,4,5,6,7,8,9,10,11,14,16,17,18,19,20,424,425,426,540,541]:
for i in [3,4,5,6,7,8,9,10,11,14,16,17,18,19,20,424,425,426,540,541,378]:
x.remove(i)
ignore_x.append(i)
# increment by one, because we are no long zero offset!
x = ",".join(map(lambda x: "C" + str(x+1), x))
ignore_x = ",".join(map(lambda x: "C" + str(x+1), ignore_x))
GLMkwargs = {
'family': 'binomial',
'x': x,
'y': 'C379',
'case': 15,
'case_mode': '>',
'max_iter': 4,
'n_folds': 1,
'family': 'binomial',
'alpha': 0.2,
'lambda': 1e-5
}
start = time.time()
glm = h2o_cmd.runGLM(parseResult=parseResult, timeoutSecs=timeoutSecs, **GLMkwargs)
elapsed = time.time() - start
h2o.check_sandbox_for_errors()
h2o_glm.simpleCheckGLM(self, glm, None, **GLMkwargs)
msg = '{:d} jvms, {:d}GB heap, {:s} {:s} GLM: {:6.2f} secs'.format(
len(h2o.nodes), h2o.nodes[0].java_heap_GB, csvFilepattern, csvFilename, elapsed)
print msg
h2o.cloudPerfH2O.message(msg)
h2o_cmd.checkKeyDistribution()
def sub_c2_nongz_fvec_long(self):
# a kludge
h2o.setup_benchmark_log()
avgMichalSize = 237270000
bucket = 'home-0xdiag-datasets'
### importFolderPath = 'more1_1200_link'
importFolderPath = 'manyfiles-nflx'
print "Using non-gz'ed files in", importFolderPath
csvFilenameList = [
("*[1][0-4][0-9].dat", "file_50_A.dat", 50 * avgMichalSize, 1800),
# ("*[1][0-9][0-9].dat", "file_100_A.dat", 100 * avgMichalSize, 3600),
]
if LOG_MACHINE_STATS:
benchmarkLogging = ['cpu', 'disk', 'network']
else:
benchmarkLogging = []
pollTimeoutSecs = 120
retryDelaySecs = 10
for trial, (csvFilepattern, csvFilename, totalBytes,
timeoutSecs) in enumerate(csvFilenameList):
csvPathname = importFolderPath + "/" + csvFilepattern
# double import still causing problems?
# (importResult, importPattern) = h2i.import_only(bucket=bucket, path=csvPathname, schema='local')
# importFullList = importResult['files']
# importFailList = importResult['fails']
# print "\n Problem if this is not empty: importFailList:", h2o.dump_json(importFailList)
# this accumulates performance stats into a benchmark log over multiple runs
# good for tracking whether we're getting slower or faster
h2o.cloudPerfH2O.change_logfile(csvFilename)
h2o.cloudPerfH2O.message("")
h2o.cloudPerfH2O.message("Parse " + csvFilename +
" Start--------------------------------")
start = time.time()
parseResult = h2i.import_parse(bucket=bucket,
path=csvPathname,
schema='local',
hex_key=csvFilename + ".hex",
timeoutSecs=timeoutSecs,
retryDelaySecs=retryDelaySecs,
pollTimeoutSecs=pollTimeoutSecs,
benchmarkLogging=benchmarkLogging)
elapsed = time.time() - start
print "Parse #", trial, "completed in", "%6.2f" % elapsed, "seconds.", \
"%d pct. of timeout" % ((elapsed*100)/timeoutSecs)
print "Parse result['destination_key']:", parseResult[
'destination_key']
h2o_cmd.columnInfoFromInspect(parseResult['destination_key'],
exceptionOnMissingValues=False)
if totalBytes is not None:
fileMBS = (totalBytes / 1e6) / elapsed
msg = '{!s} jvms, {!s}GB heap, {:s} {:s} {:6.2f} MB/sec for {:.2f} secs'.format(
len(h2o.nodes), h2o.nodes[0].java_heap_GB, csvFilepattern,
csvFilename, fileMBS, elapsed)
print msg
h2o.cloudPerfH2O.message(msg)
if DO_GLM:
# these are all the columns that are enums in the dataset...too many for GLM!
x = range(542) # don't include the output column
# remove the output too! (378)
ignore_x = []
for i in [
3, 4, 5, 6, 7, 8, 9, 10, 11, 14, 16, 17, 18, 19, 20,
424, 425, 426, 540, 541
]:
x.remove(i)
ignore_x.append(i)
# plus 1 because we are no longer 0 offset
x = ",".join(map(lambda x: "C" + str(x + 1), x))
ignore_x = ",".join(map(lambda x: "C" + str(x + 1), ignore_x))
GLMkwargs = {
'ignored_cols': ignore_x,
'family': 'binomial',
'response': 'C379',
'max_iter': 4,
'n_folds': 1,
'family': 'binomial',
'alpha': 0.2,
'lambda': 1e-5
}
# are the unparsed keys slowing down exec?
h2i.delete_keys_at_all_nodes(pattern="manyfile")
# convert to binomial
execExpr = "A.hex=%s" % parseResult['destination_key']
h2e.exec_expr(execExpr=execExpr, timeoutSecs=180)
execExpr = "A.hex[,%s]=(A.hex[,%s]>%s)" % ('379', '379', 15)
h2e.exec_expr(execExpr=execExpr, timeoutSecs=180)
aHack = {'destination_key': "A.hex"}
start = time.time()
glm = h2o_cmd.runGLM(parseResult=aHack,
timeoutSecs=timeoutSecs,
**GLMkwargs)
elapsed = time.time() - start
h2o.check_sandbox_for_errors()
h2o_glm.simpleCheckGLM(self, glm, None, **GLMkwargs)
msg = '{:d} jvms, {:d}GB heap, {:s} {:s} GLM: {:6.2f} secs'.format(
len(h2o.nodes), h2o.nodes[0].java_heap_GB, csvFilepattern,
csvFilename, elapsed)
print msg
h2o.cloudPerfH2O.message(msg)
h2o_cmd.checkKeyDistribution()
def test_parse_10k_files(self):
SYNDATASETS_DIR = h2o.make_syn_dir()
csvFilename = "syn.csv.gz"
headerData = "ID,CAPSULE,AGE,RACE,DPROS,DCAPS,PSA,VOL,GLEASON"
totalRows = 10
maxFilenum = 10000
for filenum in range(maxFilenum):
rowData = rand_rowData()
filePrefix = "%04d" % filenum
csvPathname = SYNDATASETS_DIR + '/' + filePrefix + "_" + csvFilename
write_syn_dataset_gz(csvPathname, totalRows, headerData, rowData)
avgFileSize = os.path.getsize(csvPathname)
importFolderPath = SYNDATASETS_DIR
print "\nimportFolderPath:", importFolderPath
csvFilenameList = [
# try one thousand files first
("*[1][0-9][0-9][0-9]_syn.csv.gz", "syn_all.1000.csv",
maxFilenum * avgFileSize, 1200),
# try two thousand
("*[1-2][0-9][0-9][0-9]_syn.csv.gz", "syn_all.2000.csv",
maxFilenum * avgFileSize, 1200),
]
trialMax = 1
base_port = 54321
tryHeap = 4
DO_GLM = True
noPoll = False
benchmarkLogging = ['cpu', 'disk', 'iostats'] # , 'jstack'
benchmarkLogging = ['cpu', 'disk']
pollTimeoutSecs = 120
retryDelaySecs = 10
for i, (csvFilepattern, csvFilename, totalBytes,
timeoutSecs) in enumerate(csvFilenameList):
localhost = h2o.decide_if_localhost()
if (localhost):
h2o.build_cloud(3,
java_heap_GB=tryHeap,
base_port=base_port,
enable_benchmark_log=True)
else:
h2o_hosts.build_cloud_with_hosts(1,
java_heap_GB=tryHeap,
base_port=base_port,
enable_benchmark_log=True)
### h2b.browseTheCloud()
# don't let the config json redirect import folder to s3 or s3n, because
# we're writing to the syn_datasets locally. (just have to worry about node 0's copy of this state)
print "This test creates files in syn_datasets for import folder\n" + \
"so h2o and python need to be same machine"
h2o.nodes[0].redirect_import_folder_to_s3_path = False
h2o.nodes[0].redirect_import_folder_to_s3n_path = False
for trial in range(trialMax):
importFolderResult = h2i.setupImportFolder(
None, importFolderPath)
importFullList = importFolderResult['files']
print "importFullList:", importFullList
importFailList = importFolderResult['fails']
print "importFailList:", importFailList
print "\n Problem if this is not empty: importFailList:", h2o.dump_json(
importFailList)
h2o.cloudPerfH2O.change_logfile(csvFilename)
h2o.cloudPerfH2O.message("")
h2o.cloudPerfH2O.message(
"Parse " + csvFilename +
" Start--------------------------------")
start = time.time()
parseKey = h2i.parseImportFolderFile(
None,
csvFilepattern,
importFolderPath,
key2=csvFilename + ".hex",
timeoutSecs=timeoutSecs,
retryDelaySecs=retryDelaySecs,
pollTimeoutSecs=pollTimeoutSecs,
noPoll=noPoll,
benchmarkLogging=benchmarkLogging)
elapsed = time.time() - start
print "Parse #", trial, "completed in", "%6.2f" % elapsed, "seconds.", \
"%d pct. of timeout" % ((elapsed*100)/timeoutSecs)
if noPoll:
# does it take a little while to show up in Jobs, from where we issued the parse?
time.sleep(2)
# FIX! use the last (biggest?) timeoutSecs? maybe should increase since parallel
h2o_jobs.pollWaitJobs(pattern=csvFilename,
timeoutSecs=timeoutSecs,
benchmarkLogging=benchmarkLogging)
totalBytes += totalBytes2 + totalBytes3
elapsed = time.time() - start
h2o.check_sandbox_for_errors()
if totalBytes is not None:
fileMBS = (totalBytes / 1e6) / elapsed
l = '{!s} jvms, {!s}GB heap, {:s} {:s} {:6.2f} MB/sec for {:.2f} secs'.format(
len(h2o.nodes), tryHeap, csvFilepattern, csvFilename,
fileMBS, elapsed)
print l
h2o.cloudPerfH2O.message(l)
print csvFilepattern, 'parse time:', parseKey['response'][
'time']
print "Parse result['destination_key']:", parseKey[
'destination_key']
# BUG here?
if not noPoll:
h2o_cmd.get_columnInfoFromInspect(
parseKey['destination_key'],
exceptionOnMissingValues=True)
print "\n" + csvFilepattern
#**********************************************************************************
# Do GLM too
# Argument case error: Value 0.0 is not between 12.0 and 9987.0 (inclusive)
if DO_GLM:
GLMkwargs = {
'y': 0,
'case': 1,
'case_mode': '>',
'max_iter': 10,
'n_folds': 1,
'alpha': 0.2,
'lambda': 1e-5
}
start = time.time()
glm = h2o_cmd.runGLMOnly(parseKey=parseKey,
timeoutSecs=timeoutSecs,
**GLMkwargs)
h2o_glm.simpleCheckGLM(self, glm, None, **GLMkwargs)
elapsed = time.time() - start
h2o.check_sandbox_for_errors()
l = '{:d} jvms, {:d}GB heap, {:s} {:s} GLM: {:6.2f} secs'.format(
len(h2o.nodes), tryHeap, csvFilepattern, csvFilename,
elapsed)
print l
h2o.cloudPerfH2O.message(l)
#**********************************************************************************
h2o_cmd.checkKeyDistribution()
h2o_cmd.deleteCsvKey(csvFilename, importFolderResult)
h2o.tear_down_cloud()
if not localhost:
print "Waiting 30 secs before building cloud again (sticky ports?)"
time.sleep(30)
sys.stdout.write('.')
sys.stdout.flush()
def test_parse_10k_files(self):
SYNDATASETS_DIR = h2o.make_syn_dir()
csvFilename = "syn.csv.gz"
headerData = "ID,CAPSULE,AGE,RACE,DPROS,DCAPS,PSA,VOL,GLEASON"
totalRows = 10
maxFilenum = 10000
for filenum in range(maxFilenum):
rowData = rand_rowData()
filePrefix = "%04d" % filenum
csvPathname = SYNDATASETS_DIR + '/' + filePrefix + "_" + csvFilename
write_syn_dataset_gz(csvPathname, totalRows, headerData, rowData)
avgFileSize = os.path.getsize(csvPathname)
importFolderPath = SYNDATASETS_DIR
print "\nimportFolderPath:", importFolderPath
csvFilenameList = [
# try one thousand files first
("*[1][0-9][0-9][0-9]_syn.csv.gz", "syn_all.1000.csv", maxFilenum * avgFileSize, 1200),
# try two thousand
("*[1-2][0-9][0-9][0-9]_syn.csv.gz", "syn_all.2000.csv", maxFilenum * avgFileSize, 1200),
]
trialMax = 1
base_port = 54321
tryHeap = 4
DO_GLM = True
noPoll = False
benchmarkLogging = ['cpu','disk', 'iostats'] # , 'jstack'
benchmarkLogging = ['cpu','disk']
pollTimeoutSecs = 120
retryDelaySecs = 10
for i,(csvFilepattern, csvFilename, totalBytes, timeoutSecs) in enumerate(csvFilenameList):
localhost = h2o.decide_if_localhost()
if (localhost):
h2o.build_cloud(3,java_heap_GB=tryHeap, base_port=base_port,
enable_benchmark_log=True)
else:
h2o_hosts.build_cloud_with_hosts(1, java_heap_GB=tryHeap, base_port=base_port,
enable_benchmark_log=True)
### h2b.browseTheCloud()
# don't let the config json redirect import folder to s3 or s3n, because
# we're writing to the syn_datasets locally. (just have to worry about node 0's copy of this state)
print "This test creates files in syn_datasets for import folder\n" + \
"so h2o and python need to be same machine"
h2o.nodes[0].redirect_import_folder_to_s3_path = False
h2o.nodes[0].redirect_import_folder_to_s3n_path = False
for trial in range(trialMax):
# nice to have the list of what got imported, so we delete "just that" down below
# doing this just so we can see what we import
(importResult, importPattern) = h2i.import_only(path=importFolderPath+"/*")
importFullList = importResult['files']
print "importFullList:", importFullList
importFailList = importResult['fails']
print "importFailList:", importFailList
print "\n Problem if this is not empty: importFailList:", h2o.dump_json(importFailList)
h2o.cloudPerfH2O.change_logfile(csvFilename)
h2o.cloudPerfH2O.message("")
h2o.cloudPerfH2O.message("Parse " + csvFilename + " Start--------------------------------")
start = time.time()
parseResult = h2i.import_parse(path=importFolderPath+"/*",
hex_key=csvFilename + ".hex", timeoutSecs=timeoutSecs,
retryDelaySecs=retryDelaySecs,
pollTimeoutSecs=pollTimeoutSecs,
noPoll=noPoll,
benchmarkLogging=benchmarkLogging)
elapsed = time.time() - start
print "Parse #", trial, "completed in", "%6.2f" % elapsed, "seconds.", \
"%d pct. of timeout" % ((elapsed*100)/timeoutSecs)
if noPoll:
# does it take a little while to show up in Jobs, from where we issued the parse?
time.sleep(2)
# FIX! use the last (biggest?) timeoutSecs? maybe should increase since parallel
h2o_jobs.pollWaitJobs(pattern=csvFilename,
timeoutSecs=timeoutSecs, benchmarkLogging=benchmarkLogging)
totalBytes += totalBytes2 + totalBytes3
elapsed = time.time() - start
h2o.check_sandbox_for_errors()
if totalBytes is not None:
fileMBS = (totalBytes/1e6)/elapsed
l = '{!s} jvms, {!s}GB heap, {:s} {:s} {:6.2f} MB/sec for {:.2f} secs'.format(
len(h2o.nodes), tryHeap, csvFilepattern, csvFilename, fileMBS, elapsed)
print l
h2o.cloudPerfH2O.message(l)
print csvFilepattern, 'parse time:', parseResult['response']['time']
print "Parse result['destination_key']:", parseResult['destination_key']
# BUG here?
if not noPoll:
h2o_cmd.get_columnInfoFromInspect(parseResult['destination_key'], exceptionOnMissingValues=True)
print "\n" + csvFilepattern
#**********************************************************************************
# Do GLM too
# Argument case error: Value 0.0 is not between 12.0 and 9987.0 (inclusive)
if DO_GLM:
GLMkwargs = {'y': 0, 'case': 1, 'case_mode': '>',
'max_iter': 10, 'n_folds': 1, 'alpha': 0.2, 'lambda': 1e-5}
start = time.time()
glm = h2o_cmd.runGLMOnly(parseResult=parseResult, timeoutSecs=timeoutSecs, **GLMkwargs)
h2o_glm.simpleCheckGLM(self, glm, None, **GLMkwargs)
elapsed = time.time() - start
h2o.check_sandbox_for_errors()
l = '{:d} jvms, {:d}GB heap, {:s} {:s} GLM: {:6.2f} secs'.format(
len(h2o.nodes), tryHeap, csvFilepattern, csvFilename, elapsed)
print l
h2o.cloudPerfH2O.message(l)
#**********************************************************************************
h2o_cmd.checkKeyDistribution()
h2i.delete_keys_from_import_result(pattern=csvFilename, importResult=importResult)
h2o.tear_down_cloud()
if not localhost:
print "Waiting 30 secs before building cloud again (sticky ports?)"
time.sleep(30)
sys.stdout.write('.')
sys.stdout.flush()
def test_benchmark_import(self):
# typical size of the michal files
avgMichalSizeUncompressed = 237270000
avgMichalSize = 116561140
avgSynSize = 4020000
covtype200xSize = 15033863400
synSize = 183
if 1==1:
importFolderPath = '/home/0xdiag/datasets/more1_1200_link'
print "Using .gz'ed files in", importFolderPath
csvFilenameAll = [
("*[3-4][0-4][0-9].dat.gz", "file_100_A.dat.gz", 100 * avgMichalSize, 3600),
("*[3-4][0-4][0-9].dat.gz", "file_100_B.dat.gz", 100 * avgMichalSize, 3600),
("*[3-4][0-5][0-9].dat.gz", "file_120_A.dat.gz", 120 * avgMichalSize, 3600),
("*[3-4][0-5][0-9].dat.gz", "file_120_B.dat.gz", 120 * avgMichalSize, 3600),
("*[3-4][0-6][0-9].dat.gz", "file_140_A.dat.gz", 140 * avgMichalSize, 3600),
("*[3-4][0-6][0-9].dat.gz", "file_140_B.dat.gz", 140 * avgMichalSize, 3600),
("*[3-4][0-7][0-9].dat.gz", "file_160_A.dat.gz", 160 * avgMichalSize, 3600),
("*[3-4][0-7][0-9].dat.gz", "file_160_B.dat.gz", 160 * avgMichalSize, 3600),
("*[3-4][0-8][0-9].dat.gz", "file_180_A.dat.gz", 180 * avgMichalSize, 3600),
("*[3-4][0-8][0-9].dat.gz", "file_180_B.dat.gz", 180 * avgMichalSize, 3600),
("*[3-4][0-9][0-9].dat.gz", "file_200_A.dat.gz", 200 * avgMichalSize, 3600),
("*[3-4][0-9][0-9].dat.gz", "file_200_B.dat.gz", 200 * avgMichalSize, 3600),
("*[3-5][0-9][0-9].dat.gz", "file_300.dat.gz", 300 * avgMichalSize, 3600),
("*[3-5][0-9][0-9].dat.gz", "file_300.dat.gz", 300 * avgMichalSize, 3600),
("*[3-6][0-9][0-9].dat.gz", "file_400.dat.gz", 400 * avgMichalSize, 3600),
("*[3-6][0-9][0-9].dat.gz", "file_400.dat.gz", 400 * avgMichalSize, 3600),
("*[3-6][0-9][0-9].dat.gz", "file_400.dat.gz", 400 * avgMichalSize, 3600),
("*[3-6][0-9][0-9].dat.gz", "file_400.dat.gz", 400 * avgMichalSize, 3600),
("*[3-6][0-9][0-9].dat.gz", "file_400.dat.gz", 400 * avgMichalSize, 3600),
("*[3-6][0-9][0-9].dat.gz", "file_400.dat.gz", 400 * avgMichalSize, 3600),
("*[3-6][0-9][0-9].dat.gz", "file_400.dat.gz", 400 * avgMichalSize, 3600),
("*[3-6][0-9][0-9].dat.gz", "file_400.dat.gz", 400 * avgMichalSize, 3600),
]
# csvFilenameList = random.sample(csvFilenameAll,1)
csvFilenameList = csvFilenameAll
# split out the pattern match and the filename used for the hex
trialMax = 1
# rebuild the cloud for each file
base_port = 54321
tryHeap = 28
# can fire a parse off and go wait on the jobs queue (inspect afterwards is enough?)
DO_GLM = False
noPoll = False
# benchmarkLogging = ['cpu','disk', 'iostats', 'jstack']
# benchmarkLogging = None
benchmarkLogging = ['cpu','disk', 'network', 'iostats', 'jstack']
benchmarkLogging = ['cpu','disk', 'network', 'iostats']
# IOStatus can hang?
benchmarkLogging = ['cpu', 'disk' 'network']
pollTimeoutSecs = 120
retryDelaySecs = 10
for i,(csvFilepattern, csvFilename, totalBytes, timeoutSecs) in enumerate(csvFilenameList):
localhost = h2o.decide_if_localhost()
if (localhost):
h2o.build_cloud(2,java_heap_GB=tryHeap, base_port=base_port,
enable_benchmark_log=True)
else:
h2o_hosts.build_cloud_with_hosts(1, java_heap_GB=tryHeap, base_port=base_port,
enable_benchmark_log=True)
# pop open a browser on the cloud
### h2b.browseTheCloud()
# to avoid sticky ports?
### base_port += 2
for trial in range(trialMax):
importFolderResult = h2i.setupImportFolder(None, importFolderPath)
importFullList = importFolderResult['files']
importFailList = importFolderResult['fails']
print "\n Problem if this is not empty: importFailList:", h2o.dump_json(importFailList)
# creates csvFilename.hex from file in importFolder dir
h2o.cloudPerfH2O.change_logfile(csvFilename)
h2o.cloudPerfH2O.message("")
h2o.cloudPerfH2O.message("Parse " + csvFilename + " Start--------------------------------")
start = time.time()
parseKey = h2i.parseImportFolderFile(None, csvFilepattern, importFolderPath,
key2=csvFilename + ".hex", timeoutSecs=timeoutSecs,
retryDelaySecs=retryDelaySecs,
pollTimeoutSecs=pollTimeoutSecs,
noPoll=noPoll,
benchmarkLogging=benchmarkLogging)
if noPoll:
if (i+1) < len(csvFilenameList):
time.sleep(1)
h2o.check_sandbox_for_errors()
(csvFilepattern, csvFilename, totalBytes2, timeoutSecs) = csvFilenameList[i+1]
parseKey = h2i.parseImportFolderFile(None, csvFilepattern, importFolderPath,
key2=csvFilename + ".hex", timeoutSecs=timeoutSecs,
retryDelaySecs=retryDelaySecs,
pollTimeoutSecs=pollTimeoutSecs,
noPoll=noPoll,
benchmarkLogging=benchmarkLogging)
if (i+2) < len(csvFilenameList):
time.sleep(1)
h2o.check_sandbox_for_errors()
(csvFilepattern, csvFilename, totalBytes3, timeoutSecs) = csvFilenameList[i+2]
parseKey = h2i.parseImportFolderFile(None, csvFilepattern, importFolderPath,
key2=csvFilename + ".hex", timeoutSecs=timeoutSecs,
retryDelaySecs=retryDelaySecs,
pollTimeoutSecs=pollTimeoutSecs,
noPoll=noPoll,
benchmarkLogging=benchmarkLogging)
elapsed = time.time() - start
print "Parse #", trial, "completed in", "%6.2f" % elapsed, "seconds.", \
"%d pct. of timeout" % ((elapsed*100)/timeoutSecs)
# print stats on all three if noPoll
if noPoll:
# does it take a little while to show up in Jobs, from where we issued the parse?
time.sleep(2)
# FIX! use the last (biggest?) timeoutSecs? maybe should increase since parallel
h2o_jobs.pollWaitJobs(pattern=csvFilename,
timeoutSecs=timeoutSecs, benchmarkLogging=benchmarkLogging)
# for getting the MB/sec closer to 'right'
totalBytes += totalBytes2 + totalBytes3
elapsed = time.time() - start
h2o.check_sandbox_for_errors()
if totalBytes is not None:
fileMBS = (totalBytes/1e6)/elapsed
l = '{!s} jvms, {!s}GB heap, {:s} {:s} {:6.2f} MB/sec for {:.2f} secs'.format(
len(h2o.nodes), tryHeap, csvFilepattern, csvFilename, fileMBS, elapsed)
print l
h2o.cloudPerfH2O.message(l)
print csvFilepattern, 'parse time:', parseKey['response']['time']
print "Parse result['destination_key']:", parseKey['destination_key']
# BUG here?
if not noPoll:
# We should be able to see the parse result?
h2o_cmd.check_enums_from_inspect(parseKey)
# the nflx data doesn't have a small enough # of classes in any col
# use exec to randomFilter out 200 rows for a quick RF. that should work for everyone?
origKey = parseKey['destination_key']
# execExpr = 'a = randomFilter('+origKey+',200,12345678)'
execExpr = 'a = slice('+origKey+',1,200)'
h2e.exec_expr(h2o.nodes[0], execExpr, "a", timeoutSecs=30)
# runRFOnly takes the parseKey directly
newParseKey = {'destination_key': 'a'}
print "\n" + csvFilepattern
# poker and the water.UDP.set3(UDP.java) fail issue..
# constrain depth to 25
print "Temporarily hacking to do nothing instead of RF on the parsed file"
### RFview = h2o_cmd.runRFOnly(trees=1,depth=25,parseKey=newParseKey, timeoutSecs=timeoutSecs)
### h2b.browseJsonHistoryAsUrlLastMatch("RFView")
#**********************************************************************************
# Do GLM too
# Argument case error: Value 0.0 is not between 12.0 and 9987.0 (inclusive)
if DO_GLM:
# these are all the columns that are enums in the dataset...too many for GLM!
x = range(542) # don't include the output column
# remove the output too! (378)
for i in [3, 4, 5, 6, 7, 8, 9, 10, 11, 14, 16, 17, 18, 19, 20, 424, 425, 426, 540, 541, 378]:
x.remove(i)
x = ",".join(map(str,x))
GLMkwargs = {'x': x, 'y': 378, 'case': 15, 'case_mode': '>',
'max_iter': 10, 'n_folds': 1, 'alpha': 0.2, 'lambda': 1e-5}
start = time.time()
glm = h2o_cmd.runGLMOnly(parseKey=parseKey, timeoutSecs=timeoutSecs, **GLMkwargs)
h2o_glm.simpleCheckGLM(self, glm, None, **GLMkwargs)
elapsed = time.time() - start
h2o.check_sandbox_for_errors()
l = '{:d} jvms, {:d}GB heap, {:s} {:s} GLM: {:6.2f} secs'.format(
len(h2o.nodes), tryHeap, csvFilepattern, csvFilename, elapsed)
print l
h2o.cloudPerfH2O.message(l)
#**********************************************************************************
h2o_cmd.checkKeyDistribution()
h2o_cmd.deleteCsvKey(csvFilename, importFolderResult)
### time.sleep(3600)
h2o.tear_down_cloud()
if not localhost:
print "Waiting 30 secs before building cloud again (sticky ports?)"
### time.sleep(30)
sys.stdout.write('.')
sys.stdout.flush()
def test_benchmark_import(self):
# typical size of the michal files
avgMichalSizeUncompressed = 237270000
avgMichalSize = 116561140
avgSynSize = 4020000
covtype200xSize = 15033863400
synSize = 183
if 1==1:
# importFolderPath = '/home/0xdiag/datasets/more1_1200_link'
# importFolderPathFull = '/home/0xdiag/datasets/manyfiles-nflx-gz'
# importFolderPath = 'more1_1200_link'
importFolderPath = 'manyfiles-nflx-gz'
print "Using .gz'ed files in", importFolderPath
# this pattern from browser correctly does 100 files, 1M rowsj
# source_key=*/home/0xdiag/datasets/manyfiles-nflx-gz/file_1[0-9][0-9].dat.gz
csvFilenameAll = [
("file_1.dat.gz", "file_1_A.dat.gz", 1 * avgMichalSize, 3600),
("file_[1-2].dat.gz", "file_2_A.dat.gz", 2 * avgMichalSize, 3600),
("file_[1-4].dat.gz", "file_4_A.dat.gz", 4 * avgMichalSize, 3600),
]
# csvFilenameList = random.sample(csvFilenameAll,1)
csvFilenameList = csvFilenameAll
# split out the pattern match and the filename used for the hex
trialMax = 1
# rebuild the cloud for each file
base_port = 54321
# can fire a parse off and go wait on the jobs queue (inspect afterwards is enough?)
DO_GLM = False
noPoll = False
# benchmarkLogging = ['cpu','disk', 'iostats', 'jstack']
# benchmarkLogging = None
benchmarkLogging = ['cpu','disk', 'network', 'iostats', 'jstack']
benchmarkLogging = ['cpu','disk', 'network', 'iostats']
# IOStatus can hang?
benchmarkLogging = ['cpu', 'disk' 'network']
pollTimeoutSecs = 180
retryDelaySecs = 10
localhost = h2o.decide_if_localhost()
if localhost:
tryHeap = 4
h2o.build_cloud(2,java_heap_GB=tryHeap, base_port=base_port, enable_benchmark_log=True)
else:
tryHeap = 28
h2o_hosts.build_cloud_with_hosts(1, java_heap_GB=tryHeap, base_port=base_port,
enable_benchmark_log=True)
for i,(csvFilepattern, csvFilename, totalBytes, timeoutSecs) in enumerate(csvFilenameList):
# pop open a browser on the cloud
### h2b.browseTheCloud()
# to avoid sticky ports?
### base_port += 2
h2o.beta_features = True
for trial in range(trialMax):
# (importResult, importPattern) = h2i.import_only(path=importFolderPath+"/*")
if DO_IMPORT_CHECK:
for i in range(2):
csvPathname = importFolderPath + "/" + csvFilepattern
(importResult, importPattern) = h2i.import_only(bucket='home-0xdiag-datasets',
path=csvPathname, schema='local', timeoutSecs=timeoutSecs)
importFullList = importResult['files']
importFailList = importResult['fails']
print "\n Problem if this is not empty: importFailList:", h2o.dump_json(importFailList)
# creates csvFilename.hex from file in importFolder dir
h2o.cloudPerfH2O.change_logfile(csvFilename)
h2o.cloudPerfH2O.message("")
h2o.cloudPerfH2O.message("Parse " + csvFilename + " Start--------------------------------")
csvPathname = importFolderPath + "/" + csvFilepattern
start = time.time()
parseResult = h2i.import_parse(bucket='home-0xdiag-datasets', path=csvPathname, schema='local',
hex_key=csvFilename + ".hex", timeoutSecs=timeoutSecs,
retryDelaySecs=retryDelaySecs,
pollTimeoutSecs=pollTimeoutSecs,
noPoll=noPoll,
benchmarkLogging=benchmarkLogging)
elapsed = time.time() - start
print "Parse#", trial, parseResult['destination_key'], "took", elapsed, "seconds",\
"%d pct. of timeout" % ((elapsed*100)/timeoutSecs)
inspect = h2o_cmd.runInspect(None, parseResult['destination_key'], timeoutSecs=360)
h2o_cmd.infoFromInspect(inspect, csvPathname)
if noPoll:
if (i+1) < len(csvFilenameList):
h2o.check_sandbox_for_errors()
(csvFilepattern, csvFilename, totalBytes2, timeoutSecs) = csvFilenameList[i+1]
# parseResult = h2i.import_parse(path=importFolderPath + "/" + csvFilepattern,
csvPathname = importFolderPathFull + "/" + csvFilepattern
start = time.time()
parseResult = h2i.import_parse(path=csvPathname,
hex_key=csvFilename + ".hex",
timeoutSecs=timeoutSecs,
retryDelaySecs=retryDelaySecs,
pollTimeoutSecs=pollTimeoutSecs,
noPoll=noPoll,
benchmarkLogging=benchmarkLogging)
elapsed = time.time() - start
print "Parse#", trial, parseResult['destination_key'], "took", elapsed, "seconds",\
"%d pct. of timeout" % ((elapsed*100)/timeoutSecs)
inspect = h2o_cmd.runInspect(None, parseResult['destination_key'], timeoutSecs=360)
h2o_cmd.infoFromInspect(inspect, csvPathname)
if (i+2) < len(csvFilenameList):
h2o.check_sandbox_for_errors()
(csvFilepattern, csvFilename, totalBytes3, timeoutSecs) = csvFilenameList[i+2]
csvPathname = importFolderPathFull + "/" + csvFilepattern
parseResult = h2i.import_parse(path=csvPathname,
hex_key=csvFilename + ".hex", timeoutSecs=timeoutSecs,
retryDelaySecs=retryDelaySecs,
pollTimeoutSecs=pollTimeoutSecs,
noPoll=noPoll,
benchmarkLogging=benchmarkLogging)
elapsed = time.time() - start
print "Parse#", trial, parseResult['destination_key'], "took", elapsed, "seconds",\
"%d pct. of timeout" % ((elapsed*100)/timeoutSecs)
inspect = h2o_cmd.runInspect(None, parseResult['destination_key'], timeoutSecs=360)
h2o_cmd.infoFromInspect(inspect, csvPathname)
# print stats on all three if noPoll
if noPoll:
# does it take a little while to show up in Jobs, from where we issued the parse?
time.sleep(2)
# FIX! use the last (biggest?) timeoutSecs? maybe should increase since parallel
h2o_jobs.pollWaitJobs(pattern=csvFilename,
timeoutSecs=timeoutSecs, benchmarkLogging=benchmarkLogging)
# for getting the MB/sec closer to 'right'
totalBytes += totalBytes2 + totalBytes3
elapsed = time.time() - start
h2o.check_sandbox_for_errors()
if totalBytes is not None:
fileMBS = (totalBytes/1e6)/elapsed
l = '{!s} jvms, {!s}GB heap, {:s} {:s} {:6.2f} MB/sec for {:.2f} secs'.format(
len(h2o.nodes), tryHeap, csvFilepattern, csvFilename, fileMBS, elapsed)
print l
h2o.cloudPerfH2O.message(l)
print csvFilepattern, 'parse time:', parseResult['response']['time']
print "Parse result['destination_key']:", parseResult['destination_key']
# BUG here?
if not noPoll:
pass
# We should be able to see the parse result?
# h2o_cmd.check_enums_from_inspect(parseResult)
# the nflx data doesn't have a small enough # of classes in any col
# use exec to randomFilter out 200 rows for a quick RF. that should work for everyone?
origKey = parseResult['destination_key']
# execExpr = 'a = randomFilter('+origKey+',200,12345678)'
execExpr = 'a = slice('+origKey+',1,200)'
# h2e.exec_expr(h2o.nodes[0], execExpr, "a", timeoutSecs=30)
# runRF takes the parseResult directly
newParseKey = {'destination_key': 'a'}
print "\n" + csvFilepattern
# poker and the water.UDP.set3(UDP.java) fail issue..
# constrain depth to 25
print "Temporarily hacking to do nothing instead of RF on the parsed file"
### RFview = h2o_cmd.runRF(trees=1,depth=25,parseResult=newParseKey, timeoutSecs=timeoutSecs)
### h2b.browseJsonHistoryAsUrlLastMatch("RFView")
#**********************************************************************************
# Do GLM too
# Argument case error: Value 0.0 is not between 12.0 and 9987.0 (inclusive)
if DO_GLM:
# these are all the columns that are enums in the dataset...too many for GLM!
x = range(542) # don't include the output column
# remove the output too! (378)
for i in [3, 4, 5, 6, 7, 8, 9, 10, 11, 14, 16, 17, 18, 19, 20, 424, 425, 426, 540, 541, 378]:
x.remove(i)
x = ",".join(map(str,x))
GLMkwargs = {'x': x, 'y': 378, 'case': 15, 'case_mode': '>',
'max_iter': 10, 'n_folds': 1, 'alpha': 0.2, 'lambda': 1e-5}
start = time.time()
glm = h2o_cmd.runGLM(parseResult=parseResult, timeoutSecs=timeoutSecs, **GLMkwargs)
h2o_glm.simpleCheckGLM(self, glm, None, **GLMkwargs)
elapsed = time.time() - start
h2o.check_sandbox_for_errors()
l = '{:d} jvms, {:d}GB heap, {:s} {:s} GLM: {:6.2f} secs'.format(
len(h2o.nodes), tryHeap, csvFilepattern, csvFilename, elapsed)
print l
h2o.cloudPerfH2O.message(l)
#**********************************************************************************
# print "Waiting 30 secs"
# time.sleep(30)
h2o_cmd.checkKeyDistribution()
h2i.delete_keys_from_import_result(pattern=csvFilename, importResult=importResult)
h2o.nodes[0].remove_all_keys()
### time.sleep(3600)
### h2o.tear_down_cloud()
if not localhost:
print "Waiting 30 secs before building cloud again (sticky ports?)"
### time.sleep(30)
sys.stdout.write('.')
sys.stdout.flush()
def sub_c3_nongz_fvec_long(self, csvFilenameList):
h2o.beta_features = True
# a kludge
h2o.setup_benchmark_log()
bucket = 'home-0xdiag-datasets'
importFolderPath = 'manyfiles-nflx'
print "Using nongz'ed files in", importFolderPath
if LOG_MACHINE_STATS:
benchmarkLogging = ['cpu', 'disk', 'network']
else:
benchmarkLogging = []
pollTimeoutSecs = 120
retryDelaySecs = 10
for trial, (csvFilepattern, csvFilename, totalBytes, timeoutSecs) in enumerate(csvFilenameList):
csvPathname = importFolderPath + "/" + csvFilepattern
if DO_DOUBLE_IMPORT:
(importResult, importPattern) = h2i.import_only(bucket=bucket, path=csvPathname, schema='local')
importFullList = importResult['files']
importFailList = importResult['fails']
print "\n Problem if this is not empty: importFailList:", h2o.dump_json(importFailList)
# this accumulates performance stats into a benchmark log over multiple runs
# good for tracking whether we're getting slower or faster
h2o.cloudPerfH2O.change_logfile(csvFilename)
h2o.cloudPerfH2O.message("")
h2o.cloudPerfH2O.message("Parse " + csvFilename + " Start--------------------------------")
start = time.time()
parseResult = h2i.import_parse(bucket=bucket, path=csvPathname, schema='local',
hex_key="A.hex", timeoutSecs=timeoutSecs,
retryDelaySecs=retryDelaySecs,
pollTimeoutSecs=pollTimeoutSecs,
benchmarkLogging=benchmarkLogging)
elapsed = time.time() - start
print "Parse #", trial, "completed in", "%6.2f" % elapsed, "seconds.", \
"%d pct. of timeout" % ((elapsed*100)/timeoutSecs)
print "Parse result['destination_key']:", parseResult['destination_key']
h2o_cmd.columnInfoFromInspect(parseResult['destination_key'], exceptionOnMissingValues=False)
fileMBS = (totalBytes/1e6)/elapsed
msg = '{!s} jvms, {!s}GB heap, {:s} {:s} {:6.2f} MB/sec for {:.2f} secs'.format(
len(h2o.nodes), h2o.nodes[0].java_heap_GB, csvFilepattern, csvFilename, fileMBS, elapsed)
print msg
h2o.cloudPerfH2O.message(msg)
h2o_cmd.checkKeyDistribution()
# are the unparsed keys slowing down exec?
h2i.delete_keys_at_all_nodes(pattern="manyfile")
execExpr = 'B.hex=A.hex'
h2e.exec_expr(execExpr=execExpr, timeoutSecs=180)
h2o_cmd.checkKeyDistribution()
execExpr = 'C.hex=B.hex'
h2e.exec_expr(execExpr=execExpr, timeoutSecs=180)
h2o_cmd.checkKeyDistribution()
execExpr = 'D.hex=C.hex'
h2e.exec_expr(execExpr=execExpr, timeoutSecs=180)
h2o_cmd.checkKeyDistribution()
def sub_c3_nongz_fvec_long(self, csvFilenameList):
h2o.beta_features = True
# a kludge
h2o.setup_benchmark_log()
bucket = "home-0xdiag-datasets"
importFolderPath = "manyfiles-nflx"
print "Using nongz'ed files in", importFolderPath
if LOG_MACHINE_STATS:
benchmarkLogging = ["cpu", "disk", "network"]
else:
benchmarkLogging = []
pollTimeoutSecs = 120
retryDelaySecs = 10
for trial, (csvFilepattern, csvFilename, totalBytes, timeoutSecs) in enumerate(csvFilenameList):
csvPathname = importFolderPath + "/" + csvFilepattern
if DO_DOUBLE_IMPORT:
(importResult, importPattern) = h2i.import_only(bucket=bucket, path=csvPathname, schema="local")
importFullList = importResult["files"]
importFailList = importResult["fails"]
print "\n Problem if this is not empty: importFailList:", h2o.dump_json(importFailList)
# this accumulates performance stats into a benchmark log over multiple runs
# good for tracking whether we're getting slower or faster
h2o.cloudPerfH2O.change_logfile(csvFilename)
h2o.cloudPerfH2O.message("")
h2o.cloudPerfH2O.message("Parse " + csvFilename + " Start--------------------------------")
start = time.time()
parseResult = h2i.import_parse(
bucket=bucket,
path=csvPathname,
schema="local",
hex_key="A.hex",
timeoutSecs=timeoutSecs,
retryDelaySecs=retryDelaySecs,
pollTimeoutSecs=pollTimeoutSecs,
benchmarkLogging=benchmarkLogging,
)
elapsed = time.time() - start
print "Parse #", trial, "completed in", "%6.2f" % elapsed, "seconds.", "%d pct. of timeout" % (
(elapsed * 100) / timeoutSecs
)
print "Parse result['destination_key']:", parseResult["destination_key"]
h2o_cmd.columnInfoFromInspect(parseResult["destination_key"], exceptionOnMissingValues=False)
if totalBytes is not None:
fileMBS = (totalBytes / 1e6) / elapsed
msg = "{!s} jvms, {!s}GB heap, {:s} {:s} {:6.2f} MB/sec for {:.2f} secs".format(
len(h2o.nodes), h2o.nodes[0].java_heap_GB, csvFilepattern, csvFilename, fileMBS, elapsed
)
print msg
h2o.cloudPerfH2O.message(msg)
if DO_GLM:
# remove the output too! (378)
ignore_x = [3, 4, 5, 6, 7, 8, 9, 10, 11, 14, 16, 17, 18, 19, 20, 424, 425, 426, 540, 541]
ignore_x = ",".join(map(lambda x: "C" + str(x + 1), ignore_x))
GLMkwargs = {
"ignored_cols": ignore_x,
"response": "C379",
"max_iter": 10,
"n_folds": 1,
"family": "binomial",
"alpha": 0.2,
"lambda": 1e-5,
}
# convert to binomial
# execExpr="A.hex=%s" % parseResult['destination_key']
# h2e.exec_expr(execExpr=execExpr, timeoutSecs=180)
# are the unparsed keys slowing down exec?
h2i.delete_keys_at_all_nodes(pattern="manyfile")
execExpr = "A.hex[,378+1]=(A.hex[,378+1]>15)"
h2e.exec_expr(execExpr=execExpr, timeoutSecs=180)
aHack = {"destination_key": "A.hex"}
start = time.time()
glm = h2o_cmd.runGLM(parseResult=aHack, timeoutSecs=timeoutSecs, **GLMkwargs)
elapsed = time.time() - start
h2o.check_sandbox_for_errors()
h2o_glm.simpleCheckGLM(self, glm, None, **GLMkwargs)
msg = "{:d} jvms, {:d}GB heap, {:s} {:s} GLM: {:6.2f} secs".format(
len(h2o.nodes), h2o.nodes[0].java_heap_GB, csvFilepattern, csvFilename, elapsed
)
print msg
h2o.cloudPerfH2O.message(msg)
h2o_cmd.checkKeyDistribution()
def sub_c3_nongz_fvec_long(self, csvFilenameList):
# a kludge
h2o.setup_benchmark_log()
bucket = 'home-0xdiag-datasets'
importFolderPath = 'manyfiles-nflx'
print "Using nongz'ed files in", importFolderPath
if LOG_MACHINE_STATS:
benchmarkLogging = ['cpu', 'disk', 'network']
else:
benchmarkLogging = []
pollTimeoutSecs = 120
retryDelaySecs = 10
for trial, (csvFilepattern, csvFilename, totalBytes, timeoutSecs) in enumerate(csvFilenameList):
csvPathname = importFolderPath + "/" + csvFilepattern
if DO_DOUBLE_IMPORT:
(importResult, importPattern) = h2i.import_only(bucket=bucket, path=csvPathname, schema='local')
importFullList = importResult['files']
importFailList = importResult['fails']
print "\n Problem if this is not empty: importFailList:", h2o.dump_json(importFailList)
# this accumulates performance stats into a benchmark log over multiple runs
# good for tracking whether we're getting slower or faster
h2o.cloudPerfH2O.change_logfile(csvFilename)
h2o.cloudPerfH2O.message("")
h2o.cloudPerfH2O.message("Parse " + csvFilename + " Start--------------------------------")
start = time.time()
parseResult = h2i.import_parse(bucket=bucket, path=csvPathname, schema='local',
hex_key="A.hex", timeoutSecs=timeoutSecs,
retryDelaySecs=retryDelaySecs,
pollTimeoutSecs=pollTimeoutSecs,
benchmarkLogging=benchmarkLogging)
elapsed = time.time() - start
print "Parse #", trial, "completed in", "%6.2f" % elapsed, "seconds.", \
"%d pct. of timeout" % ((elapsed*100)/timeoutSecs)
print "Parse result['destination_key']:", parseResult['destination_key']
h2o_cmd.columnInfoFromInspect(parseResult['destination_key'], exceptionOnMissingValues=False)
fileMBS = (totalBytes/1e6)/elapsed
msg = '{!s} jvms, {!s}GB heap, {:s} {:s} {:6.2f} MB/sec for {:.2f} secs'.format(
len(h2o.nodes), h2o.nodes[0].java_heap_GB, csvFilepattern, csvFilename, fileMBS, elapsed)
print msg
h2o.cloudPerfH2O.message(msg)
h2o_cmd.checkKeyDistribution()
# are the unparsed keys slowing down exec?
h2i.delete_keys_at_all_nodes(pattern="manyfile")
execExpr = 'B.hex=A.hex'
h2e.exec_expr(execExpr=execExpr, timeoutSecs=180)
h2o_cmd.checkKeyDistribution()
execExpr = 'C.hex=B.hex'
h2e.exec_expr(execExpr=execExpr, timeoutSecs=180)
h2o_cmd.checkKeyDistribution()
execExpr = 'D.hex=C.hex'
h2e.exec_expr(execExpr=execExpr, timeoutSecs=180)
h2o_cmd.checkKeyDistribution()
def test_benchmark_import(self):
covtype200xSize = 15033863400
csvFilenameList = [
("covtype200x.data", "covtype200x.data", covtype200xSize, 700),
]
trialMax = 1
base_port = 54321
tryHeap = 28
# can fire a parse off and go wait on the jobs queue (inspect afterwards is enough?)
DO_GLM = False
noPoll = False
benchmarkLogging = ['cpu', 'disk' 'network']
pollTimeoutSecs = 120
retryDelaySecs = 10
for i,(csvFilepattern, csvFilename, totalBytes, timeoutSecs) in enumerate(csvFilenameList):
localhost = h2o.decide_if_localhost()
if (localhost):
h2o.build_cloud(2,java_heap_GB=tryHeap, base_port=base_port,
enable_benchmark_log=True)
else:
h2o_hosts.build_cloud_with_hosts(1, java_heap_GB=tryHeap/2, base_port=base_port,
enable_benchmark_log=True)
for trial in range(trialMax):
csvPathname = "/home/0xdiag/datasets/standard/" + csvFilepattern
h2o.cloudPerfH2O.change_logfile(csvFilename)
h2o.cloudPerfH2O.message("")
h2o.cloudPerfH2O.message("Parse " + csvFilename + " Start--------------------------------")
start = time.time()
parseKey = h2o_cmd.parseFile(csvPathname=csvPathname,
key2=csvFilename + ".hex", timeoutSecs=timeoutSecs,
retryDelaySecs=retryDelaySecs,
pollTimeoutSecs=pollTimeoutSecs,
noPoll=noPoll,
benchmarkLogging=benchmarkLogging)
elapsed = time.time() - start
print "Parse #", trial, "completed in", "%6.2f" % elapsed, "seconds.", \
"%d pct. of timeout" % ((elapsed*100)/timeoutSecs)
if noPoll:
# does it take a little while to show up in Jobs, from where we issued the parse?
time.sleep(2)
# FIX! use the last (biggest?) timeoutSecs? maybe should increase since parallel
h2o_jobs.pollWaitJobs(pattern=csvFilename,
timeoutSecs=timeoutSecs, benchmarkLogging=benchmarkLogging)
# for getting the MB/sec closer to 'right'
totalBytes += totalBytes2 + totalBytes3
elapsed = time.time() - start
h2o.check_sandbox_for_errors()
if totalBytes is not None:
fileMBS = (totalBytes/1e6)/elapsed
l = '{!s} jvms, {!s}GB heap, {:s} {:s} {:6.2f} MB/sec for {:.2f} secs'.format(
len(h2o.nodes), tryHeap, csvFilepattern, csvFilename, fileMBS, elapsed)
print l
h2o.cloudPerfH2O.message(l)
print csvFilepattern, 'parse time:', parseKey['response']['time']
print "Parse result['destination_key']:", parseKey['destination_key']
# BUG here?
if not noPoll:
# We should be able to see the parse result?
h2o_cmd.check_enums_from_inspect(parseKey)
# use exec to randomFilter out 200 rows for a quick RF. that should work for everyone?
origKey = parseKey['destination_key']
# execExpr = 'a = randomFilter('+origKey+',200,12345678)'
execExpr = 'a = slice('+origKey+',1,200)'
h2e.exec_expr(h2o.nodes[0], execExpr, "a", timeoutSecs=30)
# runRFOnly takes the parseKey directly
newParseKey = {'destination_key': 'a'}
print "\n" + csvFilepattern
#**********************************************************************************
if DO_GLM:
# these are all the columns that are enums in the dataset...too many for GLM!
x = range(54) # don't include the output column
x = ",".join(map(str,x))
GLMkwargs = {'x': x, 'y': 54, 'case': 1, 'case_mode': '>',
'max_iter': 10, 'n_folds': 1, 'alpha': 0.2, 'lambda': 1e-5}
start = time.time()
glm = h2o_cmd.runGLMOnly(parseKey=parseKey, timeoutSecs=timeoutSecs, **GLMkwargs)
h2o_glm.simpleCheckGLM(self, glm, None, **GLMkwargs)
elapsed = time.time() - start
h2o.check_sandbox_for_errors()
l = '{:d} jvms, {:d}GB heap, {:s} {:s} GLM: {:6.2f} secs'.format(
len(h2o.nodes), tryHeap, csvFilepattern, csvFilename, elapsed)
print l
h2o.cloudPerfH2O.message(l)
#**********************************************************************************
h2o_cmd.checkKeyDistribution()
h2o.tear_down_cloud()
sys.stdout.write('.')
sys.stdout.flush()
def test_parse_manyfiles_fvec(self):
# typical size of the michal files
avgMichalSizeUncompressed = 237270000
avgMichalSize = 116561140
avgSynSize = 4020000
covtype200xSize = 15033863400
synSize = 183
if 1==1:
# importFolderPath = '/home/0xdiag/datasets/more1_1200_link'
# importFolderPathFull = '/home/0xdiag/datasets/manyfiles-nflx-gz'
# importFolderPath = 'more1_1200_link'
importFolderPath = 'manyfiles-nflx-gz'
print "Using .gz'ed files in", importFolderPath
# this pattern from browser correctly does 100 files, 1M rowsj
# source_key=*/home/0xdiag/datasets/manyfiles-nflx-gz/file_1[0-9][0-9].dat.gz
csvFilenameAll = [
("file_1.dat.gz", "file_1_A.dat.gz", 1 * avgMichalSize, 3600),
("file_[1-2].dat.gz", "file_2_A.dat.gz", 2 * avgMichalSize, 3600),
("file_[1-4].dat.gz", "file_4_A.dat.gz", 4 * avgMichalSize, 3600),
]
# csvFilenameList = random.sample(csvFilenameAll,1)
csvFilenameList = csvFilenameAll
# split out the pattern match and the filename used for the hex
trialMax = 1
# rebuild the cloud for each file
# can fire a parse off and go wait on the jobs queue (inspect afterwards is enough?)
DO_GLM = False
noPoll = False
# benchmarkLogging = ['cpu','disk', 'iostats', 'jstack']
# benchmarkLogging = None
benchmarkLogging = ['cpu','disk', 'network', 'iostats', 'jstack']
benchmarkLogging = ['cpu','disk', 'network', 'iostats']
# IOStatus can hang?
benchmarkLogging = ['cpu', 'disk' 'network']
pollTimeoutSecs = 180
retryDelaySecs = 10
tryHeap = 6
h2o.init(2, java_heap_GB=tryHeap, enable_benchmark_log=True)
for i,(csvFilepattern, csvFilename, totalBytes, timeoutSecs) in enumerate(csvFilenameList):
# pop open a browser on the cloud
### h2b.browseTheCloud()
# to avoid sticky ports?
for trial in range(trialMax):
# (importResult, importPattern) = h2i.import_only(path=importFolderPath+"/*")
if DO_IMPORT_CHECK:
for i in range(2):
csvPathname = importFolderPath + "/" + csvFilepattern
(importResult, importPattern) = h2i.import_only(bucket='home-0xdiag-datasets',
path=csvPathname, schema='local', timeoutSecs=timeoutSecs)
importFullList = importResult['files']
importFailList = importResult['fails']
print "\n Problem if this is not empty: importFailList:", h2o.dump_json(importFailList)
# creates csvFilename.hex from file in importFolder dir
h2o.cloudPerfH2O.change_logfile(csvFilename)
h2o.cloudPerfH2O.message("")
h2o.cloudPerfH2O.message("Parse " + csvFilename + " Start--------------------------------")
csvPathname = importFolderPath + "/" + csvFilepattern
start = time.time()
parseResult = h2i.import_parse(bucket='home-0xdiag-datasets', path=csvPathname, schema='local',
hex_key=csvFilename + ".hex", timeoutSecs=timeoutSecs,
retryDelaySecs=retryDelaySecs,
pollTimeoutSecs=pollTimeoutSecs,
noPoll=noPoll,
benchmarkLogging=benchmarkLogging)
elapsed = time.time() - start
print "Parse#", trial, parseResult['destination_key'], "took", elapsed, "seconds",\
"%d pct. of timeout" % ((elapsed*100)/timeoutSecs)
inspect = h2o_cmd.runInspect(None, parseResult['destination_key'], timeoutSecs=360)
h2o_cmd.infoFromInspect(inspect, csvPathname)
if noPoll:
if (i+1) < len(csvFilenameList):
h2o.check_sandbox_for_errors()
(csvFilepattern, csvFilename, totalBytes2, timeoutSecs) = csvFilenameList[i+1]
# parseResult = h2i.import_parse(path=importFolderPath + "/" + csvFilepattern,
csvPathname = importFolderPathFull + "/" + csvFilepattern
start = time.time()
parseResult = h2i.import_parse(path=csvPathname,
hex_key=csvFilename + ".hex",
timeoutSecs=timeoutSecs,
retryDelaySecs=retryDelaySecs,
pollTimeoutSecs=pollTimeoutSecs,
noPoll=noPoll,
benchmarkLogging=benchmarkLogging)
elapsed = time.time() - start
print "Parse#", trial, parseResult['destination_key'], "took", elapsed, "seconds",\
"%d pct. of timeout" % ((elapsed*100)/timeoutSecs)
inspect = h2o_cmd.runInspect(None, parseResult['destination_key'], timeoutSecs=360)
h2o_cmd.infoFromInspect(inspect, csvPathname)
if (i+2) < len(csvFilenameList):
h2o.check_sandbox_for_errors()
(csvFilepattern, csvFilename, totalBytes3, timeoutSecs) = csvFilenameList[i+2]
csvPathname = importFolderPathFull + "/" + csvFilepattern
parseResult = h2i.import_parse(path=csvPathname,
hex_key=csvFilename + ".hex", timeoutSecs=timeoutSecs,
retryDelaySecs=retryDelaySecs,
pollTimeoutSecs=pollTimeoutSecs,
noPoll=noPoll,
benchmarkLogging=benchmarkLogging)
elapsed = time.time() - start
print "Parse#", trial, parseResult['destination_key'], "took", elapsed, "seconds",\
"%d pct. of timeout" % ((elapsed*100)/timeoutSecs)
inspect = h2o_cmd.runInspect(None, parseResult['destination_key'], timeoutSecs=360)
h2o_cmd.infoFromInspect(inspect, csvPathname)
# print stats on all three if noPoll
if noPoll:
# does it take a little while to show up in Jobs, from where we issued the parse?
time.sleep(2)
# FIX! use the last (biggest?) timeoutSecs? maybe should increase since parallel
h2o_jobs.pollWaitJobs(pattern=csvFilename,
timeoutSecs=timeoutSecs, benchmarkLogging=benchmarkLogging)
# for getting the MB/sec closer to 'right'
totalBytes += totalBytes2 + totalBytes3
elapsed = time.time() - start
h2o.check_sandbox_for_errors()
if totalBytes is not None:
fileMBS = (totalBytes/1e6)/elapsed
l = '{!s} jvms, {!s}GB heap, {:s} {:s} {:6.2f} MB/sec for {:.2f} secs'.format(
len(h2o.nodes), tryHeap, csvFilepattern, csvFilename, fileMBS, elapsed)
print l
h2o.cloudPerfH2O.message(l)
print "Parse result['destination_key']:", parseResult['destination_key']
# BUG here?
if not noPoll:
pass
# We should be able to see the parse result?
# h2o_cmd.check_enums_from_inspect(parseResult)
# the nflx data doesn't have a small enough # of classes in any col
# use exec to randomFilter out 200 rows for a quick RF. that should work for everyone?
origKey = parseResult['destination_key']
# execExpr = 'a = randomFilter('+origKey+',200,12345678)'
execExpr = 'a = slice('+origKey+',1,200)'
# h2e.exec_expr(h2o.nodes[0], execExpr, "a", timeoutSecs=30)
# runRF takes the parseResult directly
newParseKey = {'destination_key': 'a'}
print "\n" + csvFilepattern
# poker and the water.UDP.set3(UDP.java) fail issue..
# constrain depth to 25
print "Temporarily hacking to do nothing instead of RF on the parsed file"
### RFview = h2o_cmd.runRF(trees=1,depth=25,parseResult=newParseKey, timeoutSecs=timeoutSecs)
### h2b.browseJsonHistoryAsUrlLastMatch("RFView")
#**********************************************************************************
# Do GLM too
# Argument case error: Value 0.0 is not between 12.0 and 9987.0 (inclusive)
if DO_GLM:
# these are all the columns that are enums in the dataset...too many for GLM!
x = range(542) # don't include the output column
# remove the output too! (378)
for i in [3, 4, 5, 6, 7, 8, 9, 10, 11, 14, 16, 17, 18, 19, 20, 424, 425, 426, 540, 541, 378]:
x.remove(i)
x = ",".join(map(str,x))
GLMkwargs = {'x': x, 'y': 378, 'case': 15, 'case_mode': '>',
'max_iter': 10, 'n_folds': 1, 'alpha': 0.2, 'lambda': 1e-5}
start = time.time()
glm = h2o_cmd.runGLM(parseResult=parseResult, timeoutSecs=timeoutSecs, **GLMkwargs)
h2o_glm.simpleCheckGLM(self, glm, None, **GLMkwargs)
elapsed = time.time() - start
h2o.check_sandbox_for_errors()
l = '{:d} jvms, {:d}GB heap, {:s} {:s} GLM: {:6.2f} secs'.format(
len(h2o.nodes), tryHeap, csvFilepattern, csvFilename, elapsed)
print l
h2o.cloudPerfH2O.message(l)
#**********************************************************************************
# print "Waiting 30 secs"
# time.sleep(30)
h2o_cmd.checkKeyDistribution()
h2i.delete_keys_from_import_result(pattern=csvFilename, importResult=importResult)
h2o.nodes[0].remove_all_keys()
### time.sleep(3600)
### h2o.tear_down_cloud()
if not h2o.localhost:
print "Waiting 30 secs before building cloud again (sticky ports?)"
### time.sleep(30)
sys.stdout.write('.')
sys.stdout.flush()
def sub_c2_nongz_fvec_long(self):
# a kludge
h2o.setup_benchmark_log()
avgMichalSize = 237270000
bucket = 'home-0xdiag-datasets'
### importFolderPath = 'more1_1200_link'
importFolderPath = 'manyfiles-nflx'
print "Using non-gz'ed files in", importFolderPath
csvFilenameList= [
("*[1][0-4][0-9].dat", "file_50_A.dat", 50 * avgMichalSize, 1800),
# ("*[1][0-9][0-9].dat", "file_100_A.dat", 100 * avgMichalSize, 3600),
]
if LOG_MACHINE_STATS:
benchmarkLogging = ['cpu', 'disk', 'network']
else:
benchmarkLogging = []
pollTimeoutSecs = 120
retryDelaySecs = 10
for trial, (csvFilepattern, csvFilename, totalBytes, timeoutSecs) in enumerate(csvFilenameList):
csvPathname = importFolderPath + "/" + csvFilepattern
# double import still causing problems?
# (importResult, importPattern) = h2i.import_only(bucket=bucket, path=csvPathname, schema='local')
# importFullList = importResult['files']
# importFailList = importResult['fails']
# print "\n Problem if this is not empty: importFailList:", h2o.dump_json(importFailList)
# this accumulates performance stats into a benchmark log over multiple runs
# good for tracking whether we're getting slower or faster
h2o.cloudPerfH2O.change_logfile(csvFilename)
h2o.cloudPerfH2O.message("")
h2o.cloudPerfH2O.message("Parse " + csvFilename + " Start--------------------------------")
start = time.time()
parseResult = h2i.import_parse(bucket=bucket, path=csvPathname, schema='local',
hex_key=csvFilename + ".hex", timeoutSecs=timeoutSecs,
retryDelaySecs=retryDelaySecs,
pollTimeoutSecs=pollTimeoutSecs,
benchmarkLogging=benchmarkLogging)
elapsed = time.time() - start
print "Parse #", trial, "completed in", "%6.2f" % elapsed, "seconds.", \
"%d pct. of timeout" % ((elapsed*100)/timeoutSecs)
print "Parse result['destination_key']:", parseResult['destination_key']
h2o_cmd.columnInfoFromInspect(parseResult['destination_key'], exceptionOnMissingValues=False)
if totalBytes is not None:
fileMBS = (totalBytes/1e6)/elapsed
msg = '{!s} jvms, {!s}GB heap, {:s} {:s} {:6.2f} MB/sec for {:.2f} secs'.format(
len(h2o.nodes), h2o.nodes[0].java_heap_GB, csvFilepattern, csvFilename, fileMBS, elapsed)
print msg
h2o.cloudPerfH2O.message(msg)
if DO_GLM:
# remove the output too! (378)
ignore_x = [3,4,5,6,7,8,9,10,11,14,16,17,18,19,20,424,425,426,540,541]
ignore_x = ",".join(map(lambda x: "C" + str(x+1), ignore_x))
GLMkwargs = {
'ignored_cols': ignore_x,
'family': 'binomial',
'response': 'C379',
'max_iter': 4,
'n_folds': 1,
'family': 'binomial',
'alpha': 0.2,
'lambda': 1e-5
}
# are the unparsed keys slowing down exec?
h2i.delete_keys_at_all_nodes(pattern="manyfile")
# convert to binomial
execExpr="A.hex=%s" % parseResult['destination_key']
h2e.exec_expr(execExpr=execExpr, timeoutSecs=180)
execExpr="A.hex[,%s]=(A.hex[,%s]>%s)" % ('379', '379', 15)
h2e.exec_expr(execExpr=execExpr, timeoutSecs=180)
aHack = {'destination_key': "A.hex"}
start = time.time()
glm = h2o_cmd.runGLM(parseResult=aHack, timeoutSecs=timeoutSecs, **GLMkwargs)
elapsed = time.time() - start
h2o.check_sandbox_for_errors()
h2o_glm.simpleCheckGLM(self, glm, None, **GLMkwargs)
msg = '{:d} jvms, {:d}GB heap, {:s} {:s} GLM: {:6.2f} secs'.format(
len(h2o.nodes), h2o.nodes[0].java_heap_GB, csvFilepattern, csvFilename, elapsed)
print msg
h2o.cloudPerfH2O.message(msg)
h2o_cmd.checkKeyDistribution()
def sub_c3_nongz_fvec_long(self, csvFilenameList):
# a kludge
h2o.setup_benchmark_log()
bucket = 'home-0xdiag-datasets'
importFolderPath = 'manyfiles-nflx'
print "Using nongz'ed files in", importFolderPath
if LOG_MACHINE_STATS:
benchmarkLogging = ['cpu', 'disk', 'network']
else:
benchmarkLogging = []
pollTimeoutSecs = 120
retryDelaySecs = 10
for trial, (csvFilepattern, csvFilename, totalBytes, timeoutSecs) in enumerate(csvFilenameList):
csvPathname = importFolderPath + "/" + csvFilepattern
if DO_DOUBLE_IMPORT:
(importResult, importPattern) = h2i.import_only(bucket=bucket, path=csvPathname, schema='local')
importFullList = importResult['files']
importFailList = importResult['fails']
print "\n Problem if this is not empty: importFailList:", h2o.dump_json(importFailList)
# this accumulates performance stats into a benchmark log over multiple runs
# good for tracking whether we're getting slower or faster
h2o.cloudPerfH2O.change_logfile(csvFilename)
h2o.cloudPerfH2O.message("")
h2o.cloudPerfH2O.message("Parse " + csvFilename + " Start--------------------------------")
start = time.time()
parseResult = h2i.import_parse(bucket=bucket, path=csvPathname, schema='local',
hex_key="A.hex", timeoutSecs=timeoutSecs,
retryDelaySecs=retryDelaySecs,
pollTimeoutSecs=pollTimeoutSecs,
benchmarkLogging=benchmarkLogging)
elapsed = time.time() - start
print "Parse #", trial, "completed in", "%6.2f" % elapsed, "seconds.", \
"%d pct. of timeout" % ((elapsed*100)/timeoutSecs)
print "Parse result['destination_key']:", parseResult['destination_key']
h2o_cmd.columnInfoFromInspect(parseResult['destination_key'], exceptionOnMissingValues=False)
if totalBytes is not None:
fileMBS = (totalBytes/1e6)/elapsed
msg = '{!s} jvms, {!s}GB heap, {:s} {:s} {:6.2f} MB/sec for {:.2f} secs'.format(
len(h2o.nodes), h2o.nodes[0].java_heap_GB, csvFilepattern, csvFilename, fileMBS, elapsed)
print msg
h2o.cloudPerfH2O.message(msg)
if DO_GLM:
# output 378 can't be in this
ignore_x = [3,4,5,6,7,8,9,10,11,14,16,17,18,19,20,424,425,426,540,541]
ignore_x = ",".join(map(lambda x: "C" + str(x+1), ignore_x))
GLMkwargs = {
'ignored_cols': ignore_x,
'response': 'C379',
'max_iter': 10,
'n_folds': 1,
'family': 'binomial',
'alpha': 0.2,
'lambda': 1e-5
}
# convert to binomial
# execExpr="A.hex=%s" % parseResult['destination_key']
# h2e.exec_expr(execExpr=execExpr, timeoutSecs=180)
# are the unparsed keys slowing down exec?
h2i.delete_keys_at_all_nodes(pattern="manyfile")
execExpr = 'A.hex[,378+1]=(A.hex[,378+1]>15)'
h2e.exec_expr(execExpr=execExpr, timeoutSecs=180)
aHack = {'destination_key': "A.hex"}
start = time.time()
glm = h2o_cmd.runGLM(parseResult=aHack, timeoutSecs=timeoutSecs, **GLMkwargs)
elapsed = time.time() - start
h2o.check_sandbox_for_errors()
h2o_glm.simpleCheckGLM(self, glm, None, **GLMkwargs)
msg = '{:d} jvms, {:d}GB heap, {:s} {:s} GLM: {:6.2f} secs'.format(
len(h2o.nodes), h2o.nodes[0].java_heap_GB, csvFilepattern, csvFilename, elapsed)
print msg
h2o.cloudPerfH2O.message(msg)
h2o_cmd.checkKeyDistribution()
def test_benchmark_import(self):
# typical size of the michal files
avgMichalSizeUncompressed = 237270000
avgMichalSize = 116561140
avgSynSize = 4020000
covtype200xSize = 15033863400
synSize = 183
if 1==0:
importFolderPath = '/home/0xdiag/datasets/more1_1200_link'
print "Using .gz'ed files in", importFolderPath
csvFilenameAll = [
# this should hit the "more" files too?
# ("*.dat.gz", "file_200.dat.gz", 1200 * avgMichalSize, 1800),
# ("*.dat.gz", "file_200.dat.gz", 1200 * avgMichalSize, 1800),
# ("*[1][0-2][0-9].dat.gz", "file_30.dat.gz", 50 * avgMichalSize, 1800),
("*file_[0-9][0-9].dat.gz", "file_100.dat.gz", 100 * avgMichalSize, 1800),
("*file_[12][0-9][0-9].dat.gz", "file_200_A.dat.gz", 200 * avgMichalSize, 1800),
("*file_[34][0-9][0-9].dat.gz", "file_200_B.dat.gz", 200 * avgMichalSize, 1800),
("*file_[56][0-9][0-9].dat.gz", "file_200_C.dat.gz", 200 * avgMichalSize, 1800),
("*file_[78][0-9][0-9].dat.gz", "file_200_D.dat.gz", 200 * avgMichalSize, 1800),
# ("*.dat.gz", "file_1200.dat.gz", 1200 * avgMichalSize, 3600),
]
if 1==1:
importFolderPath = '/home/0xdiag/datasets/more1_1200_link'
print "Using .gz'ed files in", importFolderPath
csvFilenameAll = [
# this should hit the "more" files too?
# ("*10[0-9].dat.gz", "file_10.dat.gz", 10 * avgMichalSize, 3600),
# ("*1[0-4][0-9].dat.gz", "file_50.dat.gz", 50 * avgMichalSize, 3600),
# ("*[1][0-9][0-9].dat.gz", "file_100.dat.gz", 100 * avgMichalSize, 3600),
# ("*3[0-9][0-9].dat.gz", "file_100.dat.gz", 100 * avgMichalSize, 3600),
# ("*1[0-9][0-9].dat.gz", "file_100.dat.gz", 100 * avgMichalSize, 1800),
#("*[1-2][0-9][0-9].dat.gz", "file_200.dat.gz", 200 * avgMichalSize, 3600),
# ("*[3-4][0-9][0-9].dat.gz", "file_200.dat.gz", 200 * avgMichalSize, 3600),
("*[3-4][0-4][0-9].dat.gz", "file_100_A.dat.gz", 100 * avgMichalSize, 3600),
("*[3-4][0-4][0-9].dat.gz", "file_100_B.dat.gz", 100 * avgMichalSize, 3600),
("*[3-4][0-5][0-9].dat.gz", "file_120_A.dat.gz", 120 * avgMichalSize, 3600),
("*[3-4][0-5][0-9].dat.gz", "file_120_B.dat.gz", 120 * avgMichalSize, 3600),
("*[3-4][0-6][0-9].dat.gz", "file_140_A.dat.gz", 140 * avgMichalSize, 3600),
("*[3-4][0-6][0-9].dat.gz", "file_140_B.dat.gz", 140 * avgMichalSize, 3600),
("*[3-4][0-7][0-9].dat.gz", "file_160_A.dat.gz", 160 * avgMichalSize, 3600),
("*[3-4][0-7][0-9].dat.gz", "file_160_B.dat.gz", 160 * avgMichalSize, 3600),
("*[3-4][0-8][0-9].dat.gz", "file_180_A.dat.gz", 180 * avgMichalSize, 3600),
("*[3-4][0-8][0-9].dat.gz", "file_180_B.dat.gz", 180 * avgMichalSize, 3600),
("*[3-4][0-9][0-9].dat.gz", "file_200_A.dat.gz", 200 * avgMichalSize, 3600),
("*[3-4][0-9][0-9].dat.gz", "file_200_B.dat.gz", 200 * avgMichalSize, 3600),
("*[3-5][0-9][0-9].dat.gz", "file_300.dat.gz", 300 * avgMichalSize, 3600),
("*[3-5][0-9][0-9].dat.gz", "file_300.dat.gz", 300 * avgMichalSize, 3600),
# for now, take too long on 2x100GB heap on 164
# ("*[3-6][0-9][0-9].dat.gz", "file_400.dat.gz", 400 * avgMichalSize, 3600),
# ("*[3-6][0-9][0-9].dat.gz", "file_400.dat.gz", 400 * avgMichalSize, 3600),
# ("*[3-6][0-9][0-9].dat.gz", "file_400.dat.gz", 400 * avgMichalSize, 3600),
# ("*[3-6][0-9][0-9].dat.gz", "file_400.dat.gz", 400 * avgMichalSize, 3600),
# ("*[3-6][0-9][0-9].dat.gz", "file_400.dat.gz", 400 * avgMichalSize, 3600),
# ("*[3-6][0-9][0-9].dat.gz", "file_400.dat.gz", 400 * avgMichalSize, 3600),
# ("*[3-6][0-9][0-9].dat.gz", "file_400.dat.gz", 400 * avgMichalSize, 3600),
# ("*[3-6][0-9][0-9].dat.gz", "file_400.dat.gz", 400 * avgMichalSize, 3600),
]
if 1==0:
importFolderPath = '/home/0xdiag/datasets/manyfiles-nflx-gz'
print "Using .gz'ed files in", importFolderPath
csvFilenameAll = [
# this should hit the "more" files too?
("*_[123][0-9][0-9]*.dat.gz", "file_300.dat.gz", 300 * avgMichalSize, 3600),
("*_[1][5-9][0-9]*.dat.gz", "file_100.dat.gz", 50 * avgMichalSize, 3600),
]
if 1==0:
importFolderPath = '/home2/0xdiag/datasets'
print "Using non-.gz'ed files in", importFolderPath
csvFilenameAll = [
# I use different files to avoid OS caching effects
("manyfiles-nflx/file_[0-9][0-9]*.dat", "file_100.dat", 100 * avgMichalSizeUncompressed, 700),
("manyfiles-nflx/file_[0-9][0-9]*.dat", "file_100.dat", 100 * avgMichalSizeUncompressed, 700),
("manyfiles-nflx/file_[0-9][0-9]*.dat", "file_100.dat", 100 * avgMichalSizeUncompressed, 700),
# ("onefile-nflx/file_1_to_100.dat", "file_single.dat", 100 * avgMichalSizeUncompressed, 1200),
# ("manyfiles-nflx/file_1.dat", "file_1.dat", 1 * avgMichalSizeUncompressed, 700),
# ("manyfiles-nflx/file_[2][0-9].dat", "file_10.dat", 10 * avgMichalSizeUncompressed, 700),
# ("manyfiles-nflx/file_[34][0-9].dat", "file_20.dat", 20 * avgMichalSizeUncompressed, 700),
# ("manyfiles-nflx/file_[5-9][0-9].dat", "file_50.dat", 50 * avgMichalSizeUncompressed, 700),
]
if 1==0:
importFolderPath = '/home/0xdiag/datasets/standard'
print "Using .gz'ed files in", importFolderPath
# all exactly the same prior to gzip!
# could use this, but remember import folder -> import folder s3 for jenkins?
# how would it get it right?
# os.path.getsize(f)
csvFilenameAll = [
# ("manyfiles-nflx-gz/file_1[0-9].dat.gz", "file_10.dat.gz", 700),
# 100 files takes too long on two machines?
# ("covtype200x.data", "covtype200x.data", 15033863400, 700),
# I use different files to avoid OS caching effects
# ("syn_datasets/syn_7350063254201195578_10000x200.csv_000[0-9][0-9]", "syn_100.csv", 100 * avgSynSize, 700),
# ("syn_datasets/syn_7350063254201195578_10000x200.csv_00000", "syn_1.csv", avgSynSize, 700),
# ("syn_datasets/syn_7350063254201195578_10000x200.csv_0001[0-9]", "syn_10.csv", 10 * avgSynSize, 700),
# ("syn_datasets/syn_7350063254201195578_10000x200.csv_000[23][0-9]", "syn_20.csv", 20 * avgSynSize, 700),
# ("syn_datasets/syn_7350063254201195578_10000x200.csv_000[45678][0-9]", "syn_50.csv", 50 * avgSynSize, 700),
# ("manyfiles-nflx-gz/file_10.dat.gz", "file_10_1.dat.gz", 1 * avgMichalSize, 700),
# ("manyfiles-nflx-gz/file_1[0-9].dat.gz", "file_10.dat.gz", 10 * avgMichalSize, 700),
("manyfiles-nflx-gz/file_1.dat.gz", "file_1.dat.gz", 1 * avgMichalSize, 700),
("manyfiles-nflx-gz/file_[2][0-9].dat.gz", "file_10.dat.gz", 10 * avgMichalSize, 700),
("manyfiles-nflx-gz/file_[34][0-9].dat.gz", "file_20.dat.gz", 20 * avgMichalSize, 700),
("manyfiles-nflx-gz/file_[5-9][0-9].dat.gz", "file_50.dat.gz", 50 * avgMichalSize, 700),
("manyfiles-nflx-gz/file_1[0-9][0-9].dat.gz", "file_100.dat.gz", 50 * avgMichalSize, 700),
("manyfiles-nflx-gz/file_[12][0-9][0-9].dat.gz", "file_200.dat.gz", 50 * avgMichalSize, 700),
("manyfiles-nflx-gz/file_[12]?[0-9][0-9].dat.gz", "file_300.dat.gz", 50 * avgMichalSize, 700),
("manyfiles-nflx-gz/file_*.dat.gz", "file_384.dat.gz", 100 * avgMichalSize, 1200),
("covtype200x.data", "covtype200x.data", covtype200xSize, 700),
# do it twice
# ("covtype.data", "covtype.data"),
# ("covtype20x.data", "covtype20x.data"),
# "covtype200x.data",
# "100million_rows.csv",
# "200million_rows.csv",
# "a5m.csv",
# "a10m.csv",
# "a100m.csv",
# "a200m.csv",
# "a400m.csv",
# "a600m.csv",
# "billion_rows.csv.gz",
# "new-poker-hand.full.311M.txt.gz",
]
# csvFilenameList = random.sample(csvFilenameAll,1)
csvFilenameList = csvFilenameAll
# split out the pattern match and the filename used for the hex
trialMax = 1
# rebuild the cloud for each file
base_port = 54321
tryHeap = 28
# can fire a parse off and go wait on the jobs queue (inspect afterwards is enough?)
DO_GLM = False
noPoll = False
# benchmarkLogging = ['cpu','disk', 'iostats', 'jstack']
# benchmarkLogging = None
benchmarkLogging = ['cpu','disk', 'network', 'iostats', 'jstack']
benchmarkLogging = ['cpu','disk', 'network', 'iostats']
# IOStatus can hang?
benchmarkLogging = ['cpu', 'disk', 'network']
pollTimeoutSecs = 120
retryDelaySecs = 10
jea = '-XX:MaxDirectMemorySize=512m -XX:+PrintGCDetails' + ' -Dh2o.find-ByteBuffer-leaks'
jea = '-XX:MaxDirectMemorySize=512m -XX:+PrintGCDetails'
jea = "-XX:+UseParNewGC -XX:+UseConcMarkSweepGC"
jea = ' -Dcom.sun.management.jmxremote.port=54330' + \
' -Dcom.sun.management.jmxremote.authenticate=false' + \
' -Dcom.sun.management.jmxremote.ssl=false' + \
' -Dcom.sun.management.jmxremote' + \
' -Dcom.sun.management.jmxremote.local.only=false'
jea = ' -Dlog.printAll=true'
for i,(csvFilepattern, csvFilename, totalBytes, timeoutSecs) in enumerate(csvFilenameList):
localhost = h2o.decide_if_localhost()
if (localhost):
h2o.build_cloud(2,java_heap_GB=tryHeap, base_port=base_port,
# java_extra_args=jea,
enable_benchmark_log=True)
else:
h2o_hosts.build_cloud_with_hosts(base_port=base_port,
# java_extra_args=jea,
enable_benchmark_log=True)
# pop open a browser on the cloud
### h2b.browseTheCloud()
# to avoid sticky ports?
### base_port += 2
for trial in range(trialMax):
importFolderResult = h2i.setupImportFolder(None, importFolderPath)
importFullList = importFolderResult['files']
importFailList = importFolderResult['fails']
print "\n Problem if this is not empty: importFailList:", h2o.dump_json(importFailList)
# creates csvFilename.hex from file in importFolder dir
h2o.cloudPerfH2O.change_logfile(csvFilename)
h2o.cloudPerfH2O.message("")
h2o.cloudPerfH2O.message("Parse " + csvFilename + " Start--------------------------------")
start = time.time()
parseKey = h2i.parseImportFolderFile(None, csvFilepattern, importFolderPath,
key2=csvFilename + ".hex", timeoutSecs=timeoutSecs,
retryDelaySecs=retryDelaySecs,
pollTimeoutSecs=pollTimeoutSecs,
noPoll=noPoll,
benchmarkLogging=benchmarkLogging)
if noPoll:
if (i+1) < len(csvFilenameList):
time.sleep(1)
h2o.check_sandbox_for_errors()
(csvFilepattern, csvFilename, totalBytes2, timeoutSecs) = csvFilenameList[i+1]
parseKey = h2i.parseImportFolderFile(None, csvFilepattern, importFolderPath,
key2=csvFilename + ".hex", timeoutSecs=timeoutSecs,
retryDelaySecs=retryDelaySecs,
pollTimeoutSecs=pollTimeoutSecs,
noPoll=noPoll,
benchmarkLogging=benchmarkLogging)
if (i+2) < len(csvFilenameList):
time.sleep(1)
h2o.check_sandbox_for_errors()
(csvFilepattern, csvFilename, totalBytes3, timeoutSecs) = csvFilenameList[i+2]
parseKey = h2i.parseImportFolderFile(None, csvFilepattern, importFolderPath,
key2=csvFilename + ".hex", timeoutSecs=timeoutSecs,
retryDelaySecs=retryDelaySecs,
pollTimeoutSecs=pollTimeoutSecs,
noPoll=noPoll,
benchmarkLogging=benchmarkLogging)
elapsed = time.time() - start
print "Parse #", trial, "completed in", "%6.2f" % elapsed, "seconds.", \
"%d pct. of timeout" % ((elapsed*100)/timeoutSecs)
# print stats on all three if noPoll
if noPoll:
# does it take a little while to show up in Jobs, from where we issued the parse?
time.sleep(2)
# FIX! use the last (biggest?) timeoutSecs? maybe should increase since parallel
h2o_jobs.pollWaitJobs(pattern=csvFilename,
timeoutSecs=timeoutSecs, benchmarkLogging=benchmarkLogging)
# for getting the MB/sec closer to 'right'
totalBytes += totalBytes2 + totalBytes3
elapsed = time.time() - start
h2o.check_sandbox_for_errors()
if totalBytes is not None:
fileMBS = (totalBytes/1e6)/elapsed
l = '{!s} jvms, {!s}GB heap, {:s} {:s} {:6.2f} MB/sec for {:.2f} secs'.format(
len(h2o.nodes), h2o.nodes[0].java_heap_GB, csvFilepattern, csvFilename, fileMBS, elapsed)
print l
h2o.cloudPerfH2O.message(l)
print csvFilepattern, 'parse time:', parseKey['response']['time']
print "Parse result['destination_key']:", parseKey['destination_key']
# BUG here?
if not noPoll:
# We should be able to see the parse result?
h2o_cmd.columnInfoFromInspect(parseKey['destination_key'], exceptionOnMissingValues=False)
# the nflx data doesn't have a small enough # of classes in any col
# use exec to randomFilter out 200 rows for a quick RF. that should work for everyone?
origKey = parseKey['destination_key']
# execExpr = 'a = randomFilter('+origKey+',200,12345678)'
execExpr = 'a = slice('+origKey+',1,200)'
h2e.exec_expr(h2o.nodes[0], execExpr, "a", timeoutSecs=30)
# runRFOnly takes the parseKey directly
newParseKey = {'destination_key': 'a'}
print "\n" + csvFilepattern
# poker and the water.UDP.set3(UDP.java) fail issue..
# constrain depth to 25
print "Temporarily hacking to do nothing instead of RF on the parsed file"
### RFview = h2o_cmd.runRFOnly(trees=1,depth=25,parseKey=newParseKey, timeoutSecs=timeoutSecs)
### h2b.browseJsonHistoryAsUrlLastMatch("RFView")
#**********************************************************************************
# Do GLM too
# Argument case error: Value 0.0 is not between 12.0 and 9987.0 (inclusive)
if DO_GLM:
# these are all the columns that are enums in the dataset...too many for GLM!
x = range(542) # don't include the output column
# remove the output too! (378)
for i in [3, 4, 5, 6, 7, 8, 9, 10, 11, 14, 16, 17, 18, 19, 20, 424, 425, 426, 540, 541, 378]:
x.remove(i)
x = ",".join(map(str,x))
GLMkwargs = {'x': x, 'y': 378, 'case': 15, 'case_mode': '>',
'max_iter': 10, 'n_folds': 1, 'alpha': 0.2, 'lambda': 1e-5}
start = time.time()
glm = h2o_cmd.runGLMOnly(parseKey=parseKey, timeoutSecs=timeoutSecs, **GLMkwargs)
h2o_glm.simpleCheckGLM(self, glm, None, **GLMkwargs)
elapsed = time.time() - start
h2o.check_sandbox_for_errors()
l = '{:d} jvms, {:d}GB heap, {:s} {:s} GLM: {:6.2f} secs'.format(
len(h2o.nodes), h2o.nodes[0].java_heap_GB, csvFilepattern, csvFilename, elapsed)
print l
h2o.cloudPerfH2O.message(l)
#**********************************************************************************
h2o_cmd.checkKeyDistribution()
h2o_cmd.deleteCsvKey(csvFilename, importFolderResult)
### time.sleep(3600)
h2o.tear_down_cloud()
if not localhost:
print "Waiting 30 secs before building cloud again (sticky ports?)"
### time.sleep(30)
sys.stdout.write('.')
sys.stdout.flush()
'max_iter': 10, 'n_folds': 1, 'alpha': 0.2, 'lambda': 1e-5}
start = time.time()
glm = h2o_cmd.runGLM(parseResult=parseResult, timeoutSecs=timeoutSecs, **GLMkwargs)
h2o_glm.simpleCheckGLM(self, glm, None, **GLMkwargs)
elapsed = time.time() - start
h2o.check_sandbox_for_errors()
l = '{:d} jvms, {:d}GB heap, {:s} {:s} GLM: {:6.2f} secs'.format(
len(h2o.nodes), tryHeap, csvFilepattern, csvFilename, elapsed)
print l
h2o.cloudPerfH2O.message(l)
#**********************************************************************************
# print "Waiting 30 secs"
# time.sleep(30)
h2o_cmd.checkKeyDistribution()
h2i.delete_keys_from_import_result(pattern=csvFilename, importResult=importResult)
h2o.nodes[0].remove_all_keys()
### time.sleep(3600)
### h2o.tear_down_cloud()
if not h2o.localhost:
print "Waiting 30 secs before building cloud again (sticky ports?)"
### time.sleep(30)
sys.stdout.write('.')
sys.stdout.flush()
if __name__ == '__main__':
h2o.unit_main()