Files
impala/common/thrift/generate_metrics.py
Joe McDonnell 1913ab46ed IMPALA-14501: Migrate most scripts from impala-python to impala-python3
To remove the dependency on Python 2, existing scripts need to use
python3 rather than python. These commands find those
locations (for impala-python and regular python):
git grep impala-python | grep -v impala-python3 | grep -v impala-python-common | grep -v init-impala-python
git grep bin/python | grep -v python3

This removes or switches most of these locations by various means:
1. If a python file has a #!/bin/env impala-python (or python) but
   doesn't have a main function, it removes the hash-bang and makes
   sure that the file is not executable.
2. Most scripts can simply switch from impala-python to impala-python3
   (or python to python3) with minimal changes.
3. The cm-api pypi package (which doesn't support Python 3) has been
   replaced by the cm-client pypi package and interfaces have changed.
   Rather than migrating the code (which hasn't been used in years), this
   deletes the old code and stops installing cm-api into the virtualenv.
   The code can be restored and revamped if there is any interest in
   interacting with CM clusters.
4. This switches tests/comparison over to impala-python3, but this code has
   bit-rotted. Some pieces can be run manually, but it can't be fully
   verified with Python 3. It shouldn't hold back the migration on its own.
5. This also replaces locations of impala-python in comments / documentation /
   READMEs.
6. kazoo (used for interacting with HBase) needed to be upgraded to a
   version that supports Python 3. The newest version of kazoo requires
   upgrades of other component versions, so this uses kazoo 2.8.0 to avoid
   needing other upgrades.

The two remaining uses of impala-python are:
 - bin/cmake_aux/create_virtualenv.sh
 - bin/impala-env-versioned-python
These will be removed separately when we drop Python 2 support
completely. In particular, these are useful for testing impala-shell
with Python 2 until we stop supporting Python 2 for impala-shell.

The docker-based tests still use /usr/bin/python, but this can
be switched over independently (and doesn't impact impala-python)

Testing:
 - Ran core job
 - Ran build + dataload on Centos 7, Redhat 8
 - Manual testing of individual scripts (except some bitrotted areas like the
   random query generator)

Change-Id: If209b761290bc7e7c716c312ea757da3e3bca6dc
Reviewed-on: http://gerrit.cloudera.org:8080/23468
Reviewed-by: Michael Smith <michael.smith@cloudera.com>
Tested-by: Michael Smith <michael.smith@cloudera.com>
2025-10-22 16:30:17 +00:00

253 lines
8.4 KiB
Python
Executable File

#!/usr/bin/env python3
#
# Licensed to the Apache Software Foundation (ASF) under one
# or more contributor license agreements. See the NOTICE file
# distributed with this work for additional information
# regarding copyright ownership. The ASF licenses this file
# to you under the Apache License, Version 2.0 (the
# "License"); you may not use this file except in compliance
# with the License. You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing,
# software distributed under the License is distributed on an
# "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY
# KIND, either express or implied. See the License for the
# specific language governing permissions and limitations
# under the License.
from __future__ import absolute_import, division, print_function
import sys
import os
import re
import collections
from optparse import OptionParser
try:
import json
except ImportError:
import simplejson as json # For Python 2.4
THRIFT_DIR = os.path.join(os.getenv('IMPALA_HOME'), 'common/thrift')
parser = OptionParser()
parser.add_option("-i", dest="input_schema_path",
default=os.path.join(THRIFT_DIR, "metrics.json"),
help="The path of the output mdl file. Default: %default")
parser.add_option("--generate_thrift", dest="generate_thrift",
action="store_true", default=True,
help="Generates the metric thrift definitions. Default: %default")
parser.add_option("--generate_mdl", dest="generate_mdl",
action="store_true", default=False,
help="Generates a CM-compatible mdl file. Default: %default")
parser.add_option("-o", dest="output_thrift_path",
default=os.path.join(THRIFT_DIR, "MetricDefs.thrift"),
help="The path of the output MetricDefs thrift file. Default: %default")
parser.add_option("--output_mdl_path", dest="output_mdl_path",
default="/tmp/impala_schema.mdl",
help="The path of the output mdl file. Default: %default")
# TODO: get default version value from bin/save-version.sh
parser.add_option("--output_mdl_version", dest="output_mdl_version",
metavar="IMPALA_VERSION", default="2.8.0-SNAPSHOT",
help="The Impala version that is written in the output mdl.")
options, args = parser.parse_args()
def load_metrics(source_file):
"""Reads the json file of metric definitions and returns a map of metric names to
metric definitions"""
raw_metrics = json.loads(open(source_file).read())
metrics = { }
for m in raw_metrics:
if m['key'] in metrics:
assert False, "Metric key %s already used, check definition of %s" % (m['key'], m)
m['kind'] = "Metrics.TMetricKind.%s" % m['kind']
m['units'] = "Metrics.TUnit.%s" % m['units']
metrics[m['key']] = m
return metrics
THRIFT_PREAMBLE = """
// Licensed to the Apache Software Foundation (ASF) under one
// or more contributor license agreements. See the NOTICE file
// distributed with this work for additional information
// regarding copyright ownership. The ASF licenses this file
// to you under the Apache License, Version 2.0 (the
// "License"); you may not use this file except in compliance
// with the License. You may obtain a copy of the License at
//
// http://www.apache.org/licenses/LICENSE-2.0
//
// Unless required by applicable law or agreed to in writing,
// software distributed under the License is distributed on an
// "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY
// KIND, either express or implied. See the License for the
// specific language governing permissions and limitations
// under the License.
//
//
// THIS FILE IS AUTO GENERATED BY generate_metrics.py DO NOT MODIFY IT BY HAND.
//
namespace py impala_thrift_gen.Metrics
namespace cpp impala
namespace java org.apache.impala.thrift
include "Metrics.thrift"
// All metadata associated with a metric. Used to instantiate metrics.
struct TMetricDef {
1: optional string key
2: optional Metrics.TMetricKind kind
3: optional Metrics.TUnit units
4: optional list<string> contexts
5: optional string label
6: optional string description
}
"""
def generate_thrift():
"""Generates the thrift metric definitions file used by Impala."""
metrics = load_metrics(options.input_schema_path)
metrics_json = json.dumps(metrics, sort_keys=True, indent=2)
# dumps writes the TMetricKind and TUnit as quoted strings which is not
# interpreted by the thrift compiler correctly. Need to remove the quotes around
# the enum values.
metrics_json = re.sub(r'"(Metrics.TMetricKind.\S+)"', r'\1', metrics_json)
metrics_json = re.sub(r'"(Metrics.TUnit.\S+)"', r'\1', metrics_json)
target_file = options.output_thrift_path
fid = open(target_file, "w")
try:
fid.write(THRIFT_PREAMBLE)
fid.write("const map<string,TMetricDef> TMetricDefs =\n")
fid.write(metrics_json)
finally:
fid.close()
print("%s created." % target_file)
def metric_to_mdl(m):
"""Returns the metric in the mdl format, or None if the metric isn't supported."""
# TODO: Stamp out metrics with arguments, e.g. output each rpc call_duration metric.
if '$0' in m['key']:
print("Skipping metrics with unbound argument, key=%s" % m['key'], file=sys.stderr)
return None
# TODO: Stamp out individual metrics for other metric types.
SUPPORTED_METRIC_KINDS = ['COUNTER', 'GAUGE']
if m['kind'] not in SUPPORTED_METRIC_KINDS:
print("Skipping %s metric %s" % (m['kind'], m['key']), file=sys.stderr)
return None
return dict(
context=(m['key']),
name=('impala_' + m['key'].lower().replace('-', '_').replace('.', '_')),
counter=(m['kind'] == 'COUNTER'),
numeratorUnit=m['units'].lower(),
description=m['description'],
label=m['label'])
# Base MDL for the Impala Service. Does not contain metrics.
MDL_BASE = """
{
"name" : "IMPALA",
"version" : "$PROJECT_VERSION",
"nameForCrossEntityAggregateMetrics" : "impalas",
"roles" : [
{
"name" : "IMPALAD",
"nameForCrossEntityAggregateMetrics" : "impalads"
},
{
"name" : "STATESTORE",
"nameForCrossEntityAggregateMetrics" : "statestores"
},
{
"name" : "CATALOGSERVER",
"nameForCrossEntityAggregateMetrics" : "catalogservers"
}
],
"metricEntityTypeDefinitions" : [
{
"name" : "IMPALA_POOL",
"nameForCrossEntityAggregateMetrics" : "impala_pools",
"entityNameFormat" : [
"serviceName",
"poolName"
],
"label" : "Impala Pool",
"labelPlural" : "Impala Pools",
"description" : "A resource pool within which Impala schedules queries.",
"immutableAttributeNames" : [
"poolName",
"serviceName"
]
},
{
"name" : "IMPALA_DAEMON_POOL",
"nameForCrossEntityAggregateMetrics" : "impala_daemon_pools",
"entityNameFormat" : [
"roleName",
"poolName"
],
"label" : "Impala Daemon Pool",
"labelPlural" : "Impala Daemon Pools",
"description" : "An Impala Daemon's view of a specific Impala resource pool.",
"immutableAttributeNames" : [
"poolName",
"roleName",
"serviceName"
],
"parentMetricEntityTypeNames" : [
"IMPALA_POOL",
"IMPALA-IMPALAD"
]
}
]
}
"""
def generate_mdl():
"""Generates the CM compatible metric definition (MDL) file."""
metrics = []
input_file = open(options.input_schema_path)
try:
metrics = json.load(input_file)
finally:
input_file.close()
# A map of entity type -> [metric dicts].
metrics_by_role = collections.defaultdict(lambda: [])
for m in metrics:
# Convert to the format that CM expects.
mdl_metric = metric_to_mdl(m)
if mdl_metric is None:
continue
for ctx in m['contexts']:
metrics_by_role[ctx].append(mdl_metric)
mdl = json.loads(MDL_BASE)
mdl['version'] = options.output_mdl_version
for role in mdl['roles']:
role_metrics = []
if role['name'] in metrics_by_role:
role_metrics = metrics_by_role[role['name']]
role['metricDefinitions'] = role_metrics
target_file = options.output_mdl_path
fid = open(target_file, "w")
try:
fid.write(json.dumps(mdl, indent=4))
finally:
fid.close()
print("%s created." % target_file)
if __name__ == "__main__":
if options.generate_thrift:
generate_thrift()
if options.generate_mdl:
generate_mdl()