diff options
Diffstat (limited to 'csit.infra.etl')
| -rw-r--r-- | csit.infra.etl/coverage_device_rls2210.py | 2 | ||||
| -rw-r--r-- | csit.infra.etl/coverage_ndrpdr_rls2210.py | 2 | ||||
| -rw-r--r-- | csit.infra.etl/coverage_reconf_rls2210.json | 223 | ||||
| -rw-r--r-- | csit.infra.etl/coverage_reconf_rls2210.py | 171 | ||||
| -rw-r--r-- | csit.infra.etl/coverage_soak_rls2210.py | 2 | ||||
| -rw-r--r-- | csit.infra.etl/iterative_reconf_rls2210.json | 223 | ||||
| -rw-r--r-- | csit.infra.etl/iterative_reconf_rls2210.py | 171 | ||||
| -rw-r--r-- | csit.infra.etl/trending_reconf.json | 239 | ||||
| -rw-r--r-- | csit.infra.etl/trending_reconf.py | 171 |
9 files changed, 1201 insertions, 3 deletions
diff --git a/csit.infra.etl/coverage_device_rls2210.py b/csit.infra.etl/coverage_device_rls2210.py index 9c9e1c9603..0822d13a9a 100644 --- a/csit.infra.etl/coverage_device_rls2210.py +++ b/csit.infra.etl/coverage_device_rls2210.py @@ -143,7 +143,7 @@ paths = wr.s3.list_objects( filtered_paths = [path for path in paths if "report-coverage-2210" in path] -out_sdf = process_json_to_dataframe("mrr", filtered_paths) +out_sdf = process_json_to_dataframe("device", filtered_paths) out_sdf.printSchema() out_sdf = out_sdf \ .withColumn("year", lit(datetime.now().year)) \ diff --git a/csit.infra.etl/coverage_ndrpdr_rls2210.py b/csit.infra.etl/coverage_ndrpdr_rls2210.py index 9c9e1c9603..c0bd1d3c19 100644 --- a/csit.infra.etl/coverage_ndrpdr_rls2210.py +++ b/csit.infra.etl/coverage_ndrpdr_rls2210.py @@ -143,7 +143,7 @@ paths = wr.s3.list_objects( filtered_paths = [path for path in paths if "report-coverage-2210" in path] -out_sdf = process_json_to_dataframe("mrr", filtered_paths) +out_sdf = process_json_to_dataframe("ndrpdr", filtered_paths) out_sdf.printSchema() out_sdf = out_sdf \ .withColumn("year", lit(datetime.now().year)) \ diff --git a/csit.infra.etl/coverage_reconf_rls2210.json b/csit.infra.etl/coverage_reconf_rls2210.json new file mode 100644 index 0000000000..fdd6eab6c0 --- /dev/null +++ b/csit.infra.etl/coverage_reconf_rls2210.json @@ -0,0 +1,223 @@ +{ + "fields": [ + { + "metadata": {}, + "name": "job", + "nullable": false, + "type": "string" + }, + { + "metadata": {}, + "name": "build", + "nullable": false, + "type": "integer" + }, + { + "metadata": {}, + "name": "duration", + "nullable": true, + "type": "double" + }, + { + "metadata": {}, + "name": "dut_type", + "nullable": true, + "type": "string" + }, + { + "metadata": {}, + "name": "dut_version", + "nullable": true, + "type": "string" + }, + { + "metadata": {}, + "name": "tg_type", + "nullable": true, + "type": "string" + }, + { + "metadata": {}, + "name": "tg_version", + "nullable": true, + "type": "string" + }, + { + "metadata": {}, + "name": "result", + "nullable": true, + "type": { + "fields": [ + { + "metadata": {}, + "name": "aggregate_rate", + "nullable": true, + "type": { + "fields": [ + { + "metadata": {}, + "name": "bandwidth", + "nullable": true, + "type": { + "fields": [ + { + "metadata": {}, + "name": "unit", + "nullable": true, + "type": "string" + }, + { + "metadata": {}, + "name": "value", + "nullable": true, + "type": "double" + } + ], + "type": "struct" + } + }, + { + "metadata": {}, + "name": "rate", + "nullable": true, + "type": { + "fields": [ + { + "metadata": {}, + "name": "unit", + "nullable": true, + "type": "string" + }, + { + "metadata": {}, + "name": "value", + "nullable": true, + "type": "double" + } + ], + "type": "struct" + } + } + ], + "type": "struct" + } + }, + { + "metadata": {}, + "name": "loss", + "nullable": true, + "type": { + "fields": [ + { + "metadata": {}, + "name": "packets", + "nullable": true, + "type": { + "fields": [ + { + "metadata": {}, + "name": "unit", + "nullable": true, + "type": "string" + }, + { + "metadata": {}, + "name": "value", + "nullable": true, + "type": "integer" + } + ], + "type": "struct" + } + }, + { + "metadata": {}, + "name": "time", + "nullable": true, + "type": { + "fields": [ + { + "metadata": {}, + "name": "unit", + "nullable": true, + "type": "string" + }, + { + "metadata": {}, + "name": "value", + "nullable": true, + "type": "double" + } + ], + "type": "struct" + } + } + ], + "type": "struct" + } + }, + { + "metadata": {}, + "name": "type", + "nullable": true, + "type": "string" + } + ], + "type": "struct" + } + }, + { + "metadata": {}, + "name": "start_time", + "nullable": true, + "type": "timestamp" + }, + { + "metadata": {}, + "name": "passed", + "nullable": true, + "type": "boolean" + }, + { + "metadata": {}, + "name": "test_id", + "nullable": true, + "type": "string" + }, + { + "metadata": {}, + "name": "test_name_long", + "nullable": true, + "type": "string" + }, + { + "metadata": {}, + "name": "test_name_short", + "nullable": true, + "type": "string" + }, + { + "metadata": {}, + "name": "test_type", + "nullable": true, + "type": "string" + }, + { + "metadata": {}, + "name": "tags", + "nullable": true, + "type": { + "containsNull": true, + "elementType": "string", + "type": "array" + } + }, + { + "metadata": {}, + "name": "version", + "nullable": true, + "type": "string" + } + ], + "type": "struct" +}
\ No newline at end of file diff --git a/csit.infra.etl/coverage_reconf_rls2210.py b/csit.infra.etl/coverage_reconf_rls2210.py new file mode 100644 index 0000000000..b2a540d9e4 --- /dev/null +++ b/csit.infra.etl/coverage_reconf_rls2210.py @@ -0,0 +1,171 @@ +#!/usr/bin/env python3 + +# Copyright (c) 2022 Cisco and/or its affiliates. +# Licensed 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. + +"""ETL script running on top of the s3://""" + +from datetime import datetime, timedelta +from json import load +from os import environ +from pytz import utc + +import awswrangler as wr +from awswrangler.exceptions import EmptyDataFrame +from awsglue.context import GlueContext +from boto3 import session +from pyspark.context import SparkContext +from pyspark.sql.functions import col, lit, regexp_replace +from pyspark.sql.types import StructType + + +S3_LOGS_BUCKET="fdio-logs-s3-cloudfront-index" +S3_DOCS_BUCKET="fdio-docs-s3-cloudfront-index" +PATH=f"s3://{S3_LOGS_BUCKET}/vex-yul-rot-jenkins-1/csit-*-perf-*" +SUFFIX="info.json.gz" +IGNORE_SUFFIX=[ + "suite.info.json.gz", + "setup.info.json.gz", + "teardown.info.json.gz", + "suite.output.info.json.gz", + "setup.output.info.json.gz", + "teardown.output.info.json.gz" +] +LAST_MODIFIED_END=utc.localize( + datetime.strptime( + f"{datetime.now().year}-{datetime.now().month}-{datetime.now().day}", + "%Y-%m-%d" + ) +) +LAST_MODIFIED_BEGIN=LAST_MODIFIED_END - timedelta(1) + + +def flatten_frame(nested_sdf): + """Unnest Spark DataFrame in case there nested structered columns. + + :param nested_sdf: Spark DataFrame. + :type nested_sdf: DataFrame + :returns: Unnest DataFrame. + :rtype: DataFrame + """ + stack = [((), nested_sdf)] + columns = [] + while len(stack) > 0: + parents, sdf = stack.pop() + for column_name, column_type in sdf.dtypes: + if column_type[:6] == "struct": + projected_sdf = sdf.select(column_name + ".*") + stack.append((parents + (column_name,), projected_sdf)) + else: + columns.append( + col(".".join(parents + (column_name,))) \ + .alias("_".join(parents + (column_name,))) + ) + return nested_sdf.select(columns) + + +def process_json_to_dataframe(schema_name, paths): + """Processes JSON to Spark DataFrame. + + :param schema_name: Schema name. + :type schema_name: string + :param paths: S3 paths to process. + :type paths: list + :returns: Spark DataFrame. + :rtype: DataFrame + """ + drop_subset = [ + "dut_type", "dut_version", + "passed", + "test_name_long", "test_name_short", + "test_type", + "version" + ] + + # load schemas + with open(f"coverage_{schema_name}.json", "r", encoding="UTF-8") as f_schema: + schema = StructType.fromJson(load(f_schema)) + + # create empty DF out of schemas + sdf = spark.createDataFrame([], schema) + + # filter list + filtered = [path for path in paths if schema_name in path] + + # select + for path in filtered: + print(path) + + sdf_loaded = spark \ + .read \ + .option("multiline", "true") \ + .schema(schema) \ + .json(path) \ + .withColumn("job", lit(path.split("/")[4])) \ + .withColumn("build", lit(path.split("/")[5])) + sdf = sdf.unionByName(sdf_loaded, allowMissingColumns=True) + + # drop rows with all nulls and drop rows with null in critical frames + sdf = sdf.na.drop(how="all") + sdf = sdf.na.drop(how="any", thresh=None, subset=drop_subset) + + # flatten frame + sdf = flatten_frame(sdf) + + return sdf + + +# create SparkContext and GlueContext +spark_context = SparkContext.getOrCreate() +spark_context.setLogLevel("WARN") +glue_context = GlueContext(spark_context) +spark = glue_context.spark_session + +# files of interest +paths = wr.s3.list_objects( + path=PATH, + suffix=SUFFIX, + last_modified_begin=LAST_MODIFIED_BEGIN, + last_modified_end=LAST_MODIFIED_END, + ignore_suffix=IGNORE_SUFFIX, + ignore_empty=True +) + +filtered_paths = [path for path in paths if "report-coverage-2210" in path] + +out_sdf = process_json_to_dataframe("reconf", filtered_paths) +out_sdf.show(truncate=False) +out_sdf.printSchema() +out_sdf = out_sdf \ + .withColumn("year", lit(datetime.now().year)) \ + .withColumn("month", lit(datetime.now().month)) \ + .withColumn("day", lit(datetime.now().day)) \ + .repartition(1) + +try: + wr.s3.to_parquet( + df=out_sdf.toPandas(), + path=f"s3://{S3_DOCS_BUCKET}/csit/parquet/coverage_rls2210", + dataset=True, + partition_cols=["test_type", "year", "month", "day"], + compression="snappy", + use_threads=True, + mode="overwrite_partitions", + boto3_session=session.Session( + aws_access_key_id=environ["OUT_AWS_ACCESS_KEY_ID"], + aws_secret_access_key=environ["OUT_AWS_SECRET_ACCESS_KEY"], + region_name=environ["OUT_AWS_DEFAULT_REGION"] + ) + ) +except EmptyDataFrame: + pass diff --git a/csit.infra.etl/coverage_soak_rls2210.py b/csit.infra.etl/coverage_soak_rls2210.py index 9c9e1c9603..9ef9a36c68 100644 --- a/csit.infra.etl/coverage_soak_rls2210.py +++ b/csit.infra.etl/coverage_soak_rls2210.py @@ -143,7 +143,7 @@ paths = wr.s3.list_objects( filtered_paths = [path for path in paths if "report-coverage-2210" in path] -out_sdf = process_json_to_dataframe("mrr", filtered_paths) +out_sdf = process_json_to_dataframe("soak", filtered_paths) out_sdf.printSchema() out_sdf = out_sdf \ .withColumn("year", lit(datetime.now().year)) \ diff --git a/csit.infra.etl/iterative_reconf_rls2210.json b/csit.infra.etl/iterative_reconf_rls2210.json new file mode 100644 index 0000000000..fdd6eab6c0 --- /dev/null +++ b/csit.infra.etl/iterative_reconf_rls2210.json @@ -0,0 +1,223 @@ +{ + "fields": [ + { + "metadata": {}, + "name": "job", + "nullable": false, + "type": "string" + }, + { + "metadata": {}, + "name": "build", + "nullable": false, + "type": "integer" + }, + { + "metadata": {}, + "name": "duration", + "nullable": true, + "type": "double" + }, + { + "metadata": {}, + "name": "dut_type", + "nullable": true, + "type": "string" + }, + { + "metadata": {}, + "name": "dut_version", + "nullable": true, + "type": "string" + }, + { + "metadata": {}, + "name": "tg_type", + "nullable": true, + "type": "string" + }, + { + "metadata": {}, + "name": "tg_version", + "nullable": true, + "type": "string" + }, + { + "metadata": {}, + "name": "result", + "nullable": true, + "type": { + "fields": [ + { + "metadata": {}, + "name": "aggregate_rate", + "nullable": true, + "type": { + "fields": [ + { + "metadata": {}, + "name": "bandwidth", + "nullable": true, + "type": { + "fields": [ + { + "metadata": {}, + "name": "unit", + "nullable": true, + "type": "string" + }, + { + "metadata": {}, + "name": "value", + "nullable": true, + "type": "double" + } + ], + "type": "struct" + } + }, + { + "metadata": {}, + "name": "rate", + "nullable": true, + "type": { + "fields": [ + { + "metadata": {}, + "name": "unit", + "nullable": true, + "type": "string" + }, + { + "metadata": {}, + "name": "value", + "nullable": true, + "type": "double" + } + ], + "type": "struct" + } + } + ], + "type": "struct" + } + }, + { + "metadata": {}, + "name": "loss", + "nullable": true, + "type": { + "fields": [ + { + "metadata": {}, + "name": "packets", + "nullable": true, + "type": { + "fields": [ + { + "metadata": {}, + "name": "unit", + "nullable": true, + "type": "string" + }, + { + "metadata": {}, + "name": "value", + "nullable": true, + "type": "integer" + } + ], + "type": "struct" + } + }, + { + "metadata": {}, + "name": "time", + "nullable": true, + "type": { + "fields": [ + { + "metadata": {}, + "name": "unit", + "nullable": true, + "type": "string" + }, + { + "metadata": {}, + "name": "value", + "nullable": true, + "type": "double" + } + ], + "type": "struct" + } + } + ], + "type": "struct" + } + }, + { + "metadata": {}, + "name": "type", + "nullable": true, + "type": "string" + } + ], + "type": "struct" + } + }, + { + "metadata": {}, + "name": "start_time", + "nullable": true, + "type": "timestamp" + }, + { + "metadata": {}, + "name": "passed", + "nullable": true, + "type": "boolean" + }, + { + "metadata": {}, + "name": "test_id", + "nullable": true, + "type": "string" + }, + { + "metadata": {}, + "name": "test_name_long", + "nullable": true, + "type": "string" + }, + { + "metadata": {}, + "name": "test_name_short", + "nullable": true, + "type": "string" + }, + { + "metadata": {}, + "name": "test_type", + "nullable": true, + "type": "string" + }, + { + "metadata": {}, + "name": "tags", + "nullable": true, + "type": { + "containsNull": true, + "elementType": "string", + "type": "array" + } + }, + { + "metadata": {}, + "name": "version", + "nullable": true, + "type": "string" + } + ], + "type": "struct" +}
\ No newline at end of file diff --git a/csit.infra.etl/iterative_reconf_rls2210.py b/csit.infra.etl/iterative_reconf_rls2210.py new file mode 100644 index 0000000000..836cf81de4 --- /dev/null +++ b/csit.infra.etl/iterative_reconf_rls2210.py @@ -0,0 +1,171 @@ +#!/usr/bin/env python3 + +# Copyright (c) 2022 Cisco and/or its affiliates. +# Licensed 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. + +"""ETL script running on top of the s3://""" + +from datetime import datetime, timedelta +from json import load +from os import environ +from pytz import utc + +import awswrangler as wr +from awswrangler.exceptions import EmptyDataFrame +from awsglue.context import GlueContext +from boto3 import session +from pyspark.context import SparkContext +from pyspark.sql.functions import col, lit, regexp_replace +from pyspark.sql.types import StructType + + +S3_LOGS_BUCKET="fdio-logs-s3-cloudfront-index" +S3_DOCS_BUCKET="fdio-docs-s3-cloudfront-index" +PATH=f"s3://{S3_LOGS_BUCKET}/vex-yul-rot-jenkins-1/csit-*-perf-*" +SUFFIX="info.json.gz" +IGNORE_SUFFIX=[ + "suite.info.json.gz", + "setup.info.json.gz", + "teardown.info.json.gz", + "suite.output.info.json.gz", + "setup.output.info.json.gz", + "teardown.output.info.json.gz" +] +LAST_MODIFIED_END=utc.localize( + datetime.strptime( + f"{datetime.now().year}-{datetime.now().month}-{datetime.now().day}", + "%Y-%m-%d" + ) +) +LAST_MODIFIED_BEGIN=LAST_MODIFIED_END - timedelta(1) + + +def flatten_frame(nested_sdf): + """Unnest Spark DataFrame in case there nested structered columns. + + :param nested_sdf: Spark DataFrame. + :type nested_sdf: DataFrame + :returns: Unnest DataFrame. + :rtype: DataFrame + """ + stack = [((), nested_sdf)] + columns = [] + while len(stack) > 0: + parents, sdf = stack.pop() + for column_name, column_type in sdf.dtypes: + if column_type[:6] == "struct": + projected_sdf = sdf.select(column_name + ".*") + stack.append((parents + (column_name,), projected_sdf)) + else: + columns.append( + col(".".join(parents + (column_name,))) \ + .alias("_".join(parents + (column_name,))) + ) + return nested_sdf.select(columns) + + +def process_json_to_dataframe(schema_name, paths): + """Processes JSON to Spark DataFrame. + + :param schema_name: Schema name. + :type schema_name: string + :param paths: S3 paths to process. + :type paths: list + :returns: Spark DataFrame. + :rtype: DataFrame + """ + drop_subset = [ + "dut_type", "dut_version", + "passed", + "test_name_long", "test_name_short", + "test_type", + "version" + ] + + # load schemas + with open(f"iterative_{schema_name}.json", "r", encoding="UTF-8") as f_schema: + schema = StructType.fromJson(load(f_schema)) + + # create empty DF out of schemas + sdf = spark.createDataFrame([], schema) + + # filter list + filtered = [path for path in paths if schema_name in path] + + # select + for path in filtered: + print(path) + + sdf_loaded = spark \ + .read \ + .option("multiline", "true") \ + .schema(schema) \ + .json(path) \ + .withColumn("job", lit(path.split("/")[4])) \ + .withColumn("build", lit(path.split("/")[5])) + sdf = sdf.unionByName(sdf_loaded, allowMissingColumns=True) + + # drop rows with all nulls and drop rows with null in critical frames + sdf = sdf.na.drop(how="all") + sdf = sdf.na.drop(how="any", thresh=None, subset=drop_subset) + + # flatten frame + sdf = flatten_frame(sdf) + + return sdf + + +# create SparkContext and GlueContext +spark_context = SparkContext.getOrCreate() +spark_context.setLogLevel("WARN") +glue_context = GlueContext(spark_context) +spark = glue_context.spark_session + +# files of interest +paths = wr.s3.list_objects( + path=PATH, + suffix=SUFFIX, + last_modified_begin=LAST_MODIFIED_BEGIN, + last_modified_end=LAST_MODIFIED_END, + ignore_suffix=IGNORE_SUFFIX, + ignore_empty=True +) + +filtered_paths = [path for path in paths if "report-iterative-2210" in path] + +out_sdf = process_json_to_dataframe("reconf", filtered_paths) +out_sdf.show(truncate=False) +out_sdf.printSchema() +out_sdf = out_sdf \ + .withColumn("year", lit(datetime.now().year)) \ + .withColumn("month", lit(datetime.now().month)) \ + .withColumn("day", lit(datetime.now().day)) \ + .repartition(1) + +try: + wr.s3.to_parquet( + df=out_sdf.toPandas(), + path=f"s3://{S3_DOCS_BUCKET}/csit/parquet/iterative_rls2210", + dataset=True, + partition_cols=["test_type", "year", "month", "day"], + compression="snappy", + use_threads=True, + mode="overwrite_partitions", + boto3_session=session.Session( + aws_access_key_id=environ["OUT_AWS_ACCESS_KEY_ID"], + aws_secret_access_key=environ["OUT_AWS_SECRET_ACCESS_KEY"], + region_name=environ["OUT_AWS_DEFAULT_REGION"] + ) + ) +except EmptyDataFrame: + pass diff --git a/csit.infra.etl/trending_reconf.json b/csit.infra.etl/trending_reconf.json new file mode 100644 index 0000000000..bb4c0eea15 --- /dev/null +++ b/csit.infra.etl/trending_reconf.json @@ -0,0 +1,239 @@ +{ + "fields": [ + { + "metadata": {}, + "name": "job", + "nullable": false, + "type": "string" + }, + { + "metadata": {}, + "name": "build", + "nullable": false, + "type": "integer" + }, + { + "metadata": {}, + "name": "duration", + "nullable": true, + "type": "double" + }, + { + "metadata": {}, + "name": "dut_type", + "nullable": true, + "type": "string" + }, + { + "metadata": {}, + "name": "dut_version", + "nullable": true, + "type": "string" + }, + { + "metadata": {}, + "name": "hosts", + "nullable": true, + "type": { + "containsNull": true, + "elementType": "string", + "type": "array" + } + }, + { + "metadata": {}, + "name": "tg_type", + "nullable": true, + "type": "string" + }, + { + "metadata": {}, + "name": "tg_version", + "nullable": true, + "type": "string" + }, + { + "metadata": {}, + "name": "result", + "nullable": true, + "type": { + "fields": [ + { + "metadata": {}, + "name": "aggregate_rate", + "nullable": true, + "type": { + "fields": [ + { + "metadata": {}, + "name": "bandwidth", + "nullable": true, + "type": { + "fields": [ + { + "metadata": {}, + "name": "unit", + "nullable": true, + "type": "string" + }, + { + "metadata": {}, + "name": "value", + "nullable": true, + "type": "double" + } + ], + "type": "struct" + } + }, + { + "metadata": {}, + "name": "rate", + "nullable": true, + "type": { + "fields": [ + { + "metadata": {}, + "name": "unit", + "nullable": true, + "type": "string" + }, + { + "metadata": {}, + "name": "value", + "nullable": true, + "type": "double" + } + ], + "type": "struct" + } + } + ], + "type": "struct" + } + }, + { + "metadata": {}, + "name": "loss", + "nullable": true, + "type": { + "fields": [ + { + "metadata": {}, + "name": "packets", + "nullable": true, + "type": { + "fields": [ + { + "metadata": {}, + "name": "unit", + "nullable": true, + "type": "string" + }, + { + "metadata": {}, + "name": "value", + "nullable": true, + "type": "integer" + } + ], + "type": "struct" + } + }, + { + "metadata": {}, + "name": "time", + "nullable": true, + "type": { + "fields": [ + { + "metadata": {}, + "name": "unit", + "nullable": true, + "type": "string" + }, + { + "metadata": {}, + "name": "value", + "nullable": true, + "type": "double" + } + ], + "type": "struct" + } + } + ], + "type": "struct" + } + }, + { + "metadata": {}, + "name": "type", + "nullable": true, + "type": "string" + } + ], + "type": "struct" + } + }, + { + "metadata": {}, + "name": "start_time", + "nullable": true, + "type": "timestamp" + }, + { + "metadata": {}, + "name": "passed", + "nullable": true, + "type": "boolean" + }, + { + "metadata": {}, + "name": "telemetry", + "nullable": true, + "type": { + "containsNull": true, + "elementType": "string", + "type": "array" + } + }, + { + "metadata": {}, + "name": "test_id", + "nullable": true, + "type": "string" + }, + { + "metadata": {}, + "name": "test_name_long", + "nullable": true, + "type": "string" + }, + { + "metadata": {}, + "name": "test_name_short", + "nullable": true, + "type": "string" + }, + { + "metadata": {}, + "name": "test_type", + "nullable": true, + "type": "string" + }, + { + "metadata": {}, + "name": "message", + "nullable": true, + "type": "string" + }, + { + "metadata": {}, + "name": "version", + "nullable": true, + "type": "string" + } + ], + "type": "struct" +}
\ No newline at end of file diff --git a/csit.infra.etl/trending_reconf.py b/csit.infra.etl/trending_reconf.py new file mode 100644 index 0000000000..e30808c457 --- /dev/null +++ b/csit.infra.etl/trending_reconf.py @@ -0,0 +1,171 @@ +#!/usr/bin/env python3 + +# Copyright (c) 2022 Cisco and/or its affiliates. +# Licensed 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. + +"""ETL script running on top of the s3://""" + +from datetime import datetime, timedelta +from json import load +from os import environ +from pytz import utc + +import awswrangler as wr +from awswrangler.exceptions import EmptyDataFrame +from awsglue.context import GlueContext +from boto3 import session +from pyspark.context import SparkContext +from pyspark.sql.functions import col, lit, regexp_replace +from pyspark.sql.types import StructType + + +S3_LOGS_BUCKET="fdio-logs-s3-cloudfront-index" +S3_DOCS_BUCKET="fdio-docs-s3-cloudfront-index" +PATH=f"s3://{S3_LOGS_BUCKET}/vex-yul-rot-jenkins-1/csit-*-perf-*" +SUFFIX="info.json.gz" +IGNORE_SUFFIX=[ + "suite.info.json.gz", + "setup.info.json.gz", + "teardown.info.json.gz", + "suite.output.info.json.gz", + "setup.output.info.json.gz", + "teardown.output.info.json.gz" +] +LAST_MODIFIED_END=utc.localize( + datetime.strptime( + f"{datetime.now().year}-{datetime.now().month}-{datetime.now().day}", + "%Y-%m-%d" + ) +) +LAST_MODIFIED_BEGIN=LAST_MODIFIED_END - timedelta(1) + + +def flatten_frame(nested_sdf): + """Unnest Spark DataFrame in case there nested structered columns. + + :param nested_sdf: Spark DataFrame. + :type nested_sdf: DataFrame + :returns: Unnest DataFrame. + :rtype: DataFrame + """ + stack = [((), nested_sdf)] + columns = [] + while len(stack) > 0: + parents, sdf = stack.pop() + for column_name, column_type in sdf.dtypes: + if column_type[:6] == "struct": + projected_sdf = sdf.select(column_name + ".*") + stack.append((parents + (column_name,), projected_sdf)) + else: + columns.append( + col(".".join(parents + (column_name,))) \ + .alias("_".join(parents + (column_name,))) + ) + return nested_sdf.select(columns) + + +def process_json_to_dataframe(schema_name, paths): + """Processes JSON to Spark DataFrame. + + :param schema_name: Schema name. + :type schema_name: string + :param paths: S3 paths to process. + :type paths: list + :returns: Spark DataFrame. + :rtype: DataFrame + """ + drop_subset = [ + "dut_type", "dut_version", + "passed", + "test_name_long", "test_name_short", + "test_type", + "version" + ] + + # load schemas + with open(f"trending_{schema_name}.json", "r", encoding="UTF-8") as f_schema: + schema = StructType.fromJson(load(f_schema)) + + # create empty DF out of schemas + sdf = spark.createDataFrame([], schema) + + # filter list + filtered = [path for path in paths if schema_name in path] + + # select + for path in filtered: + print(path) + + sdf_loaded = spark \ + .read \ + .option("multiline", "true") \ + .schema(schema) \ + .json(path) \ + .withColumn("job", lit(path.split("/")[4])) \ + .withColumn("build", lit(path.split("/")[5])) + sdf = sdf.unionByName(sdf_loaded, allowMissingColumns=True) + + # drop rows with all nulls and drop rows with null in critical frames + sdf = sdf.na.drop(how="all") + sdf = sdf.na.drop(how="any", thresh=None, subset=drop_subset) + + # flatten frame + sdf = flatten_frame(sdf) + + return sdf + + +# create SparkContext and GlueContext +spark_context = SparkContext.getOrCreate() +spark_context.setLogLevel("WARN") +glue_context = GlueContext(spark_context) +spark = glue_context.spark_session + +# files of interest +paths = wr.s3.list_objects( + path=PATH, + suffix=SUFFIX, + last_modified_begin=LAST_MODIFIED_BEGIN, + last_modified_end=LAST_MODIFIED_END, + ignore_suffix=IGNORE_SUFFIX, + ignore_empty=True +) + +filtered_paths = [path for path in paths if "daily" in path or "weekly" in path] + +out_sdf = process_json_to_dataframe("reconf", filtered_paths) +out_sdf.show(truncate=False) +out_sdf.printSchema() +out_sdf = out_sdf \ + .withColumn("year", lit(datetime.now().year)) \ + .withColumn("month", lit(datetime.now().month)) \ + .withColumn("day", lit(datetime.now().day)) \ + .repartition(1) + +try: + wr.s3.to_parquet( + df=out_sdf.toPandas(), + path=f"s3://{S3_DOCS_BUCKET}/csit/parquet/trending", + dataset=True, + partition_cols=["test_type", "year", "month", "day"], + compression="snappy", + use_threads=True, + mode="overwrite_partitions", + boto3_session=session.Session( + aws_access_key_id=environ["OUT_AWS_ACCESS_KEY_ID"], + aws_secret_access_key=environ["OUT_AWS_SECRET_ACCESS_KEY"], + region_name=environ["OUT_AWS_DEFAULT_REGION"] + ) + ) +except EmptyDataFrame: + pass |