aboutsummaryrefslogtreecommitdiffstats
path: root/resources/tools
diff options
context:
space:
mode:
authorPeter Mikus <pmikus@cisco.com>2022-02-24 14:19:54 +0100
committerPeter Mikus <pmikus@cisco.com>2022-03-16 15:06:29 +0000
commit646c242bfaea75db747df8c178c050499994c789 (patch)
tree5b55404db1c923253d8a4199825e3d6c15d759a1 /resources/tools
parent6d99a2a08376860e18701174146506046c46b92c (diff)
feat(uti): Data source
Signed-off-by: Peter Mikus <pmikus@cisco.com> Change-Id: Idbd1f0f5a4b08909c2c8e783da62024c850ec90a
Diffstat (limited to 'resources/tools')
-rw-r--r--resources/tools/dash/app/pal/report/data.py254
-rw-r--r--resources/tools/dash/app/pal/report/report.py50
-rw-r--r--resources/tools/dash/app/requirements.txt1
-rw-r--r--resources/tools/dash/docker-compose.yaml1
4 files changed, 291 insertions, 15 deletions
diff --git a/resources/tools/dash/app/pal/report/data.py b/resources/tools/dash/app/pal/report/data.py
index 43e0239228..848259be4a 100644
--- a/resources/tools/dash/app/pal/report/data.py
+++ b/resources/tools/dash/app/pal/report/data.py
@@ -13,14 +13,256 @@
"""Prepare data for Plotly Dash."""
-import pandas as pd
+from logging import info
+from time import time
+import awswrangler as wr
+from awswrangler.exceptions import EmptyDataFrame, NoFilesFound
+from boto3 import session
-def create_dataframe():
- """Create Pandas DataFrame from local CSV.
+
+S3_DOCS_BUCKET="fdio-docs-s3-cloudfront-index"
+
+def create_dataframe_from_parquet(
+ path, partition_filter=None, columns=None,
+ validate_schema=False, last_modified_begin=None,
+ last_modified_end=None):
+ """Read parquet stored in S3 compatible storage and returns Pandas
+ Dataframe.
+
+ :param path: S3 prefix (accepts Unix shell-style wildcards) (e.g.
+ s3://bucket/prefix) or list of S3 objects paths (e.g. [s3://bucket/key0,
+ s3://bucket/key1]).
+ :param partition_filter: Callback Function filters to apply on PARTITION
+ columns (PUSH-DOWN filter). This function MUST receive a single argument
+ (Dict[str, str]) where keys are partitions names and values are
+ partitions values. Partitions values will be always strings extracted
+ from S3. This function MUST return a bool, True to read the partition or
+ False to ignore it. Ignored if dataset=False.
+ :param columns: Names of columns to read from the file(s).
+ :param validate_schema: Check that individual file schemas are all the
+ same / compatible. Schemas within a folder prefix should all be the
+ same. Disable if you have schemas that are different and want to disable
+ this check.
+ :param last_modified_begin: Filter the s3 files by the Last modified date of
+ the object. The filter is applied only after list all s3 files.
+ :param last_modified_end: Filter the s3 files by the Last modified date of
+ the object. The filter is applied only after list all s3 files.
+ :type path: Union[str, List[str]]
+ :type partition_filter: Callable[[Dict[str, str]], bool], optional
+ :type columns: List[str], optional
+ :type validate_schema: bool, optional
+ :type last_modified_begin: datetime, optional
+ :type last_modified_end: datetime, optional
+ :returns: Pandas DataFrame or None if DataFrame cannot be fetched.
+ :rtype: DataFrame
+ """
+ df = None
+ start = time()
+ try:
+ df = wr.s3.read_parquet(
+ path=path,
+ path_suffix="parquet",
+ ignore_empty=True,
+ validate_schema=validate_schema,
+ use_threads=True,
+ dataset=True,
+ columns=columns,
+ partition_filter=partition_filter,
+ last_modified_begin=last_modified_begin,
+ last_modified_end=last_modified_end
+ )
+ info(f"Create dataframe {path} took: {time() - start}")
+ info(df)
+ info(df.info(memory_usage="deep"))
+ except NoFilesFound:
+ return df
+
+ return df
+
+
+def read_stats():
+ """Read Suite Result Analysis data partition from parquet.
+ """
+ lambda_f = lambda part: True if part["stats_type"] == "sra" else False
+
+ return create_dataframe_from_parquet(
+ path=f"s3://{S3_DOCS_BUCKET}/csit/parquet/stats",
+ partition_filter=lambda_f
+ )
+
+def read_trending_mrr():
+ """Read MRR data partition from parquet.
+ """
+ lambda_f = lambda part: True if part["test_type"] == "mrr" else False
+
+ return create_dataframe_from_parquet(
+ path=f"s3://{S3_DOCS_BUCKET}/csit/parquet/trending",
+ partition_filter=lambda_f,
+ columns=["job", "build", "dut_type", "dut_version", "hosts",
+ "start_time", "passed", "test_id", "test_name_long",
+ "test_name_short", "version",
+ "result_receive_rate_rate_avg",
+ "result_receive_rate_rate_stdev",
+ "result_receive_rate_rate_unit",
+ "result_receive_rate_rate_values"
+ ]
+ )
+
+def read_iterative_mrr():
+ """Read MRR data partition from iterative parquet.
+ """
+ lambda_f = lambda part: True if part["test_type"] == "mrr" else False
+
+ return create_dataframe_from_parquet(
+ path=f"s3://{S3_DOCS_BUCKET}/csit/parquet/iterative_rls2202",
+ partition_filter=lambda_f,
+ columns=["job", "build", "dut_type", "dut_version", "hosts",
+ "start_time", "passed", "test_id", "test_name_long",
+ "test_name_short", "version",
+ "result_receive_rate_rate_avg",
+ "result_receive_rate_rate_stdev",
+ "result_receive_rate_rate_unit",
+ "result_receive_rate_rate_values"
+ ]
+ )
+
+def read_trending_ndrpdr():
+ """Read NDRPDR data partition from iterative parquet.
+ """
+ lambda_f = lambda part: True if part["test_type"] == "ndrpdr" else False
+
+ return create_dataframe_from_parquet(
+ path=f"s3://{S3_DOCS_BUCKET}/csit/parquet/trending",
+ partition_filter=lambda_f,
+ columns=["job", "build", "dut_type", "dut_version", "hosts",
+ "start_time", "passed", "test_id", "test_name_long",
+ "test_name_short", "version",
+ "result_pdr_upper_rate_unit",
+ "result_pdr_upper_rate_value",
+ "result_pdr_upper_bandwidth_unit",
+ "result_pdr_upper_bandwidth_value",
+ "result_pdr_lower_rate_unit",
+ "result_pdr_lower_rate_value",
+ "result_pdr_lower_bandwidth_unit",
+ "result_pdr_lower_bandwidth_value",
+ "result_ndr_upper_rate_unit",
+ "result_ndr_upper_rate_value",
+ "result_ndr_upper_bandwidth_unit",
+ "result_ndr_upper_bandwidth_value",
+ "result_ndr_lower_rate_unit",
+ "result_ndr_lower_rate_value",
+ "result_ndr_lower_bandwidth_unit",
+ "result_ndr_lower_bandwidth_value",
+ "result_latency_reverse_pdr_90_avg",
+ "result_latency_reverse_pdr_90_hdrh",
+ "result_latency_reverse_pdr_90_max",
+ "result_latency_reverse_pdr_90_min",
+ "result_latency_reverse_pdr_90_unit",
+ "result_latency_reverse_pdr_50_avg",
+ "result_latency_reverse_pdr_50_hdrh",
+ "result_latency_reverse_pdr_50_max",
+ "result_latency_reverse_pdr_50_min",
+ "result_latency_reverse_pdr_50_unit",
+ "result_latency_reverse_pdr_10_avg",
+ "result_latency_reverse_pdr_10_hdrh",
+ "result_latency_reverse_pdr_10_max",
+ "result_latency_reverse_pdr_10_min",
+ "result_latency_reverse_pdr_10_unit",
+ "result_latency_reverse_pdr_0_avg",
+ "result_latency_reverse_pdr_0_hdrh",
+ "result_latency_reverse_pdr_0_max",
+ "result_latency_reverse_pdr_0_min",
+ "result_latency_reverse_pdr_0_unit",
+ "result_latency_forward_pdr_90_avg",
+ "result_latency_forward_pdr_90_hdrh",
+ "result_latency_forward_pdr_90_max",
+ "result_latency_forward_pdr_90_min",
+ "result_latency_forward_pdr_90_unit",
+ "result_latency_forward_pdr_50_avg",
+ "result_latency_forward_pdr_50_hdrh",
+ "result_latency_forward_pdr_50_max",
+ "result_latency_forward_pdr_50_min",
+ "result_latency_forward_pdr_50_unit",
+ "result_latency_forward_pdr_10_avg",
+ "result_latency_forward_pdr_10_hdrh",
+ "result_latency_forward_pdr_10_max",
+ "result_latency_forward_pdr_10_min",
+ "result_latency_forward_pdr_10_unit",
+ "result_latency_forward_pdr_0_avg",
+ "result_latency_forward_pdr_0_hdrh",
+ "result_latency_forward_pdr_0_max",
+ "result_latency_forward_pdr_0_min",
+ "result_latency_forward_pdr_0_unit"
+ ]
+ )
+
+def read_iterative_ndrpdr():
+ """Read NDRPDR data partition from parquet.
"""
+ lambda_f = lambda part: True if part["test_type"] == "ndrpdr" else False
- return pd.read_csv(
- u"https://s3-docs.fd.io/csit/master/trending/_static/vpp/"
- u"csit-vpp-perf-mrr-daily-master-2n-skx-trending.csv"
+ return create_dataframe_from_parquet(
+ path=f"s3://{S3_DOCS_BUCKET}/csit/parquet/iterative_rls2202",
+ partition_filter=lambda_f,
+ columns=["job", "build", "dut_type", "dut_version", "hosts",
+ "start_time", "passed", "test_id", "test_name_long",
+ "test_name_short", "version",
+ "result_pdr_upper_rate_unit",
+ "result_pdr_upper_rate_value",
+ "result_pdr_upper_bandwidth_unit",
+ "result_pdr_upper_bandwidth_value",
+ "result_pdr_lower_rate_unit",
+ "result_pdr_lower_rate_value",
+ "result_pdr_lower_bandwidth_unit",
+ "result_pdr_lower_bandwidth_value",
+ "result_ndr_upper_rate_unit",
+ "result_ndr_upper_rate_value",
+ "result_ndr_upper_bandwidth_unit",
+ "result_ndr_upper_bandwidth_value",
+ "result_ndr_lower_rate_unit",
+ "result_ndr_lower_rate_value",
+ "result_ndr_lower_bandwidth_unit",
+ "result_ndr_lower_bandwidth_value",
+ "result_latency_reverse_pdr_90_avg",
+ "result_latency_reverse_pdr_90_hdrh",
+ "result_latency_reverse_pdr_90_max",
+ "result_latency_reverse_pdr_90_min",
+ "result_latency_reverse_pdr_90_unit",
+ "result_latency_reverse_pdr_50_avg",
+ "result_latency_reverse_pdr_50_hdrh",
+ "result_latency_reverse_pdr_50_max",
+ "result_latency_reverse_pdr_50_min",
+ "result_latency_reverse_pdr_50_unit",
+ "result_latency_reverse_pdr_10_avg",
+ "result_latency_reverse_pdr_10_hdrh",
+ "result_latency_reverse_pdr_10_max",
+ "result_latency_reverse_pdr_10_min",
+ "result_latency_reverse_pdr_10_unit",
+ "result_latency_reverse_pdr_0_avg",
+ "result_latency_reverse_pdr_0_hdrh",
+ "result_latency_reverse_pdr_0_max",
+ "result_latency_reverse_pdr_0_min",
+ "result_latency_reverse_pdr_0_unit",
+ "result_latency_forward_pdr_90_avg",
+ "result_latency_forward_pdr_90_hdrh",
+ "result_latency_forward_pdr_90_max",
+ "result_latency_forward_pdr_90_min",
+ "result_latency_forward_pdr_90_unit",
+ "result_latency_forward_pdr_50_avg",
+ "result_latency_forward_pdr_50_hdrh",
+ "result_latency_forward_pdr_50_max",
+ "result_latency_forward_pdr_50_min",
+ "result_latency_forward_pdr_50_unit",
+ "result_latency_forward_pdr_10_avg",
+ "result_latency_forward_pdr_10_hdrh",
+ "result_latency_forward_pdr_10_max",
+ "result_latency_forward_pdr_10_min",
+ "result_latency_forward_pdr_10_unit",
+ "result_latency_forward_pdr_0_avg",
+ "result_latency_forward_pdr_0_hdrh",
+ "result_latency_forward_pdr_0_max",
+ "result_latency_forward_pdr_0_min",
+ "result_latency_forward_pdr_0_unit"
+ ]
)
diff --git a/resources/tools/dash/app/pal/report/report.py b/resources/tools/dash/app/pal/report/report.py
index d22a0b6705..769a6dd63e 100644
--- a/resources/tools/dash/app/pal/report/report.py
+++ b/resources/tools/dash/app/pal/report/report.py
@@ -18,10 +18,10 @@ import dash
from dash import dcc
from dash import html
from dash import dash_table
-import numpy as np
-import pandas as pd
-from .data import create_dataframe
+from .data import read_stats
+from .data import read_trending_mrr, read_trending_ndrpdr
+from .data import read_iterative_mrr, read_iterative_ndrpdr
from .layout import html_layout
@@ -43,34 +43,66 @@ def init_report(server):
],
)
- # Load DataFrame
- df = create_dataframe()
-
# Custom HTML layout
dash_app.index_string = html_layout
# Create Layout
dash_app.layout = html.Div(
children=[
- create_data_table(df),
+ html.Div(
+ children=create_data_table(
+ read_stats().dropna(),
+ u"database-table-stats"
+ )
+ ),
+ html.Div(
+ children=create_data_table(
+ read_trending_mrr().dropna(),
+ u"database-table-mrr"
+ )
+ ),
+ html.Div(
+ children=create_data_table(
+ read_trending_ndrpdr().dropna(),
+ u"database-table-ndrpdr"
+ )
+ ),
+ html.Div(
+ children=create_data_table(
+ read_iterative_mrr().dropna(),
+ u"database-table-iterative-mrr"
+ )
+ ),
+ html.Div(
+ children=create_data_table(
+ read_iterative_ndrpdr().dropna(),
+ u"database-table-iterative-ndrpdr"
+ )
+ )
],
id=u"dash-container",
)
return dash_app.server
-def create_data_table(df):
+def create_data_table(df, id):
"""Create Dash datatable from Pandas DataFrame.
DEMO
"""
table = dash_table.DataTable(
- id=u"database-table",
+ id=id,
columns=[{u"name": i, u"id": i} for i in df.columns],
data=df.to_dict(u"records"),
+ fixed_rows={'headers': True},
sort_action=u"native",
sort_mode=u"native",
page_size=5,
+ style_header={
+ 'overflow': 'hidden',
+ 'textOverflow': 'ellipsis',
+ 'minWidth': 95, 'maxWidth': 95, 'width': 95,
+ }
)
return table
diff --git a/resources/tools/dash/app/requirements.txt b/resources/tools/dash/app/requirements.txt
index befdc8a83b..5c3a5488f0 100644
--- a/resources/tools/dash/app/requirements.txt
+++ b/resources/tools/dash/app/requirements.txt
@@ -1,4 +1,5 @@
attrs==21.2.0
+awswrangler==2.14.0
Brotli==1.0.9
click==8.0.3
dash==2.0.0
diff --git a/resources/tools/dash/docker-compose.yaml b/resources/tools/dash/docker-compose.yaml
index 335bcdaf94..4fe12bd11e 100644
--- a/resources/tools/dash/docker-compose.yaml
+++ b/resources/tools/dash/docker-compose.yaml
@@ -16,4 +16,5 @@ services:
- "5000:5000"
volumes:
- "./app/:/app"
+ - "/home/vagrant/.aws:/root/.aws"
working_dir: "/app"