openstack
/
ci-log-processing
Code Issues Proposed changes

Initial project commit 

This commit provides Zuul logscraper tool responsible for
getting newest logs by using Zuul API and pushing them to
log processing services.

Change-Id: Iff45fbcb6d4813cc60dc705c60e95f3045984b5c
This commit is contained in:
Daniel Pawlik 2021-10-27 10:26:28 +02:00
parent a35bc55fb9
commit a6bdcc96b4
22 changed files with 1404 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

11
.gitignore vendored Normal file
View File

@ -0,0 +1,11 @@
.DS_Store
*.swp
*~
*.pyc
doc/build/
.tox/
logscraper.egg-info/
.eggs
AUTHORS
ChangeLog
.stestr/

3
.stestr.conf Normal file
View File

@ -0,0 +1,3 @@
[DEFAULT]
test_path=./logscraper/tests
top_dir=./

9
.zuul.yaml Normal file
View File

@ -0,0 +1,9 @@
---
- project:
templates:
- build-tox-docs
check: &logcheck
jobs:
- openstack-tox-pep8
- openstack-tox-py38
gate: *logcheck

25
Dockerfile Normal file
View File

@ -0,0 +1,25 @@
# Copyright (C) 2021 Red Hat
#
# 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.
FROM opendevorg/python-builder:3.8 as builder
COPY . /tmp/src
RUN assemble
FROM opendevorg/python-base:3.8 as logscraper
COPY --from=builder /output/ /output
RUN /output/install-from-bindep
ENTRYPOINT ["/usr/local/bin/logscraper"]

202
LICENSE Normal file
View File

@ -0,0 +1,202 @@
Apache License
Version 2.0, January 2004
http://www.apache.org/licenses/
TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
1. Definitions.
"License" shall mean the terms and conditions for use, reproduction,
and distribution as defined by Sections 1 through 9 of this document.
"Licensor" shall mean the copyright owner or entity authorized by
the copyright owner that is granting the License.
"Legal Entity" shall mean the union of the acting entity and all
other entities that control, are controlled by, or are under common
control with that entity. For the purposes of this definition,
"control" means (i) the power, direct or indirect, to cause the
direction or management of such entity, whether by contract or
otherwise, or (ii) ownership of fifty percent (50%) or more of the
outstanding shares, or (iii) beneficial ownership of such entity.
"You" (or "Your") shall mean an individual or Legal Entity
exercising permissions granted by this License.
"Source" form shall mean the preferred form for making modifications,
including but not limited to software source code, documentation
source, and configuration files.
"Object" form shall mean any form resulting from mechanical
transformation or translation of a Source form, including but
not limited to compiled object code, generated documentation,
and conversions to other media types.
"Work" shall mean the work of authorship, whether in Source or
Object form, made available under the License, as indicated by a
copyright notice that is included in or attached to the work
(an example is provided in the Appendix below).
"Derivative Works" shall mean any work, whether in Source or Object
form, that is based on (or derived from) the Work and for which the
editorial revisions, annotations, elaborations, or other modifications
represent, as a whole, an original work of authorship. For the purposes
of this License, Derivative Works shall not include works that remain
separable from, or merely link (or bind by name) to the interfaces of,
the Work and Derivative Works thereof.
"Contribution" shall mean any work of authorship, including
the original version of the Work and any modifications or additions
to that Work or Derivative Works thereof, that is intentionally
submitted to Licensor for inclusion in the Work by the copyright owner
or by an individual or Legal Entity authorized to submit on behalf of
the copyright owner. For the purposes of this definition, "submitted"
means any form of electronic, verbal, or written communication sent
to the Licensor or its representatives, including but not limited to
communication on electronic mailing lists, source code control systems,
and issue tracking systems that are managed by, or on behalf of, the
Licensor for the purpose of discussing and improving the Work, but
excluding communication that is conspicuously marked or otherwise
designated in writing by the copyright owner as "Not a Contribution."
"Contributor" shall mean Licensor and any individual or Legal Entity
on behalf of whom a Contribution has been received by Licensor and
subsequently incorporated within the Work.
2. Grant of Copyright License. Subject to the terms and conditions of
this License, each Contributor hereby grants to You a perpetual,
worldwide, non-exclusive, no-charge, royalty-free, irrevocable
copyright license to reproduce, prepare Derivative Works of,
publicly display, publicly perform, sublicense, and distribute the
Work and such Derivative Works in Source or Object form.
3. Grant of Patent License. Subject to the terms and conditions of
this License, each Contributor hereby grants to You a perpetual,
worldwide, non-exclusive, no-charge, royalty-free, irrevocable
(except as stated in this section) patent license to make, have made,
use, offer to sell, sell, import, and otherwise transfer the Work,
where such license applies only to those patent claims licensable
by such Contributor that are necessarily infringed by their
Contribution(s) alone or by combination of their Contribution(s)
with the Work to which such Contribution(s) was submitted. If You
institute patent litigation against any entity (including a
cross-claim or counterclaim in a lawsuit) alleging that the Work
or a Contribution incorporated within the Work constitutes direct
or contributory patent infringement, then any patent licenses
granted to You under this License for that Work shall terminate
as of the date such litigation is filed.
4. Redistribution. You may reproduce and distribute copies of the
Work or Derivative Works thereof in any medium, with or without
modifications, and in Source or Object form, provided that You
meet the following conditions:
(a) You must give any other recipients of the Work or
Derivative Works a copy of this License; and
(b) You must cause any modified files to carry prominent notices
stating that You changed the files; and
(c) You must retain, in the Source form of any Derivative Works
that You distribute, all copyright, patent, trademark, and
attribution notices from the Source form of the Work,
excluding those notices that do not pertain to any part of
the Derivative Works; and
(d) If the Work includes a "NOTICE" text file as part of its
distribution, then any Derivative Works that You distribute must
include a readable copy of the attribution notices contained
within such NOTICE file, excluding those notices that do not
pertain to any part of the Derivative Works, in at least one
of the following places: within a NOTICE text file distributed
as part of the Derivative Works; within the Source form or
documentation, if provided along with the Derivative Works; or,
within a display generated by the Derivative Works, if and
wherever such third-party notices normally appear. The contents
of the NOTICE file are for informational purposes only and
do not modify the License. You may add Your own attribution
notices within Derivative Works that You distribute, alongside
or as an addendum to the NOTICE text from the Work, provided
that such additional attribution notices cannot be construed
as modifying the License.
You may add Your own copyright statement to Your modifications and
may provide additional or different license terms and conditions
for use, reproduction, or distribution of Your modifications, or
for any such Derivative Works as a whole, provided Your use,
reproduction, and distribution of the Work otherwise complies with
the conditions stated in this License.
5. Submission of Contributions. Unless You explicitly state otherwise,
any Contribution intentionally submitted for inclusion in the Work
by You to the Licensor shall be under the terms and conditions of
this License, without any additional terms or conditions.
Notwithstanding the above, nothing herein shall supersede or modify
the terms of any separate license agreement you may have executed
with Licensor regarding such Contributions.
6. Trademarks. This License does not grant permission to use the trade
names, trademarks, service marks, or product names of the Licensor,
except as required for reasonable and customary use in describing the
origin of the Work and reproducing the content of the NOTICE file.
7. Disclaimer of Warranty. Unless required by applicable law or
agreed to in writing, Licensor provides the Work (and each
Contributor provides its Contributions) on an "AS IS" BASIS,
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
implied, including, without limitation, any warranties or conditions
of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
PARTICULAR PURPOSE. You are solely responsible for determining the
appropriateness of using or redistributing the Work and assume any
risks associated with Your exercise of permissions under this License.
8. Limitation of Liability. In no event and under no legal theory,
whether in tort (including negligence), contract, or otherwise,
unless required by applicable law (such as deliberate and grossly
negligent acts) or agreed to in writing, shall any Contributor be
liable to You for damages, including any direct, indirect, special,
incidental, or consequential damages of any character arising as a
result of this License or out of the use or inability to use the
Work (including but not limited to damages for loss of goodwill,
work stoppage, computer failure or malfunction, or any and all
other commercial damages or losses), even if such Contributor
has been advised of the possibility of such damages.
9. Accepting Warranty or Additional Liability. While redistributing
the Work or Derivative Works thereof, You may choose to offer,
and charge a fee for, acceptance of support, warranty, indemnity,
or other liability obligations and/or rights consistent with this
License. However, in accepting such obligations, You may act only
on Your own behalf and on Your sole responsibility, not on behalf
of any other Contributor, and only if You agree to indemnify,
defend, and hold each Contributor harmless for any liability
incurred by, or claims asserted against, such Contributor by reason
of your accepting any such warranty or additional liability.
END OF TERMS AND CONDITIONS
APPENDIX: How to apply the Apache License to your work.
To apply the Apache License to your work, attach the following
boilerplate notice, with the fields enclosed by brackets "[]"
replaced with your own identifying information. (Don't include
the brackets!) The text should be enclosed in the appropriate
comment syntax for the file format. We also recommend that a
file or class name and description of purpose be included on the
same "printed page" as the copyright notice for easier
identification within third-party archives.
Copyright [yyyy] [name of copyright owner]
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.

44
README.rst Normal file
View File

@ -0,0 +1,44 @@
Openstack CI log processing
===========================
The goal of this repository is to provide and check
functionality of new log processing system base on
zuul log scraper tool.
Zuul Log Scraper
----------------
The Zuul Log Scraper tool is responsible for periodical
check by using Zuul CI API if there are new builds available
and if there are some, it would push the informations to
the log processing system.
Testing
-------
The part of Openstack CI log processing runs a complete testing and
continuous-integration environment, powered by `Zuul
<https://zuul-ci.org/>`__.
Any changes to logscraper script or tests will trigger jobs to
thoroughly test those changes.
Continuous Deployment
---------------------
Once changes are reviewed and committed, they will be applied
automatically to the production hosts.
Contributing
============
Contributions are welcome!
Currently only unit tests are available. In the future,
functional tests would be added.
Documentation
=============
The latest documentation is available at
http://docs.openstack.org/infra/ci-log-processing
That documentation is generated from this repository. You can generate
it yourself with ``tox -e docs``.

BIN
doc/assets/openstack.png Normal file
View File

Binary file not shown.
Side by Side

After

Width:  |  Height:  |  Size: 923 B

3
doc/requirements.txt Normal file
View File

@ -0,0 +1,3 @@
sphinx!=1.6.6,!=1.6.7 # BSD
openstackdocstheme>=1.32.0 # Apache-2.0
zuul-sphinx>=0.1.1

1
doc/source/_static/openstack.png Symbolic link
View File

@ -0,0 +1 @@
../../assets/openstack.png

51
doc/source/conf.py Normal file
View File

@ -0,0 +1,51 @@
# -*- coding: utf-8 -*-
#
# system-config documentation build configuration file
import datetime
import os
import sys
# -- General configuration ------------------------------------------------
# If extensions (or modules to document with autodoc) are in another directory,
# add these directories to sys.path here. If the directory is relative to the
# documentation root, use os.path.abspath to make it absolute, like shown here.
sys.path.insert(0, os.path.abspath('.'))
# Add any Sphinx extension module names here, as strings. They can be
# extensions coming with Sphinx (named 'sphinx.ext.*') or your custom
# ones.
extensions = ['zuul_sphinx']
# We have roles split between zuul-suitable roles at top level roles/*
# (automatically detected by zuul-sphinx) and playbook-specific roles
# (might have plugins, etc that make them unsuitable as potential zuul
# roles). Document both.
zuul_role_paths = ['playbooks/roles']
# The suffix of source filenames.
source_suffix = '.rst'
# The master toctree document.
master_doc = 'index'
# General information about the project.
project = u'Openstack System Documentation'
copyright = ('%d, Openstack Contributors.' % datetime.date.today().year)
# List of patterns, relative to source directory, that match files and
# directories to ignore when looking for source files.
exclude_patterns = ['_build']
# The name of the Pygments (syntax highlighting) style to use.
pygments_style = 'sphinx'
# -- Options for HTML output ----------------------------------------------
# This static content is used by the logo below
html_static_path = [
'_static/',
]
# The theme to use for HTML and HTML Help pages. See the documentation for
# a list of builtin themes.
html_theme = 'alabaster'
html_theme_options = {
'logo': 'openstack.png'
}
# -- Options for LaTeX output ---------------------------------------------
# Grouping the document tree into LaTeX files. List of tuples
# (source start file, target name, title,
# author, documentclass [howto, manual, or own class]).
latex_documents = [
('index', 'system-config.tex', u'system-config Documentation',
u'OpenStack CI Log Processing team', 'manual'),
]

28
doc/source/index.rst Normal file
View File

@ -0,0 +1,28 @@
Openstack CI Log Processing
===========================
This documentation covers the installation and maintenance of the
Openstack CI Log Processing system.
Security policy
---------------
If you find or suspect a security issue with any Openstack CI Log
Processing services, please inform the administrators via email at
service-incident@lists.opendev.org.
Contents:
.. sidebar:: HOWTOs
* :doc:`logscraper`
.. toctree::
:maxdepth: 2
logscraper
Indices and tables
==================
* :ref:`search`

58
doc/source/logscraper.rst Normal file
View File

@ -0,0 +1,58 @@
Logscraper
==========
The logscraper tool can be running as a one-shot log scrape or
as periodical check, if some new log jobs are available.
The tool have help function, that is showing available options for it.
It is available by typing:
.. code-block::
logscraper --help
Basic usage
-----------
Base on the use case, we can run logscraper.
Example:
* periodical check if there are some new logs for `openstack` tenant:
.. code-block::
logscraper --gearman-server somehost --zuul-api-url https://zuul.opendev.org/api/tenant/openstack --checkpoint-file /tmp/results-checkpoint.txt --follow
* one shot on getting logs from `zuul` tenant:
.. code-block::
logscraper --gearman-server localhost --zuul-api-url https://zuul.opendev.org/api/tenant/zuul --checkpoint-file /tmp/zuul-result-timestamp.txt
* periodically scrape logs from tenants: `openstack`, `zuul` and `local`
.. code-block::
logscraper --gearman-server localhost --zuul-api-url https://zuul.opendev.org/api/tenant/openstack --zuul-api-url https://zuul.opendev.org/api/tenant/zuul --zuul-api-url https://zuul.opendev.org/api/tenant/local --checkpoint-file /tmp/someresults.txt --follow
Containerize tool
-----------------
Instead of using `pip` tool, you can build your own container image
that contains logscraper tool, for example:
.. code-block::
docker build -t logscraper -f Dockerfile
Then you can execute commands that are described above.
NOTE: if you want to use parameter `--checkpoint-file`, you need to mount a volume
to the container, for example:
.. code-block::
docker run -v $(pwd):/checkpoint-dir:z -d logscraper logscraper --gearman-server somehost --zuul-api-url https://zuul.opendev.org/api/tenant/openstack --checkpoint-file /checkpoint-dir/checkpoint.txt --follow

0
logscraper/__init__.py Normal file
View File

472
logscraper/logscraper.py Executable file
View File

@ -0,0 +1,472 @@
#!/usr/bin/env python3
#
# Copyright (C) 2021 Red Hat
#
# 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.
"""
The goal is to push recent zuul builds into log gearman processor.
[ CLI ] -> [ Config ] -> [ ZuulFetcher ] -> [ LogPublisher ]
"""
import argparse
import gear
import json
import logging
import multiprocessing
import requests
import socket
import sys
import time
import urllib
import yaml
from distutils.version import StrictVersion as s_version
GEARMAN_SERVER = None
GEARMAN_PORT = None
file_to_check = [
"job-output.txt.gz",
"job-output.txt",
"postci.txt",
"postci.txt.gz",
"var/log/extra/logstash.txt",
"var/log/extra/logstash.txt.gz",
"var/log/extra/errors.txt",
"var/log/extra/errors.txt.gz",
]
# From: https://opendev.org/opendev/base-jobs/src/branch/master/roles/submit-logstash-jobs/defaults/main.yaml # noqa
logstash_processor_config = """
files:
- name: job-output.txt
tags:
- console
- console.html
- name: grenade.sh.txt
tags:
- console
- console.html
- name: devstacklog.txt(?!.*summary)
tags:
- console
- console.html
- name: apache/keystone.txt
tags:
- screen
- oslofmt
- name: apache/horizon_error.txt
tags:
- apacheerror
# TODO(clarkb) Add swift proxy logs here.
- name: syslog.txt
tags:
- syslog
- name: tempest.txt
tags:
- screen
- oslofmt
- name: javelin.txt
tags:
- screen
- oslofmt
# Neutron index log files (files with messages from all test cases)
- name: dsvm-functional-index.txt
tags:
- oslofmt
- name: dsvm-fullstack-index.txt
tags:
- oslofmt
- name: screen-s-account.txt
tags:
- screen
- apachecombined
- name: screen-s-container.txt
tags:
- screen
- apachecombined
- name: screen-s-object.txt
tags:
- screen
- apachecombined
# tripleo logs
- name: postci.txt
tags:
- console
- postci
- name: var/log/extra/logstash.txt
tags:
- console
- postci
- name: var/log/extra/errors.txt
tags:
- console
- errors
# wildcard logs
- name: devstack-gate-.*.txt
tags:
- console
- console.html
# NOTE(mriedem): Logs that are known logstash index OOM killers are
# blacklisted here until fixed.
# screen-monasca-persister.txt: https://storyboard.openstack.org/#!/story/2003911
# screen-ovn-northd.txt: https://bugs.launchpad.net/networking-ovn/+bug/1795069
- name: screen-(?!(peakmem_tracker|dstat|karaf|kubelet|mistral-engine|monasca-persister|monasca-api|ovn-northd|q-svc)).*.txt
tags:
- screen
- oslofmt
""" # noqa
###############################################################################
# CLI #
###############################################################################
def get_arguments():
parser = argparse.ArgumentParser(description="Fetch and push last Zuul "
"CI job logs into gearman.")
parser.add_argument("--zuul-api-url", help="URL(s) for Zuul API. Parameter"
" can be set multiple times.",
required=True,
action='append')
parser.add_argument("--gearman-server", help="Gearman host addresss",
required=True)
parser.add_argument("--gearman-port", help="Gearman listen port. "
"Defaults to 4731.",
default=4731)
parser.add_argument("--follow", help="Keep polling zuul builds",
action="store_true")
parser.add_argument("--insecure", help="Skip validating SSL cert",
action="store_false")
parser.add_argument("--checkpoint-file", help="File that will keep "
"information about last uuid timestamp for a job.")
parser.add_argument("--logstash-url", help="When provided, script will "
"check connection to Logstash service before sending "
"to log processing system. For example: "
"logstash.local:9999")
parser.add_argument("--workers", help="Worker processes for logscraper",
default=1)
parser.add_argument("--max-skipped", help="How many job results should be "
"checked until last uuid written in checkpoint file "
"is founded",
default=500)
parser.add_argument("--debug", help="Print more information",
action="store_true")
args = parser.parse_args()
return args
###############################################################################
# Configuration of this process #
###############################################################################
class Config:
def __init__(self, args, zuul_api_url):
self.checkpoint = None
url_path = zuul_api_url.split("/")
if url_path[-3] != "api" and url_path[-2] != "tenant":
print(
"ERROR: zuul-api-url needs to be in the form "
"of: https://<fqdn>/api/tenant/<tenant-name>"
)
sys.exit(1)
self.tenant = url_path[-1]
self.filename = "%s-%s" % (args.checkpoint_file, self.tenant)
try:
with open(self.filename) as f:
self.checkpoint = f.readline()
except Exception:
logging.exception("Can't load the checkpoint. Creating file")
def save(self, job_uuid):
try:
with open(self.filename, 'w') as f:
f.write(job_uuid)
except Exception as e:
raise("Can not write status to the checkpoint file %s" % e)
###############################################################################
# Log Processing #
###############################################################################
class LogMatcher(object):
def __init__(self, server, port, success, log_url, host_vars):
self.client = gear.Client()
self.client.addServer(server, port)
self.hosts = host_vars
self.success = success
self.log_url = log_url
def submitJobs(self, jobname, files, result):
self.client.waitForServer(90)
ret = []
for f in files:
output = self.makeOutput(f, result)
output = json.dumps(output).encode("utf8")
job = gear.TextJob(jobname, output)
self.client.submitJob(job, background=True)
ret.append(dict(handle=job.handle, arguments=output))
return ret
def makeOutput(self, file_object, result):
output = {}
output["retry"] = False
output["event"] = self.makeEvent(file_object, result)
output["source_url"] = output["event"]["fields"]["log_url"]
return output
def makeEvent(self, file_object, result):
out_event = {}
tags = []
out_event["fields"] = self.makeFields(file_object, result)
config_files = yaml.safe_load(logstash_processor_config)
for f in config_files["files"]:
if file_object in f["name"] or \
file_object.replace(".gz", "") in f["name"]:
tags = f["tags"]
break
out_event["tags"] = [file_object] + tags
return out_event
def makeFields(self, filename, result):
fields = {}
fields["build_node"] = "zuul-executor"
fields["filename"] = filename
fields["build_name"] = result["job_name"]
fields["build_status"] = (
"SUCCESS" if result["result"] == "SUCCESS" else "FAILURE"
)
fields["project"] = result["project"]
fields["voting"] = int(result["voting"])
fields["build_set"] = result["buildset"]
fields["build_queue"] = result["pipeline"]
fields["build_ref"] = result["ref"]
fields["build_branch"] = result.get("branch", "UNKNOWN")
fields["build_zuul_url"] = "N/A"
if "change" in result:
fields["build_change"] = result["change"]
fields["build_patchset"] = result["patchset"]
elif "newrev" in result:
fields["build_newrev"] = result.get("newrev", "UNKNOWN")
fields["node_provider"] = "local"
log_url = urllib.parse.urljoin(result["log_url"], filename)
fields["log_url"] = log_url
fields["tenant"] = result["tenant"]
if "executor" in result and "hostname" in result["executor"]:
fields["zuul_executor"] = result["executor"]["hostname"]
fields["build_uuid"] = result["buildset"]["uuid"]
return fields
###############################################################################
# Fetch zuul builds #
###############################################################################
def parse_version(zuul_version_txt):
"""Parse the zuul version returned by the different services:
>>> parse_version("4.6.0-1.el7")
StrictVersion ('4.6')
>>> parse_version("4.10.2.dev6 22f04be1")
StrictVersion ('4.10.2')
>>> parse_version("4.10.2.dev6 22f04be1") > parse_version("4.6.0-1.el7")
True
>>> parse_version("4.6.0-1.el7") > parse_version("4.7.0")
False
"""
if not zuul_version_txt:
return
zuul_version = zuul_version_txt
# drop rpm package suffix
zuul_version = zuul_version.split("-")[0]
# drop pip package suffix
zuul_version = zuul_version.split(".dev")[0]
try:
return s_version(zuul_version)
except Exception:
raise ValueError("Invalid zuul version: %s" % zuul_version_txt)
def _zuul_complete_available(zuul_url, insecure):
"""Return additional parameter for zuul url
When Zuul version is newer that 4.7.0, return additional
parameter.
"""
url = zuul_url + "/status"
zuul_status = requests.get(url, verify=insecure)
zuul_status.raise_for_status()
zuul_version = parse_version(zuul_status.json().get("zuul_version"))
if zuul_version and zuul_version >= s_version("4.7.0"):
return "&complete=true"
def get_builds(zuul_url, insecure):
"""Yield builds dictionary."""
pos, size = 0, 100
zuul_url = zuul_url.rstrip("/")
zuul_complete = _zuul_complete_available(zuul_url, insecure)
if zuul_complete:
extra = "" + zuul_complete
base_url = zuul_url + "/builds?limit=" + str(size) + extra
known_builds = set()
while True:
url = base_url + "&skip=" + str(pos)
logging.info("Getting job results %s", url)
jobs_result = requests.get(url, verify=insecure)
jobs_result.raise_for_status()
for job in jobs_result.json():
# It is important here to check we didn't yield builds twice,
# as this can happen when using skip if new build get reported
# between the two requests.
if job["uuid"] not in known_builds:
yield job
known_builds.add(job["uuid"])
pos += 1
def get_last_job_results(zuul_url, insecure, max_skipped, last_uuid):
"""Yield builds until we find the last uuid."""
count = 0
for build in get_builds(zuul_url, insecure):
if count > max_skipped:
break
if build["uuid"] == last_uuid:
break
yield build
count += 1
###############################################################################
# Log scraper #
###############################################################################
def check_specified_files(job_result):
"""Return list of specified files if they exists on logserver. """
available_files = []
for f in file_to_check:
if not job_result["log_url"]:
continue
response = requests.get("%s%s" % (job_result["log_url"], f))
if response.status_code == 200:
available_files.append(f)
return available_files
def setup_logging(debug):
if debug:
logging.basicConfig(format="%(asctime)s %(message)s",
level=logging.DEBUG)
else:
logging.basicConfig(level=logging.INFO)
logging.debug("Zuul Job Scraper is starting...")
def run_build(build):
"""Submit job informations into log processing system. """
logging.info(
"Processing logs for %s | %s | %s | %s",
build["job_name"],
build["end_time"],
build["result"],
build["uuid"],
)
results = dict(files=[], jobs=[], invocation={})
lmc = LogMatcher(
GEARMAN_SERVER,
GEARMAN_PORT,
build["result"],
build["log_url"],
{},
)
results["files"] = check_specified_files(build)
lmc.submitJobs("push-log", results["files"], build)
def check_connection(logstash_url):
"""Return True when Logstash service is reachable
Check if service is up before pushing results.
"""
host, port = logstash_url.split(':')
logging.debug("Checking connection to %s on port %s" % (host, port))
with socket.socket(socket.AF_INET, socket.SOCK_STREAM) as s:
return s.connect_ex((host, port)) == 0
def run_scraping(args, zuul_api_url):
"""Get latest job results and push them into log processing service.
On the end, write newest uuid into checkpoint file, so in the future
script will not push log duplication.
"""
config = Config(args, zuul_api_url)
builds = []
for build in get_last_job_results(zuul_api_url, args.insecure,
args.max_skipped, config.checkpoint):
logging.debug("Working on build %s" % build['uuid'])
# add missing informations
build["tenant"] = config.tenant
builds.append(build)
logging.info("Processing %d builds", len(builds))
if args.logstash_url and not check_connection(args.logstash_url):
logging.critical("Can not connect to logstash %s. "
"Is it up?" % args.logstash_url)
return
if builds:
pool = multiprocessing.Pool(int(args.workers))
try:
pool.map(run_build, builds)
finally:
config.save(builds[0]['uuid'])
def run(args):
for zuul_api_url in args.zuul_api_url:
logging.info("Starting checking logs for %s" % zuul_api_url)
run_scraping(args, zuul_api_url)
def main():
global GEARMAN_SERVER
global GEARMAN_PORT
args = get_arguments()
setup_logging(args.debug)
GEARMAN_SERVER = args.gearman_server
GEARMAN_PORT = args.gearman_port
while True:
run(args)
if not args.follow:
break
time.sleep(120)
if __name__ == "__main__":
main()

0
logscraper/tests/__init__.py Normal file
View File

38
logscraper/tests/base.py Normal file
View File

@ -0,0 +1,38 @@
#!/usr/bin/env python3
#
# Copyright (C) 2021 Red Hat
#
# 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.
import os
import fixtures
import testtools
class TestCase(testtools.TestCase):
true = ('True', 'true', '1', 'yes')
def setUp(self):
super(TestCase, self).setUp()
if os.environ.get('OS_STDOUT_CAPTURE') in self.true:
stdout = self.useFixture(fixtures.StringStream('stdout')).stream
self.useFixture(fixtures.MonkeyPatch('sys.stdout', stdout))
if os.environ.get('OS_STDERR_CAPTURE') in self.true:
stderr = self.useFixture(fixtures.StringStream('stderr')).stream
self.useFixture(fixtures.MonkeyPatch('sys.stderr', stderr))
if (os.environ.get('OS_LOG_CAPTURE') != 'False' and os.environ.get(
'OS_LOG_CAPTURE') != '0'):
self.useFixture(fixtures.LoggerFixture(nuke_handlers=False,
level=None))

378
logscraper/tests/test_logscraper.py Normal file
View File

@ -0,0 +1,378 @@
#!/usr/bin/env python3
#
# Copyright (C) 2021 Red Hat
#
# 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.
import json
from logscraper import logscraper
from logscraper.tests import base
from unittest import mock
builds_result = [{
'uuid': 'a0f8968bf8534409bb998e079b41d658',
'job_name': 'openstack-tox-py38',
'result': 'SUCCESS',
'held': False,
'start_time': '2021-11-04T08:21:19',
'end_time': '2021-11-04T08:26:26',
'duration': 307.0,
'voting': True,
'log_url': 'https://t.com/openstack/a0f8968/',
'nodeset': 'ubuntu-focal',
'error_detail': None,
'final': True,
'artifacts': [],
'provides': [],
'project': 'openstack/tempest',
'branch': 'master',
'pipeline': 'check',
'change': 806255,
'patchset': '9',
'ref': 'refs/changes/55/806255/9',
'newrev': None,
'ref_url': 'https://review.opendev.org/806255',
'event_id': 'cfa1a0a471f3447ca9b81b20132234bd',
'buildset': {
'uuid': 'bf11828235c649ff859ad87d7c4aa525'
}
}, {
'uuid': '39828646e9b847b6b8560df93838c405',
'job_name': 'tripleo-centos-8',
'result': 'FAILURE',
'held': False,
'start_time': '2021-11-04T08:17:46',
'end_time': '2021-11-04T08:27:49',
'duration': 603.0,
'voting': True,
'log_url': 'https://t.com/tripleo-8/3982864/',
'nodeset': 'centos-8-stream',
'error_detail': None,
'final': True,
'artifacts': [],
'provides': [],
'project': 'openstack/tripleo-ansible',
'branch': 'master',
'pipeline': 'check',
'change': 816445,
'patchset': '1',
'ref': 'refs/changes/45/816445/1',
'newrev': None,
'ref_url': 'https://review.opendev.org/816445',
'event_id': '0b8a45988023464fba508d72e51e23ad',
'buildset': {
'uuid': '4a0ffebe30a94efe819fffc03cf33ea4'
}
}, {
'uuid': 'a3fbc73ce599466e9ae1645f6b708f1b',
'job_name': 'openstack-tox-lower-constraints',
'result': 'ABORTED',
'held': False,
'start_time': '2021-11-04T08:04:34',
'end_time': '2021-11-04T08:04:52',
'duration': 18,
'voting': True,
'log_url': None,
'nodeset': 'ubuntu-bionic',
'error_detail': None,
'final': True,
'artifacts': [],
'provides': [],
'project': 'openstack/nova',
'branch': 'stable/victoria',
'pipeline': 'check',
'change': 816486,
'patchset': '1',
'ref': 'refs/changes/86/816486/1',
'newrev': None,
'ref_url': 'https://review.opendev.org/816486',
'event_id': '7be89d6aae0944949c3e1b7c811794b0',
'buildset': {'uuid': 'bd044dfe3ecc484fbbf74fdeb7fb56aa'}
}]
class FakeArgs(object):
def __init__(self, zuul_api_url=None, gearman_server=None,
gearman_port=None, follow=False, insecure=False,
checkpoint_file=None, ignore_checkpoint=None,
logstash_url=None, workers=None, max_skipped=None):
self.zuul_api_url = zuul_api_url
self.gearman_server = gearman_server
self.gearman_port = gearman_port
self.follow = follow
self.insecure = insecure
self.checkpoint_file = checkpoint_file
self.ignore_checkpoint = ignore_checkpoint
self.logstash_url = logstash_url
self.workers = workers
self.max_skipped = max_skipped
class TestScraper(base.TestCase):
def test_parse_version(self):
ver1 = logscraper.parse_version('4.6.0-1.el7')
ver2 = logscraper.parse_version('4.10.2.dev6-22f04be1')
ver3 = logscraper.parse_version('4.10.2.dev6 22f04be1')
self.assertEqual('4.6', ver1)
self.assertEqual('4.10.2', ver2)
self.assertEqual('4.10.2', ver3)
self.assertRaises(ValueError,
logscraper.parse_version, '123412test123')
@mock.patch('socket.socket')
def test_check_connection(self, mock_socket):
with mock.patch('argparse.ArgumentParser.parse_args') as mock_args:
mock_args.return_value = FakeArgs(
zuul_api_url='somehost.com',
gearman_server='localhost',
logstash_url='localhost:9999')
args = logscraper.get_arguments()
logscraper.check_connection(args.logstash_url)
mock_socket.assert_called_once()
@mock.patch('socket.socket')
def test_check_connection_wrong_host(self, mock_socket):
with mock.patch('argparse.ArgumentParser.parse_args') as mock_args:
mock_args.return_value = FakeArgs(
zuul_api_url='somehost.com',
gearman_server='localhost',
logstash_url='localhost')
args = logscraper.get_arguments()
self.assertRaises(ValueError, logscraper.check_connection,
args.logstash_url)
@mock.patch('multiprocessing.pool.Pool.map')
@mock.patch('builtins.open', new_callable=mock.mock_open())
@mock.patch('os.path.isfile')
@mock.patch('logscraper.logscraper.GEARMAN_PORT',
return_value=4731)
@mock.patch('logscraper.logscraper.GEARMAN_SERVER',
return_value='localhost')
@mock.patch('logscraper.logscraper.check_specified_files',
return_value=['job-output.txt'])
@mock.patch('logscraper.logscraper.LogMatcher.submitJobs')
@mock.patch('argparse.ArgumentParser.parse_args',
return_value=FakeArgs(
zuul_api_url=['http://somehost.com/api/tenant/tenant1'],
gearman_server='localhost',
workers=1))
def test_run_scraping(self, mock_args, mock_submit, mock_files,
mock_server, mock_port, mock_isfile, mock_readfile,
mock_map):
with mock.patch('logscraper.logscraper.get_last_job_results'
) as mock_job_results:
args = logscraper.get_arguments()
mock_job_results.return_value = [builds_result[0]]
logscraper.run_scraping(args,
'http://somehost.com/api/tenant/tenant1')
self.assertEqual(builds_result[0], mock_map.call_args.args[1][0])
@mock.patch('logscraper.logscraper.run_scraping')
def test_run(self, mock_scraping):
with mock.patch('argparse.ArgumentParser.parse_args') as mock_args:
mock_args.return_value = FakeArgs(
zuul_api_url=['http://somehost.com/api/tenant/tenant1',
'http://somehost.com/api/tenant/tenant2',
'http://somehost.com/api/tenant/tenant3'],
gearman_server='localhost')
args = logscraper.get_arguments()
logscraper.run(args)
self.assertEqual(3, mock_scraping.call_count)
class TestConfig(base.TestCase):
@mock.patch('sys.exit')
def test_save(self, mock_sys):
# Assume that url is wrong so it raise IndexError
with mock.patch('argparse.ArgumentParser.parse_args') as mock_args:
mock_args.return_value = FakeArgs(
zuul_api_url='somehost.com',
gearman_server='localhost')
args = logscraper.get_arguments()
self.assertRaises(IndexError, logscraper.Config, args,
args.zuul_api_url)
# url without tenant
with mock.patch('argparse.ArgumentParser.parse_args') as mock_args:
mock_args.return_value = FakeArgs(
zuul_api_url='https://somehost.com',
gearman_server='localhost')
args = logscraper.get_arguments()
logscraper.Config(args, args.zuul_api_url)
mock_sys.assert_called()
# correct url without job name
with mock.patch('argparse.ArgumentParser.parse_args') as mock_args:
mock_args.return_value = FakeArgs(
zuul_api_url='http://somehost.com/api/tenant/sometenant',
gearman_server='localhost',
checkpoint_file='/tmp/testfile')
args = logscraper.get_arguments()
with mock.patch('builtins.open',
new_callable=mock.mock_open()
) as mock_file:
some_config = logscraper.Config(args, args.zuul_api_url)
some_config.save('123412312341234')
mock_file.assert_called_with('/tmp/testfile-sometenant', 'w')
class TestLogMatcher(base.TestCase):
@mock.patch('gear.TextJob')
@mock.patch('gear.Client.submitJob')
@mock.patch('gear.BaseClient.waitForServer')
def test_submitJobs(self, mock_gear, mock_gear_client, mock_gear_job):
result = builds_result[0]
result['files'] = ['job-output.txt']
result['tenant'] = 'sometenant'
parsed_job = {
"build_branch": "master",
"build_change": 806255,
"build_name": "openstack-tox-py38",
"build_node": "zuul-executor",
"build_patchset": "9",
"build_queue": "check",
"build_ref": "refs/changes/55/806255/9",
"build_set": {"uuid": "bf11828235c649ff859ad87d7c4aa525"},
"build_status": "SUCCESS",
"build_uuid": "bf11828235c649ff859ad87d7c4aa525",
"build_zuul_url": "N/A",
"filename": "job-output.txt",
"log_url": "https://t.com/openstack/a0f8968/job-output.txt",
"node_provider": "local",
"project": "openstack/tempest",
"tenant": "sometenant",
"voting": 1}
expected_gear_job = {"retry": False, "event": {
"fields": parsed_job,
"tags": ["job-output.txt", "console", "console.html"]},
"source_url": "https://t.com/openstack/a0f8968/job-output.txt"}
with mock.patch('argparse.ArgumentParser.parse_args') as mock_args:
mock_args.return_value = FakeArgs(
zuul_api_url='http://somehost.com/api/tenant/sometenant',
gearman_server='localhost',
gearman_port='4731')
args = logscraper.get_arguments()
lmc = logscraper.LogMatcher(args.gearman_server, args.gearman_port,
result['result'], result['log_url'],
{})
lmc.submitJobs('push-log', result['files'], result)
mock_gear_client.assert_called_once()
self.assertEqual(
expected_gear_job,
json.loads(mock_gear_job.call_args.args[1].decode('utf-8'))
)
@mock.patch('gear.TextJob')
@mock.patch('gear.Client.submitJob')
@mock.patch('gear.BaseClient.waitForServer')
def test_submitJobs_failure(self, mock_gear, mock_gear_client,
mock_gear_job):
# Take job result that build_status is "ABORTED"
result = builds_result[1]
result['files'] = ['job-output.txt']
result['tenant'] = 'sometenant'
parsed_job = {
'build_branch': 'master',
'build_change': 816445,
'build_name': 'tripleo-centos-8',
'build_node': 'zuul-executor',
'build_patchset': '1',
'build_queue': 'check',
'build_ref': 'refs/changes/45/816445/1',
'build_set': {'uuid': '4a0ffebe30a94efe819fffc03cf33ea4'},
'build_status': 'FAILURE',
'build_uuid': '4a0ffebe30a94efe819fffc03cf33ea4',
'build_zuul_url': 'N/A',
'filename': 'job-output.txt',
'log_url': 'https://t.com/tripleo-8/3982864/job-output.txt',
'node_provider': 'local',
'project': 'openstack/tripleo-ansible',
'tenant': 'sometenant',
'voting': 1}
expected_gear_job = {"retry": False, "event": {
"fields": parsed_job,
"tags": ["job-output.txt", "console", "console.html"]},
"source_url": "https://t.com/tripleo-8/3982864/job-output.txt"}
with mock.patch('argparse.ArgumentParser.parse_args') as mock_args:
mock_args.return_value = FakeArgs(
zuul_api_url='http://somehost.com/api/tenant/sometenant',
gearman_server='localhost',
gearman_port='4731')
args = logscraper.get_arguments()
lmc = logscraper.LogMatcher(args.gearman_server, args.gearman_port,
result['result'], result['log_url'],
{})
lmc.submitJobs('push-log', result['files'], result)
mock_gear_client.assert_called_once()
self.assertEqual(
expected_gear_job,
json.loads(mock_gear_job.call_args.args[1].decode('utf-8'))
)
@mock.patch('gear.TextJob')
@mock.patch('gear.Client.submitJob')
@mock.patch('gear.BaseClient.waitForServer')
def test_submitJobs_aborted(self, mock_gear, mock_gear_client,
mock_gear_job):
# Take job result that build_status is "ABORTED"
result = builds_result[2]
result['files'] = ['job-output.txt']
result['tenant'] = 'sometenant'
parsed_job = {
'build_branch': 'stable/victoria',
'build_change': 816486,
'build_name': 'openstack-tox-lower-constraints',
'build_node': 'zuul-executor',
'build_patchset': '1',
'build_queue': 'check',
'build_ref': 'refs/changes/86/816486/1',
'build_set': {'uuid': 'bd044dfe3ecc484fbbf74fdeb7fb56aa'},
'build_status': 'FAILURE',
'build_uuid': 'bd044dfe3ecc484fbbf74fdeb7fb56aa',
'build_zuul_url': 'N/A',
'filename': 'job-output.txt',
'log_url': 'job-output.txt',
'node_provider': 'local',
'project': 'openstack/nova',
'tenant': 'sometenant',
'voting': 1}
# NOTE: normally ABORTED jobs does not provide log_url,
# so source_url will be just a file to iterate.
# In the logscraper, aborted jobs are just skipped.
expected_gear_job = {"retry": False, "event": {
"fields": parsed_job,
"tags": ["job-output.txt", "console", "console.html"]},
"source_url": "job-output.txt"}
with mock.patch('argparse.ArgumentParser.parse_args') as mock_args:
mock_args.return_value = FakeArgs(
zuul_api_url='http://somehost.com/api/tenant/sometenant',
gearman_server='localhost',
gearman_port='4731')
args = logscraper.get_arguments()
lmc = logscraper.LogMatcher(args.gearman_server, args.gearman_port,
result['result'], result['log_url'],
{})
lmc.submitJobs('push-log', result['files'], result)
mock_gear_client.assert_called_once()
self.assertEqual(
expected_gear_job,
json.loads(mock_gear_job.call_args.args[1].decode('utf-8'))
)

4
requirements.txt Normal file
View File

@ -0,0 +1,4 @@
pbr>=1.6 # Apache-2.0
gear<0.17
requests<2.27 # Apache-2.0
PyYAML<6.1 # MIT

23
setup.cfg Normal file
View File

@ -0,0 +1,23 @@
[metadata]
name = logscraper
summary = OpenStack CI Log Processing tool
description-file =
README.rst
author = Openstack Contributors
author-email = openstack-discuss@lists.openstack.org
home-page = http://docs.openstack.org/infra/ci-log-processing
classifier =
Environment :: OpenStack
Intended Audience :: Information Technology
Intended Audience :: System Administrators
License :: OSI Approved :: Apache Software License
Operating System :: POSIX :: Linux
Programming Language :: Python
Programming Language :: Python :: 3
Programming Language :: Python :: 3.6
Programming Language :: Python :: 3.7
Programming Language :: Python :: 3.8
[entry_points]
console_scripts =
logscraper = logscraper.logscraper:main

19
setup.py Normal file
View File

@ -0,0 +1,19 @@
# Copyright (C) 2021 Red Hat
#
# 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.
import setuptools
setuptools.setup(
setup_requires=['pbr'],
pbr=True)

5
test-requirements.txt Normal file
View File

@ -0,0 +1,5 @@
hacking<4.1.1 # Apache-2.0
flake8<3.8.5
pep8<1.7.2
testtools<2.5.1 # MIT
stestr<3.3 # Apache-2.0

30
tox.ini Normal file
View File

@ -0,0 +1,30 @@
[tox]
envlist = linters,docs,py38
[testenv]
basepython = python3
usedevelop = True
deps = -r{toxinidir}/requirements.txt
-r{toxinidir}/test-requirements.txt
allowlist_externals = find
commands =
find . -type f -name "*.pyc" -delete
find . -type d -name '__pycache__' -delete
stestr run {posargs}
[testenv:pep8]
commands = flake8
[testenv:linters]
commands = flake8
[testenv:venv]
commands = {posargs}
[flake8]
show-source = True
exclude = .venv,.tox,dist,doc,build,*.egg
[testenv:docs]
deps = -r{toxinidir}/doc/requirements.txt
commands = sphinx-build -W -E -b html doc/source doc/build/html