├── .gitignore ├── CONTRIBUTING.md ├── Dockerfile ├── LICENSE ├── Makefile ├── README.md ├── deploy ├── clusterrole.yaml ├── clusterrolebinding.yaml ├── deployment.yaml └── serviceaccount.yaml ├── requirements.txt └── spot_price_monitor ├── __init__.py └── spot_price_monitor.py /.gitignore: -------------------------------------------------------------------------------- 1 | # Byte-compiled / optimized / DLL files 2 | __pycache__/ 3 | *.py[cod] 4 | *$py.class 5 | 6 | # C extensions 7 | *.so 8 | 9 | # Distribution / packaging 10 | .Python 11 | env/ 12 | build/ 13 | develop-eggs/ 14 | dist/ 15 | downloads/ 16 | eggs/ 17 | .eggs/ 18 | lib/ 19 | lib64/ 20 | parts/ 21 | sdist/ 22 | var/ 23 | wheels/ 24 | *.egg-info/ 25 | .installed.cfg 26 | *.egg 27 | 28 | # PyInstaller 29 | # Usually these files are written by a python script from a template 30 | # before PyInstaller builds the exe, so as to inject date/other infos into it. 31 | *.manifest 32 | *.spec 33 | 34 | # Installer logs 35 | pip-log.txt 36 | pip-delete-this-directory.txt 37 | 38 | # Unit test / coverage reports 39 | htmlcov/ 40 | .tox/ 41 | .coverage 42 | .coverage.* 43 | .cache 44 | nosetests.xml 45 | coverage.xml 46 | *.cover 47 | .hypothesis/ 48 | 49 | # Translations 50 | *.mo 51 | *.pot 52 | 53 | # Django stuff: 54 | *.log 55 | local_settings.py 56 | 57 | # Flask stuff: 58 | instance/ 59 | .webassets-cache 60 | 61 | # Scrapy stuff: 62 | .scrapy 63 | 64 | # Sphinx documentation 65 | docs/_build/ 66 | 67 | # PyBuilder 68 | target/ 69 | 70 | # Jupyter Notebook 71 | .ipynb_checkpoints 72 | 73 | # pyenv 74 | .python-version 75 | 76 | # celery beat schedule file 77 | celerybeat-schedule 78 | 79 | # SageMath parsed files 80 | *.sage.py 81 | 82 | # dotenv 83 | .env 84 | 85 | # virtualenv 86 | .venv 87 | venv/ 88 | ENV/ 89 | 90 | # Spyder project settings 91 | .spyderproject 92 | .spyproject 93 | 94 | # Rope project settings 95 | .ropeproject 96 | 97 | # mkdocs documentation 98 | /site 99 | 100 | # mypy 101 | .mypy_cache/ 102 | 103 | # Wercker local cache 104 | .wercker/ 105 | 106 | # Kubernetes local config 107 | credentials/ 108 | kubeconfig 109 | -------------------------------------------------------------------------------- /CONTRIBUTING.md: -------------------------------------------------------------------------------- 1 | # Contributing 2 | To contribute to this project, please fork the repo and PR back any changes you make. 3 | 4 | ## Pull Requests and Issues 5 | We track bugs and issues using Github. 6 | 7 | If you find a bug, please open an Issue. 8 | 9 | If you want to fix a bug, please fork, fix the bug and open a PR back to this repo. 10 | Please mention the open bug issue number within your PR if applicable. 11 | -------------------------------------------------------------------------------- /Dockerfile: -------------------------------------------------------------------------------- 1 | FROM python:3.6-alpine 2 | 3 | ARG VERSION=undefined 4 | ENV VERSION ${VERSION} 5 | 6 | COPY spot_price_monitor/spot_price_monitor.py / 7 | COPY requirements.txt / 8 | 9 | RUN apk add --no-cache --virtual build-dependencies gcc musl-dev && \ 10 | pip install --no-cache-dir -r /requirements.txt && \ 11 | apk del build-dependencies 12 | 13 | ENTRYPOINT ["python", "-u", "spot_price_monitor.py"] 14 | -------------------------------------------------------------------------------- /LICENSE: -------------------------------------------------------------------------------- 1 | Apache License 2 | Version 2.0, January 2004 3 | http://www.apache.org/licenses/ 4 | 5 | TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION 6 | 7 | 1. Definitions. 8 | 9 | "License" shall mean the terms and conditions for use, reproduction, 10 | and distribution as defined by Sections 1 through 9 of this document. 11 | 12 | "Licensor" shall mean the copyright owner or entity authorized by 13 | the copyright owner that is granting the License. 14 | 15 | "Legal Entity" shall mean the union of the acting entity and all 16 | other entities that control, are controlled by, or are under common 17 | control with that entity. For the purposes of this definition, 18 | "control" means (i) the power, direct or indirect, to cause the 19 | direction or management of such entity, whether by contract or 20 | otherwise, or (ii) ownership of fifty percent (50%) or more of the 21 | outstanding shares, or (iii) beneficial ownership of such entity. 22 | 23 | "You" (or "Your") shall mean an individual or Legal Entity 24 | exercising permissions granted by this License. 25 | 26 | "Source" form shall mean the preferred form for making modifications, 27 | including but not limited to software source code, documentation 28 | source, and configuration files. 29 | 30 | "Object" form shall mean any form resulting from mechanical 31 | transformation or translation of a Source form, including but 32 | not limited to compiled object code, generated documentation, 33 | and conversions to other media types. 34 | 35 | "Work" shall mean the work of authorship, whether in Source or 36 | Object form, made available under the License, as indicated by a 37 | copyright notice that is included in or attached to the work 38 | (an example is provided in the Appendix below). 39 | 40 | "Derivative Works" shall mean any work, whether in Source or Object 41 | form, that is based on (or derived from) the Work and for which the 42 | editorial revisions, annotations, elaborations, or other modifications 43 | represent, as a whole, an original work of authorship. For the purposes 44 | of this License, Derivative Works shall not include works that remain 45 | separable from, or merely link (or bind by name) to the interfaces of, 46 | the Work and Derivative Works thereof. 47 | 48 | "Contribution" shall mean any work of authorship, including 49 | the original version of the Work and any modifications or additions 50 | to that Work or Derivative Works thereof, that is intentionally 51 | submitted to Licensor for inclusion in the Work by the copyright owner 52 | or by an individual or Legal Entity authorized to submit on behalf of 53 | the copyright owner. For the purposes of this definition, "submitted" 54 | means any form of electronic, verbal, or written communication sent 55 | to the Licensor or its representatives, including but not limited to 56 | communication on electronic mailing lists, source code control systems, 57 | and issue tracking systems that are managed by, or on behalf of, the 58 | Licensor for the purpose of discussing and improving the Work, but 59 | excluding communication that is conspicuously marked or otherwise 60 | designated in writing by the copyright owner as "Not a Contribution." 61 | 62 | "Contributor" shall mean Licensor and any individual or Legal Entity 63 | on behalf of whom a Contribution has been received by Licensor and 64 | subsequently incorporated within the Work. 65 | 66 | 2. Grant of Copyright License. Subject to the terms and conditions of 67 | this License, each Contributor hereby grants to You a perpetual, 68 | worldwide, non-exclusive, no-charge, royalty-free, irrevocable 69 | copyright license to reproduce, prepare Derivative Works of, 70 | publicly display, publicly perform, sublicense, and distribute the 71 | Work and such Derivative Works in Source or Object form. 72 | 73 | 3. Grant of Patent License. Subject to the terms and conditions of 74 | this License, each Contributor hereby grants to You a perpetual, 75 | worldwide, non-exclusive, no-charge, royalty-free, irrevocable 76 | (except as stated in this section) patent license to make, have made, 77 | use, offer to sell, sell, import, and otherwise transfer the Work, 78 | where such license applies only to those patent claims licensable 79 | by such Contributor that are necessarily infringed by their 80 | Contribution(s) alone or by combination of their Contribution(s) 81 | with the Work to which such Contribution(s) was submitted. If You 82 | institute patent litigation against any entity (including a 83 | cross-claim or counterclaim in a lawsuit) alleging that the Work 84 | or a Contribution incorporated within the Work constitutes direct 85 | or contributory patent infringement, then any patent licenses 86 | granted to You under this License for that Work shall terminate 87 | as of the date such litigation is filed. 88 | 89 | 4. Redistribution. You may reproduce and distribute copies of the 90 | Work or Derivative Works thereof in any medium, with or without 91 | modifications, and in Source or Object form, provided that You 92 | meet the following conditions: 93 | 94 | (a) You must give any other recipients of the Work or 95 | Derivative Works a copy of this License; and 96 | 97 | (b) You must cause any modified files to carry prominent notices 98 | stating that You changed the files; and 99 | 100 | (c) You must retain, in the Source form of any Derivative Works 101 | that You distribute, all copyright, patent, trademark, and 102 | attribution notices from the Source form of the Work, 103 | excluding those notices that do not pertain to any part of 104 | the Derivative Works; and 105 | 106 | (d) If the Work includes a "NOTICE" text file as part of its 107 | distribution, then any Derivative Works that You distribute must 108 | include a readable copy of the attribution notices contained 109 | within such NOTICE file, excluding those notices that do not 110 | pertain to any part of the Derivative Works, in at least one 111 | of the following places: within a NOTICE text file distributed 112 | as part of the Derivative Works; within the Source form or 113 | documentation, if provided along with the Derivative Works; or, 114 | within a display generated by the Derivative Works, if and 115 | wherever such third-party notices normally appear. The contents 116 | of the NOTICE file are for informational purposes only and 117 | do not modify the License. You may add Your own attribution 118 | notices within Derivative Works that You distribute, alongside 119 | or as an addendum to the NOTICE text from the Work, provided 120 | that such additional attribution notices cannot be construed 121 | as modifying the License. 122 | 123 | You may add Your own copyright statement to Your modifications and 124 | may provide additional or different license terms and conditions 125 | for use, reproduction, or distribution of Your modifications, or 126 | for any such Derivative Works as a whole, provided Your use, 127 | reproduction, and distribution of the Work otherwise complies with 128 | the conditions stated in this License. 129 | 130 | 5. Submission of Contributions. Unless You explicitly state otherwise, 131 | any Contribution intentionally submitted for inclusion in the Work 132 | by You to the Licensor shall be under the terms and conditions of 133 | this License, without any additional terms or conditions. 134 | Notwithstanding the above, nothing herein shall supersede or modify 135 | the terms of any separate license agreement you may have executed 136 | with Licensor regarding such Contributions. 137 | 138 | 6. Trademarks. This License does not grant permission to use the trade 139 | names, trademarks, service marks, or product names of the Licensor, 140 | except as required for reasonable and customary use in describing the 141 | origin of the Work and reproducing the content of the NOTICE file. 142 | 143 | 7. Disclaimer of Warranty. Unless required by applicable law or 144 | agreed to in writing, Licensor provides the Work (and each 145 | Contributor provides its Contributions) on an "AS IS" BASIS, 146 | WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or 147 | implied, including, without limitation, any warranties or conditions 148 | of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A 149 | PARTICULAR PURPOSE. You are solely responsible for determining the 150 | appropriateness of using or redistributing the Work and assume any 151 | risks associated with Your exercise of permissions under this License. 152 | 153 | 8. Limitation of Liability. In no event and under no legal theory, 154 | whether in tort (including negligence), contract, or otherwise, 155 | unless required by applicable law (such as deliberate and grossly 156 | negligent acts) or agreed to in writing, shall any Contributor be 157 | liable to You for damages, including any direct, indirect, special, 158 | incidental, or consequential damages of any character arising as a 159 | result of this License or out of the use or inability to use the 160 | Work (including but not limited to damages for loss of goodwill, 161 | work stoppage, computer failure or malfunction, or any and all 162 | other commercial damages or losses), even if such Contributor 163 | has been advised of the possibility of such damages. 164 | 165 | 9. Accepting Warranty or Additional Liability. While redistributing 166 | the Work or Derivative Works thereof, You may choose to offer, 167 | and charge a fee for, acceptance of support, warranty, indemnity, 168 | or other liability obligations and/or rights consistent with this 169 | License. However, in accepting such obligations, You may act only 170 | on Your own behalf and on Your sole responsibility, not on behalf 171 | of any other Contributor, and only if You agree to indemnify, 172 | defend, and hold each Contributor harmless for any liability 173 | incurred by, or claims asserted against, such Contributor by reason 174 | of your accepting any such warranty or additional liability. 175 | 176 | END OF TERMS AND CONDITIONS 177 | 178 | APPENDIX: How to apply the Apache License to your work. 179 | 180 | To apply the Apache License to your work, attach the following 181 | boilerplate notice, with the fields enclosed by brackets "[]" 182 | replaced with your own identifying information. (Don't include 183 | the brackets!) The text should be enclosed in the appropriate 184 | comment syntax for the file format. We also recommend that a 185 | file or class name and description of purpose be included on the 186 | same "printed page" as the copyright notice for easier 187 | identification within third-party archives. 188 | 189 | Copyright [yyyy] [name of copyright owner] 190 | 191 | Licensed under the Apache License, Version 2.0 (the "License"); 192 | you may not use this file except in compliance with the License. 193 | You may obtain a copy of the License at 194 | 195 | http://www.apache.org/licenses/LICENSE-2.0 196 | 197 | Unless required by applicable law or agreed to in writing, software 198 | distributed under the License is distributed on an "AS IS" BASIS, 199 | WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. 200 | See the License for the specific language governing permissions and 201 | limitations under the License. 202 | -------------------------------------------------------------------------------- /Makefile: -------------------------------------------------------------------------------- 1 | VERSION := $(shell git describe --always --dirty --tags 2>/dev/null || echo "undefined") 2 | IMG ?= quay.io/pusher/k8s-spot-price-monitor 3 | 4 | RED := \033[31m 5 | GREEN := \033[32m 6 | NC := \033[0m 7 | 8 | .PHONY: all 9 | all: lint 10 | 11 | .PHONY: lint 12 | lint: venv pip-install 13 | @ echo "$(GREEN)Linting code$(NC)" 14 | @ if [ ! $$(which flake8) ]; then echo "$(RED)flake8 not found - please install 'python -m pip install flake8'$(NC)"; exit 1; fi 15 | . venv/bin/activate; flake8 spot_price_monitor --max-line-length=120 --max-complexity=8 16 | @ if [ ! $$(which pylint) ]; then echo "$(RED)pylint not found - please install 'python -m pip install pylint'$(NC)"; exit 1; fi 17 | . venv/bin/activate ; pylint spot_price_monitor --max-line-length=120 18 | @ echo 19 | 20 | venv: 21 | python3 -m venv venv 22 | 23 | .PHONY: pip-install 24 | pip-install: venv 25 | . venv/bin/activate ; \ 26 | pip3 install -r requirements.txt 27 | 28 | .PHONY: docker-build 29 | docker-build: 30 | docker build --build-arg VERSION=${VERSION} . -t ${IMG}:${VERSION} 31 | @echo "$(GREEN)Built $(IMG):$(VERSION)$(NC)" 32 | 33 | TAGS ?= latest 34 | .PHONY: docker-tag 35 | docker-tag: docker-build 36 | @IFS=","; tags=${TAGS}; for tag in $${tags}; do docker tag ${IMG}:${VERSION} ${IMG}:$${tag}; echo "$(GREEN)Tagged $(IMG):$(VERSION) as $${tag}$(NC)"; done 37 | 38 | PUSH_TAGS ?= ${VERSION}, latest 39 | .PHONY: docker-push 40 | docker-push: docker-build docker-tag 41 | @IFS=","; tags=${PUSH_TAGS}; for tag in $${tags}; do docker push ${IMG}:$${tag}; echo "$(GREEN)Pushed $(IMG):$${tag}$(NC)"; done 42 | 43 | TAGS ?= latest 44 | .PHONY: docker-clean 45 | docker-clean: 46 | @IFS=","; tags=${TAGS}; for tag in $${tags}; do docker rmi -f ${IMG}:${VERSION} ${IMG}:$${tag}; done 47 | -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- 1 | # Spot Price Monitor 2 | 3 | > NOTE: this repository is currently **UNMAINTAINED** and is looking for new owner(s). See [#19](/../../issues/19) for more information. 4 | 5 | ## Table of contents 6 | * [Introduction](#introduction) 7 | * [Usage](#usage) 8 | * [Related](#related) 9 | * [Communication](#communication) 10 | * [Contributing](#contributing) 11 | * [License](#license) 12 | 13 | ## Introduction 14 | 15 | Reads instance types and availability zones from Kubernetes labels to expose as 16 | Prometheus metrics, the current spot prices of spot instances within a cluster. 17 | 18 | ## Usage 19 | 20 | ### Deploy to Kubernetes 21 | A docker image is available at `quay.io/pusher/k8s-spot-price-monitor`. 22 | These images are currently built on pushes to master. Releases will be tagged. 23 | 24 | Sample Kubernetes manifests are available in the [deploy](deploy/) folder. 25 | 26 | To deploy in clusters using RBAC, please apply all of the manifests (Deployment, ClusterRole, ClusterRoleBinding and ServiceAccount) in the [deploy](deploy/) folder but uncomment the `serviceAccountName` in the [Deployment](deploy/deployment.yaml). 27 | 28 | #### Requirements 29 | 30 | For the K8s Spot Price Monitor to filter spot instances as expected; 31 | you will need an identifying label on your spot instances. 32 | 33 | We add a label `node-role.kubernetes.io/spot-worker` to our spot instances and 34 | hence this is the default for the `spot-label` flag. 35 | 36 | To achieve this, add the following flag to your Kubelet: 37 | ``` 38 | --node-labels="node-role.kubernetes.io/spot-worker=true" 39 | ``` 40 | 41 | Since the script uses a built-in, well-known label for looking up instance types 42 | (`beta.kubernetes.io/instance-type`), this project supports K8s v1.7+. 43 | 44 | ##### IAM 45 | To fetch Spot Prices, the Spot Price Monitor will need the following IAM role policy. 46 | 47 | ```json 48 | { 49 | "Version": "2012-10-17", 50 | "Statement": [ 51 | { 52 | "Sid": "Stmt1519813867626", 53 | "Action": [ 54 | "ec2:DescribeSpotPriceHistory" 55 | ], 56 | "Effect": "Allow", 57 | "Resource": "*" 58 | } 59 | ] 60 | } 61 | ``` 62 | 63 | ### Product descriptions 64 | For EC2 Classic accounts the default `Linux/UNIX` product description will only 65 | work for non-VPC instance types, and for VPC accounts it will only work for VPC 66 | instance types. 67 | 68 | It's possible to override the product descriptions with the `-p`/`--products` 69 | flag to work around this: 70 | 71 | ``` 72 | spot_price_monitor.py --products "Linux/UNIX" "Linux/UNIX (Amazon VPC)" 73 | ``` 74 | 75 | ### Flags 76 | ``` 77 | usage: spot_price_monitor.py [-h] [--running-in-cluster RUNNING_IN_CLUSTER] 78 | [-l SPOT_LABEL] [-i SCRAPE_INTERVAL] 79 | [-m METRICS_PORT] [-r REGION] 80 | [-p PRODUCTS [PRODUCTS ...]] 81 | 82 | Monitors kubernetes for spot instances and exposes the current spot prices as 83 | prometheus metrics 84 | 85 | optional arguments: 86 | -h, --help show this help message and exit 87 | --running-in-cluster RUNNING_IN_CLUSTER 88 | Will load kubernetes config from the pod environment 89 | if running within the cluster, else loads a kubeconfig 90 | from the running environemnt (Default: False) 91 | -l LABEL, --spot-label LABEL 92 | Specifies the label applied to all spot instances in 93 | the cluster to identify these from other types of 94 | instances (Default: node-role.kubernetes.io/spot- 95 | worker) 96 | -i SCRAPE_INTERVAL, --scrape-interval SCRAPE_INTERVAL 97 | How often (in seconds) should the prices be scraped 98 | from AWS (Default: 60) 99 | -m METRICS_PORT, --metrics-port METRICS_PORT 100 | Port to expose prometheus metrics on (Default: 8000) 101 | -r REGION, --region REGION 102 | The region that the cluster is running in (Default: 103 | us-east-1) 104 | -p PRODUCTS [PRODUCTS ...], --products PRODUCTS [PRODUCTS ...] 105 | List of product (descriptions) to use for filtering 106 | (Default: Linux/UNIX) 107 | ``` 108 | 109 | ## Related 110 | - [K8s Spot Rescheduler](https://github.com/pusher/k8s-spot-rescheduler): Move nodes from on-demand instances to spot instances when space is available. 111 | - [K8s Spot Termination Handler](https://github.com/pusher/k8s-spot-termination-handler): Gracefully drain spot instances when they are issued with a termination notice. 112 | 113 | ## Communication 114 | 115 | * Found a bug? Please open an issue. 116 | * Have a feature request. Please open an issue. 117 | * If you want to contribute, please submit a pull request 118 | 119 | ## Contributing 120 | Please see our [Contributing](CONTRIBUTING.md) guidelines. 121 | 122 | ## License 123 | This project is licensed under Apache 2.0 and a copy of the license is available [here](LICENSE). 124 | -------------------------------------------------------------------------------- /deploy/clusterrole.yaml: -------------------------------------------------------------------------------- 1 | --- 2 | kind: ClusterRole 3 | apiVersion: rbac.authorization.k8s.io/v1 4 | metadata: 5 | name: k8s-spot-price-monitor 6 | rules: 7 | - apiGroups: 8 | - "" 9 | resources: 10 | - nodes 11 | verbs: 12 | - list 13 | -------------------------------------------------------------------------------- /deploy/clusterrolebinding.yaml: -------------------------------------------------------------------------------- 1 | --- 2 | apiVersion: rbac.authorization.k8s.io/v1 3 | kind: ClusterRoleBinding 4 | metadata: 5 | name: k8s-spot-price-monitor 6 | roleRef: 7 | apiGroup: rbac.authorization.k8s.io 8 | kind: ClusterRole 9 | name: k8s-spot-price-monitor 10 | subjects: 11 | - kind: ServiceAccount 12 | name: k8s-spot-price-monitor 13 | namespace: kube-system 14 | -------------------------------------------------------------------------------- /deploy/deployment.yaml: -------------------------------------------------------------------------------- 1 | --- 2 | apiVersion: extensions/v1beta1 3 | kind: Deployment 4 | metadata: 5 | name: k8s-spot-price-monitor 6 | namespace: kube-system 7 | labels: 8 | app: k8s-spot-price-monitor 9 | spec: 10 | replicas: 1 11 | selector: 12 | matchLabels: 13 | app: k8s-spot-price-monitor 14 | template: 15 | metadata: 16 | labels: 17 | app: k8s-spot-price-monitor 18 | spec: 19 | # Uncomment the following line if using RBAC 20 | # serviceAccountName: k8s-spot-price-monitor 21 | containers: 22 | - image: quay.io/pusher/k8s-spot-price-monitor:v0.2.0 23 | name: k8s-spot-price-monitor 24 | resources: 25 | limits: 26 | cpu: 20m 27 | memory: 100Mi 28 | requests: 29 | cpu: 10m 30 | memory: 50Mi 31 | args: 32 | - --running-in-cluster=True 33 | - --scrape-interval=60 34 | - --metrics-port=8000 35 | ports: 36 | - name: http 37 | containerPort: 8000 38 | -------------------------------------------------------------------------------- /deploy/serviceaccount.yaml: -------------------------------------------------------------------------------- 1 | --- 2 | apiVersion: v1 3 | kind: ServiceAccount 4 | metadata: 5 | labels: 6 | app: k8s-spot-price-monitor 7 | name: k8s-spot-price-monitor 8 | namespace: kube-system 9 | -------------------------------------------------------------------------------- /requirements.txt: -------------------------------------------------------------------------------- 1 | kubernetes==6.0.0 2 | boto3==1.7.7 3 | prometheus-client==0.2.0 4 | botocore==1.10.7 5 | flake8==3.6.0 6 | pylint==2.3.1 7 | requests==2.21.0 8 | urllib3<1.25,>=1.21.1 9 | -------------------------------------------------------------------------------- /spot_price_monitor/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pusher/k8s-spot-price-monitor/91e25577f32c1f3aef0443b6310acf2a8aef2cfc/spot_price_monitor/__init__.py -------------------------------------------------------------------------------- /spot_price_monitor/spot_price_monitor.py: -------------------------------------------------------------------------------- 1 | #!/usr/bin/python 2 | '''Exposes Prometheus metrics for current spot prices.''' 3 | 4 | import re 5 | import time 6 | import json 7 | import argparse 8 | import logging 9 | from datetime import datetime 10 | 11 | import boto3 12 | import requests 13 | from botocore.exceptions import ClientError 14 | from kubernetes import client, config 15 | from prometheus_client import start_http_server, Gauge, Counter 16 | 17 | logger = logging.getLogger(__name__) # noqa pylint: disable=C0103 18 | 19 | EC2_PRICING_API = 'https://raw.githubusercontent.com/powdahound/ec2instances.info/master/www/instances.json' 20 | ALLOWED_PRODUCTS = [ 21 | 'Linux/UNIX', 22 | 'SUSE Linux', 23 | 'Windows', 24 | 'Linux/UNIX (Amazon VPC)', 25 | 'SUSE Linux (Amazon VPC)', 26 | 'Windows (Amazon VPC)' 27 | ] 28 | 29 | 30 | def get_zones_from_k8s(k8s_client): 31 | '''Returns a list of unique availability zones used in the cluster''' 32 | 33 | nodes = k8s_client.list_node(watch=False) 34 | availability_zones = set([]) 35 | for node in nodes.items: 36 | availability_zones.add( 37 | node.metadata.labels['failure-domain.beta.kubernetes.io/zone'] 38 | ) 39 | return list(availability_zones) 40 | 41 | 42 | def matches_label(label, node_labels): 43 | ''' 44 | Returns true if the label provided is the node metadata labels. Supports 45 | both new and node-role label schema. Old depreciated in v1.15, removed in 46 | 1.16. Support for both is intended to ease the transition. 47 | ''' 48 | 49 | # determine if the label is new or old schema 50 | split = label.split("=", 2) 51 | 52 | if len(split) == 1: # no '=' 53 | return label in node_labels 54 | if len(split) == 2: # one '=' 55 | label_key = split[0] 56 | label_val = split[1] 57 | 58 | val = node_labels[label_key] 59 | return val == label_val 60 | 61 | return False 62 | 63 | 64 | def get_instance_types_from_k8s(k8s_client, label): 65 | '''Returns a list of unique instance types used in the cluster''' 66 | 67 | nodes = k8s_client.list_node(watch=False) 68 | instance_types = set([]) 69 | for node in nodes.items: 70 | if matches_label(label, node.metadata.labels): 71 | instance_types.add( 72 | node.metadata.labels['beta.kubernetes.io/instance-type'] 73 | ) 74 | return list(instance_types) 75 | 76 | 77 | def get_spot_prices(ec2_client, instance_types, availability_zones, products): 78 | '''Returns a list of spot prices by instance type and availability zone''' 79 | 80 | response = ec2_client.describe_spot_price_history( 81 | Filters=[ 82 | { 83 | 'Name': 'availability-zone', 84 | 'Values': availability_zones 85 | }, 86 | ], 87 | InstanceTypes=instance_types, 88 | StartTime=datetime.now(), 89 | ProductDescriptions=products 90 | ) 91 | return response['SpotPriceHistory'] 92 | 93 | 94 | def get_ondemand_price_metrics(num_of_retries=5, time_interval=2, timeout=5): 95 | '''Returns a dict of on-demand spot prices''' 96 | 97 | response = get_ondemand_prices_from_api(num_of_retries, time_interval, timeout) 98 | parsed_json = json.loads(response.text) 99 | on_demand_prices = {} 100 | for instance_type in parsed_json: 101 | for region in instance_type['pricing']: 102 | if region not in on_demand_prices: 103 | on_demand_prices[region] = {} 104 | if 'linux' in instance_type['pricing'][region] and 'ondemand' in instance_type['pricing'][region]['linux']: 105 | price = instance_type['pricing'][region]['linux']['ondemand'] 106 | on_demand_prices[region][instance_type['instance_type']] = price 107 | 108 | logger.debug("Ondemand prices:\n %s", on_demand_prices) 109 | 110 | return on_demand_prices 111 | 112 | 113 | def get_ondemand_prices_from_api(num_of_retries, time_interval, timeout): 114 | '''Fetches a list of ondemand prices from the EC2_PRICING_API''' 115 | for _ in range(num_of_retries): 116 | try: 117 | logger.debug("Downloading daily ondemand prices") 118 | response = requests.get(EC2_PRICING_API, timeout=timeout) 119 | 120 | if response.status_code != 200: 121 | logger.error("Failed to download ondemand prices. Status code for page %d", response.status_code) 122 | raise Exception("Failed to download ondemand prices") 123 | 124 | return response 125 | except requests.exceptions.RequestException as exception: 126 | logger.error("Failed to download ondemand prices. Exception: %s. Retrying...", str(exception)) 127 | time.sleep(time_interval) 128 | 129 | # Should only get here once num_of_retries is exceeded 130 | logger.error("Maximum retries hit") 131 | raise Exception("Failed to get ondemand prices after %d tries.", ) 132 | 133 | 134 | def get_args(): 135 | '''Processes command line arguments''' 136 | parser = argparse.ArgumentParser( 137 | description='''Monitors kubernetes for spot instances and exposes the 138 | current spot prices as prometheus metrics''' 139 | ) 140 | 141 | parser.add_argument('--running-in-cluster', type=bool, default=False, 142 | help='''Will load kubernetes config from the pod 143 | environment if running within the cluster, else loads a 144 | kubeconfig from the running environemnt (Default: 145 | False)''') 146 | parser.add_argument('-l', '--spot-label', type=str, required=False, 147 | help='''Specifies the label that identifies nodes as 148 | spot instances.''', 149 | default='kubernetes.io/role=spot-worker') 150 | parser.add_argument('-i', '--scrape-interval', type=int, default=60, 151 | help='''How often (in seconds) should the prices be 152 | scraped from AWS (Default: 60)''') 153 | parser.add_argument('-m', '--metrics-port', type=int, default=8000, 154 | help='''Port to expose prometheus metrics on (Default: 155 | 8000)''') 156 | parser.add_argument('-r', '--region', type=str, default='us-east-1', 157 | help='''The region that the cluster is running 158 | in (Default: us-east-1)''') 159 | parser.add_argument('--on-demand', action="store_true", default=False, 160 | help='''Will enable ondemand prices''') 161 | parser.add_argument('-v', '--verbose', action="store_true", default=False, 162 | help='''Enable verbose output''') 163 | parser.add_argument('-p', '--products', type=str, nargs='+', default=['Linux/UNIX'], 164 | help='''List of product (descriptions) to use for filtering, separated 165 | by spaces, e.g. `-p "Linux/UNIX" "Linux/UNIX (Amazon VPC)"` 166 | (Default: Linux/UNIX)''') 167 | 168 | return parser.parse_args() 169 | 170 | 171 | def update_spot_price_metrics(metric, prices): 172 | '''Updates prometheus gauge based on input list of prices''' 173 | 174 | for price in prices: 175 | metric.labels( 176 | instance_type=price['InstanceType'], 177 | availability_zone=price['AvailabilityZone'] 178 | ).set(price['SpotPrice']) 179 | 180 | 181 | def update_ondemand_price_metrics(metric, prices, types, zones): 182 | '''Updates a Prometheus gauge with on demand prices''' 183 | 184 | for zone in zones: 185 | region = re.sub(r"[a-z]$", "", zone) 186 | for instance_type in types: 187 | metric.labels( 188 | instance_type=instance_type, 189 | availability_zone=zone 190 | ).set(prices[region][instance_type]) 191 | 192 | 193 | def update_ondemand_prices(last_ondemand_update, on_demand_spot_gauge, spot_prices, spot_error): 194 | '''Refresh ondemand prices once a day''' 195 | if last_ondemand_update + 86400 < time.time(): 196 | try: 197 | last_ondemand_update = time.time() 198 | price_zones = {} 199 | price_instance_types = {} 200 | for price in spot_prices: 201 | price_zones[price['AvailabilityZone']] = 1 202 | price_instance_types[price['InstanceType']] = 1 203 | ondemand_prices = get_ondemand_price_metrics() 204 | update_ondemand_price_metrics( 205 | on_demand_spot_gauge, 206 | ondemand_prices, 207 | price_instance_types.keys(), price_zones.keys()) 208 | return last_ondemand_update 209 | except Exception as exception: # noqa pylint: disable=broad-except 210 | logger.error("Ondemand prices load failed. I won't retry for another day. Error: %s", str(exception)) 211 | spot_error.labels(code='ondemand_failure').inc() # noqa pylint: disable=E1101 212 | else: 213 | return last_ondemand_update 214 | 215 | 216 | def load_config(running_in_cluster): 217 | '''Load the correct Kubernetes config based on in-cluster or not''' 218 | if running_in_cluster: 219 | config.incluster_config.load_incluster_config() 220 | else: 221 | config.load_kube_config() 222 | 223 | 224 | def check_allowed_products(products): 225 | '''Raises and error if an invalid product is requested''' 226 | for product in products: 227 | if product not in ALLOWED_PRODUCTS: 228 | raise ValueError('invalid product {}, expected one of {}'.format(product, ALLOWED_PRODUCTS)) 229 | 230 | 231 | def main(): 232 | '''Main''' 233 | args = get_args() 234 | 235 | if len(args.spot_label.split("=", 2)) > 2: 236 | raise ValueError("""the spot node label is not correctly formatted: 237 | expected '' or '=', but got {}""".format(args.spot_label)) 238 | 239 | logging_level = logging.DEBUG if args.verbose else logging.WARN 240 | logging.basicConfig(format='%(asctime)s %(levelname)s %(message)s', level=logging_level) 241 | 242 | check_allowed_products(args.products) 243 | load_config(args.running_in_cluster) 244 | 245 | k8s_client = client.CoreV1Api() 246 | ec2 = boto3.client('ec2', args.region) 247 | start_http_server(args.metrics_port) 248 | 249 | on_demand_spot_gauge = None 250 | spot_gauge = Gauge( 251 | 'aws_spot_price_dollars_per_hour', 252 | 'Reports the AWS spot price of node types used in the cluster', 253 | ['instance_type', 'availability_zone'] 254 | ) 255 | spot_error = Counter( 256 | 'aws_spot_price_request_errors', 257 | 'Reports errors while calling the AWS api.', 258 | ['code'] 259 | ) 260 | if args.on_demand: 261 | on_demand_spot_gauge = Gauge( 262 | 'aws_on_demand_dollars_per_hour', 263 | 'Reports the AWS ondemand of node types used in the cluster', 264 | ['instance_type', 'availability_zone'] 265 | ) 266 | 267 | last_ondemand_update = 0 268 | backoff_multiplier = 1 269 | 270 | spot_prices = [] 271 | while True: 272 | zones = get_zones_from_k8s(k8s_client) 273 | try: 274 | types = get_instance_types_from_k8s(k8s_client, args.spot_label) 275 | spot_prices = get_spot_prices(ec2, types, zones, args.products) 276 | backoff_multiplier = 1 277 | except ClientError as exception: 278 | spot_error.labels(exception.response['Error']['Code']).inc() # noqa pylint: disable=E1101 279 | if exception.response['Error']['Code'] == 'RequestLimitExceeded': 280 | logger.error("RequestLimitExceeded. Doubling backoff multiplier. Error: %s", str(exception)) 281 | backoff_multiplier *= 2 282 | update_spot_price_metrics(spot_gauge, spot_prices) 283 | 284 | if args.on_demand: 285 | last_ondemand_update = update_ondemand_prices( 286 | last_ondemand_update, 287 | on_demand_spot_gauge, 288 | spot_prices, 289 | spot_error 290 | ) 291 | 292 | time.sleep(args.scrape_interval * backoff_multiplier) 293 | 294 | 295 | if __name__ == '__main__': 296 | main() 297 | --------------------------------------------------------------------------------