Airflow 气流资源利用率峰值

我们有32个V-CPU和28 GB ram，带有

本地执行器

，但仍在利用所有资源，这导致资源过度利用，最终破坏系统执行

下面是按内存使用情况排序的ps-aux输出

   PID %CPU %MEM    VSZ   RSS TTY      STAT START   TIME COMMAND
  1336  3.5  0.9 1600620 271644 ?      Ss   Feb18  23:41 /usr/bin/python /usr/local/bin/airflow webs
  9434 32.3  0.9 1835796 267844 ?      Sl   03:09   0:31 [ready] gunicorn: worker [airflow-webserver
 10043  9.1  0.9 1835796 267844 ?      Sl   03:05   0:33 [ready] gunicorn: worker [airflow-webserver
 25397 17.4  0.9 1835796 267844 ?      Sl   03:08   0:30 [ready] gunicorn: worker [airflow-webserver
 30680 13.0  0.9 1835796 267844 ?      Sl   03:06   0:36 [ready] gunicorn: worker [airflow-webserver
 28434 60.5  0.5 1720548 152380 ?      Rl   03:10   0:12 gunicorn: worker [airflow-webserver]       
 20202  2.2  0.3 1671280 111316 ?      Sl   03:07   0:04 /usr/bin/python /usr/local/bin/airflow run 
 14353  1.9  0.3 1671484 111208 ?      Sl   03:07   0:04 /usr/bin/python /usr/local/bin/airflow run 
 14497  1.8  0.3 1671480 111192 ?      Sl   03:07   0:03 /usr/bin/python /usr/local/bin/airflow run 
 25170  2.0  0.3 1671024 110964 ?      Sl   03:08   0:03 /usr/bin/python /usr/local/bin/airflow run 
 21887  1.8  0.3 1670692 110672 ?      Sl   03:07   0:03 /usr/bin/python /usr/local/bin/airflow run 
  5211  4.7  0.3 1670488 110456 ?      Sl   03:09   0:05 /usr/bin/python /usr/local/bin/airflow run 
  8819  4.9  0.3 1670140 110264 ?      Sl   03:09   0:04 /usr/bin/python /usr/local/bin/airflow run 
  6034  3.9  0.3 1670324 110080 ?      Sl   03:09   0:04 /usr/bin/python /usr/local/bin/airflow run 
  8817  4.6  0.3 1670136 110044 ?      Sl   03:09   0:04 /usr/bin/python /usr/local/bin/airflow run 
  8829  4.0  0.3 1670076 110012 ?      Sl   03:09   0:04 /usr/bin/python /usr/local/bin/airflow run 
 14349  1.6  0.3 1670360 109988 ?      Sl   03:07   0:03 /usr/bin/python /usr/local/bin/airflow run 
  8815  3.5  0.3 1670140 109984 ?      Sl   03:09   0:03 /usr/bin/python /usr/local/bin/airflow run 
  8917  4.2  0.3 1669980 109980 ?      Sl   03:09   0:04 /usr/bin/python /usr/local/bin/airflow run 

从

RSS

字段中，我们可以看到web服务器使用的RAM超过10gb，每个任务平均使用1gb

这些任务仅用于监视RESTAPI的端点

下面是气流配置文件

[core]
# The home folder for airflow, default is ~/airflow
airflow_home = /airflow
# The folder where your airflow pipelines live, most likely a
# subfolder in a code repository
# This path must be absolute
dags_folder = /airflow/dags
# The folder where airflow should store its log files
# This path must be absolute
base_log_folder = /airflow/logs/
# Airflow can store logs remotely in AWS S3 or Google Cloud Storage. Users
# must supply an Airflow connection id that provides access to the storage
# location.
remote_logging = True
remote_log_conn_id = datalake_gcp_connection
encrypt_s3_logs = False
# Logging level
logging_level = INFO
# Logging class
# Specify the class that will specify the logging configuration
# This class has to be on the python classpath
logging_config_class = log_config.LOGGING_CONFIG
# Log format
log_format = [%%(asctime)s] {%%(filename)s:%%(lineno)d} %%(levelname)s - %%(message)s
simple_log_format = %%(asctime)s %%(levelname)s - %%(message)s
# The executor class that airflow should use. Choices include
# SequentialExecutor, LocalExecutor, CeleryExecutor, DaskExecutor
executor = LocalExecutor
# The SqlAlchemy connection string to the metadata database.
# SqlAlchemy supports many different database engine, more information
# their website
sql_alchemy_conn = mysql://user:pass@127.0.0.1/airflow_db
# The SqlAlchemy pool size is the maximum number of database connections
# in the pool.
sql_alchemy_pool_size = 400

# The SqlAlchemy pool recycle is the number of seconds a connection
# can be idle in the pool before it is invalidated. This config does
# not apply to sqlite.
sql_alchemy_pool_recycle = 3000

# The amount of parallelism = 32
# the max number of task instances that should run simultaneously
# on this airflow installation
parallelism = 64

# The number of task instances allowed to run concurrently by the scheduler
dag_concurrency = 32

# Are DAGs paused by default at creation
dags_are_paused_at_creation = True

# When not using pools, tasks are run in the "default pool",
# whose size is guided by this config element
non_pooled_task_slot_count = 400

# The maximum number of active DAG runs per DAG
max_active_runs_per_dag = 16

# Whether to load the examples that ship with Airflow. It's good to
# get started, but you probably want to set this to False in a production
# environment
load_examples = False

# Where your Airflow plugins are stored
plugins_folder = /airflow/plugins

# Secret key to save connection passwords in the db
fernet_key = <FERNET KEY>

# Whether to disable pickling dags
donot_pickle = False

# How long before timing out a python file import while filling the DagBag
dagbag_import_timeout = 120

# The class to use for running task instances in a subprocess
task_runner = BashTaskRunner

# If set, tasks without a `run_as_user` argument will be run with this user
# Can be used to de-elevate a sudo user running Airflow when executing tasks
default_impersonation =

# What security module to use (for example kerberos):
security =

# Turn unit test mode on (overwrites many configuration options with test
# values at runtime)
unit_test_mode = False

# Name of handler to read task instance logs.
# Default to use file task handler.
task_log_reader = gcs.task

# Whether to enable pickling for xcom (note that this is insecure and allows for
# RCE exploits). This will be deprecated in Airflow 2.0 (be forced to False).
enable_xcom_pickling = True

# When a task is killed forcefully, this is the amount of time in seconds that
# it has to cleanup after it is sent a SIGTERM, before it is SIGKILLED
killed_task_cleanup_time = 60

[cli]
# In what way should the cli access the API. The LocalClient will use the
# database directly, while the json_client will use the api running on the
# webserver
api_client = airflow.api.client.json_client
endpoint_url = http://0.0.0.0:8080

[api]
# How to authenticate users of the API
auth_backend = airflow.api.auth.backend.default

[operators]
# The default owner assigned to each new operator, unless
# provided explicitly or passed via `default_args`
default_owner = Airflow
default_cpus = 1
default_ram = 125
default_disk = 125
default_gpus = 0


[webserver]
# The base url of your website as airflow cannot guess what domain or
# cname you are using. This is used in automated emails that
# airflow sends to point links to the right web server
base_url = http://localhost:8080

authenticate = False
auth_backend = airflow.contrib.auth.backends.password_auth

# The ip specified when starting the web server
web_server_host = 0.0.0.0

# The port on which to run the web server
web_server_port = 8080

# Paths to the SSL certificate and key for the web server. When both are
# provided SSL will be enabled. This does not change the web server port.
web_server_ssl_cert =
web_server_ssl_key =

# Number of seconds the gunicorn webserver waits before timing out on a worker
web_server_worker_timeout = 120

# Number of workers to refresh at a time. When set to 0, worker refresh is
# disabled. When nonzero, airflow periodically refreshes webserver workers by
# bringing up new ones and killing old ones.
worker_refresh_batch_size = 1

# Number of seconds to wait before refreshing a batch of workers.
worker_refresh_interval = 30

# Secret key used to run your flask app
secret_key = temporary_key

# Number of workers to run the Gunicorn web server
workers = 4

# The worker class gunicorn should use. Choices include
# sync (default), eventlet, gevent
worker_class = sync

# Log files for the gunicorn webserver. '-' means log to stderr.
access_logfile = -
error_logfile = -

# Expose the configuration file in the web server
expose_config = False

# Set to true to turn on authentication:
# http://pythonhosted.org/airflow/security.html#web-authentication
#authenticate = False

# Filter the list of dags by owner name (requires authentication to be enabled)
filter_by_owner = False

# Filtering mode. Choices include user (default) and ldapgroup.
# Ldap group filtering requires using the ldap backend
#
# Note that the ldap server needs the "memberOf" overlay to be set up
# in order to user the ldapgroup mode.
owner_mode = user

# Default DAG view.  Valid values are:
# tree, graph, duration, gantt, landing_times
dag_default_view = graph

# Default DAG orientation. Valid values are:
# LR (Left->Right), TB (Top->Bottom), RL (Right->Left), BT (Bottom->Top)
dag_orientation = LR

# Puts the webserver in demonstration mode; blurs the names of Operators for
# privacy.
demo_mode = False

# The amount of time (in secs) webserver will wait for initial handshake
# while fetching logs from other worker machine
log_fetch_timeout_sec = 5

# By default, the webserver shows paused DAGs. Flip this to hide paused
# DAGs by default
hide_paused_dags_by_default = True

# Consistent page size across all listing views in the UI
page_size = 40

[email]
email_backend = airflow.utils.email.send_email_smtp


[smtp]
# If you want airflow to send emails on retries, failure, and you want to use
# the airflow.utils.email.send_email_smtp function, you have to configure an
# smtp server here
smtp_host = smtp.gmail.com
smtp_starttls = True
smtp_ssl = False
# Uncomment and set the user/pass settings if you want to use SMTP AUTH
#smtp_user = airflow
#smtp_password = airflow
smtp_port = 25
smtp_mail_from = airflow@example.com


[celery]
# This section only applies if you are using the CeleryExecutor in
# [core] section above

# The app name that will be used by celery
celery_app_name = airflow.executors.celery_executor

# The concurrency that will be used when starting workers with the
# "airflow worker" command. This defines the number of task instances that
# a worker will take, so size up your workers based on the resources on
# your worker box and the nature of your tasks
celeryd_concurrency = 16

# When you start an airflow worker, airflow starts a tiny web server
# subprocess to serve the workers local log files to the airflow main
# web server, who then builds pages and sends them to users. This defines
# the port on which the logs are served. It needs to be unused, and open
# visible from the main web server to connect into the workers.
worker_log_server_port = 8793

# The Celery broker URL. Celery supports RabbitMQ, Redis and experimentally
# a sqlalchemy database. Refer to the Celery documentation for more
# information.
broker_url = sqla+mysql://user:pass@127.0.0.1/airflow_db

# Another key Celery setting
celery_result_backend = db+mysql://user:pass@127.0.0.1/airflow_db

# Celery Flower is a sweet UI for Celery. Airflow has a shortcut to start
# it `airflow flower`. This defines the IP that Celery Flower runs on
flower_host = 0.0.0.0

# This defines the port that Celery Flower runs on
flower_port = 5555

# Default queue that tasks get assigned to and that worker listen on.
default_queue = default

# Import path for celery configuration options
celery_config_options = airflow.config_templates.default_celery.DEFAULT_CELERY_CONFIG

[dask]
# This section only applies if you are using the DaskExecutor in
# [core] section above

# The IP address and port of the Dask cluster's scheduler.
cluster_address = 127.0.0.1:8786


[scheduler]
# Task instances listen for external kill signal (when you clear tasks
# from the CLI or the UI), this defines the frequency at which they should
# listen (in seconds).
job_heartbeat_sec = 20

# The scheduler constantly tries to trigger new tasks (look at the
# scheduler section in the docs for more information). This defines
# how often the scheduler should run (in seconds).
scheduler_heartbeat_sec = 60

# after how much time should the scheduler terminate in seconds
# -1 indicates to run continuously (see also num_runs)
run_duration = -1

# after how much time a new DAGs should be picked up from the filesystem
min_file_process_interval = 5

dag_dir_list_interval = 300

# How often should stats be printed to the logs
print_stats_interval = 30

child_process_log_directory = /airflow/logs/scheduler

# Local task jobs periodically heartbeat to the DB. If the job has
# not heartbeat in this many seconds, the scheduler will mark the
# associated task instance as failed and will re-schedule the task.
scheduler_zombie_task_threshold = 300

# Turn off scheduler catchup by setting this to False.
# Default behavior is unchanged and
# Command Line Backfills still work, but the scheduler
# will not do scheduler catchup if this is False,
# however it can be set on a per DAG basis in the
# DAG definition (catchup)
catchup_by_default = False

# This changes the batch size of queries in the scheduling main loop.
# This depends on query length limits and how long you are willing to hold locks.
# 0 for no limit
max_tis_per_query = 256

# Statsd (https://github.com/etsy/statsd) integration settings
statsd_on = False
statsd_host = localhost
statsd_port = 8125
statsd_prefix = airflow

# The scheduler can run multiple threads in parallel to schedule dags.
# This defines how many threads will run.
max_threads = 12

authenticate = False

[ldap]
# set this to ldaps://<your.ldap.server>:<port>
uri =
user_filter = objectClass=*
user_name_attr = uid
group_member_attr = memberOf
superuser_filter =
data_profiler_filter =
bind_user = cn=Manager,dc=example,dc=com
bind_password = insecure
basedn = dc=example,dc=com
cacert = /etc/ca/ldap_ca.crt
search_scope = LEVEL

[mesos]
# Mesos master address which MesosExecutor will connect to.
master = localhost:5050

# The framework name which Airflow scheduler will register itself as on mesos
framework_name = Airflow

# Number of cpu cores required for running one task instance using
# 'airflow run <dag_id> <task_id> <execution_date> --local -p <pickle_id>'
# command on a mesos slave
task_cpu = 1

# Memory in MB required for running one task instance using
# 'airflow run <dag_id> <task_id> <execution_date> --local -p <pickle_id>'
# command on a mesos slave
task_memory = 256

# Enable framework checkpointing for mesos
# See http://mesos.apache.org/documentation/latest/slave-recovery/
checkpoint = False

# Failover timeout in milliseconds.
# When checkpointing is enabled and this option is set, Mesos waits
# until the configured timeout for
# the MesosExecutor framework to re-register after a failover. Mesos
# shuts down running tasks if the
# MesosExecutor framework fails to re-register within this timeframe.
# failover_timeout = 604800

# Enable framework authentication for mesos
# See http://mesos.apache.org/documentation/latest/configuration/
authenticate = False

# Mesos credentials, if authentication is enabled
# default_principal = admin
# default_secret = admin


[kerberos]
ccache = /tmp/airflow_krb5_ccache
# gets augmented with fqdn
principal = airflow
reinit_frequency = 3600
kinit_path = kinit
keytab = airflow.keytab


[github_enterprise]
api_rev = v3


[admin]
# UI to hide sensitive variable fields when set to True
hide_sensitive_variable_fields = True

[core]
#气流的主文件夹，默认为~/airflow
空气流量_home=/空气流量
#气流管道所在的文件夹，很可能是
#代码存储库中的子文件夹
#这条路必须是绝对的
dags_文件夹=/afflow/dags
#气流应存储其日志文件的文件夹
#这条路必须是绝对的
基本日志文件夹=/afflow/logs/
#Airflow可以在AWS S3或Google云存储中远程存储日志。使用者
#必须提供能够访问存储的气流连接id
#地点。
远程日志记录=真
远程日志连接id=datalake\u gcp\u连接
加密\u s3\u日志=False
#日志记录级别
日志记录\u级别=信息
#日志类
#指定将指定日志记录配置的类
#此类必须位于python类路径上
logging\u config\u class=log\u config.logging\u config
#日志格式
日志格式=[%%（asctime）s]{%%（文件名）s:%%（行号）d}%%（levelname）s-%%（消息）s
简单日志格式=%%（asctime）s%%（levelname）s-%%（message）s
#气流应使用的执行器类。选择包括
#顺序执行器、本地执行器、CeleryExecutor、DaskExecutor
executor=LocalExecutor
#指向元数据数据库的SqlAlchemy连接字符串。
#SqlAlchemy支持许多不同的数据库引擎，更多信息
#他们的网站
sql\u炼金术\u连接=mysql://user:pass@127.0.0.1/气流单位db
#SqlAlchemy池大小是数据库连接的最大数量
#在游泳池里。
sql\u炼金术\u池大小=400
#SqlAlchemy池循环是连接的秒数
#可以在无效之前在池中处于空闲状态。此配置不支持
#不适用于sqlite。
sql\u炼金术\u池\u回收=3000
#并行量=32
#应同时运行的最大任务实例数
#在这个气流装置上
并行度=64
#计划程序允许并发运行的任务实例数
dag_并发性=32
#默认情况下，DAG是否在创建时暂停
DAG在创建时暂停=True
#不使用池时，任务在“默认池”中运行，
#其大小由此配置元素引导
非池任务槽计数=400
#每个DAG的最大活动DAG运行数
每个dag的最大活动运行次数=16
#是否加载附带气流的示例。很高兴见到你
#开始吧，但您可能希望在生产中将其设置为False
#环境
加载示例=False
#气流插件的存储位置
plugins\u folder=/afflow/plugins
#在数据库中保存连接密码的密钥
fernet_键=
#是否禁用酸洗DAG
donot_pickle=错误
#填充数据包时，python文件导入超时需要多长时间
dagbag\u导入\u超时=120
#用于在子流程中运行任务实例的类
task\u runner=BashTaskRunner
#如果设置，则不带“以用户身份运行”参数的任务将与此用户一起运行
#可用于在执行任务时取消sudo用户运行气流的提升
默认模拟=
#要使用的安全模块（例如kerberos）：
保安=
#打开单元测试模式（使用测试覆盖许多配置选项
#（运行时的值）
单元测试模式=错误
#用于读取任务实例日志的处理程序的名称。
#默认使用文件任务处理程序。
任务\日志\读卡器=gcs.task
#是否为xcom启用酸洗（请注意，这是不安全的，并且允许
#RCE漏洞）。在Airflow 2.0中将不推荐使用此选项（强制为False）。
启用\u xcom\u酸洗=真
#当任务被强制终止时，这是以秒为单位的时间量
#它必须在发送SIGTERM后进行清理，然后才能执行SIGTELM
已终止任务清理时间=60
[cli]
#cli应以何种方式访问API。本地客户端将使用
#直接访问数据库，而json_客户端将使用在
#网络服务器
api_client=afflow.api.client.json_client
端点\ url=http://0.0.0.0:8080
[空气污染指数]
#如何对API的用户进行身份验证
auth_backend=afflow.api.auth.backend.default
[操作员]
#分配给每个新操作员的默认所有者，除非
#通过“默认参数”显式提供或传递`
默认所有者=气流
默认\u CPU=1
默认内存=125
默认磁盘=125
默认gpu=0
[网络服务器]
#您的网站的基本url无法猜测是哪个域或
#您正在使用的cname。这在自动电子邮件中使用
#气流将指向点的链接发送到正确的web服务器
基本url=http://localhost:8080
验证=错误
auth\u backend=afflow.contrib.auth.backends.password\u auth
#启动web服务器时指定的ip
web_服务器_主机=0.0.0.0
#运行web服务器的端口
web_服务器_端口=8080
#web服务器的SSL证书和密钥的路径。当两者都是
#提供的SSL将被启用。这不会更改web服务器端口。
网络服务器ssl证书=
web\u服务器\u ssl\u密钥=
#gunicorn Web服务器在工作进程超时之前等待的秒数
web\u服务器\u工作者\u超时=120
#一次要刷新的工作进程数。当设置为0时，将启用辅助刷新
#残疾人。当非零时，气流通过以下方式定期刷新Web服务器工作进程：
#培养新的，杀死旧的。
工作进程刷新批量大小=1
#刷新一批工作进程之前等待的秒数。
工作线程刷新间隔=30
#用于运行flask应用程序的密钥
秘密密钥=临时密钥
#运行Gunicorn web服务器的工作进程数
工人=4
#工人类gunicorn应该使用。选择一