我正在运行一个一次性的Fargate任务，该任务运行一个小的python脚本。任务定义配置为使用awslogs将日志发送到Cloudwatch，但是我面临一个非常奇怪的间歇性问题。
日志有时会出现在新创建的Cloudwatch流中，有时却不会出现。我已经尝试删除部分代码，而现在，这就是我所拥有的。
当我删除asyncio / aiohttp提取逻辑时，打印语句通常显示在Cloudwatch日志中。尽管由于问题是断断续续的，但我不能100％肯定会一直发生这种情况。
但是，由于包含了获取逻辑，有时在Fargate任务退出后，我会得到完全为空的日志流。没有日志显示“作业开始”，“作业结束”或“将文件放入S3”。也没有错误日志。尽管如此，当我检查S3存储桶时，仍创建了具有相应时间戳的文件，表明脚本确实运行完毕。我无法理解这是怎么可能的。
#!/usr/bin/env python3.6
import asyncio
import datetime
import time
from aiohttp import ClientSession
import boto3
def s3_put(bucket, key, body):
try:
print(f"Putting file into {bucket}/{key}")
client = boto3.client("s3")
client.put_object(Bucket=bucket,Key=key,Body=body)
except Exception:
print(f"Error putting object into S3 Bucket: {bucket}/{key}")
raise
async def fetch(session, number):
url = f'https://jsonplaceholder.typicode.com/todos/{number}'
try:
async with session.get(url) as response:
return await response.json()
except Exception as e:
print(f"Failed to fetch {url}")
print(e)
return None
async def fetch_all():
tasks = []
async with ClientSession() as session:
for x in range(1, 6):
for number in range(1, 200):
task = asyncio.ensure_future(fetch(session=session,number=number))
tasks.append(task)
responses = await asyncio.gather(*tasks)
return responses
def main():
try:
loop = asyncio.get_event_loop()
future = asyncio.ensure_future(fetch_all())
responses = list(filter(None, loop.run_until_complete(future)))
except Exception:
print("uh oh")
raise
# do stuff with responses
body = "whatever"
key = f"{datetime.datetime.fromtimestamp(time.time()).strftime('%Y-%m-%d_%H-%M-%S')}_test"
s3_put(bucket="my-s3-bucket", key=key, body=body)
if __name__ == "__main__":
print("Job starting")
main()
print("Job complete")
FROM python:3.6-alpine
COPY docker/test_fargate_logging/requirements.txt /
COPY docker/test_fargate_logging/dostuff.py /
WORKDIR /
RUN pip install --upgrade pip && \
pip install -r requirements.txt
ENTRYPOINT python dostuff.py
{
"ipcMode": null,
"executionRoleArn": "arn:aws:iam::xxxxxxxxxxxx:role/ecsInstanceRole",
"containerDefinitions": [
{
"dnsSearchDomains": null,
"logConfiguration": {
"logDriver": "awslogs",
"options": {
"awslogs-group": "test-fargate-logging-stg-log-group",
"awslogs-region": "ap-northeast-1",
"awslogs-stream-prefix": "ecs"
}
},
"entryPoint": null,
"portMappings": [],
"command": null,
"linuxParameters": null,
"cpu": 256,
"environment": [],
"ulimits": null,
"dnsServers": null,
"mountPoints": [],
"workingDirectory": null,
"secrets": null,
"dockerSecurityOptions": null,
"memory": 512,
"memoryReservation": null,
"volumesFrom": [],
"image": "xxxxxxxxxxxx.dkr.ecr.ap-northeast-1.amazonaws.com/test-fargate-logging-stg-ecr-repository:xxxxxxxxxxxxxxxxxxxxxxxxxxxx",
"disableNetworking": null,
"interactive": null,
"healthCheck": null,
"essential": true,
"links": null,
"hostname": null,
"extraHosts": null,
"pseudoTerminal": null,
"user": null,
"readonlyRootFilesystem": null,
"dockerLabels": null,
"systemControls": null,
"privileged": null,
"name": "test_fargate_logging"
}
],
"placementConstraints": [],
"memory": "512",
"taskRoleArn": "arn:aws:iam::xxxxxxxxxxxx:role/ecsInstanceRole",
"compatibilities": [
"EC2",
"FARGATE"
],
"taskDefinitionArn": "arn:aws:ecs:ap-northeast-1:xxxxxxxxxxxx:task-definition/test-fargate-logging-stg-task-definition:2",
"family": "test-fargate-logging-stg-task-definition",
"requiresAttributes": [
{
"targetId": null,
"targetType": null,
"value": null,
"name": "ecs.capability.execution-role-ecr-pull"
},
{
"targetId": null,
"targetType": null,
"value": null,
"name": "com.amazonaws.ecs.capability.docker-remote-api.1.18"
},
{
"targetId": null,
"targetType": null,
"value": null,
"name": "ecs.capability.task-eni"
},
{
"targetId": null,
"targetType": null,
"value": null,
"name": "com.amazonaws.ecs.capability.ecr-auth"
},
{
"targetId": null,
"targetType": null,
"value": null,
"name": "com.amazonaws.ecs.capability.task-iam-role"
},
{
"targetId": null,
"targetType": null,
"value": null,
"name": "ecs.capability.execution-role-awslogs"
},
{
"targetId": null,
"targetType": null,
"value": null,
"name": "com.amazonaws.ecs.capability.logging-driver.awslogs"
},
{
"targetId": null,
"targetType": null,
"value": null,
"name": "com.amazonaws.ecs.capability.docker-remote-api.1.19"
}
],
"pidMode": null,
"requiresCompatibilities": [
"FARGATE"
],
"networkMode": "awsvpc",
"cpu": "256",
"revision": 2,
"status": "ACTIVE",
"volumes": []
}
logging库也发生了问题，我更改为print以排除logging的问题答案 0 :(得分：0)
我遇到了同样的问题；在CloudWatch中间歇性地丢失ECS Fargate任务的日志。
虽然我无法回答为什么会发生这种情况，但我可以提供一种经过测试的解决方法。
升级到Python 3.7版本（遇到相同问题时，我看到的是使用3.6。
我现在正在查看所有日志，并从最新版本的Python中受益。
我希望这对您有所帮助。
答案 1 :(得分：0)
根据此AWS Forums链接，此问题现在似乎已解决 我遇到了类似的问题，并且在此问题的答案中有一些有用的解决方法：Missing log lines when writing to cloudwatch from ECS Docker containers
您不应再遇到此问题。如果是这样，请尝试部署任务定义的新版本，这应该可以对其进行修复。