问：

我正在运行一个运行小型 python 脚本的一次性 Fargate 任务。任务定义配置为用于将日志发送到 Cloudwatch，但我遇到了一个非常奇怪的间歇性问题。awslogs

日志有时会出现在新创建的 Cloudwatch 流中，有时则不会。我已经尝试删除部分代码，现在，这是我所拥有的。

当我删除 asyncio/aiohttp 提取逻辑时，print 语句会正常显示在 Cloudwatch Logs 中。虽然由于问题是间歇性的，我不能 100% 确定这种情况会一直发生。

但是，在包含提取逻辑的情况下，我有时会在 Fargate 任务退出后获得完全为空的日志流。没有显示“作业启动”、“作业结束”或“将文件放入 S3”的日志。也没有错误日志。尽管如此，当我检查 S3 存储桶时，还是创建了具有相应时间戳的文件，表明脚本确实运行完成。我无法理解这怎么可能。

dostuff.py

#!/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")

Docker文件

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

任务定义

{
    "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": []
}

观察

• 当我将任务数量（要获取的 url）减少到 10 而不是 ~1000 时，日志似乎在大部分时间/全部（？） 出现。同样，这个问题是间歇性的，所以我不能 100% 确定。
• 我的原始脚本具有额外的逻辑，用于在失败时重试获取，并解析我在故障排除时删除的逻辑。当时的日志记录行为至少具有“作业启动”的日志和异步 aiohttp 请求期间的日志。但是，写入 S3 的日志和最终的“作业完成”日志间歇性地出现。使用上面的简化脚本，我似乎要么获得所有日志，要么根本没有日志。
• python 的库也发生了问题，我更改为以排除问题loggingprintlogging