使用 AWS re:Post 即表示您同意 AWS re:Post 使用條款

Network traffic limits on EC2 instances

0

I am running a network-intensive task that sends several thousand pings/traceroute packets per second to external IP addresses. I've noticed that the network throughput is high soon after creating the instance, but drops off exponentially after the ping process has been running for more than an hour or so. I've tried this on a variety of instance sizes. Even on a c6.2xlarge (whose stated baseline network bandwidth is 2.5 Gbps), it drops down to around 200 packets a minute. Any ideas why this might be happening? Is there any way I can reserve more bandwidth for my instance?

已提問 3 年前檢視次數 9186 次
1 個回答
1
An instance receives the maximum number of network I/O credits at launch. If the instance exhausts its network I/O credits, it returns to its baseline bandwidth. A running instance earns network I/O credits whenever it uses less network bandwidth than its baseline bandwidth. A stopped instance does not earn network I/O credits. Instance burst is on a best effort basis, even when the instance has credits available, as burst bandwidth is a shared resource.

You can find more information at AWS official documentation .

Specific to c6g instance, you can find the baseline network performance here at https://docs.aws.amazon.com/AWSEC2/latest/UserGuide/compute-optimized-instances.html#compute-network-performance

If you would like to get much higher baseline performance, then look for the instance type that ends with letter "n". For example C5n, M5n, C6gn, etc

已回答 3 年前

您尚未登入。 登入 去張貼答案。

一個好的回答可以清楚地回答問題並提供建設性的意見回饋,同時有助於提問者的專業成長。

回答問題指南