Summary
Google Cloud protects each VM by limiting ingress traffic delivered to an external IP address associated with the VM, with a limit of 1,800,000 pps (packets per second) or 20 Gbps.
1
Additionally, each core goes through a 2 Gbits/second (Gbps) cap for peak performance, with a theoretical optimum of 16 Gbps for each virtual machine.
2
Google Cloud's VPC networking services are designed to provide high throughput, low latency, global availability, and rapid scale.
3
Tools such as gcping can be used to measure network throughput and determine median latencies to Google Cloud regions.
4
According to
Summary
This document provides information on how to calculate network throughput, both within Google Cloud and to on-premises or third-party cloud locations. It explains the common use cases for a network throughput assessment, the tools used to measure network throughput, and the importance of considering round-trip time, latency, and distances when calculating network throughput. Additionally, it provides tips on how to analyze results, troubleshooting tips, and how to use the gcping command-line tool to determine median latencies to Google Cloud regions.
Calculating network throughput | Google Cloud Platform Community
google.com
Summary
Google Cloud's VPC networking services are designed to provide high throughput, low latency, global availability, and rapid scale. This model is built around a software-defined networking (SDN) model, allowing users to quickly customize and scale their services to meet the needs of their growing customer base. Google Cloud's VPC networking features include networks, subnets, IP addresses, routes, firewalls, Cloud VPN, and Cloud Router, as well as Identity and Access Management (IAM) roles, firewalls, and routes to help manage and secure the network.
Google Cloud for Data Center Professionals: Networking
google.com
