Linux: Everything is a file; peekfd: peek write/read of every file
· β˜• 2 min read
Most of the data flows in Linux, including inter-process communication, sockets, etc., are implemented through file descriptors (fd) reading and writing. When troubleshooting, if you can peek at the fd traffic, many problems can be quickly proved/falsified. This article introduces an old tool peekfd, which can accomplish this task in a certain environment.

Please prove that it is the network's fault - the lost Envoy sidecar
· β˜• 4 min read
Network quality issues such as packet loss can be discovered, quantified, and monitored using Envoy sidecar. During testing, Envoy can be used as an egress on the client side such as JMeter to monitor traffic. This article discusses one of the implementation solutions.

Flow control and backpressure of Envoy/Istio
· β˜• 14 min read
Like all proxy software, Envoy takes flow control seriously because CPU/memory resources are limited. But flow control is never a simple matter. It involves all the players in the data flow path. This article tries to explain the principles and synergies involved.

My new book - Istio & Envoy Insider
· β˜• 3 min read
Istio & Envoy Insider - A book focus on Envoy Proxy & Istio mechanism and implementation deep dive

Envoy WASM Network Filter to fix illegal HTTP Header
· β˜• 5 min read
The normal HTTP request was responded with HTTP status code 400 after migrating to Istio. The problem traffic has HTTP headers that do not comply with the HTTP 1.1 specification. So I try to develop an Envoy WASM Network Filter to fix the illegal HTTP Header.

My real-life Istio Performance Tuning - Part 1
· β˜• 7 min read
Why tuning If it takes interest and momentum to push a new technology, then what is needed to get this technology go to live production is hard working. Including Cloud Native and Istio. In pre-launch performance testing, Istio out-of-box provided observability, operational convenience, and also introduced pain: Increased service latency. How to minimize latency has become a critical task. My Scenario: SERVICE-A invoke SERVICE-B Latency of Service-A, which was previously 9ms at P50, is now 14ms at P50.