A Journey in Observability
-
Performance Diagnostics Part 5- Optimising Worker Threads
Background A few (ok many) years ago I was working with a customer who was launching a new application and was expecting a high load on their launch, which for whatever reason was at 3pm on a Friday (1). As 3pm hit, and the load balancers started directing traffic to the now production system, there…
-
Learning eBPF Review
What makes Learning eBPF different to BPF Performance tools (which I wrote about recently) is that it moves beyond theObservability and performance lens towards Security and modification behaviour inside the Linux kernel. The author Liz Rice is the Chief Open Source Officer at Isovalent and recently presented at the eBPF Virtual Summit in September of…
-
Performance Diagnostics Part 3 — Latency beyond Ping
Network teams often use ICMP as a mechanism to determine the latency (propagation delay etc) and reachability between two endpoints using the trusty Ping utility. Ping appeared in late 1983 created Mike Muuss while working US Ballistics Research Laboratory. Additionally, what was interesting about 1983 is that it was the year the that the US military converged on…
-
Why Are We Seeing Cloud Migrations in Reverse?
I’ve always loved using excess or old computers and network infrastructure to lab things up or run a PoC for an application or service. I still have a Dell R710 and HP ML10v2 I use to run services like Home Assistant and various observability tools for testing. So what does this have to do with…
-
BPF Performance Tools Review
BPF Performance Tools the kind of book an observability specialist picks up and thinks this will make a good reference book for my library, and then reads the whole thing cover to cover. Brendan Gregg formerly of NetFlix has contributed significantly to the world of observability and uses his experience in troubleshooting and tracing some…
-
Performance Diagnostics Part 4 -HTTPS Performance
Unlike HTTPS, analysing HTTP traffic with tools like Wireshark is pretty easy because everything is in clear text. Wireshark will even give you the request performance (49ms highlighted below). I can also see that the request was sent in packet 4 (after the three way handshake), and the response came in packet 6. The delta…
-
Top 5 Wireshark Tips for Network Analysis
I’ve been using Wireshark since it was named Ethereal back in the very early 2000s, and I still use it daily for research. Wireshark recently turned 25 with creator Gerald Combs announcing it on the Wireshark blog and celebrating it at Sharkfest ‘23 Asia and US. To celebrate I’m going to offer my top 5 Wireshark tips for 2023! Tip 1 — Use Profiles…
-
Who’s Using My Bandwidth?
One of the questions I hate is “who’s using my bandwidth?!?” and not at all because I was the child consuming and all of the available dial-up (28.8Kbps) bandwidth downloading the latest FreeBSD or Linux distribution image. In fact this was the age of magazines with CDs that contained Mandrake, RedHat, or if I was…
-
Performance Diagnostics Part 2 — Revenge of the OSI Model
Continuing on from the previous article where I discussed an amalgamation of performance diagnostics with fat client applications. I thought it was a good time to go back to computer science 101 where we were introduced to the OSI model and the TCP/IP model. Both are models that some architectures and platforms more or less…
-
Performance Diagnostics Part 1
Over the last 20 years I’ve been sent in by customers to investigate some of the most intriguing application performance problems that have had customers investing in infrastructure, time in war rooms, connectivity to try and resolve a problem that is eluding the technical team, or the technical team is unable to quantify what will…