Archive
When Load Shedding Looks Like Failure
Reading Latency Effectively
High Linux Load, Low CPU usage: When CPU Throttling Increased CPU Load
Anatomy of a Silent 502: The Four Characters That Explained a 60-Second Timeout
From The Vault: How SNAT Turned UDP Into a Stateful Protocol
Surviving A Complete ETCD Outage, Part 2: Restoration
Surviving A Complete ETCD Outage, Part 1: Snapshots, And Getting Them Back When the Cluster Is Gone
Onboarding Claude Code Harness: The Hard Way
Cache Stampede - Outage from Concurrency
Underneath (Micro)VMs: A Primer in H/W Virtualisation
Why etcd Disk I/O Stalls Crash Your K8s Pods
Opinion: K8s IS Data-Oriented Programming. We Just Call It YAML.
How Invisible Default Setting Can Break Production- War Story
The Fastest Operation Is the One You Never Perform
From the Vault: Designing a Hybrid Cloud Render Farm Under Time Constraints
Hidden Kubernetes Scheduling Quirks: Resource Allocation Traps Silently Breaking Deployments
nftables vs iptables: A Kubernetes Platform Engineer's Perspective
Silent Node Killer: How Mem-Backed emptyDir Vols. degraded our k8s Perf. Cluster
Python3 - 'GIL'T Free parallel processing is finally here
Synchronos Replication Does NOT Solve read-after-write consistency challenges
Why does time command may report more CPU time than the program actually ran?