Autovacuum is the most misunderstood background process on a small PostgreSQL VPS. Left at defaults sized for large dedicated servers, it either runs too rarely — letting dead tuples bloat…
Read MoreEnforcing Disk I/O QoS with cgroup v2 io.latency and io.max on Noisy Instances
Stop one runaway process from starving everything else on the disk. Use io.latency target-latency control and io.max bandwidth caps to enforce per-workload disk QoS on cgroup v2.
Read Morezram vs Swap Partition on a VPS: Latency, Memory Savings and When Each One Hurts
On a VPS you cannot add physical RAM, so when memory pressure arrives you have two broad escapes: spill to disk-backed swap, or compress cold pages in RAM with zram….
Read MoreTCP BBR vs CUBIC on a VPS WAN Link: What grep bw = (delivery_rate) Actually Tells You
Comparing congestion control algorithms by download speed alone is how you end up with a tuning change that helps one flow shape and hurts another. The kernel exposes a far…
Read Moreext4 Journal Commit Interval on a VPS: The Durability vs Throughput Tradeoff, Measured
Every ext4 filesystem on your VPS makes a silent promise: after fsync() returns, the data is on stable storage. Between those explicit syncs, the kernel batches writes and flushes the…
Read Morevirtio-net Multi-Queue RX/TX Tuning on a VPS: Reducing Single-vCPU Packet Drop
A VPS virtual NIC is not a physical card. It is a paravirtualised device whose packets are delivered by the hypervisor into your guest’s receive path, often through a single…
Read MoreLinux Memory Accounting for Small VPS Hosts: MemAvailable vs Free, and Every Bit of Overhead You Forgot
Every “is my VPS out of memory?” decision rests on two numbers from /proc/meminfo, and most operators read the wrong one. MemFree tells you how much RAM is completely unused…
Read MoreEphemeral Port Exhaustion and SO_REUSEPORT Tuning on Linux Servers
When a busy server starts refusing new connections but traffic and CPU look normal, the cause is often a quiet resource limit: the ephemeral port range, or the loading of…
Read MoreTuning net.ipv4.tcp_rmem for High-Latency VPS Workloads: Buffer Sizing by Bandwidth-Delay Product
The default 6 MB TCP receive-buffer ceiling caps single-stream throughput on high-RTT links. Measure the bandwidth-delay product, size tcp_rmem and core.rmem_max correctly, and verify with live socket statistics.
Read MoreFinding Packet Loss on a VPS Uplink with tcpdump, nstat, and eBPF Drop Tracing
Map packet-loss symptoms to the layer that caused them using kernel counters, targeted tcpdump captures, and eBPF kfree_skb reason codes. Includes a counter-to-cause reference table.
Read More