The Netflix TechBlog

OCTOBER 19, 2020

If we had an ID for each streaming session then distributed tracing could easily reconstruct session failure by providing service topology, retry and error tags, and latency measurements for all service calls. Using simple lookup indices in Cassandra gives us the ability to maintain acceptable read latencies while doing heavy writes.

Infrastructure 233

Infrastructure Transportation Storage Open Source 233

Brendan Gregg

SEPTEMBER 25, 2021

A Cassandra database cluster had switched to Ubuntu and noticed write latency increased by over 30%. Since instances of both CentOS and Ubuntu were running in parallel, I could collect flame graphs at the same time (same time-of-day traffic mix) and compare them side by side. include <sys/time.h>

Speed 126

Speed Java AWS Virtualization 126

Alex Russell

MARCH 6, 2021

TL;DR: A lot has changed since 2017 when we last estimated a global baseline resource per-page resource budget of 130-170KiB. To update our global baseline from 2017, we want to update our priors on a few dimensions: The evolved device landscape. The Moto G4 , for example. Here begins our 2021 adventure. Hard Reset.

Performance 124

Performance Network Cache Metrics 124

Brendan Gregg

SEPTEMBER 25, 2021

A Cassandra database cluster had switched to Ubuntu and noticed write latency increased by over 30%. Since instances of both CentOS and Ubuntu were running in parallel, I could collect flame graphs at the same time (same time-of-day traffic mix) and compare them side by side. include <sys/time.h>

Speed 40

Speed Java AWS Virtualization 40

Alex Russell

OCTOBER 22, 2017

— Alex Russell (@slightlylate) October 4, 2017. Budgets are scaled to a benchmark network & device. Deciding what benchmark to use for a performance budget is crucial. It simulates a link with a 400ms RTT and 400-600Kbps of throughput (plus latency variability and simulated packet loss). Global Ground-Truth.

Performance 68

Performance Benchmarking Network Mobile 68