SShortSingh.
Back to feed

New eBPF tool reveals hidden AWS network costs by attributing data transfers to workloads

0
·1 views

A significant portion of AWS costs for Kubernetes clusters is often hidden within broad network data transfer charges. Traditional tools like AWS Cost Explorer show the total bill but cannot attribute these costs to specific pods, teams, or applications. By using eBPF-based instrumentation, engineers can now track bytes at the kernel level and enrich the data with Kubernetes metadata. This method allows for precise cost attribution to individual workloads and communication pairs. The initial deployment of this tool quickly identified concrete cost-saving opportunities that were previously invisible.

Read the full story at DEV Community

This is an AI-generated summary. ShortSingh links to the original source for the complete article.

Discussion (0)

Log in to join the discussion and vote.

Log in

Related stories

0
ProgrammingHacker News ·

Nobel Peace Prize Awarded to Navanethem Pillay for 2026

The Nobel Committee has awarded the 2026 Nobel Peace Prize to human rights advocate Navanethem 'Navi' Pillay. She was recognized for her decades of work in international justice and human rights. The official announcement was made by the Norwegian Nobel Committee. Pillay's career includes serving as a UN High Commissioner for Human Rights and a judge on the International Criminal Court.

0
ProgrammingDEV Community ·

Data Freshness, Not Real-Time, Key for Market Insights

A blog post on DEV Community argues that most businesses do not require true real-time market data. Instead, teams should ensure data is fresh enough to support the specific decisions it informs. The key is to define a maximum acceptable age for data before acting on it becomes risky, establishing a freshness service-level objective. This approach reduces false reactions and makes systems easier to debug by focusing on the relevance of data to the required action.

0
ProgrammingDEV Community ·

Django 6.1 increases default password hashing iterations, affecting login speed

Django 6.1, released in August, increased the default PBKDF2 password hashing iteration count from 1.2 million to 1.5 million. This change increases CPU time for password verification by approximately 25%, adding 50-90 milliseconds per login. Benchmark tests confirmed the performance impact but showed the hashing process scales across multiple CPU cores. The framework automatically updates existing password hashes to the new standard when users next log in.