Remove AWS Remove Benchmarking Remove Internet Remove Latency
article thumbnail

The Speed of Time

Brendan Gregg

A Cassandra database cluster had switched to Ubuntu and noticed write latency increased by over 30%. Colleagues/Internet I love using [Linux performance tools]. But I also love solving issues quickly, and sometimes that means just asking colleagues or searching the Internet. include <sys/time.h>

Speed 126
article thumbnail

The Speed of Time

Brendan Gregg

A Cassandra database cluster had switched to Ubuntu and noticed write latency increased by over 30%. Colleagues/Internet I love using Linux performance tools. But I also love solving issues quickly, and sometimes that means just asking colleagues or searching the Internet. Running this on the two systems saw similar results.

Speed 52
Insiders

Sign Up for our Newsletter

This site is protected by reCAPTCHA and the Google Privacy Policy and Terms of Service apply.

Trending Sources

article thumbnail

What Is a Workload in Cloud Computing

Scalegrid

With extensive computational resources at their disposal alongside massive pools of information, developers can utilize these powerful tools to train ML models efficiently or run AI algorithms effectively by accessing stored datasets from anywhere through the internet connection provided by most reputable providers’ hosting services.

Cloud 130
article thumbnail

The Speed of Time

Brendan Gregg

A Cassandra database cluster had switched to Ubuntu and noticed write latency increased by over 30%. Colleagues/Internet I love using [Linux performance tools]. But I also love solving issues quickly, and sometimes that means just asking colleagues or searching the Internet. include <sys/time.h>

Speed 40
article thumbnail

Why OpenStack is like a Crowdfunded Viking Movie

VoltDB

In addition, such custom systems could only be benchmarked once they were deployed, so by the time multiple layers of management had each added a 50% safety margin to the initial SWAG , it was not unusual to see them running at 10% of capacity (but 150% of the lucky hardware salesman’s annual quota). The “Public Private Cloud” folks.

article thumbnail

This week in review: GPUs, Zombies, Biomimicry and Tom Waits.

All Things Distributed

There was an excellent first benchmarking report of the Cluster GPU Instances by the folks at Cycle Computing - " A Couple More Nails in the Coffin of the Private Compute Cluster " The Top500 supercomputer list. Driving Storage Costs Down for AWS Customers. Expanding the Cloud - The AWS Storage Gateway. All postings.

AWS 68
article thumbnail

Why OpenStack is like a Crowdfunded Viking Movie

VoltDB

In addition, such custom systems could only be benchmarked once they were deployed, so by the time multiple layers of management had each added a 50% safety margin to the initial SWAG , it was not unusual to see them running at 10% of capacity (but 150% of the lucky hardware salesman’s annual quota). The “Public Private Cloud” folks.