Adrian Cockcroft

JANUARY 20, 2023

Most of the top supercomputers are similar to Frontier, they use AMD or Intel CPUs, with GPU accelerators, and Cray Slingshot or Infiniband networks in a Dragonfly+ configuration. The four categories still make sense: kernel managed network sockets, user mode message passing libraries, coherent memory interfaces, and on-chip communication.

Architecture 52

Architecture Latency Benchmarking AWS 52

The Netflix TechBlog

FEBRUARY 9, 2021

A few years ago, we decided to address this complexity by spinning up a new initiative, and eventually a new team, to move the complex handling of user and device authentication, and various security protocols and tokens, to the edge of the network, managed by a set of centralized services, and a single team.

Architecture 221

Architecture Latency Servers Website 221

Adrian Cockcroft

JANUARY 29, 2023

The mean and percentile measurements hide this structure, but the rest of this post will show how the structure can be measured and analyzed so that you can figure out a useful model of your system, understand what is driving the long tail of latencies and come up with better SLAs and measures of capacity.

Lambda 98

Lambda Latency Cache C++ 98

O'Reilly

DECEMBER 2, 2019

The most obvious change 5G might bring about isn’t to cell phones but to local networks, whether at home or in the office. High-speed networks through 5G may represent the next generation of cord cutting. Those waits can be significant, even if you’re on a corporate network. What will 5G mean in practice? I don’t, do you?

Wireless 53

Wireless Serverless IoT Artificial Intelligence 53

Brendan Gregg

JULY 4, 2021

AWS Graviton2); for memory with the arrival of DDR5 and High Bandwidth Memory (HBM) on-processor; for storage including new uses for 3D Xpoint as a 3D NAND accelerator; for networking with the rise of QUIC and eXpress Data Path (XDP); and so on. In case you are interested, at the same conference I also gave a talk on [BPF Internals].

Performance 52

Performance Latency Hardware Storage 52

Tasktop

JUNE 18, 2019

At Tasktop, we’re gearing up for yet another fantastic conference (Booth P4). As veteran platinum sponsors , we’ve gained a lot of wisdom over the years into how best to maximize the your time at the conference. Tip #2 – Embrace the opportunity to network. Networking is almost always priceless.

DevOps 74

DevOps Network Software Software 74

Brendan Gregg

AUGUST 18, 2019

For example, iostat(1), or a monitoring agent, may tell you your average disk latency, but not the distribution of this latency. For smaller environments, it can be of more use helping eliminate latency outliers. Block I/O latency as a histogram. This traces block I/O, and shows latency as a power-of-2 histogram.

Latency 68

Latency C++ Cache Programming 68

The Morning Paper

SEPTEMBER 5, 2019

For response times (latencies) reporting a simple metric such as ‘average’ is next to useless. Instead we want to understand what’s happening at different latency percentiles (e.g A characteristic of latency distributions is that they have a long tail. Why do we need a new sketch?

Latency 52

Latency Metrics Open Source Java 52

VoltDB

JUNE 1, 2017

Earlier this month I spent a week at the OpenStack conference. But once you realize that there are, in fact, several OpenStack conferences happening at the same time and place, it makes more sense. Latency Optimizers” – need support for very large federated deployments.

Hardware 56

Hardware Latency Virtualization Cloud 56

cdemi

JUNE 10, 2017

The bitcoin network works in parallel to generate a chain of Hashcash style proof-of-work (also known as CPU Cost Function, Client Puzzle, Computational Puzzle or CPU Pricing Function). Because these are real-time systems, their Byzantine fault tolerance solutions must have very low latency. Byzantine Fault Tolerance in Practice.

Blockchain 62

Blockchain Latency Systems C++ 62

The Morning Paper

DECEMBER 8, 2019

At the start of November I was privileged to attend HPTS (the High Performance Transaction Systems) conference in Asilomar. On the last morning of the conference Daniel Bittman presented some of the work being done in the context of the Twizzler OS project to explore new programming models for NVM.

Hardware 56

Hardware Programming Media Storage 56

VoltDB

JUNE 1, 2017

Earlier this month I spent a week at the OpenStack conference. But once you realize that there are, in fact, several OpenStack conferences happening at the same time and place, it makes more sense. Latency Optimizers” – need support for very large federated deployments.

Hardware 40

Hardware Latency Virtualization Cloud 40

Speed Curve

SEPTEMBER 4, 2013

The network constraints and what makes the web slow? Bandwidth, latency and it's fundamental impact on the speed of the web. Responsive web design is solid gold Etsy - Building Resilient User Experiences Velocity Conference Videos Browser Diet References. Illustrations by Scott Johnson via Browser Diet.

Speed 40

Speed Benchmarking Latency Mobile 40

Adrian Cockcroft

NOVEMBER 11, 2019

It would take 5–10 minutes after the problem occurred to appear as a problem, then people have to notice and respond to emails or pager text messages, dial into a conference call, and log in to monitoring dashboards before any human response can start. Try to measure your mean time to respond (MTTR) for incidents.

Latency 52

Latency Engineering Systems Hardware 52

Adrian Cockcroft

NOVEMBER 11, 2019

It would take 5–10 minutes after the problem occurred to appear as a problem, then people have to notice and respond to emails or pager text messages, dial into a conference call, and log in to monitoring dashboards before any human response can start. Try to measure your mean time to respond (MTTR) for incidents.

Latency 53

Latency Engineering Systems Hardware 53

Brendan Gregg

SEPTEMBER 5, 2017

Here's some output from my zfsdist tool, in bcc/BPF, which measures ZFS latency as a histogram on Linux: # zfsdist. Tracing ZFS operation latency. At my employer we sometimes use SR-IOV for direct network interface access, and NVMe for direct disk access. Hit Ctrl-C to end. ^C

Virtualization 76

Virtualization AWS Engineering Hardware 76

Smashing Magazine

AUGUST 22, 2021

As we will see, QUIC and HTTP/3 indeed have great web performance potential, but mainly for users on slow networks. If your average visitor is on a fast cabled or cellular network, they probably won’t benefit from the new protocols all that much. Two-way latency is often called round-trip time (RTT). Congestion Control.

Performance 105

Performance Network Latency Servers 105

Smashing Magazine

AUGUST 9, 2021

You may have read some blog posts or heard conference talks on this topic and think you know the answers. It also, however, takes a full network round trip to complete before anything else can be done on a connection. and lower), this typically takes two network round trips. Robin Marx. 2021-08-09T11:00:00+00:00.

Transportation 145

Transportation Internet Internet Network 145

All Things Distributed

OCTOBER 2, 2017

The success of our early results with the Dynamo database encouraged us to write Amazon's Dynamo whitepaper and share it at the 2007 ACM Symposium on Operating Systems Principles (SOSP conference), so that others in the industry could benefit.

Internet 130

Internet Internet AWS Performance 130