The Morning Paper

NOVEMBER 10, 2019

Snap: a microkernel approach to host networking Marty et al., This paper describes the networking stack, Snap , that has been running in production at Google for the last three years+. What’s left is a design whereby Snap runs as userspace ‘microkernel’, which applications communicate with using shared memory reads and writes.

Network 92

Network Transportation Latency Entertainment 92

Smashing Magazine

DECEMBER 15, 2021

Touch Design For Mobile Interfaces: Defining Mobile Devices (Excerpt). Touch Design For Mobile Interfaces: Defining Mobile Devices (Excerpt). Mobile phones are rapidly becoming touchscreens and touchscreen phones are increasingly all-touch, with the largest possible display area and fewer and fewer hardware buttons.

Mobile 104

Mobile Design Internet Internet 104

Scalegrid

MAY 13, 2020

Greenplum Database is an open-source , hardware-agnostic MPP database for analytics, based on PostgreSQL and developed by Pivotal who was later acquired by VMware. Greenplum uses an MPP database design that can help you develop a scalable, high performance deployment. Greenplum Architectural Design. What Exactly is Greenplum?

Big Data 321

Big Data Database Artificial Intelligence Open Source 321

Dynatrace

DECEMBER 8, 2021

This centralization means all aspects of the system can share underlying hardware, are generally written in the same programming language, and the operating system level monitoring and diagnostic tools can help developers understand the entire state of the system. Dynamic applications with ephemeral services.

Cloud 233

Cloud Serverless Hardware Operating System 233

High Scalability

DECEMBER 16, 2022

Cloud computing is a model of computing that delivers computing services over the internet, including storage, data processing, and networking. This means that users only pay for the computing resources they actually use, rather than having to invest in expensive hardware and software upfront.

Cloud 201

Cloud Serverless Internet Internet 201

Percona

APRIL 17, 2023

Note that the intent of tuning the settings is not exclusively about improving performance but also enhancing the high availability and resilience of the MongoDB database. There is an issue with this, which causes the OS to swap even with memory available. Spoiler alert: This post focuses on MongoDB 3.6.X 25.84 - Total 21.04

Best Practices 52

Best Practices Design Tuning Database 52

The Morning Paper

NOVEMBER 15, 2020

With more nodes and more coordination comes more complexity, both in design and operation. An IDS/IPS monitors network flows and matches incoming packets (or more strictly, Protocol Data Units, PDUs) against a set of rules. FPGAs are chosen because they are both energy efficient and available on SmartNICs).

Servers 128

Servers Hardware Latency Design 128

Dynatrace

AUGUST 11, 2022

Cloud providers then manage physical hardware, virtual machines, and web server software management. Infrastructure as a service (IaaS) handles compute, storage, and network resources. Increased availability. Consider a monolithic application, for example, designed to perform a host of functions. But how does FaaS fit in?

Development 259

Development Serverless Best Practices Lambda 259

The Netflix TechBlog

NOVEMBER 15, 2022

But it’s not easy: to pull this off, VFX studios need to build and operate serious technical infrastructure (compute, storage, networking, and software licensing), otherwise known as a “ render farm.” via direct plug-ins, and is available on multi-cloud platform services. Additionally, Conductor supports render management systems?—?including

Cloud 282

Cloud Entertainment AWS Infrastructure 282

The Morning Paper

MAY 12, 2019

An open-source benchmark suite for microservices and their hardware-software implications for cloud & edge systems Gan et al., It’s a pretty impressive effort to pull together and make available in open source (not yet available as I write this) such a suite, and I’m sure explains much of the long list of 24 authors on this paper.

Open Source 61

Open Source Hardware Benchmarking Systems 61

Percona

AUGUST 30, 2023

In general terms, here are potential trouble spots: Hardware failure: Manufacturing defects, wear and tear, physical damage, and other factors can cause hardware to fail. heat) can damage hardware components and prompt data loss. Human mistakes: Incorrect configuration is an all-too-common cause of hardware and software failure.

Database 88

Database Hardware Open Source Strategy 88

The Netflix TechBlog

AUGUST 30, 2021

Complementing the hardware is the software on the RAE and in the cloud, and bridging the software on both ends is a bi-directional control plane. For example, when running tests, the state of the device will change from “available for testing” to “in test.” In this blog post, we will focus on the latter feature set.

Latency 213

Latency Traffic Transportation Hardware 213

The Morning Paper

JUNE 11, 2019

Beyond data and model parallelism for deep neural networks Jia et al., Traditional approaches to training exploit either data parallelism (dividing up the training samples), model parallelism (dividing up the model parameters), or expert-designed hybrids for particular situations. SysML’2019. Expanding the search space.

Network 81

Network Strategy Hardware Benchmarking 81

The Morning Paper

JUNE 25, 2019

Designing far memory data structures: think outside the box Aguilera et al., There’s another emerging option that we didn’t talk about there: the use of far-memory , memory attached to the network that can be remotely accessed without mediation by a local processor. HotOS’19. It’s not all straightforward though. The last word.

Design 80

Design Cache Hardware Scalability 80

The Netflix TechBlog

NOVEMBER 9, 2021

We were very pleased to see that AV1 streaming improved members’ viewing experience, particularly under challenging network conditions. AV1 playback on TV platforms relies on hardware solutions, which generally take longer to be deployed. Throughout 2020 the industry made impressive progress on AV1 hardware solutions.

Media 246

Media Open Source Efficiency Software Engineering 246

High Scalability

OCTOBER 24, 2022

Each cloud-native evolution is about using the hardware more efficiently. Network effects are not the same as monopoly control. It's not because there are no other options available to them because of structural issues. Does anyone really want to go back to the VM-centric days when we rolled everything ourselves? It's a choice.

Cloud 187

Cloud Hardware Infrastructure Innovation 187

Dynatrace

OCTOBER 28, 2021

The crisis could be technical, natural, or malicious events, for example an earthquake affecting data center availability, or a cyberattack infecting applications and websites. Intelligence from chaos testing funnels back to developers who can implement design changes that make software more durable and improve production quality.

Engineering 234

Engineering Entertainment Cloud Infrastructure 234

Testlodge

NOVEMBER 12, 2021

Software testers explore the effectiveness of processes that should lead to quality software products to make sure they perform the purpose for which they have been designed. For medium to large scale applications, compatible with all commonly available operating systems and internet browsers is essential.

Testing 78

Testing Hardware Operating System Mobile 78

Dynatrace

SEPTEMBER 30, 2021

Cloud migration is the process of transferring some or all your data, software, and operations to a cloud-based computing environment that offers unlimited scale and high availability. They need enough hardware to serve their anticipated volume and keep things running smoothly without buying too much or too little. Reduced cost.

Cloud 172

Cloud Traffic Best Practices Strategy 172

Adrian Cockcroft

JANUARY 17, 2022

There were five trends and topics for 2021, Serverless First, Chaos Engineering, Wardley Mapping, Huge Hardware, Sustainability. The need for systems to be resilient is still increasing, and chaos engineering tools and techniques are developing as a key way to validate that resilience is working as designed.

Serverless 98

Serverless Hardware AWS Architecture 98

Dynatrace

NOVEMBER 11, 2020

” Meaning, you don’t need to worry about OneAgent updates because they’re performed automatically, safely, and promptly as soon as new versions are available (no manual effort required). As such, it’s quite often a network-shared mount point that multiple hosts use to store third party software and libraries.

Best Practices 206

Best Practices Storage Java Benchmarking 206

Scalegrid

JANUARY 25, 2024

Understanding Redis Performance Indicators Redis is designed to handle high traffic and low latency with its in-memory data store and efficient data structures. It’s important to note that recommended throughput levels may vary depending on factors such as operating system type, network bandwidth availability, and hardware quality.

Metrics 130

Metrics Monitoring Latency Cache 130

All Things Distributed

MAY 22, 2013

Amazon Redshift and Designing for Security. How do you handle availability, security, and integration?â?? ve talked about performance and availability in Amazon Redshift before. Amazon Redshift can also be set up to encrypt all data at rest using hardware-accelerated AES-256. All Things Distributed. Comments ().

Design 110

Design AWS Hardware Media 110

ACM Sigarch

APRIL 26, 2018

BPU: Brain Processing Unit is the design of the AI chips by Horizon Robotics. With its modular architecture, DLA is scalable, highly configurable, and designed to simplify integration and portability. HPU: Holographic Processing Unit (HPU) is the specific hardware of Microsoft’s Hololens.

Hardware 99

Hardware Artificial Intelligence Architecture Google 99

Dynatrace

APRIL 5, 2021

You will likely need to write code to integrate systems and handle complex tasks or incoming network requests. As a bonus, operations staff never needs to update operating systems or hardware, because AWS manages servers with no stoppage of application functionality. Customizing and connecting these services requires code.

Lambda 186

Lambda AWS Serverless Hardware 186

Sutter's Mill

NOVEMBER 11, 2023

Instead, you want a library that is tuned for your target hardware architecture and ready for par_unseq vectorized algorithms, for blazing speed. There are a handful of design questions still to decide, norably the semantics of implicit lambda capture, consteval , and multiple declarations. Seeing only the end result of T.[0]

C++ 107

C++ Lambda Network Programming 107

SQL Server According to Bob

SEPTEMBER 26, 2016

When we released Always On Availability Groups in SQL Server 2012 as a new and powerful way to achieve high availability, hardware environments included NUMA machines with low-end multi-core processors and SATA and SAN drives for storage (some SSDs). As we moved towards SQL Server 2014, the pace of hardware accelerated.

Availability 40

Availability Servers Hardware Benchmarking 40

Percona

FEBRUARY 24, 2023

Let’s take a look at how to get the benefits you need while spending less, based on the recommendations presented by Dani Guzmán Burgos, our Percona Monitoring and Management (PMM) Tech Lead, on this webinar (now available on demand) hosted in November last year. These color-coded states on panels are available in PMM 2.32.0

Cloud 119

Cloud Serverless AWS Storage 119

The Morning Paper

MARCH 3, 2020

It takes you through the thinking processes and engineering practices behind the design of a key part of the control plane for AWS Elastic Block Storage (EBS): the Physalia database that stores configuration information. EBS uses chain replication for availability, with data flowing from client to primary to replica. NSDI’20.

Database 106

Database AWS Network Design 106

The Morning Paper

MARCH 1, 2020

We looked at a couple of papers that had pre-prints available last week, today we’ll be looking at one of the most anticipated papers of this year’s crop: Amazon’s Firecracker. The design of Firecracker. These simplifying assumptions are reflected in Firecracker’s design and implementation.

Serverless 101

Serverless Virtualization Lambda AWS 101

All Things Distributed

MARCH 19, 2018

So, when designing Amazon SageMaker we took on a challenge: to build machine learning algorithms that can handle an infinite amount of data. This post lifts the veil on some of the scientific, system design, and engineering decisions we made along the way. What does that even mean though? This sounds like a pipe dream.

Scalability 159

Scalability Hardware AWS Tuning 159

Alex Russell

JANUARY 30, 2024

It's time once again to update our priors regarding the global device and network situation. This split decision was available via last year's update , but was somewhat buried. seconds on the target device and network profile, consuming 120KiB of critical path resources to become interactive, only 8KiB of which is script.

Performance 90

Performance Network Mobile Speed 90

All Things Distributed

MARCH 11, 2016

But we couldn’t adopt the old style approach of upgrading systems through a maintenance outage, as many businesses around the world are relying on our platform for 24/7 availability. This is a given, whether you are using the highest quality hardware or lowest cost components. Systems need to keep running even if the “house is on fire.”

AWS 144

AWS Hardware Retail Virtualization 144

The Morning Paper

MAY 19, 2019

The net result of rapid advancements in the networking world is that inter-tier communications latency will approach the fundamental lower bound of speed-of-light propagation in the foreseeable future. While this core is stalled on the TLB miss(es), it is best to dispatch RPCs to other available cores on the server. Evaluation.

Latency 80

Latency Hardware Network Architecture 80

O'Reilly

NOVEMBER 28, 2023

A year after the first web servers became available, how many companies had websites or were experimenting with building them? Such policies would be designed to mitigate legal problems and require regulatory compliance. That pricing won’t be sustainable, particularly as hardware shortages drive up the cost of building infrastructure.

Open Source 106

Open Source Artificial Intelligence Google Infrastructure 106

The Netflix TechBlog

JUNE 4, 2019

Because microprocessors are so fast, computer architecture design has evolved towards adding various levels of caching between compute units and the main memory, in order to hide the latency of bringing the bits to the brains. As an illustrative example, let’s consider a toy instance of 16 hyperthreads.

Cache 251

Cache Latency Airlines Logistics 251

Testlodge

JUNE 16, 2021

To secure consumer data, organizations need to make sure that their networks are updated and protected against any malicious activity. Various standardized security methods are available. Penetration testing is comprehensively performed over a fully-functional system’s software and hardware. Penetration Testing Tools.

Testing 67

Testing Hardware Open Source Internet 67