The Morning Paper

MARCH 8, 2020

This paper describes the design decisions behind the Snowflake cloud-based data warehouse. This paper presents Snowflake design and implementation along with a discussion on how recent changes in cloud infrastructure (emerging hardware, fine-grained billing, etc.) From shared-nothing to disaggregation.

Storage 112

Storage Engineering Cache Serverless 112

The Morning Paper

MAY 14, 2019

Seer: leveraging big data to navigate the complexity of performance debugging in cloud microservices Gan et al., Seer is an online system that observes the behaviour of cloud applications (using the DeathStarBench microservices for the evaluation) and predicts when QoS violations may be about to occur. ASPLOS’19.

Big Data 45

Big Data Cloud Performance Hardware 45

Percona

MAY 1, 2023

Key areas include: Configuration parameter tuning : This tuning involves altering variables such as memory allocation, disk I/O settings, and concurrent connections based on specific hardware and requirements. This not only results in cost savings by minimizing hardware requirements but also has the potential to decrease cloud expenses.

Tuning 52

Tuning Efficiency Database Performance 52

HammerDB

APRIL 19, 2023

Regardless of whether the computing platform to be evaluated is on-prem, containerized, virtualized, or in the cloud, it is crucial to consider several essential factors. There are many times we get asked why some cloud instance performed poorly for their database application and almost always turned out to be some configuration error.

Performance 54

Performance Benchmarking Cache Storage 54

Scalegrid

JANUARY 5, 2024

These can be mitigated through the implementation of: efficient query optimization caching of database queries utilization of database indexes implementation of session storage employing database read replication and sharding. By implementing data abstraction techniques, these challenges can be addressed more effectively.

Efficiency 147

Efficiency Storage Database Scalability 147

The Netflix TechBlog

NOVEMBER 15, 2022

Rendering is the final step in the VFX creation process, and processing on a render farm often can take several hours to complete just a single frame of a show, even when this process runs on the latest high-end hardware. Without cloud-based rendering, this ambitious project would not have met its targeted delivery date!

Cloud 282

Cloud Entertainment AWS Infrastructure 282

Brendan Gregg

FEBRUARY 28, 2023

TCP Extensions for Multipath Operation with Multiple Addresses,” [link] , Mar 2020 [Gregg 20] Brendan Gregg, “Systems Performance: Enterprise and the Cloud, Second Edition,” Addison-Wesley, 2020 [Hruska 20] Joel Hruska, “Intel Demos PCIe 5.0 Ford, et al., “TCP

Performance 52

Performance Latency Cache Virtualization 52

Alex Russell

JUNE 19, 2020

Eleventy is I/O heavy, and for correctness sake, it didn't do much caching. The caches added by these changes are likely error prone and may bloat build memory for large sites. Details about build hardware, OS, and template configuration are particularly useful. Copied 1189 files / Wrote 1175 files in 5.75 MiB | 2.99

Cache 49

Cache Hardware Speed Cloud 49

The Morning Paper

OCTOBER 4, 2020

In the radio portion of the network, 5G buffer sizes are 5x 4G, but within the wired portion of the network only about 2.5x (this is with a 1000 Mbps provisioned cloud server). Emerging architectures that shorten the path length, e.g. edge caching and computing, may also confine the latency. Application performance.

Energy 130

Energy Latency Performance Network 130

ACM Sigarch

FEBRUARY 23, 2018

Hardware engineers design and implement solutions in RTL, while software engineers attempt to solve the problem either at the OS or application level. The same myopic view clouds us as researchers. I recall heated discussions 20+ years ago on whether speculative data in caches improves or degrades cache performance.

Architecture 47

Architecture Cache Hardware Virtualization 47

KeyCDN

JANUARY 23, 2020

A wide range of users with different operating systems, browsers, hardware configurations and other variables provides a wide sample size that helps developers discover as many issues as possible. This helps developers decide when to increase server disk space and power or whether or not using a virtual cloud server is optimal.

Strategy 72

Strategy Metrics Monitoring Servers 72

Scalegrid

FEBRUARY 8, 2024

Key Takeaways Distributed storage systems benefit organizations by enhancing data availability, fault tolerance, and system scalability, leading to cost savings from reduced hardware needs, energy consumption, and personnel. They maintain fault tolerance and redundancy by replicating this information throughout various nodes in the system.

Storage 130

Storage Systems Big Data Azure 130

Brendan Gregg

MARCH 16, 2024

Only in extreme circumstances does the cost (in processor time and I-cache footprint) translate to a tangible benefit - circumstances which usually resort to hand-coded assembly anyway. It shouldn't be 10%, unless it's cache effects. And for leaf routines (which never establish a frame), this is a non-issue.

Java 145

Java Cache Google Hardware 145

Percona

MARCH 23, 2023

Hardware Memory The amount of RAM to be provisioned for database servers can vary greatly depending on the size of the database and the specific requirements of the company. By caching hot datasets, indexes, and ongoing changes, InnoDB can provide faster response times and utilize disk IO in a much more optimal way.

Performance 125

Performance Hardware Tuning Storage 125

Dynatrace

OCTOBER 7, 2021

For many companies, the journey to modern cloud applications starts with serverless. Instead of worrying about infrastructure management functions, such as capacity provisioning and hardware maintenance, teams can focus on application design, deployment, and delivery. Dynatrace news. Simplicity. The first benefit is simplicity.

Serverless 279

Serverless AWS Lambda Storage 279

Dynatrace

AUGUST 30, 2019

She was speaking about how her team is providing Visibility as a Service (VaaS) in order to continuously monitor and optimize their systems running across private and public cloud environments. Reducing CPU Utilization to now only consume 15% of initially provisioned hardware. Missing retry and failover implementations.

Cache 197

Cache Architecture Database Government 197

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., Microservices fundamentally change a lot of assumptions current cloud systems are designed with, and present both opportunities and challenges when optimizing for quality of service (QoS) and utilization.

Open Source 61

Open Source Hardware Benchmarking Systems 61

The Netflix TechBlog

MARCH 8, 2021

They need specialized hardware, access to petabytes of images, and digital content creation applications with controlled licenses. One of our first partners for the Netflix Workstations is NetFX , a cloud-based VFX platform that enables vendors, artists, and creators worldwide to collaborate on Netflix VFX content.

Entertainment 306

Entertainment Storage Hardware Open Source 306

HammerDB

JUNE 27, 2022

It enables the user to measure database performance and make comparative judgements about database hardware and software. These factors meant that often when looking for database performance information, the results for a particular combination of software and hardware were not available. Cached vs Scaled Workloads.

Benchmarking 62

Benchmarking Open Source C++ Cache 62

Percona

JUNE 22, 2023

To make data count and to ensure cloud computing is unabated, companies and organizations must have highly available databases. Components of high availability infrastructure Multiple copies of data Data redundancy helps prevent data loss due to hardware or software failures. Redundancy is also critical for disaster recovery.

Availability 107

Availability Database Open Source Hardware 107

The Morning Paper

APRIL 14, 2019

The paper sets out what we can do in software given today’s hardware, and along the way also highlights areas where cooperation from hardware will be needed in the future. “ Preventing side-channel attacks between VMs hosted on public cloud infrastructure. Microarchitectural channels. Threat scenarios.

Hardware 44

Hardware Cache Latency Speed 44

Sutter's Mill

FEBRUARY 13, 2017

” This contains updated and new material that reflects the latest C++ standards and compilers, with a focus to using modern C++11/14/17 effectively on modern hardware and memory architectures. On April 25-27, I’ll be in Stockholm (Kista) giving a three-day seminar on “High-Performance and Low-Latency C++.”

Latency 51

Latency C++ Hardware Performance 51

SQL Performance

DECEMBER 17, 2019

One initial, easy step to moving your SQL Server on-premises workloads to the cloud is using Azure VMs to run your SQL Server workloads in an infrastructure as a service (IaaS) scenario. BTW, the "i" in the Standard_E64is_v3 naming means that the instance is isolated to hardware dedicated to a single customer.

Azure 72

Azure Virtualization Servers Storage 72

All Things Distributed

JULY 14, 2015

Streams provide you with the underlying infrastructure to create new applications, such as continuously updated free-text search indexes, caches, or other creative extensions requiring up-to-date table changes. Their cloud architecture has two main components: a point-of-sales system and a merchandising system.

Database 167

Database Lambda AWS IoT 167

The Morning Paper

SEPTEMBER 19, 2019

We hear a lot from Google and Microsoft about their cloud platforms, but not quite so much from the other key industry players. Autoscaling tiered cloud storage in Anna. This VLDB’19 paper describes “ how we extended a distributed key-value store called Anna into an autoscaling, multi-tier service for the cloud.”

Blockchain 46

Blockchain Hardware Google Analytics 46

Abhishek Tiwari

DECEMBER 27, 2017

With the arrival of new cloud-native tools and platform, ETL is becoming obsolete. Apache Arrow's in-memory columnar layout is specifically optimized for data locality for better performance on modern hardware like CPUs and GPUs. In contrast, Alluxio a middleware for data access - think Alluxio storage layer as fast cache.

Big Data 49

Big Data Artificial Intelligence Storage Hardware 49

ScaleOut Software

JULY 27, 2018

Hosted on commodity clusters or cloud infrastructures, IMDGs harness the power of distributed computing to deliver scalable storage capacity and access throughput, along with integrated high availability. Looking beyond distributed caching, it’s their ability to perform data-parallel analysis that gives IMDGs such exciting capabilities.

Scalability 40

Scalability Cache Airlines Healthcare 40

ScaleOut Software

JULY 27, 2018

Hosted on commodity clusters or cloud infrastructures, IMDGs harness the power of distributed computing to deliver scalable storage capacity and access throughput, along with integrated high availability. Looking beyond distributed caching, it’s their ability to perform data-parallel analysis that gives IMDGs such exciting capabilities.

Scalability 40

Scalability Cache Airlines Healthcare 40

Alex Russell

MARCH 6, 2021

A then-representative $200USD device had 4-8 slow (in-order, low-cache) cores, ~2GiB of RAM, and relatively slow MLC NAND flash storage. A silver lining on this dark cloud is that mobile JavaScript payload growth paused in 2020. Hardware Past As Performance Prologue. The Moto G4 , for example. Mind The Gap.

Performance 124

Performance Network Cache Metrics 124

Percona

JANUARY 17, 2019

On multi-core machines – which is the majority of the hardware nowadays – and in the cloud, we have multiple cores available for use. Aurora Parallel Query response time (for queries which can not use indexes) can be 5x-10x better compared to the non-parallel fully cached operations. This query is 100% cached.

Cache 46

Cache C++ AWS Airlines 46

All Things Distributed

JANUARY 18, 2012

DynamoDB is the result of 15 years of learning in the areas of large scale non-relational databases and cloud services. With Amazon DynamoDB, developers scaling cloud-based applications can start small with just the capacity they need and then increase the request capacity of a given table as their app grows in popularity.

Scalability 167

Scalability Database Ecommerce Latency 167

The Morning Paper

SEPTEMBER 12, 2019

SQL provides a declarative programming interface, below which the system itself can figure out the most effective execution plans based on data size and statistics, layout, compute hardware etc. Declarative recursive computation on an RDBMS… or, why you should use a database for distributed machine learing Jankov et al., VLDB’19.

Network 44

Network Database Programming Hardware 44

ACM Sigarch

NOVEMBER 1, 2019

This blog post gives a glimpse of the computer systems research papers presented at the USENIX Annual Technical Conference (ATC) 2019, with an emphasis on systems that use new hardware architectures. GAIA proposed to expand the OS page cache into accelerator memory. ATC ’19 was refreshingly different. Heterogeneous ISA.

Architecture 12

Architecture Hardware Cache Storage 12

Smashing Magazine

JANUARY 11, 2021

Build Optimizations JavaScript modules, module/nomodule pattern, tree-shaking, code-splitting, scope-hoisting, Webpack, differential serving, web worker, WebAssembly, JavaScript bundles, React, SPA, partial hydration, import on interaction, 3rd-parties, cache. This improves page load time and caching during navigations.

Performance 145

Performance Cache Media Metrics 145

Smashing Magazine

JANUARY 6, 2020

On the other hand, we have hardware constraints on memory and CPU due to JavaScript parsing times (we’ll talk about them in detail later). Gatsby (React), Vuepress (Vue) Preact CLI , and PWA Starter Kit provide reasonable defaults for fast loading out of the box on average mobile hardware. ??Also,

Performance 145

Performance Cache Network Metrics 145

Smashing Magazine

JANUARY 7, 2019

On the other hand, we have hardware constraints on memory and CPU due to JavaScript parsing times (we’ll talk about them in detail later). Gatsby.js (React), Preact CLI , and PWA Starter Kit provide reasonable defaults for fast loading out of the box on average mobile hardware. Image credit: Addy Osmani ) ( Large preview ).

Performance 104

Performance Cache Network Metrics 104

High Scalability

NOVEMBER 25, 2019

Our only option was to roll up our sleeves and build basic cloud file system components such as object store ourselves. To add elasticity, reliability and durability, these data centers are connected to Google Cloud platform using high speed, secure Google Interconnect network. Edge caching. Migration to cloud.

Architecture 52

Architecture Cache Azure Storage 52