Uber Engineering

OCTOBER 16, 2019

Michelangelo , Uber’s machine learning (ML) platform, supports the training and serving of thousands of models in production across the company. Designed to cover the end-to-end ML workflow, the system currently supports classical machine learning, time series forecasting, and deep … The post Evolving Michelangelo Model Representation for Flexibility at Scale appeared first on Uber Engineering Blog.

Engineering 111

Engineering Design Systems Architecture 111

ScaleOut Software

OCTOBER 16, 2019

Digital twins are typically used in the field of product life-cycle management (PLM) to model the behavior of individual devices or components within a system. This assists in their design and development and helps lower costs. A digital twin model of a device simulates both the device’s behavior and its interactions with other components in the system.

Analytics 40

Analytics Cloud Design Systems 40

Dynatrace

OCTOBER 17, 2019

Dynatrace news. We’re no longer living in an age where large companies require only physical servers, with similar and rarely changing configurations, that could be manually maintained in a single Datacenter. We’re currently in a technological era where we have a large variety of computing endpoints at our disposal like containers, Platform as a Service (PaaS), serverless, virtual machines, APIs, etc. with more being added continually.

Code 112

Code Infrastructure DevOps Serverless 112

Scalegrid

OCTOBER 17, 2019

A long time ago, in a galaxy far far away, ‘threads’ were a programming novelty rarely used and seldom trusted. In that environment, the first PostgreSQL developers decided forking a process for each connection to the database is the safest choice. It would be a shame if your database crashed, after all. Since then, a lot of water has flown under that bridge, but the PostgreSQL community has stuck by their original decision.

Architecture 200

Architecture Database Latency Servers 200

The Netflix TechBlog

OCTOBER 16, 2019

By Ammar Khaku Introduction In a microservice architecture such as Netflix’s, propagating datasets from a single source to multiple downstream destinations can be challenging. These datasets can represent anything from service configuration to the results of a batch job, are often needed in-memory to optimize access and must be updated as they change over time.

Cache 190

Cache Architecture Metrics Java 190

DZone

OCTOBER 18, 2019

[link]. I’m a Unix guy. Note that I did not say Linux. When I started my career, many small to mid-sized companies were running on minicomputers from companies such as IBM, Digital Equipment Corporation (DEC), PR1ME Computer, and others. Dr. Who fans might get a chuckle out of this blast from the past.

Development 166

Development Software Software Performance 166

Dynatrace

OCTOBER 14, 2019

Dynatrace news. You might already use Dynatrace Log Monitoring to gain direct access to the log content of your system’s mission-critical processes. Log Monitoring is a great way to search for text patterns like log files with errors or exceptions. But sometimes you might have a scenario where simple access to log file content is not enough—you need to create a metric for log entries that contain “Error,” for instance, or something more complex like “Error and not Warning.

Metrics 119

Metrics Monitoring AWS Availability 119

The Netflix TechBlog

OCTOBER 18, 2019

Faisal Siddiqi Infrastructure for Contextual Bandits and Reinforcement Learning?—? theme of the ML Platform meetup hosted at Netflix, Los Gatos on Sep 12, 2019. Contextual and Multi-armed Bandits enable faster and adaptive alternatives to traditional A/B Testing. They enable rapid learning and better decision-making for product rollouts. Broadly speaking, these approaches can be seen as a stepping stone to full-on Reinforcement Learning (RL) with closed-loop, on-policy evaluation and model objec

Infrastructure 129

Infrastructure Metrics Architecture Efficiency 129

DZone

OCTOBER 14, 2019

Faster loading? Sign me up! If you implement testing your landing page you will get to know that you are wasting your money by just throwing them inside pits. The reason behind this is that your pages are simply not loading as expected as fast enough. Not only you are losing your cost of click but also the potential customers who would always remain a stranger to you.

Website 114

Website Testing Cache Speed 114

Dynatrace

OCTOBER 17, 2019

Dynatrace news. Cloud Foundry BOSH is a powerful tool that combines release engineering, deployment, and life cycle management of distributed software in the cloud. While BOSH is platform agnostic, it’s the standard vehicle for rolling out and managing Cloud Foundry on virtualized infrastructure, across cloud providers. BOSH loves YAML (so it’s in good company with Kubernetes) and follows a declarative approach for defining the desired state of Cloud Foundry’s various components as w

Cloud 104

Cloud Virtualization Internet Internet 104

Uber Engineering

OCTOBER 16, 2019

Michelangelo , Uber’s machine learning (ML) platform, supports the training and serving of thousands of models in production across the company. Designed to cover the end-to-end ML workflow, the system currently supports classical machine learning, time series forecasting, and deep … The post Evolving Michelangelo Model Representation for Flexibility at Scale appeared first on Uber Engineering Blog.

Engineering 90

Engineering Design Systems Architecture 90

The Netflix TechBlog

OCTOBER 18, 2019

Faisal Siddiqi Infrastructure for Contextual Bandits and Reinforcement Learning?—? theme of the ML Platform meetup hosted at Netflix, Los Gatos on Sep 12, 2019. Contextual and Multi-armed Bandits enable faster and adaptive alternatives to traditional A/B Testing. They enable rapid learning and better decision-making for product rollouts. Broadly speaking, these approaches can be seen as a stepping stone to full-on Reinforcement Learning (RL) with closed-loop, on-policy evaluation and model objec

Infrastructure 100

Infrastructure Metrics Architecture Efficiency 100

DZone

OCTOBER 15, 2019

Marvel at this article! You may also like: The Observability Pipeline. “[You’ve] been fighting with one arm behind your back. What happens when [you’re] finally set free?” — Paraphrasing Carol Danvers, a.k.a. Captain Marvel. BOOK REVIEW: '' How to Architect and Build Highly Observable Systems'' by Baron Schwartz. Observability is a property of an application or system, not the actual act of analysis.

Monitoring 107

Monitoring Systems Code Processing 107

The Morning Paper

OCTOBER 14, 2019

Invisible mask: practical attacks on face recognition with infrared Zhou et al., arXiv’18. You might have seen selected write-ups from The Morning Paper appearing in ACM Queue. The editorial board there are also kind enough to send me paper recommendations when they come across something that sparks their interest. So this week things are going to get a little bit circular as we’ll be looking at three papers originally highlighted to me by the ACM Queue board!

Tuning 85

Tuning Systems Google Testing 85

Brendan Gregg

OCTOBER 15, 2019

If you start digging into Linux kernel internals, like function disassembly and profiling, you may run into two mysteries of kernel engineering, as I did: 1. What is this "__fentry__" stuff at the start of _every_ kernel function? Profiling? Why doesn't it massively slow down the Linux kernel? 2. How can Ftrace instrument _all_ kernel functions almost instantly, and with low overhead?

C++ 76

C++ Engineering Technology Technology 76

HammerDB

OCTOBER 18, 2019

HammerDB doesn’t publish competitive database benchmarks, instead we always encourage people to be better informed by running their own. Nevertheless in this blog sometimes we do publish performance data to highlight best practices or potential configuration pitfalls and although we’ve mentioned this one before it is worth dedicating an entire post to it as this issue seems to appear numerous times running database workloads on Linux.

Benchmarking 63

Benchmarking Performance Hardware C++ 63

DZone

OCTOBER 18, 2019

Prompts to banish writer's block. Trying to write an article but have nothing to write about? You're in the right place! This is the solution to all your writer's block needs! No more excuses, just solutions. Below, you will find a couple of prompts to get you started in writing for our Performance zone! Find these helpful? Have ideas for future prompts?

Performance 100

Performance Performance Testing Engineering Testing 100

Edge Perspectives

OCTOBER 17, 2019

Three years ago I sketched out three dimensions of business model evolution in response to the mounting performance pressure of the Big Shift. In this blog post, I want to highlight the role of this business model evolution in restoring trust in our corporations. A growing number of surveys around the world highlight the continuing erosion of trust in all our institutions.

Efficiency 57

Efficiency Technology Technology Scalability 57

Brendan Gregg

OCTOBER 14, 2019

If you start digging into Linux kernel internals, like function disassembly and profiling, you may run into two mysteries of kernel engineering, as I did: 1. What is this "__fentry__" stuff at the start of _every_ kernel function? Profiling? Why doesn't it massively slow down the Linux kernel? 2. How can Ftrace instrument _all_ kernel functions almost instantly, and with low overhead?

C++ 52

C++ Engineering Technology Technology 52

Tasktop

OCTOBER 18, 2019

If you who haven’t read Project to Product yet or any of my previous posts on the four key flow items from the Flow Framework , let me give you a bit of background. There are four flow items that provide value to the end-user of your software product: features (new business value), defects (quality), technical debt (removal of impediments to future delivery) and risk (security, governance, compliance). .

Software 56

Software Software DevOps Metrics 56

DZone

OCTOBER 17, 2019

She is monitoring Prow resources very closely. At Loodse we’re making extensive use of Prow , Kubernetes’ own CI/CD framework , for our public and private projects. Prow is responsible for managing source code builds which are usually triggered by creating Pull Requests (PRs) on our GitHub repositories or sometimes periodically for nightly cleanup jobs.

Monitoring 100

Monitoring Code Performance 100

The Morning Paper

OCTOBER 15, 2019

“I was told to buy a software or lose my computer. I ignored it”: a study of ransomware Simoiu et al., SOUPS 2019. This is a very easy to digest paper shedding light on the prevalence of ransomware and the characteristics of those most likely to be vulnerable to it. The data comes from a survey of 1,180 US adults conducted by YouGov, an online global market research firm.

Software 52

Software Software Strategy Design 52

MachMetrics

OCTOBER 16, 2019

Elon Musk’s need for speed. As the media coverage of the project ramps up, you may have heard of Starlink – SpaceX’s new satellite constellation project. The ultimate goal of this venture is to deploy nearly 12,000 satellites into very low orbit, creating a “blanket” of coverage spanning the globe. A lot of coverage on this project is centered (rightfully) around the potential of this project to deliver fast internet to underdeveloped nations at a minimal cost.

Internet 44

Internet Internet Latency Speed 44

KeyCDN

OCTOBER 17, 2019

The major application for high quality compression of photos is Internet speed. While bandwidth does continue to increase each year, so does the quality and size of most Internet media. What that means is that even though data can be transferred more quickly, the need for compressing media into smaller files without losing visual quality has not gone away.

Media 43

Media Internet Internet Speed 43

DZone

OCTOBER 16, 2019

Quality over quantity. Poor-quality software has huge and growing economic consequences for organizations in the United States. But what are the actual monetary costs — and how can your technology company mitigate them?

Software 100

Software Software Technology Technology 100

The Morning Paper

OCTOBER 17, 2019

HackPPL: a universal probabilistic programming language Ai et al., MAPL’19. The Hack programming language, as the authors proudly tell us, is “ a dominant web development language across large technology firms with over 100 million lines of production code.” Nail that niche! Does your market get any smaller if we also require those firms to have names starting with ‘F’ ?

Programming 50

Programming Social Media Media Open Source 50

CSS - Tricks

OCTOBER 15, 2019

At a recent conference talk (sorry, I forget which one), there was a quick example of poor web performance in the form of a third-party widget. The example showed a site that installed the widget in order add a "email us" button fixed to the bottom right of the viewport. Not even a live-chat widget — just an email thing. It weighed in at something like 470KB, which is straight bananas.

Performance 42

Performance 42

Testsigma

OCTOBER 14, 2019

In its initial days, Software Testing was completely manual. The repetitive nature of testing mundane tasks and the time required to test led to the wide adoption of automated testing. With Automation, testers could automate their repetitive tasks and focus on other testing tasks like choosing the right test cases for a test run and testing new features.

Testing 42

Testing Testing Tools Programming Website 42

DZone

OCTOBER 15, 2019

We've got to keep track of these bugs! Identifying bugs is one of the crucial phases in the software development lifecycle. Tracking the bug ensures quality assurance of software as well as eliminates the risk of post-release glitches. Addressing any software or an app plagued with bugs is the worst nightmare of the testers. Sometimes, the issues or discrepancies are so inconsequential that even the testers fail to track them.

Testing 100

Testing Software Software Development 100

Apica

OCTOBER 18, 2019

The two buzz words this year have been the “Connected Car” and “IoT Device.” The automotive industry has taken the lead in ensuring both are integrated into their innovations and even the services they offer. Automotive manufacturers are moving to not only deliver the most innovative autonomous cars, but also the ability to connect to any device or service from these vehicles.

IoT 40

IoT Automotive Monitoring Innovation 40

Tim Kadlec

OCTOBER 18, 2019

Netlify hosted their JAMStack Conf in San Francisco this past Wednesday. Quibbles with the JAMStack name aside, there were some great talks in the schedule and they’ve started to fill up my watch later list. One thing that Netlify announced during the event was their new build plugins functionality. Netlify’s build process now exposes different events during the build and deploy lifecycle that you can use as hooks to attach certain functionality to.

Testing 40

Testing Processing Code Availability 40

Dotcom-Montior

OCTOBER 17, 2019

Network Throttling. When it comes to monitoring web application performance, not only is it necessary emulate user actions, but also network conditions of end-user devices. Network throttling allows you to control connection speeds to better match the experience of real users, allowing you to see web application behavior in specific network conditions.

Network 40

Network Monitoring Latency Website 40

DZone

OCTOBER 14, 2019

We'll help you improve performance! You may also like: 7 Simple Ways to Improve Website and Database Performance. Overview. I've been investigating US federal lobbying using Open Data published by the US government. I developed a program that loads the lobbying filing data into Neo4J , but severe performance problems reduced how much data could be loaded; the time required increased as filings were persisted to the point that one calendar year quarter could take over six hours.

Performance 100

Performance Government Programming Website 100

Apica

OCTOBER 18, 2019

The two buzz words this year have been the “Connected Car” and “IoT Device.” The automotive industry has taken the lead in ensuring both are integrated into their innovations and even the services they offer. Automotive manufacturers are moving to not only deliver the most innovative autonomous cars, but also the ability to connect to […].

IoT 40

IoT Automotive Monitoring Innovation 40

SQL Server According to Bob

OCTOBER 17, 2019

When executing a query to enumerate the locks, such as select * from sys.dm_tran_locks, how does SQL Server scan the locks and avoid impacting the overall concurrency? I recently posted on aspects of the SQL Server Lock Manager and found the iteration of the locks interesting as I was stepping in the code. [link] [link]. SQL Server has a lock iterator class which is used by Lock Monitor (deadlock detection), DMVs such as dm_tran_locks and other workers.

Servers 40

Servers Software Engineering Database Monitoring 40

SQL Performance

OCTOBER 17, 2019

My colleague, Erin Stellato, recently asked me a question about where and why event loss could happen with Extended Events. The question was the result of a comment someone had made on one of her blog posts that was claiming that showplan_xml events can not be collected by the XE Profiler or through a "live" stream of the events from the server. I happen to know that this is not correct because I have routinely demonstrated the negative performance impacts of using the post_query_execution_showp

Servers 40

Servers Systems Performance Availability 40

DZone

OCTOBER 16, 2019

Efficiency is everything! This part of the series will show how to verify our applications with code-level as well as system-level integration tests.

Efficiency 100

Efficiency Testing Systems Code 100