The Netflix TechBlog

AUGUST 29, 2023

A brief history of IPC at Netflix Netflix was early to the cloud, particularly for large-scale companies: we began the migration in 2008, and by 2010, Netflix streaming was fully run on AWS. To improve availability, we designed systems where components could fail separately and avoid single points of failure.

Traffic 231

Traffic Latency Cloud C++ 231

DZone

AUGUST 21, 2019

CMake is a cross-platform system for automating project builds. This system is much older than the PVS-Studio static code analyzer, but no one has tried to apply the analyzer on its code and review the errors. CMake is a cross-platform system for automating software building from source code. The CMake audience is huge.

Programming 100

Programming Code Systems Software 100

Dynatrace

NOVEMBER 10, 2020

Current Operating systems support changes. The following operating systems will no longer be supported starting 01 December 2020. Upcoming Operating systems support changes. The following operating systems will no longer be supported starting 01 January 2021. Windows: Windows Server 2008. Node.js 13.

Operating System 105

Operating System Java Google Servers 105

Dynatrace

OCTOBER 14, 2020

Upcoming Operating systems support changes. The following operating systems will no longer be supported starting 01 December 2020. The following operating systems will no longer be supported starting 01 January 2021. Windows: Windows Server 2008. Added support for Oracle Hotspot JVM 15 for Solaris (SPARC).

Operating System 100

Operating System Java Google Servers 100

All Things Distributed

MARCH 10, 2017

Blockchain technology first came on the scene in 2008, as a core component of the bitcoin cryptocurrency. Blockchain's robust, decentralized functionality is very attractive for global financial systems, but can easily be applied to contracts, or operations such as global supply chain tracking.

Blockchain 103

Blockchain Media Internet Internet 103

Dynatrace

JULY 31, 2020

Current Operating systems support changes. The following operating systems will no longer be supported starting 01 August 2020. Windows: Windows Server 2008. Upcoming Operating systems support changes. The following operating systems will no longer be supported starting 01 November 2020. OpenJDK 12. ONE-38026).

Operating System 124

Operating System Java Infrastructure Monitoring 124

Dynatrace

FEBRUARY 10, 2021

set-system-logs-access-enabled. Upcoming Operating systems support changes. The following operating systems will no longer be supported starting 01 April 2020. The following operating systems will no longer be supported starting 01 May 2020. The following operating systems will no longer be supported starting 01 May 2020.

Operating System 100

Operating System Servers Google Systems 100

Brendan Gregg

JULY 4, 2021

I also wrote about these topics in detail for my recent [Systems Performance 2nd Edition] book. 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

Performance 121

Performance Latency Hardware Storage 121

The Morning Paper

NOVEMBER 5, 2019

File systems unfit as distributed storage backends: lessons from 10 years of Ceph evolution Aghayev et al., In this case, the assumption that a distributed storage backend should clearly be layered on top of a local file system. A distributed file system provides a unified view over aggregated storage from multiple physical machines.

Storage 64

Storage Systems Hardware Efficiency 64

High Scalability

APRIL 3, 2019

PostgreSQL is an open source object-relational database system that has soared in popularity over the past 30 years from its active, loyal, and growing community. For the 2nd year in a row, PostgreSQL has kept the title of #1 fastest growing database in the world according to the DBMS of the Year report by the experts at DB-Engines.

Database 177

Database Cloud Open Source Systems 177

All Things Distributed

AUGUST 24, 2012

Werner Vogels weblog on building scalable and robust distributed systems. Goetz Graefe, ACM Queue 6(4): 40-52 (2008). All Things Distributed. Back-to-Basics Weekend Reading - The 5 Minute Rule. By Werner Vogels on 24 August 2012 04:00 PM. Comments (). per GB/month. blog comments powered by Disqus. Contact Info. Werner Vogels.

Storage 87

Storage Hardware AWS Data Engineering 87

Adrian Cockcroft

OCTOBER 23, 2024

Fujitsu used SPARC for everything from servers to embedded systems like cameras for a long time. Another reason is that most of the SPARC ecosystem was built around Solaris, rather than Linux, and the failure of Sun to survive and the replacement of Solaris by Linux based systems vendors took SPARC down with it.

Architecture 96

Architecture Mobile Design Government 96

Smashing Magazine

AUGUST 20, 2021

During the 90s, we saw two content management systems for static sites — Microsoft FrontPage in 1996 and Macromedia Dreamweaver in 1997. These desktop applications incremented the tooling an inch closer to the modern Jamstack content management systems of today. Drupal has a rich and extendable permission system.

Ecommerce 140

Ecommerce Website Government Internet 140

Percona

APRIL 14, 2023

During the recession of 2008, they experienced firsthand how fast money and assets can vanish. Here are a few ways you can scale down and save: Audit your systems: Auditing your system for unused servers and eliminating those servers can reduce your cloud spend. If needed, you can spin up a backup.

Database 86

Database Serverless Tuning Cloud 86

All Things Distributed

MAY 8, 2012

Werner Vogels weblog on building scalable and robust distributed systems. Amazon RDS currently supports SQL Server 2008 R2 and plans to add support for SQL Server 2012 later this year. All Things Distributed. Expanding the Cloud for Windows Developers. By Werner Vogels on 08 May 2012 02:00 PM. Comments ().

Cloud 94

Cloud Development AWS Servers 94

All Things Distributed

MARCH 26, 2018

March 26, 2008 doesn't have any delicious desserts associated with it, but that's the day when we launched Availability Zones for Amazon EC2. Zones impact how we build, deploy, and operate software, as well as how we enforce security controls between our largest systems. The Amazon S3 team still celebrate with homemade pies!

AWS 113

AWS Latency Lambda Architecture 113

All Things Distributed

APRIL 5, 2012

Werner Vogels weblog on building scalable and robust distributed systems. Jack: Since our launch in late 2008, weve grown to over 6 million teachers and students globally primarily through word of mouth of teachers who have shared Edmodo with each other. All Things Distributed. By Werner Vogels on 06 April 2012 06:00 AM. Comments ().

Innovation 116

Innovation AWS Education Network 116

Brendan Gregg

FEBRUARY 28, 2023

This talk originated from my updates to [Systems Performance 2nd Edition], and this was the first time I've given this talk in person! CXL in a way allows a custom memory controller to be added to a system, to increase memory capacity, bandwidth, and overall performance. Ford, et al., “TCP

Performance 103

Performance Latency Cache Virtualization 103

Highly Scalable

MARCH 10, 2015

Most of this article represents an overview of the results published by retailers and researchers who built practical decision making and optimization systems combining abstract economic models with data mining methods. The most typical use cases for this problem are recommender systems, personalized search results ranking, and targeted ads.

Retail 152

Retail C++ Analytics Metrics 152

All Things Distributed

MARCH 24, 2011

Werner Vogels weblog on building scalable and robust distributed systems. The images from the 2008 TNW Conference have travelled around the world in my Animoto demo: This year TNW is showing that it is not just a conference for talkers but also for builders by organizing a massive Hackaton in the two days running up to the conference.

AWS 75

AWS Internet Internet Storage 75

Sutter's Mill

SEPTEMBER 24, 2010

6 Use Lock Hierarchies to Avoid Deadlock (Jan 2008). Feb 2008). 8 Going Superlinear (Mar 2008). 9 Super Linearity and the Bigger Machine (Apr 2008). 10 Interrupt Politely (May 2008). 11 Maximize Locality, Minimize Contention (Jun 2008). 12 Choose Concurrency-Friendly Data Structures (Jul 2008).

Programming 40

Programming Website Scalability Design 40

Sutter's Mill

AUGUST 27, 2010

6 Use Lock Hierarchies to Avoid Deadlock (Jan 2008). Feb 2008). 8 Going Superlinear (Mar 2008). 9 Super Linearity and the Bigger Machine (Apr 2008). 10 Interrupt Politely (May 2008). 11 Maximize Locality, Minimize Contention (Jun 2008). 12 Choose Concurrency-Friendly Data Structures (Jul 2008).

Website 40

Website Scalability Code Design 40

Sutter's Mill

JULY 12, 2010

6 Use Lock Hierarchies to Avoid Deadlock (Jan 2008). Feb 2008). 8 Going Superlinear (Mar 2008). 9 Super Linearity and the Bigger Machine (Apr 2008). 10 Interrupt Politely (May 2008). 11 Maximize Locality, Minimize Contention (Jun 2008). 12 Choose Concurrency-Friendly Data Structures (Jul 2008).

C++ 40

C++ Java Programming Website 40

All Things Distributed

DECEMBER 22, 2012

Werner Vogels weblog on building scalable and robust distributed systems. 2008: Hercules and Love Affair, Hercules and Love Affair. All Things Distributed. An Album for Each Year - 2012 Version. By Werner Vogels on 22 December 2012 06:00 PM. Comments (). 1958: Jerry Lee Lewis, Great Balls of Fire. 1959: Ray Charles, What Id Say.

Traffic 72

Traffic Scalability Systems 72

The Agile Manager

AUGUST 31, 2024

And yes, there were a few setbacks (banks pulled back in the wake of the 2008 financial crisis), but in macro terms the setbacks were short lived. The decision is simply whether to cut (based on sales forecasts) and when to cut (systemically or opportunistically to boost FCF for the coming quarter). Then the music stopped, abruptly.

Open Source 96

Open Source Engineering Performance Innovation 96

O'Reilly

SEPTEMBER 19, 2023

” Consider the structural evolutions of that theme: Stage 1: Hadoop and Big Data By 2008, many companies found themselves at the intersection of “a steep increase in online activity” and “a sharp decline in costs for storage and computing.” This technique simulates interactions in a complex system.

Hardware 101

Hardware Storage Big Data Blockchain 101

All Things Distributed

APRIL 19, 2010

Werner Vogels weblog on building scalable and robust distributed systems. Here are the laurels given by the editors: Debuting in November 2008, Amazons entry into the CDN market quickly became a major player. All Things Distributed. Amazon Cloudfront is Streaming Media 2010 Editors pick. By Werner Vogels on 19 April 2010 03:02 AM.

Media 60

Media AWS Storage Big Data 60

Tasktop

APRIL 2, 2020

After the collapses of 2000 and 2008, governments acted narrowly to save finance, allowing the installation mode and investment mentality to return. Calamity lies ahead for companies that still do not know how to measure and optimize the flow of value in a systemic and scalable way.

Government 109

Government Innovation Strategy Technology 109

O'Reilly Software

OCTOBER 23, 2018

Technology systems are difficult to wrangle. Our systems grow in accidental complexity and complication over time. The product management team states what must be done to solve the problem, and the architect describes how to realize that vision in a system. To do so, we borrow metaphors from roles in other industries.

Strategy 100

Strategy Architecture Technology Technology 100

PDC

APRIL 14, 2019

For example, PDC’s Beskow system has 11 cabinets, 515 blades, 2,060 compute nodes, and a total of 67,456 cores. This is also commonly known as “double precision” on many computer systems. Some particularly useful information that is available from the Top500 list website highlights the performance development of supercomputer systems.

Energy 40

Energy Benchmarking Efficiency Website 40

SQL Performance

AUGUST 27, 2019

This system has one AMD EPYC 7502P 32-core processor and 512GB of RAM. The price per QphH for this system is 0.34 That is a higher score, but this system used two Intel Xeon Platinum 8180 28-core processors (that had a total of 56C/112T) and 512GB of RAM. The price per QphH for this system is 0.47 In this case, 6,716.88/64

Servers 52

Servers Benchmarking Virtualization Architecture 52

SQL Server According to Bob

JUNE 22, 2016

Keep in mind that the vast majority of CMemThread objects (SQL 2005, 2008, 2008 R2, 2012, 2014, Azure DB and 2016) are not partitioned. Recommendation Unchanged: Prior to SQL Server 2016 enable –T8048 on larger systems. The three types of CMemThread partitioning and associated details are described in my previous post: [link].

Servers 40

Servers Azure Software Engineering Design 40

SQL Performance

MARCH 15, 2021

In my last post , I illustrated one reason you should stop using deprecated system tables like sysprocesses. Since SQL Server 2012 (and, to a much lesser extent, since SQL Server 2008), the most complete and flexible solution for monitoring events on a SQL Server instance has been Extended Events.

Servers 64

Servers Azure Best Practices Monitoring 64

Randon ASCII

FEBRUARY 11, 2018

I immediately saw that CcmExec.exe (part of Microsoft’s System Management Server ) had 508,000 handles open, which is both a lot and also amazingly close to my zombie count. I work on the Windows version of Chrome, and one of my tasks is optimizing its build system, which requires doing a lot of test builds.

Processing 72

Processing Programming Code Systems 72

SQL Performance

MAY 1, 2020

I was a bit perplexed by this issue, since the system was certainly no slouch — plenty of cores, 3TB of memory, and XtremIO storage. If you have instances running older versions like SQL Server 2008 R2 (I found one!), writes/sec average throughput: 46.96

C++ 58

C++ Database Servers Storage 58

SQL Performance

SEPTEMBER 17, 2019

SSRS 2008 brought that component into the reporting service module. Unlike the system database tempdb, ReportServerTempDB is not recreated at startup. You need to be monitoring memory/disk/CPU utilization, network I/O, tempdb usage, waits, and other counters to know what is normal for the overall workload of those systems.

Tuning 67

Tuning Servers Database Best Practices 67

The Agile Manager

APRIL 30, 2013

Revenues plummeted at the end of 2008. This prevented companies from losing employees with systemic knowledge of the business and intimate knowledge of customers. The people who got salary bumps in the boom years from 2006 through 2008 became "high-salary outliers" in 2009. Companies retrenched by laying people off.

Small Business 40

Small Business Efficiency Innovation Systems 40