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 52

Performance Latency Cache Virtualization 52

All Things Distributed

MARCH 5, 2012

Werner Vogels weblog on building scalable and robust distributed systems. By Werner Vogels on 05 March 2012 02:01 PM. AWS today announced a substantial price drop from March 1, 2012 for many of the Amazon EC2, Amazon RDS, and Amazon ElastiCache instances types around the world. All Things Distributed. Comments ().

AWS 110

AWS Innovation Scalability Cache 110

All Things Distributed

SEPTEMBER 25, 2012

Werner Vogels weblog on building scalable and robust distributed systems. By Werner Vogels on 25 September 2012 06:00 PM. Amazon RDS Provisioned IOPS is ideal for mission-critical online transaction processing (OLTP) workloads that require a high performance storage option with consistent IOPS, within a narrow band of tolerance.

Cloud 117

Cloud AWS Storage Database 117

All Things Distributed

APRIL 5, 2012

Werner Vogels weblog on building scalable and robust distributed systems. By Werner Vogels on 06 April 2012 06:00 AM. Troy: We moved our service from internal servers to AWS. Lack of root access to the underlying server OS was unique – but we have found it does not hinder us in anyway. All Things Distributed.

Innovation 146

Innovation AWS Education Network 146

SQL Server According to Bob

JUNE 3, 2016

SQL Server 2016 changes the internal design to (CheckScanner), applying no lock semantics and a design similar to those used with In-Memory Optimized (Hekaton) objects, allowing DBCC operations to scale far better than previous releases. Ryan Stonecipher – Principle SQL Server Software Engineer. SQL Server. set nocount on.

Hardware 40

Hardware Cache Servers Software Engineering 40

All Things Distributed

AUGUST 16, 2012

Werner Vogels weblog on building scalable and robust distributed systems. By Werner Vogels on 16 August 2012 10:00 AM. 3-Year Heavy Utilization Reserved Instances offer the maximum savings over equivalent servers deployed in an on-premises environment. All Things Distributed. Total Cost of Ownership and the Return on Agility.

AWS 118

AWS Hardware Traffic Best Practices 118

Percona

JUNE 6, 2023

This blog was originally published in January 2012 and was updated in June 2023. Full backups are most suitable for critical systems or sensitive data that cannot afford any loss or downtime, allowing for a complete recovery of data in the event of data corruption, hacking, system failures, or natural disasters.

Storage 68

Storage Strategy Network Efficiency 68

Brendan Gregg

NOVEMBER 29, 2017

In this configuration, the AMI and boot is paravirt (PV), the kernel is making hypercalls instead of privileged instructions, and the system is using paravirt network and storage drivers. But not all workloads: some are network bound (proxies) and storage bound (databases). ## 5. The AMI and boot are now HVM.

Virtualization 111

Virtualization AWS Hardware Storage 111

All Things Distributed

OCTOBER 2, 2017

With these requirements in mind, and a willingness to question the status quo, a small group of distributed systems experts came together and designed a horizontally scalable distributed database that would scale out for both reads and writes to meet the long-term needs of our business. This was the genesis of the Amazon Dynamo database.

Internet 128

Internet Internet AWS Performance 128

Brendan Gregg

NOVEMBER 28, 2017

In this configuration, the AMI and boot is paravirt (PV), the kernel is making hypercalls instead of privileged instructions, and the system is using paravirt network and storage drivers. But not all workloads: some are network bound (proxies) and storage bound (databases). ## 5. The AMI and boot are now HVM.

Virtualization 40

Virtualization AWS Hardware Storage 40

All Things Distributed

JANUARY 18, 2012

Werner Vogels weblog on building scalable and robust distributed systems. By Werner Vogels on 18 January 2012 07:00 AM. The original Dynamo design was based on a core set of strong distributed systems principles resulting in an ultra-scalable and highly reliable database system. All Things Distributed. Comments ().

Scalability 167

Scalability Database Ecommerce Latency 167

SQL Performance

APRIL 23, 2019

In SQL Server 2012, grouped (vector) aggregation was able to use parallel batch-mode execution, but only for the partial (per-thread) aggregate. SQL Server 2014 added the ability to perform parallel batch-mode grouped aggregation within a single Hash Match Aggregate operator. Columnstore storage. Introduction.

Servers 67

Servers Testing Metrics Storage 67

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. The cheapest (high volume) Androids perform like 2012/2013 iPhones, respectively. low-end Androids have finally caught up to the iPhone 5 from 2012. The Moto G4 , for example.

Performance 124

Performance Network Cache Metrics 124

O'Reilly

JULY 25, 2023

To provide some coherence to the music, I decided to use Taylor Swift songs since her discography covers the time span of most papers that I typically read: Her main albums were released in 2006, 2008, 2010, 2012, 2014, 2017, 2019, 2020, and 2022. This choice also inspired me to call my project Swift Papers.

Programming 98

Programming Code Design Benchmarking 98

ScaleOut Software

MAY 15, 2014

For example, the IMDG must be able to efficiently create millions of objects in each server to make use of its huge storage capacity. In a recent customer engagement, the application needed to load 10M objects into each server of the IMDG’s cluster to make full use of high-end servers with 60GB memory capacity.

Cache 40

Cache Servers Network Design 40

Percona

JANUARY 14, 2019

In a partitioned massively parallel database system, the storage format and sorting algorithm may not be optimized for that operation as we are reading multiple partitions in parallel. ClickHouse is a great massively parallel analytical system. blockade','arizona'] ? ? protests','occupy','romney','weiner','protesters'] ? ?

Database 40

Database Analytics Blockchain Healthcare 40