Brendan Gregg

JULY 4, 2021

AWS Graviton2); for memory with the arrival of DDR5 and High Bandwidth Memory (HBM) on-processor; for storage including new uses for 3D Xpoint as a 3D NAND accelerator; for networking with the rise of QUIC and eXpress Data Path (XDP); and so on. Ford, et al., “TCP

Performance 52

Performance Latency Hardware Storage 52

Dotcom-Montior

NOVEMBER 11, 2020

Well, to start, serverless, or serverless computing , doesn’t really mean there aren’t servers involved, because there are, rather it refers to the fact that the responsibility of having to manage, scale, provision, maintain, etc., Applications that are running continuously on a dedicated server aren’t as impacted by latency issues.

Serverless 57

Serverless Monitoring Lambda Latency 57

Brendan Gregg

FEBRUARY 28, 2023

My personal opinion is that I don't see a widespread need for more capacity given horizontal scaling and servers that can already exceed 1 Tbyte of DRAM; bandwidth is also helpful, but I'd be concerned about the increased latency for adding a hop to more memory. Ford, et al., “TCP

Performance 52

Performance Latency Cache Virtualization 52

cdemi

FEBRUARY 20, 2017

Let's talk about the elephant in the room; Serverless doesn't really mean that there are no Software or Hardware servers. It just means that from Software Development perspective, servers are abstracted and outsourced to another entity, so you don't need to worry about it. Amazon: AWS Lambda. Advantages. IBM: OpenWhisk.

Serverless 64

Serverless Architecture Lambda Azure 64

VoltDB

JUNE 29, 2017

Most existing adtech infrastructure simply can not achieve the required latency. VoltDB provides the necessary technology to achieve the latency required by header bidding. The simple answer is to just spin up more servers. More servers means more capacity. Spinning up more servers just won’t cut it.

Performance 40

Performance Hardware Latency Infrastructure 40

VoltDB

JUNE 29, 2017

Most existing adtech infrastructure simply can not achieve the required latency. VoltDB provides the necessary technology to achieve the latency required by header bidding. The simple answer is to just spin up more servers. More servers means more capacity. Spinning up more servers just won’t cut it.

Performance 40

Performance Hardware Latency Infrastructure 40

All Things Distributed

JULY 13, 2010

In particular this has been true for applications based on algorithms - often MPI-based - that depend on frequent low-latency communication and/or require significant cross sectional bandwidth. There is no more need for hardware tinkering to keep the clusters up and running (I spent many nights doing this; there is no glory in it).

Cloud 118

Cloud AWS Automotive Latency 118

Dynatrace

SEPTEMBER 29, 2020

At Dynatrace we host most of our Dynatrace SaaS clusters for paying customers as well as trial users in the Amazon Web Services (AWS) cloud. Since we moved to AWS in May 2014 we have had an availability of 99.95%! Sydney, we have a disk write latency problem!

Infrastructure 180

Infrastructure Cloud Monitoring AWS 180

Dynatrace

JANUARY 26, 2021

This allows teams to sidestep much of the cost and time associated with managing hardware, platforms, and operating systems on-premises, while also gaining the flexibility to scale rapidly and efficiently. AWS Lambda functions are an example of how a serverless framework works: Developers write a function in a supported language or platform.

Serverless 244

Serverless Efficiency Lambda Azure 244

All Things Distributed

APRIL 4, 2017

Today, I am very excited to announce our plans to open a new AWS Region in the Nordics! The new region will give Nordic-based businesses, government organisations, non-profits, and global companies with customers in the Nordics, the ability to leverage the AWS technology infrastructure from data centers in Sweden.

AWS 116

AWS Airlines Latency Games 116

Percona

JULY 1, 2023

Now that Database-as-a-service (DBaaS) is in high demand, there are multiple questions regarding AWS services that cannot always be answered easily: When should I use Aurora and when should I use RDS MySQL ? Amazon Aurora is a proprietary, cloud-native, fully managed relational database service developed by Amazon Web Services (AWS).

AWS 52

AWS Database Serverless Storage 52

Brendan Gregg

SEPTEMBER 25, 2021

A Cassandra database cluster had switched to Ubuntu and noticed write latency increased by over 30%. This server is spending about a third of its CPU cycles just checking the time! As a Xen guest, this profile was gathered using perf(1) and the kernel's software cpu-clock soft interrupts, not the hardware NMI.

Speed 126

Speed Java AWS Virtualization 126

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., The paper examines the implications of microservices at the hardware, OS and networking stack, cluster management, and application framework levels, as well as the impact of tail latency.

Open Source 61

Open Source Hardware Benchmarking Systems 61

All Things Distributed

MARCH 11, 2016

The epoch of AWS is the launch of Amazon S3 on March 14, 2006, now almost 10 years ago. Given that AWS is a pioneer in building and operating these services world-wide, these lessons have been of crucial importance to our business. This is a given, whether you are using the highest quality hardware or lowest cost components.

AWS 144

AWS Hardware Retail Virtualization 144

Brendan Gregg

SEPTEMBER 25, 2021

A Cassandra database cluster had switched to Ubuntu and noticed write latency increased by over 30%. This server is spending about a third of its CPU cycles just checking the time! As a Xen guest, this profile was gathered using perf(1) and the kernel's software cpu-clock soft interrupts, not the hardware NMI.

Speed 52

Speed Java AWS Virtualization 52

The Netflix TechBlog

FEBRUARY 9, 2021

Server-generated assets, since client-side generation would require the retrieval of many individual images, which would increase latency and time-to-render. To reduce latency, assets should be generated in an offline fashion and not in real time. We can leverage high performance VMs in AWS to generate the assets.

Engineering 165

Engineering Storage Latency Entertainment 165

Brendan Gregg

SEPTEMBER 25, 2021

A Cassandra database cluster had switched to Ubuntu and noticed write latency increased by over 30%. This server is spending about a third of its CPU cycles just checking the time! As a Xen guest, this profile was gathered using perf(1) and the kernel's software cpu-clock soft interrupts, not the hardware NMI.

Speed 40

Speed Java AWS Virtualization 40

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. For Physalia, and for AWS more generally, the guiding principle is minimise the blast radius. NSDI’20.

Database 106

Database AWS Network Design 106

All Things Distributed

JANUARY 18, 2012

Behind the scenes, Amazon DynamoDB automatically spreads the data and traffic for a table over a sufficient number of servers to meet the request capacity specified by the customer. Amazon DynamoDB offers low, predictable latencies at any scale. s read latency, particularly as dataset sizes grow. History of NoSQL at Amazon â??

Scalability 167

Scalability Database Ecommerce Latency 167

Percona

APRIL 17, 2023

It is common to see a value of “ 0″ ( or sometimes “10” ) on database servers, telling the kernel to prefer to swap to memory for better response times. The CFQ works well for many general use cases but lacks latency guarantees. A setting of 100 determines it to swap aggressively to disk.

Best Practices 52

Best Practices Design Tuning Database 52

All Things Distributed

NOVEMBER 15, 2010

For example, the most fundamental abstraction trade-off has always been latency versus throughput. Modern CPUs strongly favor lower latency of operations with clock cycles in the nanoseconds and we have built general purpose software architectures that can exploit these low latencies very well. General Purpose GPU programming.

AWS 136

AWS Latency Programming Architecture 136

Brendan Gregg

SEPTEMBER 5, 2017

Here's some output from my zfsdist tool, in bcc/BPF, which measures ZFS latency as a histogram on Linux: # zfsdist. Tracing ZFS operation latency. Oracle VM Server is based on Xen. Many new tools can now be written, and the main toolkit we're working on is [bcc]. Hit Ctrl-C to end. ^C amazon").

Virtualization 76

Virtualization AWS Engineering Hardware 76

Dynatrace

AUGUST 5, 2019

In this role, I am leading a global team that works closely with our strategic partners such as AWS, Microsoft, Google, Pivotal, Red Hat and others. Lift & Shift is where you basically just move physical or virtual hosts to the cloud – essentially you just run your host on somebody else’s hardware.

Cloud 31

Cloud Traffic Database Network 31

Percona

NOVEMBER 3, 2023

PostgreSQL Cluster One coordinator node citus-coord-01 Three worker nodes citus1 citus2 citus3 Hardware AWS Instance Ubuntu Server 20.04, SSD volume type 64-bit (x86) c5.xlarge Steps Provisioning The first step is to provision the four nodes with both PostgreSQL and Citus. psql pgbench <<_eof1_ qecho adding node citus3.

Database 104

Database Benchmarking Latency C++ 104

Smashing Magazine

JANUARY 11, 2021

In the end, it’s not the load events or server response times that define the experience, but the perception of how snappy the interface feels. It used to provide an insight into how quickly the server outputs any data. This knowledge will give you the best optimization target for ongoing efforts. What does it mean?

Performance 145

Performance Cache Media Metrics 145

Smashing Magazine

JANUARY 6, 2020

Is it worth exploring tree-shaking, scope hoisting, code-splitting, and all the fancy loading patterns with intersection observer, server push, clients hints, HTTP/2, service workers and — oh my — edge workers? It used to provide an insight into how quickly the server outputs any data. What does it mean?

Performance 145

Performance Cache Network Metrics 145

Smashing Magazine

JANUARY 7, 2019

Is it worth exploring tree-shaking, scope hoisting, code-splitting, and all the fancy loading patterns with intersection observer, server push, clients hints, HTTP/2, service workers and — oh my — edge workers? Long FMP usually indicates JavaScript blocking the main thread, but could be related to back-end/server issues as well.

Performance 104

Performance Cache Network Metrics 104