Brendan Gregg

JULY 4, 2021

This was a chance to talk about other things I've been working on, such as the present and future of hardware performance. The video is on [youtube]: The slides are on [slideshare] or as a [PDF]: I work on many areas of performance, but recently I've had a lot of demand to talk about BPF. Ford, et al., “TCP

Performance 121

Performance Latency Hardware Storage 121

All Things Distributed

JANUARY 18, 2012

Amazon DynamoDB offers low, predictable latencies at any scale. This is not just predictability of median performance and latency, but also at the end of the distribution (the 99.9th percentile), so we could provide acceptable performance for virtually every customer. s read latency, particularly as dataset sizes grow.

Scalability 164

Scalability Database Ecommerce Latency 164

Dynatrace

AUGUST 5, 2019

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. Remember: This is a critical aspect as you do not want to migrate a service and suddenly introduce high latency or costs to a system that you forgot about having a dependency with!

Cloud 31

Cloud Traffic Database Network 31

All Things Distributed

JANUARY 23, 2012

The Amazon Virtual Private Cloud extends on-premises compute with all the power of AWS, making it elastic, scalable and highly reliable. Data written to these volumes is maintained on your on-premises storage hardware while being asynchronously backed up to AWS, where it is stored in Amazon S3 in the form of Amazon EBS snapshots.

Storage 96

Storage AWS Virtualization Cloud 96

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 103

Performance Latency Cache Virtualization 103

VoltDB

JUNE 19, 2017

Unfortunately, this means that the age-old Telco bugbears will rear their ugly heads again, including latency. 5G, as a fundamental requirement, mandates a 1 millisecond latency from the datasource to its destination. In fact, 5G has plenty of valid use cases, one of which is virtual reality. This requires 1 ms network latency.

Latency 40

Latency Retail Virtualization Hardware 40

VoltDB

JUNE 19, 2017

Unfortunately, this means that the age-old Telco bugbears will rear their ugly heads again, including latency. 5G, as a fundamental requirement, mandates a 1 millisecond latency from the datasource to its destination. In fact, 5G has plenty of valid use cases, one of which is virtual reality. This requires 1 ms network latency.

Latency 40

Latency Retail Virtualization Hardware 40

Brendan Gregg

SEPTEMBER 25, 2021

A Cassandra database cluster had switched to Ubuntu and noticed write latency increased by over 30%. CLI tools The Cassandra systems were EC2 virtual machine (Xen) instances. 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 103

Speed Java AWS Virtualization 103

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. By implementing data replication strategies, distributed storage systems achieve greater.

Storage 130

Storage Systems Big Data Azure 130

VoltDB

JUNE 1, 2017

It was – like the hypothetical movie I describe above – more than a little bit odd, as you could leave a session discussing ever more abstract layers of virtualization and walk into one where they emphasized the critical importance of pinning a network interface to a specific VM for optimal performance.

Hardware 56

Hardware Latency Virtualization Cloud 56

HammerDB

OCTOBER 18, 2019

cpupower frequency-info analyzing CPU 0: driver: intel_pstate CPUs which run at the same hardware frequency: 0 CPUs which need to have their frequency coordinated by software: 0 maximum transition latency: Cannot determine or is not supported. hardware limits: 1000 MHz - 4.00 hardware limits: 1000 MHz - 4.00

Benchmarking 63

Benchmarking Performance Hardware C++ 63

The Morning Paper

DECEMBER 10, 2019

This is a companion paper to the " persistent problem " piece that we looked at earlier this week, going a little deeper into the object pointer representation choices and the mapping of a virtual object space into physical address spaces. Both abstractions must be implemented in a way that is efficient using existing hardware.

Hardware 52

Hardware Virtualization Operating System Programming 52

Brendan Gregg

AUGUST 8, 2017

They are demand on the system, albeit for software resources rather than hardware resources. ## Decomposing Linux load averages Can the Linux load average value be fully decomposed into components? Latency was acceptable and no one complained. Yes, I'd say so. They aren't idle. It spends several minutes mostly blocked on disk reads.

Latency 111

Latency Metrics C++ Systems 111

Dotcom-Montior

NOVEMBER 24, 2021

These systems can include physical servers, containers, virtual machines, or even a device, or node, that connects and communicates with the network. Software and hardware components are autonomous and execute tasks concurrently. This also includes latency, or the time it takes for data or a request to get through a network.

Systems 74

Systems Monitoring Hardware Network 74

SQL Performance

APRIL 27, 2020

Fast forward a few years after Azure SQL Database was released to when Azure SQL Managed Instance was in public preview, and "vCores" (virtual cores) were announced for Azure SQL Database. Gen 5 is the primary hardware option now for most regions since Gen 4 is aging out. New Hardware Configuration for Provisioned Compute Tier.

Azure 55

Azure Database Serverless Hardware 55

ACM Sigarch

MAY 31, 2023

There are three common mechanisms to access remote memory: modifying applications, modifying virtual memory, and hardware-level cache coherence support. even lowered the latency by introducing a multi-headed device that collapses switches and memory controllers. About CXL hardware availability with academia.

Latency 52

Latency Hardware Cache Architecture 52

HammerDB

JULY 6, 2024

In a recent project comparing systems for MariaDB performance, a user had originally been using a tool called sysbench-tpcc to compare hardware platforms before migrating to HammerDB. This is a brief post to highlight the metrics to use to do the comparison using a separate hardware platform for illustration purposes. sum: 23997083.58

C++ 52

C++ Hardware Benchmarking Virtualization 52

Brendan Gregg

AUGUST 18, 2019

For example, iostat(1), or a monitoring agent, may tell you your average disk latency, but not the distribution of this latency. For smaller environments, it can be of more use helping eliminate latency outliers. bpftrace uses BPF (Berkeley Packet Filter), an in-kernel execution engine that processes a virtual instruction set.

Latency 57

Latency C++ Cache Programming 57

Dotcom-Montior

NOVEMBER 11, 2020

Serverless computing can be a huge benefit to organizations that don’t have the necessary resources or teams to manage physical resources, like servers/hardware, and all the maintenance and licensing that goes along with that, allowing them to focus on developing their code and applications. Benefits of a Serverless Model.

Serverless 57

Serverless Monitoring Lambda Latency 57

VoltDB

JUNE 1, 2017

It was – like the hypothetical movie I describe above – more than a little bit odd, as you could leave a session discussing ever more abstract layers of virtualization and walk into one where they emphasized the critical importance of pinning a network interface to a specific VM for optimal performance.

Hardware 40

Hardware Latency Virtualization Cloud 40

Brendan Gregg

JULY 4, 2021

This was a chance to talk about other things I've been working on, such as the present and future of hardware performance. The video is on [youtube]: The slides are [here] or as a [PDF]: first prev next last / permalink/zoom I work on many areas of performance, but recently I've had a lot of demand to talk about BPF. Ford, et al., “TCP

Performance 52

Performance Latency Hardware Storage 52

Dotcom-Montior

DECEMBER 8, 2021

You cannot virtualize everything…yet. Software services still require physical devices and hardware for them to function. Knowing when and where an error, downtime, or application latency occurs is a critical factor in limiting the impact to users and customers. Asset Management.

Social Media 90

Social Media Monitoring Latency DevOps 90

Abhishek Tiwari

JULY 12, 2018

Here are 8 fallacies of data pipeline The pipeline is reliable Topology is stateless Pipeline is infinitely scalable Processing latency is minimum Everything is observable There is no domino effect Pipeline is cost­-effective Data is homogeneous The pipeline is reliable The inconvenient truth is that pipeline is not reliable.

Latency 63

Latency Analytics Scalability Engineering 63

Alex Russell

APRIL 29, 2021

Now in development in WebKit after years of radio silence, WebXR APIs provide Augmented Reality and Virtual Reality input and scene information to web applications. For heavily latency-sensitive use-cases like WebXR, this is a critical component in delivering a good experience. is access to hardware devices. Offscreen Canvas.

Media 145

Media Games Education Engineering 145

VoltDB

APRIL 25, 2024

To move as fast as they can at scale while protecting mission-critical data, more and more organizations are investing in private 5G networks, also known as private cellular networks or just “private 5G” (not to be confused with virtual private networks, which are something totally different). billion in 2022. billion, growing 48.2%

Network 52

Network IoT Wireless Infrastructure 52

The Morning Paper

DECEMBER 8, 2019

Byte-addressable non-volatile memory,) NVM will fundamentally change the way hardware interacts, the way operating systems are designed, and the way applications operate on data. Therefore any programming abstraction must be low latency and the kernel needs to be kept off the path of persistent data access as much as possible.

Hardware 56

Hardware Programming Media Storage 56

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. Even when we do flush caches, the latency of flushing can itself be used as a channel! Microarchitectural channels. Threat scenarios.

Hardware 44

Hardware Cache Latency Speed 44

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. What happens if processes really do try to populate all that virtual memory? Many new tools can now be written, and the main toolkit we're working on is [bcc]. Hit Ctrl-C to end. ^C

Virtualization 75

Virtualization AWS Engineering Hardware 75

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

Abhishek Tiwari

DECEMBER 27, 2017

Containerized data workloads running on Kubernetes offer several advantages over traditional virtual machine/bare metal based data workloads including but not limited to. direct access to raw block storage [18] without the abstraction of a filesystem for workloads that require consistent I/O performance and low latency.

Big Data 63

Big Data Storage Benchmarking Hardware 63

Brendan Gregg

SEPTEMBER 25, 2021

A Cassandra database cluster had switched to Ubuntu and noticed write latency increased by over 30%. CLI tools The Cassandra systems were EC2 virtual machine (Xen) instances. 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

HammerDB

OCTOBER 23, 2023

The data shows a scripted automated workload running a number of back to back tests each time with an increasing number of virtual users. Using MariaDB and analysing performance at a workload of 80 Virtual Users the first place we can look at is the information schema user_statistics to quantify the difference in the database traffic.

Benchmarking 63

Benchmarking Database Network C++ 63

HammerDB

OCTOBER 12, 2018

As is also the case this limitation is at the database level (especially the storage engine) rather than the hardware level. driver: intel_pstate CPUs which run at the same hardware frequency: 0 . maximum transition latency: Cannot determine or is not supported. . hardware limits: 1000 MHz - 3.80

Best Practices 40

Best Practices Scalability Performance C++ 40

Brendan Gregg

SEPTEMBER 25, 2021

A Cassandra database cluster had switched to Ubuntu and noticed write latency increased by over 30%. CLI tools The Cassandra systems were EC2 virtual machine (Xen) instances. 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

HammerDB

DECEMBER 5, 2020

A full understanding of why this is important requires some knowledge of the evolution of database hardware and software. For TPC-C this meant enough available spindles to reduce I/O latency and for TPC-H enough bandwidth for data throughput. This was both expensive and time consuming to configure.

C++ 40

C++ Benchmarking Virtualization Open Source 40

Percona

APRIL 17, 2023

Operating System (OS) settings Swappiness Swappiness is a Linux kernel setting that influences the behavior of the Virtual Memory manager when it needs to allocate a swap, ranging from 0-100. The CFQ works well for many general use cases but lacks latency guarantees. Without further ado, let’s start with the OS settings.

Best Practices 52

Best Practices Design Tuning Database 52

SQL Server According to Bob

JANUARY 11, 2020

Many high-end disk subsystems provide high-speed cache facilities to reduce the latency of read and write operations. Example 1: ​​ Hardware failure (CPU board) Battery backup on the caching controller maintained the data. Important Always consult with your hardware manufacturer for proper stable media strategies.

Servers 40

Servers Cache Media Hardware 40