Brendan Gregg

JULY 4, 2021

It's an exciting time for developments in computer performance, not just for the BPF technology (which I often [write about]) but also for processors with 3D stacking and cloud vendor CPUs (e.g., This was a chance to talk about other things I've been working on, such as the present and future of hardware performance.

Performance 52

Performance Latency Hardware Storage 52

High Scalability

JULY 20, 2018

This is where your performance goes. A typical example of modern "microservices-inspired" Java application would function along these lines: Netflix : We observed during experimentation that RAM random read latencies were rarely higher than 1 microsecond whereas typical SSD random read speeds are between 100–500 microseconds.

Internet 121

Internet Internet Scalability Automotive 121

KeyCDN

MARCH 10, 2021

It's our mission to continuously improve web performance and each POP contributes to it. The image below shows a significant drop in latency once we've launched the new point of presence in Israel. The image below shows a significant drop in latency once we've launched the new point of presence in Israel. With a population of 2.5

Latency 110

Latency Internet Internet Tuning 110

The Netflix TechBlog

MARCH 1, 2021

It supports both high throughput services that consume hundreds of thousands of CPUs at a time, and latency-sensitive workloads where humans are waiting for the results of a computation. The subsystems all communicate with each other asynchronously via Timestone, a high-scale, low-latency priority queuing system.

Serverless 228

Serverless Media Latency Social Media 228

Brendan Gregg

OCTOBER 8, 2018

Screenshot: tracing read latency for PID 181: # bpftrace -e 'kprobe:vfs_read /pid == 30153/ { @start[tid] = nsecs; } kretprobe:vfs_read /@start[tid]/ { @ns = hist(nsecs - @start[tid]); delete(@start[tid]); }'. Here's key differences as of August 2018: Type DTrace bpftrace. It's shaping up to be a DTrace version 2.0: I wrote seeksize.d

C++ 110

C++ Virtualization Programming Latency 110

High Scalability

MARCH 22, 2019

µs of replication latency on lossy Ethernet, which is faster than or comparable to specialized replication systems that use programmable switches, FPGAs, or RDMA.". BrentToderian : What city went from 14% of all trips by bike in 2001, to 22% by 2012, then leaped to 30% in 3 years by 2015, & 35% by 2018? We achieve 5.5

Internet 134

Internet Internet Scalability Wireless 134

CSS Wizardry

MAY 31, 2019

This is exactly what Rawgit did in October 2018, yet (at the time of writing) a crude GitHub code search still yielded over a million references to the now-sunset service, and almost 20,000 live sites are still linking to it! On a slower, higher-latency connection, the story is much, mush worse. Risk: Service Shutdowns. to just 3.6s.

Cache 274

Cache Latency Infrastructure Website 274

Alex Russell

MARCH 6, 2021

Back in 2016, I gave a talk outlining the causes and effects of the terrible performance of web apps built using popular tools on the fastest-growing device segment: low-end to mid-range Android phones. Poor performance has a compound effect on user expectations at an ecosystem level. Live by the link, die by the link.

Performance 124

Performance Network Cache Metrics 124

Abhishek Tiwari

DECEMBER 27, 2017

There are several emerging data trends that will define the future of ETL in 2018. In 2018, we anticipate that ETL will either lose relevance or the ETL process will disintegrate and be consumed by new data architectures. It generally improves performance by placing frequently accessed data in memory.

Big Data 49

Big Data Artificial Intelligence Storage Hardware 49

SQL Performance

FEBRUARY 26, 2020

Azure SQL Database Managed Instance became generally available in late 2018. Managed Instance provides two tiers for performance. The General Purpose tier is designed for applications with typical performance and I/O latency requirements and provides built-in HA. One size does not always fit all. GB per vCore.

Azure 63

Azure Performance Storage Latency 63

ACM Sigarch

MARCH 18, 2019

Existing systems can be studied with measurement, while prospective systems are most often studied by extrapolating from measurements of prior systems or via simulation software that mimics target system function and provides performance metrics. Can one both minimize latency and maximize throughput for unscheduled work? Little’s Law.

Systems 60

Systems Latency Performance Analytics 60

Speed Curve

FEBRUARY 5, 2024

That performance golden rule still holds true today. Charlie Vazac introduced server timing in a Performance Calendar post circa 2018. Latency – How much time does it take to deliver a packet from A to B. Here are a couple of great blog posts from last year's Web Performance Calendar. Definitely worth a read!

Servers 57

Servers Cache Retail Benchmarking 57

Smashing Magazine

JANUARY 11, 2021

Front-End Performance Checklist 2021. Front-End Performance Checklist 2021. This guide has been kindly supported by our friends at LogRocket , a service that combines frontend performance monitoring , session replay, and product analytics to help you build better customer experiences. Web performance is a tricky beast, isn’t it?

Performance 145

Performance Cache Media Metrics 145

ACM Sigarch

MARCH 25, 2019

How many buffers are needed to track pending requests as a function of needed bandwidth and expected latency? Can one both minimize latency and maximize throughput for unscheduled work? The M/M/1 queue will show us a required trade-off among (a) allowing unscheduled task arrivals, (b) minimizing latency, and (c) maximizing throughput.

Systems 53

Systems Latency Performance C++ 53

Brendan Gregg

OCTOBER 7, 2018

Screenshot: tracing read latency for PID 181: # bpftrace -e 'kprobe:vfs_read /pid == 30153/ { @start[tid] = nsecs; } kretprobe:vfs_read /@start[tid]/ { @ns = hist(nsecs - @start[tid]); delete(@start[tid]); }'. Here's key differences as of August 2018: Type DTrace bpftrace. It's shaping up to be a DTrace version 2.0: I wrote seeksize.d

C++ 40

C++ Virtualization Programming Latency 40

The Netflix TechBlog

MARCH 13, 2020

As mentioned in our earlier blog post , Intel and Netflix have been collaborating on the SVT-AV1 encoder and decoder framework since August 2018. In this tech blog, we will report the current status of the SVT-AV1 project, as well as the characteristics and performance of the encoder and decoder.

Open Source 154

Open Source Efficiency C++ Speed 154

Brendan Gregg

AUGUST 18, 2019

bpftrace is a new open source tracer for Linux for analyzing production performance problems and troubleshooting software. Linux already has many performance tools, but these are often counter-based and have limited visibility. Linux already has many performance tools, but these are often counter-based and have limited visibility.

Latency 68

Latency C++ Cache Programming 68

Brendan Gregg

AUGUST 29, 2021

A service team was debugging a performance issue and noticed it coincided with a high rate of paging. I was asked to help, and used a variety of performance tools to solve this including those that use eBPF and Ftrace. 1072-aws (xxx) 12/18/2018 _x86_64_ (16 CPU) avg-cpu: %user %nice %system %iowait %steal %idle 5.03 100.00 ^C.

Cache 105

Cache C++ AWS Latency 105

HammerDB

OCTOBER 12, 2018

This post complements the previous best practice guides this time with the focus on MySQL and MariaDB and achieving top levels of performance with the HammerDB MySQL TPC-C test. As is exactly the same with PostgreSQL for system choice a 2 socket system is optimal for MySQL OLTP performance. c_ytd_payment: 10.00 7 rows in set (0.00

Best Practices 40

Best Practices Scalability Performance C++ 40

All Things Distributed

NOVEMBER 13, 2018

Lamborghini, the world-famous manufacturer of elite, luxury sports cars based in Italy, has been using AWS to reduce the cost of their infrastructure by 50 percent, while also achieving better performance and scalability. Today, their time-to-market is close to zero. ENEL is one of the leading energy operators in the world.

AWS 167

AWS Energy Automotive Traffic 167

Smashing Magazine

OCTOBER 31, 2023

Answering Common Questions About Interpreting Page Speed Reports Answering Common Questions About Interpreting Page Speed Reports Geoff Graham 2023-10-31T16:00:00+00:00 2023-10-31T17:06:18+00:00 This article is sponsored by DebugBear Running a performance check on your site isn’t too terribly difficult. Can’t be perfect every time!

Speed 97

Speed Google Website Metrics 97

HammerDB

OCTOBER 8, 2018

This post gives a HOWTO guide on system configuration for achieving top levels of performance with the HammerDB PostgreSQL TPC-C test. Firstly for system choice a 2 socket system is optimal for PostgreSQL OLTP performance at the time of writing. Make sure that your CPU is configured for optimal performance. Setting cpu: 0.

Best Practices 40

Best Practices Scalability Performance Hardware 40

High Scalability

SEPTEMBER 14, 2018

aallan : “Moore’s Law is really dead, but the lesser know Dennard Scaling Law is also dead… we’re almost at the end of the line, last year performance only improved 3 percent,” says David Patterson. SCM slots between DRAM and flash in terms of latency, cost, and density. Feedback & Scoring, 2.

Internet 30

Internet Internet Scalability Education 30

John McCalpin

JANUARY 9, 2019

This week I updated three of those posts — two really old ones (primarily of interest to computer architecture historians), and one from 2018: July 2012: Local and Remote Memory Latency on AMD Processors in 2-socket and 4-socket servers. December 2013: Notes on Memory Bandwidth on the Xeon Phi (Knights Corner) Coprocessor.

Latency 40

Latency Architecture Servers Performance 40

Smashing Magazine

JANUARY 6, 2020

Front-End Performance Checklist 2020 [PDF, Apple Pages, MS Word]. Front-End Performance Checklist 2020 [PDF, Apple Pages, MS Word]. Web performance is a tricky beast, isn’t it? How do we actually know where we stand in terms of performance, and what our performance bottlenecks exactly are? Vitaly Friedman.

Performance 145

Performance Cache Network Metrics 145

Smashing Magazine

JANUARY 7, 2019

Front-End Performance Checklist 2019 [PDF, Apple Pages, MS Word]. Front-End Performance Checklist 2019 [PDF, Apple Pages, MS Word]. Web performance is a tricky beast, isn’t it? How do we actually know where we stand in terms of performance, and what our performance bottlenecks exactly are? Vitaly Friedman.

Performance 103

Performance Cache Metrics Network 103

CSS - Tricks

APRIL 1, 2021

Site performance is potentially the most important metric. The better the performance, the better chance that users stay on a page, read content, make purchases, or just about whatever they need to do. Google’s industry benchmarks from 2018 also provide a striking breakdown of how each second of loading affects bounce rates.

Cache 92

Cache Social Media Media Website 92

Alex Russell

OCTOBER 22, 2017

TL;DR: performance budgets are an essential but under-appreciated part of product success and team health. Nobody is trying to do a poor job, and yet the results of a “completed” PWA project often require weeks or months of painstaking rework to deliver minimally acceptable performance. Partner meetings are illuminating.

Performance 68

Performance Benchmarking Network Mobile 68

KeyCDN

OCTOBER 24, 2018

Although both countries are relatively close to one another, they are separated by a distance of approximately 500km, which adds up in terms of latency. As of August 2018, Helsinki alone had a population of almost 650,000 people. As for Finland, it covers an area of over 338,000 square kilometers and has a population of over 5.5

Internet 48

Internet Internet Speed Network 48

HammerDB

MAY 5, 2019

So the PAUSE instruction is an optimization over NOP when a thread is waiting to acquire a lock and is particularly important in spin-locks on x86 CPUs for power and performance. ” and “as the PAUSE latency has been increased significantly, workloads that are sensitive to PAUSE latency will suffer some performance loss.”

Testing 48

Testing Tuning Latency Storage 48

Testsigma

FEBRUARY 12, 2021

The latest trend in hyperautomation – Gartner projects that by the year 2023, 25% of tasks by the organisations will be able to perform autonomously and hence reducing the cost. Gartner stated that Artificial Intelligence computing resources are to expand by 5 times between 2018 and 2023. The most recent 2021 trend.

Artificial Intelligence 92

Artificial Intelligence Software Software IoT 92

Percona

JULY 1, 2023

This post was originally published in July 2018 and was updated in July 2023. These may be performance, high availability, operational cost, management, capacity planning, scalability, security, monitoring, etc. It automatically takes regular backups, capturing incremental changes since the last backup without affecting performance.

AWS 52

AWS Database Serverless Storage 52

IO River

NOVEMBER 2, 2023

Companies like Datadog and New Relic provide real-time monitoring and analytics for IT infrastructure and application performance, helping companies quickly identify and rectify issues before they can cause significant harm.

Availability 52

Availability Social Media Traffic Games 52

IO River

NOVEMBER 2, 2023

Companies like Datadog and New Relic provide real-time monitoring and analytics for IT infrastructure and application performance, helping companies quickly identify and rectify issues before they can cause significant harm.

Availability 52

Availability Social Media Traffic Games 52

Brendan Gregg

AUGUST 29, 2021

A service team was debugging a performance issue and noticed it coincided with a high rate of paging. I was asked to help, and used a variety of Linux performance tools to solve this including those that use eBPF and Ftrace. 1072-aws (xxx) 12/18/2018 _x86_64_ (16 CPU) avg-cpu: %user %nice %system %iowait %steal %idle 5.03

Cache 40

Cache C++ AWS Systems 40

Abhishek Tiwari

DECEMBER 27, 2017

In 2018, a widespread adaptation of Kubernetes for big data processing is anitcipated. overall performance comparable to bare metal. The good news is all of these challenges including performance can be tackled and in several cases, there are new developments to overcome them. Performance. Native frameworks.

Big Data 63

Big Data Storage Benchmarking Hardware 63

Adrian Cockcroft

NOVEMBER 18, 2019

OPN303 BPF performance analysis (repeats) Learn how Netflix uses eBPF to create powerful performance analysis tools. OPN304 Learnings from migrating a service from JDK 8 to JDK 11 AWS Lambda improved latency by migrating to JDK 11 with Amazon Corretto.

Open Source 40

Open Source AWS Lambda Serverless 40