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. 6 * 7 * Copyright 2018 Netflix, Inc. the "License") 9 * 10 * 13-Sep-2018 Brendan Gregg Created this.

Latency 68

Latency C++ Cache Programming 68

Brendan Gregg

FEBRUARY 9, 2018

The recently revealed [Meltdown and Spectre] bugs are not just extraordinary issues of security, but also performance. The patches that workaround Meltdown introduce the largest kernel performance regressions I've ever seen. Some older kernels have the KAISER patches for Meltdown, and so far the performance overheads look similar.

Performance 75

Performance Benchmarking Cache Tuning 75

Nick Desaulniers

JUNE 2, 2018

ccache , the compiler cache, is a fantastic way to speed up build times for C and C++ code that I previously recommended. Usually when this happens with ccache, there’s something non-deterministic about the builds that prevents cache hits. . $ Sat Mar 17 03:04:59 UTC 2018. Cold Cache. Hot Cache.

Speed 46

Speed Cache C++ Systems 46

Smashing Magazine

OCTOBER 26, 2018

2018-10-26T13:45:46+02:00. In recent years, the industry thankfully started paying more attention to performance. As a result, website performance can suffer. Improving performance with the decoupled JSON approach. Improving Performance With The Decoupled JSON Approach. Denis Žoljom. 2019-04-29T18:34:58+00:00.

Cache 79

Cache Website Speed Database 79

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? Answered in Part 2.).

Systems 60

Systems Latency Performance Analytics 60

ACM Sigarch

MARCH 25, 2019

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. For the previous cache miss buffer example, the 32-buffer answer is minimal for 100-ns average miss latency. While Little’s Law provides a black-box result, it does not expose tradeoffs.

Systems 53

Systems Latency Performance C++ 53

The Morning Paper

DECEMBER 1, 2019

Memory might be durable, but… …it is expected that caches and registers will remain volatile. Moreover, for better performance, the processor may change the order in which writes reach the NVRAM, making it difficult for the NVRAM to even reflect a consistent prefix of the computation. Performance evaluation.

Efficiency 60

Efficiency Cache C++ Performance 60

Sutter's Mill

JANUARY 25, 2021

Not only is the integer comparison operation cheap, but min and max are already being accessed by this function and so they’re already “hot” in registers or cache. Example 1(a)’s min <= max is at this other end of the scale: It’s so dirt cheap to check that it’s unlikely we’ll ever have a performance reason to disable it. [2]

C++ 52

C++ Programming Cache Testing 52

Brendan Gregg

FEBRUARY 8, 2018

The recently revealed [Meltdown and Spectre] bugs are not just extraordinary issues of security, but also performance. The patches that workaround Meltdown introduce the largest kernel performance regressions I've ever seen. Some older kernels have the KAISER patches for Meltdown, and so far the performance overheads look similar.

Performance 40

Performance Benchmarking Cache Tuning 40

Percona

JANUARY 17, 2019

In this article, we will look at how this can improve the reporting/analytical query performance in MySQL. Aurora Parallel Query response time (for queries which can not use indexes) can be 5x-10x better compared to the non-parallel fully cached operations. The second and third run used the cached data. MySQL on ec2.

Cache 46

Cache C++ AWS Airlines 46

SQL Server According to Bob

DECEMBER 18, 2018

Be sure to deploy SQL Server 2017 CU6 or newer for best data durability and performance results. “. Device level flushing may have an impact on your I/O caching, read ahead or other behaviors of the storage system. Performance points of reference: The following charts highlight the increase in performance. The Back Story.

Servers 90

Servers Media Cache Storage 90

HammerDB

NOVEMBER 5, 2018

If you are new to running Oracle, SQL Server, MySQL and PostgreSQL TPC-C workloads with HammerDB and have needed to investigate I/O performance the chances are that you have experienced waits on writing to the Redo, Transaction Log or WAL depending on the database you are testing. Logging Waits. so what are your options?

Benchmarking 40

Benchmarking Database C++ Virtualization 40

Smashing Magazine

JUNE 30, 2021

The Problem Of Unpredictable Performance. At the same time, we have a widening performance gap. In terms for performance, these phones have plateaued at the performance of a 2012 iPhone. Applications built for the Web are expected to run on devices that fall anywhere on this broad performance spectrum.

Games 145

Games Architecture Code C++ 145

Randon ASCII

FEBRUARY 25, 2018

See the end of the post for an October 2018 bug fix update, or read the whole story: Flaky failures are the worst. This was starting to look like a Windows file cache bug. Maybe something to do with multi-socket coherency of the disk and cache or ??? Update, October 2018. failure rate.

Programming 79

Programming Hardware Cache Code 79

The Netflix TechBlog

JULY 1, 2019

In a previous post , we described how our TV application consists of a C++ SDK installed natively on the device, an updatable JavaScript user interface (UI) layer, and a custom rendering layer known as Gibbon. Our UI runs on top of a custom rendering engine which uses what we call a “surface cache” to optimize our use of graphics memory.

Cache 166

Cache Design Testing Development 166

Smashing Magazine

SEPTEMBER 6, 2021

If after the previous two parts — HTTP/3 history and core concepts and HTTP/3 performance features — you’re convinced that starting to use the new protocols is a good idea (and you should be!), HTTP/3 performance features. then this final piece includes all you need to know to get started! Implementation.

Network 107

Network Servers Cache Traffic 107