The Morning Paper

MARCH 10, 2020

Characterizing, modeling, and benchmarking RocksDB key-value workloads at Facebook , Cao et al., Or in the case of key-value stores, what you benchmark. So if you want to design a system that will offer good real-world performance, it’s really useful to have benchmarks that accurately represent real-world workloads.

Benchmarking 59

Benchmarking Storage Cache Open Source 59

The Morning Paper

MAY 23, 2019

Compress objects, not cache lines: an object-based compressed memory hierarchy Tsai & Sanchez, ASPLOS’19. Existing cache and main memory compression techniques compress data in small fixed-size blocks, typically cache lines. ” The big idea.

Cache 61

Cache Benchmarking Hardware Java 61

Scalegrid

MARCH 28, 2024

Key Takeaways Redis offers complex data structures and additional features for versatile data handling, while Memcached excels in simplicity with a fast, multi-threaded architecture for basic caching needs. Redis is better suited for complex data models, and Memcached is better suited for high-throughput, string-based caching scenarios.

Cache 130

Cache Storage Scalability Architecture 130

Brendan Gregg

JUNE 30, 2018

These have inspired me to summarize another performance activity: evaluating benchmark accuracy. Accurate benchmarking rewards engineering investment that actually improves performance, but, unfortunately, inaccurate benchmarking is more common. If the benchmark reported 20k ops/sec, you should ask: why not 40k ops/sec?

Benchmarking 47

Benchmarking Latency Cache Network 47

ACM Sigarch

APRIL 2, 2025

Our STRAIGHT compiler, built on LLVM, has reached a level where it can compile and correctly execute all benchmarks from SPEC CPU2017, a widely used standard for evaluating CPU performance. His work addresses diverse aspects of computer architecture and system software.

Efficiency 54

Efficiency Hardware Architecture Design 54

Percona

JUNE 22, 2023

This includes metrics such as query execution time, the number of queries executed per second, and the utilization of query cache and adaptive hash index. query cache: Disable (query_cache_size: 0, query_cache_type:OFF) innodb_adaptive_hash_index: Check adaptive hash index usage to determine its efficiency.

Performance 136

Performance Monitoring Traffic Database 136

Smashing Magazine

SEPTEMBER 28, 2022

On your first try, you can use it as a benchmark for optimizations later. On design systems, UX, web performance and CSS/JS. Active Memory Caching. When you want to get data that you already had quickly, you need to do caching — caching stores data that a user recently retrieved. Caching Schemes.

Cache 141

Cache Performance Servers Architecture 141

Adrian Cockcroft

SEPTEMBER 23, 2024

Most publications have simply reported the benchmark improvement claims, but if you stop to think about them, the numbers dont make sense based on a simplistic view of the technology changes. So first thing to understand is that the benchmark skips a generation and compares product that differs over about a two year interval.

Benchmarking 52

Benchmarking Energy Architecture Latency 52

Percona

MARCH 17, 2023

Please note that the focus of these tests was around standard metrics gathering and display, we’ll use a future blog post to benchmark some of the more intensive query analytics (QAN) performance numbers. VictoriaMetrics maintains an in-memory cache for mapping active time series into internal series IDs.

Monitoring 117

Monitoring Scalability Database Cache 117

ACM Sigarch

OCTOBER 12, 2020

I suggest it’s long past time to move beyond C and SPEC benchmarks and our exclusive focus on “metal” languages. There are already standard benchmark suites for JavaScript performance in the browser, and we can include applications written in node.js (server-side JavaScript), Python web servers, and more.

C++ 109

C++ Benchmarking Hardware Architecture 109

Percona

MARCH 23, 2023

By caching hot datasets, indexes, and ongoing changes, InnoDB can provide faster response times and utilize disk IO in a much more optimal way. Operating system Linux is the most common operating system for high-performance MySQL servers. Benchmark before you decide. Transparent huge pages (THP) disabled.

Performance 144

Performance Hardware Tuning Storage 144

Brendan Gregg

MARCH 16, 2024

The problem is that this system has a default libc that has been compiled without frame pointers, so any stack walking stops at the libc layer, producing a partial stack that's missing the application frames. It shouldn't be 10%, unless it's cache effects. Don't blame the straw, in this case, don't blame the frame pointers.

Java 137

Java Cache Google Hardware 137

Brendan Gregg

JUNE 29, 2018

These have inspired me to summarize another performance activity: evaluating benchmark accuracy. Accurate benchmarking rewards engineering investment that actually improves performance, but, unfortunately, inaccurate benchmarking is more common. If the benchmark reported 20k ops/sec, you should ask: why not 40k ops/sec?

Benchmarking 40

Benchmarking Latency Cache Network 40

Percona

JULY 25, 2023

After the “data dictionary” (DD) engine and DD cache are initialized on a server, the Storage Engines can ask for a table definition. Initializing a DD engine and the cache adds complexity and other server dependencies. Essentially LRU cache is disabled by loading the tables as non-evictable. ibd2sdi data/test/t1.ibd

Cache 98

Cache Servers Benchmarking Design 98

Percona

AUGUST 31, 2018

If queries perform full table scans where an index could be used or perform heavy joins or expensive aggregate operations, then the system can still perform poorly even if the database parameters are tuned. The PostgreSQL buffer is called shared_buffer which is the most effective tunable parameter for most operating systems.

Tuning 79

Tuning Database Performance Benchmarking 79

The Morning Paper

AUGUST 29, 2019

use the TPC-H benchmark to assess Redshift, Redshift Spectrum, Athena, Presto, Hive, and Vertica to find out what works best and the trade-offs involved. We focused on OLAP-oriented parallel data warehouse products available for AWS and restricted our attention to commercially available systems. Key findings. Query restrictions.

Architecture 76

Architecture Cloud Storage Serverless 76

HammerDB

JUNE 27, 2022

HammerDB is a software application for database benchmarking. HammerDB has graphical and command line interfaces for the Windows and Linux operating systems. Databases are highly sophisticated software, and to design and run a fair benchmark workload is a complex undertaking. Why HammerDB was developed. HammerDB Licensing.

Benchmarking 63

Benchmarking Open Source C++ Cache 63

ScaleOut Software

MAY 15, 2014

Given all this, we thought it would be a good opportunity to see how we are doing relative to the competition, and in particular, relative to Microsoft’s AppFabric caching for Windows on-premise servers. One or more specified cache servers are unavailable, which could be caused by busy network or servers. …). Please retry later.

Cache 40

Cache Servers Network Design 40

John McCalpin

SEPTEMBER 11, 2014

The High Performance LINPACK (HPL) benchmark is well known for delivering a high fraction of peak floating-point performance. A colleague here at TACC ran into this while testing on a 2-socket Haswell EP system. But this does not mean that memory bandwidth will *never* be a performance limiter.

Benchmarking 40

Benchmarking Cache Performance Systems 40

MachMetrics

DECEMBER 14, 2019

It is typically reduced via server-side optimizations, such as enabling caching and database indexes. However, we really want to strive to be under the benchmarks that Google sets as a best practice. Even better if you’re under Google’s best practice benchmark. seconds on desktop and 2.59 seconds on mobile.

Best Practices 105

Best Practices Speed Mobile Google 105

Smashing Magazine

JUNE 2, 2021

The project consisted of upgrading the shop software to our own open-source system and redoing the shop’s front end from scratch. Today, the website is much faster and ranks highly in various showcases and benchmarks. And while you can usually cache the full page of an article, the same is not true of many shop pages and elements.

Performance 132

Performance Cache Website Mobile 132

John McCalpin

APRIL 2, 2020

The presentation discusses a family of simple performance models that I developed over the last 20 years — originally in support of processor and system design at SGI (1996-1999), IBM (1999-2005), and AMD (2006-2008), but more recently in support of system procurements at The Texas Advanced Computing Center (TACC) (2009-present).

Benchmarking 59

Benchmarking Performance Latency Architecture 59

Speed Curve

FEBRUARY 5, 2024

Looking at the industry benchmarks for US retailers , four well-known sites have backend times that are approaching – or well beyond – that threshold. Pagespeed Benchmarks - US Retail - LCP When you examine a waterfall, it's pretty obvious that TTFB is the long pole in the tent, pushing out render times for the page.

Servers 64

Servers Cache Benchmarking Retail 64

Brendan Gregg

FEBRUARY 9, 2018

This overhead can be reduced by A) pcid, fully available in Linux 4.14, and B) Huge pages. - **Cache access pattern**: the overheads are exacerbated by certain access patterns that switch from caching well to caching a little less well. Also microbenchmarks, which often stress-test the system, will suffer the largest losses.

Performance 72

Performance Benchmarking Cache Tuning 72

Alex Russell

APRIL 29, 2021

As an engineer on a browser team, I'm privy to the blow-by-blow of various performance projects, benchmark fire drills, and the ways performance marketing (deeply) impacts engineering priorities. With each team, benchmarks lost are understood as bugs. All modern browsers are fast, Chromium and Safari/WebKit included. Media Session API.

Media 145

Media Games Education Engineering 145

The Morning Paper

JUNE 16, 2019

Specifically, scalable, parallel streaming dataflow computing systems now support partially-stateful and dynamically-changing dataflows. The amount of computation required on a base update can be reduced by sharing computation and cached data between universes. Recent research has provided this missing key primitive.

Database 90

Database Cache Benchmarking Efficiency 90

HammerDB

APRIL 19, 2023

Therefore, before we attempt to measure our database performance, we should know the system or cloud instance to be tested in detail. Benchmarking the target Two of the more popular database benchmarks for MySQL are HammerDB and sysbench. Operating System: Ubuntu 22.04 Operating System: Ubuntu 22.04

Performance 55

Performance Benchmarking Cache Storage 55

Percona

SEPTEMBER 1, 2023

This can affect the overall performance of your database system, potentially leading to slower response times. This can introduce maintenance overhead, particularly in large and complex database systems. Testing and Benchmarking : Thoroughly test triggers in a staging environment to evaluate their impact on performance.

Cache 75

Cache Database Games Healthcare 75

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. Using a global ASP as a benchmark can further mislead thanks to the distorting effect of ultra-high-end prices rising while shipment volumes stagnate. The Moto G4 , for example.

Performance 127

Performance Network Mobile Cache 127

Percona

JUNE 22, 2023

Defining high availability In general terms, high availability refers to the continuous operation of a system with little to no interruption to end users in the event of hardware or software failures, power outages, or other disruptions. Some disruption might occur, but it will be minimal. Fault tolerance aims for zero downtime and data loss.

Availability 132

Availability Database Open Source Hardware 132

n0derunner

MAY 6, 2019

A 2007 paper, that still has lots to say on the subject of benchmarking storage and filesystems. Primarily aimed at researchers and developers, but is relevant to anyone about to embark on a benchmarking effort. A Nine year study of filesystem and storage benchmarking Download.

Benchmarking 40

Benchmarking Storage Cache Testing 40

HammerDB

NOVEMBER 5, 2018

This post at an entry-level discusses the options you have to improve log throughput in your benchmark environment. . To illustrate the data reads on Oracle we can flush the buffer cache. SQL> alter system flush buffer_cache; System altered. SQL> alter system set commit_wait='NOWAIT' scope=spfile; System altered.

Benchmarking 40

Benchmarking Database C++ Virtualization 40

Smashing Magazine

JUNE 1, 2022

You can adjust what browser is used, the kind of network connection to employ, the locations to test from, whether or not the browser’s cache is empty or full, how frequently to take the measurements, and more. They are more of a benchmark than a true measurement of real user experience.

Website 138

Website Design Network Testing 138

SQL Performance

DECEMBER 17, 2019

You will still have to maintain your operating system, SQL Server and databases just like you would in an on-premises scenario. Microsoft's Mine Tokus has a good article where she ran a series of scaled down TPC-E benchmarks against an E64s_v3 VM that was using the older Broadwell processor. GHz, 128MB of L3 cache, 128 PCIe 4.0

Azure 72

Azure Virtualization Servers Storage 72

Percona

MAY 1, 2023

It is primarily the responsibility of the database administrator or developer to tune PostgreSQL according to their system’s workload. Connection pooling: Minimizing connection overhead and improving response times for frequently accessed data by implementing mechanisms for connection pooling and caching strategies.

Tuning 52

Tuning Database Efficiency Performance 52

Alex Russell

OCTOBER 22, 2017

Budgets are scaled to a benchmark network & device. Tools and CI systems help them monitor progress & prevent regressions. Deciding what benchmark to use for a performance budget is crucial. Some systems show median RTTs near ~100ms for 3G users. Performance budgets are set early in the life of the project.

Performance 74

Performance Network Benchmarking Mobile 74

John McCalpin

APRIL 2, 2020

The presentation discusses a family of simple performance models that I developed over the last 20 years — originally in support of processor and system design at SGI (1996-1999), IBM (1999-2005), and AMD (2006-2008), but more recently in support of system procurements at The Texas Advanced Computing Center (TACC) (2009-present).

Benchmarking 40

Benchmarking Performance Latency Architecture 40