Percona

DECEMBER 20, 2023

Unfortunately, the performance in benchmarks is almost the same as for 4KB pages. Please check out the Why Linux HugePages are Super Important for Database Servers: A Case with PostgreSQL blog post for more information. Setup I recommend starting with 2MB huge pages because it’s trivial to set up.

C++ 95

C++ Virtualization Benchmarking Database 95

HammerDB

NOVEMBER 22, 2021

Introducing the PostgreSQL performance metrics viewer. HammerDB included a graphical performance metrics view for the Oracle database only. This enables the user to compare and contrast performance across different benchmark scenarios. Prior to version 4.3, PostgreSQL Graphical Metrics. I/opt/postgresql-14.1/include/server

Metrics 62

Metrics Benchmarking C++ Database 62

n0derunner

MARCH 13, 2020

Why do we tend to use 1MB IO sizes for throughput benchmarking? 8 Sectors = 4KB 128 Sectors = 64KB 1024 Sectors = 512KB 2048 Sectors = 1024KB (1MB). First things First. CDC 9762 SMD disk drive from 1974. Normally this is reported in “sectors” which are 512bytes in size. Using iostat.

Benchmarking 45

Benchmarking Storage Testing Performance 45

Percona

MARCH 20, 2023

MySQL router, after the 2048 connection, could not serve anything more. HAProxy performs better with a low number of connections, while ProxySQL performs better when a high number of connections is in place. That allows it to go a bit further. MySQL Router is the one that has the higher latency no matter what.

Games 118

Games Latency Traffic Cache 118

SQL Server According to Bob

JANUARY 11, 2020

​​ This is similar to the ​​ suspend and resume ​​ operations performed by ​​ the operating system. ​​ Performing ​​ safety ​​ checks ​​ of SQL Server and all other system components before production deployment is very important.

Servers 40

Servers Cache Database Media 40