IT Infrastructure Database Tuning – Fall 2015
Slotnik’s Law of Effort #1: Heterogeneous Systems LOOK UP: Slotnik vs. Amdahl (AFIPS’67), Michael Flynn’s talk on dataflow machines, Ryan Johnson’s paper on bionic databases. @ Dennis Shasha and Philippe Bonnet, 2013 Source: http://www.anandtech.com/show/2933
Bill Daly’s slide deck on exascale computing project NVidia’s vision
@ Dennis Shasha and Philippe Bonnet, 2013 IO Architecture Processor [core i7] 2x21GB/sec RAM 16 GB/sec SSD Memory bus PCI Express HDD Southbridge Chipset [z68] 5 GB/sec RAID controller 3 GB/sec SATA ports PCI HDD SSD 3 GB/sec SSD SSD SSD Byte addressable Block addressable LOOK UP: Smart Response Technology (SSD caching managed by z68) @ Dennis Shasha and Philippe Bonnet, 2013
@ Dennis Shasha and Philippe Bonnet, 2013 RAID Controller PCI bridge Batteries RAM CPU Host Bus Adapter Caching Write-back / write-through Logical disk organization JBOD RAID @ Dennis Shasha and Philippe Bonnet, 2013
Slotnik’s Law of Effort #2: The emergence of SSDs Latency of 5000 random writes on an Intel 710 SSD (10 successive passes over 250 KB with 512B random writes on a random formatted device). Throughput for 4K read IOs from product specifications Read Write Logical address space Scheduling & Mapping Wear Leveling Garbage collection Program Erase Chip … Flash memory array Channels Physical address space LOOK UP: The necessary death of the block device interface @ Dennis Shasha and Philippe Bonnet, 2013
Case: TPC-C Top Performer (01/13) Redo Log Configuration Total system cost 30,528,863 USD Performance 30,249,688 tpmC Total #processors 108 Total #cores 1728 Total storage 1,76 PB Total #users 24,300,000 LOOK UP: TPC-C OLTP Benchmark @ Dennis Shasha and Philippe Bonnet, 2013 Source: http://www.tpc.org/tpcc/results/tpcc_result_detail.asp?id=110120201
Warehouse-Scale Computer LOOK UP: Werner Voegels on virtualization. @ Dennis Shasha and Philippe Bonnet, 2013 Source: http://www.morganclaypool.com/doi/abs/10.2200/S00193ED1V01Y200905CAC006
Cloud Services IaSS: compute and storage abstractions (VM, load balancer) ex: AWS, Azure PaSS: execution environment ex: Google App Engine, AWS, Azure SaSS: managed software ex: SQL Azure, Snowflake Private, public, hybrid coud
source: Microsoft Key metric: number of servers per administrator – Amazon: 10K
@ Dennis Shasha and Philippe Bonnet, 2013 Database Appliances @ Dennis Shasha and Philippe Bonnet, 2013 Source: http://www.oracle.com/us/products/database/exadata/overview/index.html
Mainframe Fast processors, lots of hardware accelerators, lots of RAM and storage Hardware resources are virtualized: e.g., single-level store High-performance, general purpose applicance; or alternative to a private cloud
Storage Architectures source: Virtual Geek’s take on storage tree of life – A MUST READ!! Storage RAM Interconnect © Philippe Bonnet, 2014
Data-Intensive Applications: Server-side Architectures Look up Fabric Computing on Wikipedia. source: Virtual Geek’s take on storage tree of life – A MUST READ!! © Philippe Bonnet, 2014
Source: Chad Sakac,EMC, software-defined storage - what's next, vmworld 2014