QLogic/Lenovo 16Gb Gen 5 Fibre Channel for Database and Business Analytics

Similar documents
QLogic 16Gb Gen 5 Fibre Channel for Database and Business Analytics

QLogic 2500 Series FC HBAs Accelerate Application Performance

8Gb Fibre Channel Adapter of Choice in Microsoft Hyper-V Environments

NVMe over Universal RDMA Fabrics

QLE10000 Series Adapter Provides Application Benefits Through I/O Caching

The QLogic 8200 Series is the Adapter of Choice for Converged Data Centers

FC-NVMe. NVMe over Fabrics. Fibre Channel the most trusted fabric can transport NVMe natively. White Paper

Cavium FastLinQ 25GbE Intelligent Ethernet Adapters vs. Mellanox Adapters

Visualize I/O Connectivity for VMware vsphere

Benefits of Offloading I/O Processing to the Adapter

NVMe Direct. Next-Generation Offload Technology. White Paper

QLogic 10GbE High-Performance Adapters for Dell PowerEdge Servers

Evaluation Report: HP StoreFabric SN1000E 16Gb Fibre Channel HBA

Network Function Virtualization Using Data Plane Developer s Kit

Configuring Cavium SmartAN for HPE Ethernet 10/25GbE Adapters. Products Supported. HPE Ethernet 10/25Gb 621SFP28 Adapter B21

IBM Emulex 16Gb Fibre Channel HBA Evaluation

VM Aware Fibre Channel

Introduction to Ethernet Latency

Disabling the FCoE Function on HPE FlexFabric Adapters from QLogic. Products Affected. HPE FlexFabric 10Gb 2-port 534FLR-SFP B21

QLogic 2700 Series. Gen 6 FC (32GFC) Fibre Channel Adapters. Data Sheet OVERVIEW

EMC XTREMCACHE ACCELERATES VIRTUALIZED ORACLE

Emulex LPe16000B Gen 5 Fibre Channel HBA Feature Comparison

Gen 6 Fibre Channel Evaluation of Products from Emulex and Brocade

Upgrade to Microsoft SQL Server 2016 with Dell EMC Infrastructure

EMC XTREMCACHE ACCELERATES MICROSOFT SQL SERVER

TPC-E testing of Microsoft SQL Server 2016 on Dell EMC PowerEdge R830 Server and Dell EMC SC9000 Storage

Application Note Setting the QL41xxx Link Speed Using QCS CLI

An Oracle White Paper June Enterprise Database Cloud Deployment with Oracle SuperCluster T5-8

QLogic TrueScale InfiniBand and Teraflop Simulations

ACCELERATE YOUR ANALYTICS GAME WITH ORACLE SOLUTIONS ON PURE STORAGE

QLogic QLE2694 and QLE2694L

Emulex -branded Fibre Channel HBA Product Line

FlashGrid Software Enables Converged and Hyper-Converged Appliances for Oracle* RAC

Oracle Exadata: Strategy and Roadmap

Evaluation Report: Improving SQL Server Database Performance with Dot Hill AssuredSAN 4824 Flash Upgrades

Accelerating Workload Performance with Cisco 16Gb Fibre Channel Deployments

Maximize the All-Flash Data Center with Brocade Gen 6 Fibre Channel

Emulex LPe16000B 16Gb Fibre Channel HBA Evaluation

Oracle Database Exadata Cloud Service Exadata Performance, Cloud Simplicity DATABASE CLOUD SERVICE

Cisco Unified Computing System Delivering on Cisco's Unified Computing Vision

QLogic BR-815 and BR-825 Fibre Channel Adapters

Oracle Exadata Statement of Direction NOVEMBER 2017

NetApp AFF A300 Gen 6 Fibre Channel

SUPERMICRO, VEXATA AND INTEL ENABLING NEW LEVELS PERFORMANCE AND EFFICIENCY FOR REAL-TIME DATA ANALYTICS FOR SQL DATA WAREHOUSE DEPLOYMENTS

The Impact of SSD Selection on SQL Server Performance. Solution Brief. Understanding the differences in NVMe and SATA SSD throughput

Performance Testing of SQL Server on Kaminario K2 Storage

Lenovo Database Configuration

2 to 4 Intel Xeon Processor E v3 Family CPUs. Up to 12 SFF Disk Drives for Appliance Model. Up to 6 TB of Main Memory (with GB LRDIMMs)

RACKSPACE ONMETAL I/O V2 OUTPERFORMS AMAZON EC2 BY UP TO 2X IN BENCHMARK TESTING

Gen 6 Fibre Channel: Accelerating Data Access and Application Performance in the All-Flash Data Center

Data-at-Rest Encryption Addresses SAN Security Requirements

ARISTA: Improving Application Performance While Reducing Complexity

Virtuozzo Hyperconverged Platform Uses Intel Optane SSDs to Accelerate Performance for Containers and VMs

OCP Engineering Workshop - Telco

Accelerating Microsoft SQL Server 2016 Performance With Dell EMC PowerEdge R740

Lenovo Enterprise Portfolio

REFERENCE ARCHITECTURE Microsoft SQL Server 2016 Data Warehouse Fast Track. FlashStack 70TB Solution with Cisco UCS and Pure Storage FlashArray//X

SAS workload performance improvements with IBM XIV Storage System Gen3

Was ist dran an einer spezialisierten Data Warehousing platform?

Lenovo Database Configuration for Microsoft SQL Server TB

Industry Brief. Gen 5 16Gb Fibre Channel from HP Eases Data Center Traffic Jams. Featured Applications

DDN About Us Solving Large Enterprise and Web Scale Challenges

Doubling Performance in Amazon Web Services Cloud Using InfoScale Enterprise

Mellanox InfiniBand Solutions Accelerate Oracle s Data Center and Cloud Solutions

EMC XTREMCACHE ACCELERATES ORACLE

stec Host Cache Solution

HP ProLiant BladeSystem Gen9 vs Gen8 and G7 Server Blades on Data Warehouse Workloads

Microsoft SQL Server in a VMware Environment on Dell PowerEdge R810 Servers and Dell EqualLogic Storage

Accelerating Real-Time Big Data. Breaking the limitations of captive NVMe storage

Delivering High-Throughput SAN with Brocade Gen 6 Fibre Channel. Friedrich Hartmann SE Manager DACH & BeNeLux

PRESERVE DATABASE PERFORMANCE WHEN RUNNING MIXED WORKLOADS

Benefits of Gen 6 Fibre Channel for the All-Flash Data Center

THE OPEN DATA CENTER FABRIC FOR THE CLOUD

Consolidating Microsoft SQL Server databases on PowerEdge R930 server

... IBM Advanced Technical Skills IBM Oracle International Competency Center September 2013

Four-Socket Server Consolidation Using SQL Server 2008

NETWORKING FLASH STORAGE? FIBRE CHANNEL WAS ALWAYS THE ANSWER!

VEXATA FOR ORACLE. Digital Business Demands Performance and Scale. Solution Brief

BUILD BETTER MICROSOFT SQL SERVER SOLUTIONS Sales Conversation Card

Hewlett Packard Enterprise HPE GEN10 PERSISTENT MEMORY PERFORMANCE THROUGH PERSISTENCE

The Cisco HyperFlex Dynamic Data Fabric Advantage

Dell Microsoft Business Intelligence and Data Warehousing Reference Configuration Performance Results Phase III

Emulex OCe11102-N and Mellanox ConnectX-3 EN on Windows Server 2008 R2

Virtualized SQL Server Performance and Scaling on Dell EMC XC Series Web-Scale Hyper-converged Appliances Powered by Nutanix Software

Top 5 Reasons to Consider

Performance Benefits of NVMe over Fibre Channel A New, Parallel, Efficient Protocol

ADVANCED IN-MEMORY COMPUTING USING SUPERMICRO MEMX SOLUTION

Dell Microsoft Reference Configuration Performance Results

Intel PRO/1000 PT and PF Quad Port Bypass Server Adapters for In-line Server Appliances

Accelerate AI with Cisco Computing Solutions

Deploy a High-Performance Database Solution: Cisco UCS B420 M4 Blade Server with Fusion iomemory PX600 Using Oracle Database 12c

Microsoft Exchange Server 2010 workload optimization on the new IBM PureFlex System

Pivot3 Acuity with Microsoft SQL Server Reference Architecture

FIVE BEST PRACTICES FOR ENSURING A SUCCESSFUL SQL SERVER MIGRATION

IBM System Storage DCS3700

Evaluation of the Chelsio T580-CR iscsi Offload adapter

CAPEX Savings and Performance Advantages of BigTwin s Memory Optimization

Low latency and high throughput storage access

BUILD A BUSINESS CASE

Sun Fire X4170 M2 Server Frequently Asked Questions

Transcription:

QLogic/ Gen 5 Fibre Channel for Database Assessment for Database and Business Analytics Using the information from databases and business analytics helps business-line managers to understand their customer segments, build customer loyalty, and bring faster time to value. EXECUTIVE SUMMARY Fibre Channel SANs are a key component of most large data center storage environments. Large IT organizations have made huge investments in Fibre Channel storage technology to meet their high availability storage and reliability needs. The FCIA calculates that more than $10 billion has been invested in Fibre Channel technology over the last two decades. Fibre Channel continues to remain the dominant storage networking architecture for next-generation enterprise workloads, server virtualization, and cloud architectures. It is known for its ultra-reliability and mission-critical, highperformance capabilities in enterprise data centers. The data center s ability to manage mixed workloads spanning realtime warehousing, storage, and bi-directional online transactional processing (OLTP) for consumer facing sites and social applications that require continual consumer dialogue helps to deliver digital executions. Enterprise data centers still have to offer traditional warehouse support, but being able to execute across all digital channels and having that capability in one environment has been extremely helpful in accelerating business as more and more digital executions are employed. Companies need stability underneath consumer-facing applications. There is a significant amount of social, retail, and point-of-sale (POS) data. And many companies produce Web blogs, which present these challenges: Large volumes of data must be interpreted into actionable insights for clients Tasks ranging from real-time consumer analytics scoring to consumer-specific text mining with Web blog data must be performed Raw data must be quickly interpreted and turned into actionable insight for clients in a timely manner IT administrator managers need to quickly gain value from data warehousing, while supporting diverse analytical requirements and assisting with building future analytical applications. Fast, easy, and predictable implementations reduce risk and enable data centers to achieve rapid strategic value and allow customers to make optimized business decisions. Using the information from databases and business analytics helps business-line managers to understand their customer segments, build customer loyalty, and bring faster time to value. Best-in-class technology delivers the results that enterprise data centers demand. This white paper analyzes the storage performance, reliability, and scalability of the QLogic /Lenovo 6941942, 95Y2379, 8846370, 00Y3337, 00Y3341, 4XB0F286454, 4XB0F28651, 4XC0F28721 16Gb Gen 5 Fibre Channel Adapters from Cavium compared to the previous-generation QLogic 8Gb Fibre Channel adapter.

KEY FINDINGS QLogic 8Gb Fibre Channel Adapters and QLogic/ Gen 5 Fibre Channel Adapters from Cavium continue to provide a high availability ASIC architecture with complete port isolation across its dual-port architecture. During testing, the architecture demonstrated deterministic, predictable, and scalable performance across both ports. The QLogic/ Gen 5 Fibre Channel Adapter delivered three times the transactions double the bandwidth compared to the 8Gb adapter. In a real-life business analytics type environment (TPC-H), the QLogic/ Fibre Channel Adapter completed the same analytical queries in 35 percent less time. The QLogic/ Gen 5 Fibre Channel Adapter delivers double the transaction rate compared to 8Gb Fibre Channel for Oracle OLTP applications. ADAPTER ARCHITECTURE AND DESIGN The different brands of Fibre Channel Adapters tested have different designs for their dual-port adapters. The primary difference is that the QLogic design has separate processor, memory, and firmware for each port on the adapter, for both the 8Gb and 16Gb products. With these independent components in the QLogic design, activity such as high I/O loads, resets, and recoveries and errors that occur on one port do not impact the other port. Each port on the QLogic 16Gb Fibre Channel Adapter is able to achieve full line rate independent of the activity of the other port. QLOGIC/LENOVO 16GB GEN 5 FIBRE CHANNEL ADAPTER The new QLogic/Lenovo Adapters provide several features that are designed for supporting enterprise I/O workloads: Up to 1.2 million IOPS reduce latency in high transaction intensive applications and virtualized environments 16Gbps Fibre Channel per port maximum throughput for high bandwidth SAN traffic Reduced hardware, cabling, and management costs by enabling more applications (VMs) to run on a single server and Fibre Channel port Decreased power and cooling costs by using the fewest PCI Express lanes in PCIe Gen3 environments Overlapping protection domains (OPD) to ensure a high level of reliability as data moves to and from the PCI bus and Fibre Channel network Complete investment protection for legacy 8Gb and 4Gb Fibre Channel infrastructure Future-proof design enables conversion to a 10GbE Converged Network Adapter Improved reliability and diagnostics with support for Brocade ClearLink Enhanced QoS (CS_CTL) prioritizes SAN traffic for end-to-end high performance Simplified deployment and management with fabric pre-provisioning IOPS 1,400,000 1,200,000 1,000,000 800,000 600,000 400,000 200,000 0 Figure 1. Port-Level Traffic Isolation Single to Dual Port Scalability 512 Byte 100% Reads Single Port Dual Port Figure 2. Scalability Across Ports for the QLogic/Lenovo Adapter A series of Iometer runs were performed, first using one port and then both ports. The QLogic adapter scaled linearly as the second port was added to the workload.

QLogic s isolated ASIC design architecture provides the following benefits, which are key requirements for enterprise deployments of Fibre Channel SAN infrastructures: Independent Functionality. Reset or error recovery on one port does not impact the performance of the other port. High Reliability. A firmware crash on one port does not crash the other port. Best-in-Class Security. Isolation at the physical level: Physical Function (PF) for one port cannot access state information (registers, memory info, etc.) of another PF due to physical isolation. Predictable Performance. I/O spikes on one port do not affect the performance of the other port. REAL-WORLD ENTERPRISE WORKLOAD ANALYSIS To test the performance of the QLogic/ and QLogic/Lenovo 16Gb Fibre Channel Adapters in a real-world environment, QLogic ran a data warehousing (TPC-H) workload, not for the purpose of publishing official benchmark results, using Microsoft SQL Server in a Microsoft Windows Server 2012 environment. Workload Overview The read-intensive database workload consisted of a suite of business oriented ad-hoc queries and concurrent data modifications. The queries and the data populating the database had broad, industry-wide relevance. The workload illustrated decision support systems and business analytics that examine large volumes of data, execute queries with a high degree of complexity, and provide answers to critical business questions. PERFORMANCE RESULTS For the TPC-H tests, the time to complete the workloads and the I/O bandwidth rates were measured during the tests. The data was captured using the standard Performance Monitor (PerfMon) tool provided in the Windows Server operating system. As there are large, existing investments in 8Gb Fibre Channel infrastructure today and 16Gb Gen 5 Fibre Channel technology is being adopted, this analysis includes various combinations of performance tests using 8Gb and 16Gb Gen 5 Fibre Channel technology. QLOGIC 16GB GEN 5 FIBRE CHANNEL VS. QLOGIC 8GB FIBRE CHANNEL One of the key comparisons between 16Gb and 8Gb Fibre Channel is the difference in performance. The following charts show the performance improvements provided by the QLogic/ Gen 5 Fibre Channel Adapter. In Figure 3, throughput limiting is shown by the flat spots on the graph, but there is the potential for additional performance beyond the capability of the adapter. The 8Gb Fibre Channel results show this limited throughput in several places, which extends the time required to complete the task. On the other hand, specific queries of the workload in the 16Gb environment completed up to 82 percent faster compared to the 8Gb environment. As shown in Figure 4, the total time to complete a workload is noticeably less using the 16Gb Gen 5 Fibre Channel Adapter. Workload Database Queries The workload consisted of a series of twenty-two unique queries that exercised different sections of the database. Each query placed a different load on the combined CPU, memory, and storage resources. Because each repetition of the workload performed the same work, the time to complete the process was shorter for faster configurations of CPU, memory, and storage. Real-world Variable I/O Rates vs. Synthetic Workloads Synthetic workloads, such as those produced by the Iometer, serve a useful purpose and are designed primarily to exercise the storage system and its interface, with the ability to place a steady workload on the storage system. However, a real database application workload requires varying amounts of CPU, memory, and storage throughout the normal course of activity, depending on the particular transactions being processed. As a result, the I/O activity will vary during the progression of the workload. The TPC-H benchmark provides a more accurate and real-life determination of how choosing the right Fibre Channel Adapter can significantly improve real-world database analytical performance. Figure 3. Throughput Performance Comparison

ORACLE OLTP WORKLOADS OLTP applications are highly transactional, and insert and update intensive. This workload is typical for companies that have large transaction processing applications, such as airline ticketing, large order-entry, and banking applications. To make the benchmarks relevant to today s businesses, QLogic selected the market-leading Oracle Relational Database Management System (RDBMS), running on RHEL 5.8 and simulated using the Oracle-supplied ORION benchmark tool. Figure 5 shows the two-fold performance advantage of QLogic 16Gb Fibre Channel Adapters over QLogic/ Fibre Channel Adapters in the OLTP application environment. Figure 4. Total Time to Execute is Faster Using 16Gb Gen 5 Fibre Channel 16Gb Gen 5 Fibre Channel provides additional bandwidth that can be used by mission-critical database applications to improve performance over 8Gb Fibre Channel. It also supports other I/O-intensive applications, such as increased numbers of VMs running on physical servers, cloud applications, and more. In addition, the deployment of 16Gb Gen 5 Fibre Channel provides the opportunity to reduce the number of cables required within server racks. It can also play a role in consolidating the total number of Fibre Channel Switch ports required in a SAN, because of the increased bandwidth available. Figure 5. Oracle Database OLTP Performance Comparison SUMMARY AND CONCLUSION QLogic/ Fibre Channel infrastructure removes bottlenecks by providing higher bandwidth capability for environments with growing performance requirements, such as from virtualized servers, database applications, and Solid State Drives. True enterprise reliability is ensured by port-level isolation, which fully segregates the Gen 5 Fibre Channel functions of each port on the adapter. QLogic s dual-port design has isolated the functionality for the processor, memory, and firmware for each port on the adapter. The QLogic design incorporates independent components, allowing activity such as high I/O loads, resets, recoveries, and errors that occur on one port to not impact the other port. Each port on the QLogic Host Bus Adapter is able to achieve full line-rate independent of the activity of the other port, unlike competitive offerings. QLogic s Gen 5 Fibre Channel isolated dual-port designed architecture delivers: Independent Functionality Reset or error recovery on one port does not impact performance of the other port Higher Reliability Firmware crash on one port does not crash the other port Better Security Isolation at the physical level; Physical Function (PF) for one port cannot access state information (registers, memory info, etc.) of another PF due to physical isolation Predictable Performance I/O spikes on one port do not affect the performance of the other port Enhanced Scalability The QLogic dual-port adapter has better scalability than competitive offerings when traffic on the second port is added

Test results show that the QLogic adapters outperformed the competitor s adapters; the QLogic adapters provided higher bandwidth and faster completion of database workloads, as well as secure, predictable, and scalable dual-port architecture. The QLogic/ dual-port adapter scales linearly and delivers twice the performance compared to its own single-port adapter. The competition s shared architecture does not have the capacity to scale its dual-port adapter compared to its single-port adapter. The tests found that for the TPC-H workload: ABOUT CAVIUM Cavium, Inc. (NASDAQ: CAVM), offers a broad portfolio of infrastructure solutions for compute, security, storage, switching, connectivity and baseband processing. Cavium s highly integrated multi-core SoC products deliver software compatible solutions across low to high performance points enabling secure and intelligent functionality in Enterprise, Data Center and Service Provider Equipment. Cavium processors and solutions are supported by an extensive ecosystem of operating systems, tools, application stacks, hardware reference designs and other products. Cavium is headquartered in San Jose, CA with design centers in California, Massachusetts, India, Israel, China and Taiwan. Moving from QLogic 8Gb to QLogic 16Gb Gen 5 Fibre Channel improves TPC-H performance by up to 82 percent for some queries and increases the overall TPC-H full run by 35 percent. The QLogic 16Gb adapter delivers double the transactional performance for Oracle OLTP environments. Follow us: Corporate Headquarters QLogic Corporation 26650 Aliso Viejo Parkway Aliso Viejo, CA 92656 949-389-6000 International Offices UK Ireland Germany France India Japan China Hong Kong Singapore Taiwan Israel 2015-2017 Cavium, Inc. All rights reserved worldwide. QLogic Corporation is a wholly owned subsidiary of Cavium, Inc. Cavium and QLogic are registered trademarks or trademarks of Cavium Inc., registered in the United States and other countries. Lenovo and the Lenovo logo are registered trademarks or trademarks of Lenovo Corporation. All other brand and product names are trademarks or registered trademarks of their respective owners. This document is provided for informational purposes only and may contain errors. Cavium reserves the right, without notice, to make changes to this document or in product design or specifications. Cavium disclaims any warranty of any kind, expressed or implied, and does not guarantee that any results or performance described in the document will be achieved by you. All statements regarding Cavium s future direction and intent are subject to change or withdrawal without notice and represent goals and objectives only. 5