HP Extended Cluster for RAC Continuous availability with the flexibility of virtualization

ManualsBrandsHP ManualsSoftwareHP Serviceguard Extension for RAC (SGeRAC)

HP Extended Cluster for RAC

Continuous availability with the flexibility of virtualization

Executive summary............................................................................................................................... 2

Business dilemma ................................................................................................................................3

The solution......................................................................................................................................... 3

Context for the solution ..................................................................................................................... 3

Solution overview............................................................................................................................. 4

Solution components......................................................................................................................... 4

HP Extended Cluster for RAC............................................................................................................. 7

The tests ............................................................................................................................................. 8

Testing methodology ........................................................................................................................ 8

Test architecture............................................................................................................................... 9

Supported hardware configuration ................................................................................................. 9

Supported software configuration................................................................................................. 10

Test descriptions............................................................................................................................. 10

IPC test description ..................................................................................................................... 10

I/O test description .................................................................................................................... 10

OLTP test description................................................................................................................... 10

Failover test description............................................................................................................... 11

Test results and tuning..................................................................................................................... 11

The next steps.................................................................................................................................... 12

Solution flexibility .............................................................................................................................. 12

Conclusions ...................................................................................................................................... 13

References ........................................................................................................................................ 13

For more information.......................................................................................................................... 14

Summary of content (14 pages)

PAGE 1
HP Extended Cluster for RAC Continuous availability with the flexibility of virtualization Executive summary............................................................................................................................... 2 Business dilemma ................................................................................................................................ 3 The solution.................................................................................................................
PAGE 2
Executive summary The concept of optimized resource utilization has moved to the forefront of every IT organization’s agenda. The maturation of the clustering market has forced hardware vendors to differentiate their products to gain a competitive edge. Consequently, these vendors have begun to offer some variant of virtualization as the latest trend in high-availability capabilities. Traditionally, every IT manager was confronted with the dilemma of having to balance risk and cost.
PAGE 3
Business dilemma If a group of CIOs was asked to identify their primary cause of stress, the majority would answer “controlling IT risks and costs.” Indeed, many would say that this is the most important challenge within a CIO’s charter. In striving to balance risk management and fiscal responsibilities, every IT manager is faced with a difficult choice.
PAGE 4
Solution overview At the center of the “risk versus cost” challenge is the question “How can I increase application availability and resiliency while also aggressively managing costs?” The concept of using multiple data centers, with replicated system configurations, to provide fallback capabilities through redundancy has emerged as the preferred solution. This approach minimizes the impact of the total loss of one data center, but it achieves this through the gross underutilization of IT assets.
PAGE 5
Figure 1. HP Extended Cluster for RAC—100 km Cache Fusion is a key component of RAC that uses cluster interconnect technologies to facilitate virtual buffer sharing through the use of direct memory accessing. The Cache Fusion architecture creates a single virtual cache across all the nodes of the cluster. The resulting single view of all buffer caches minimizes disk I/O by allowing any database request to be served by any node in the cluster.
PAGE 6
The HP Extended Cluster for RAC architecture relies on the same components as the collocated system configuration, but it introduces several additional key technologies. System-to-system communication is now facilitated by the addition of a pair of Dense Wavelength Division Multiplexing (DWDM) devices connected by dark fiber. Database replication is achieved through host-based software mirroring, and RAC synchronizes the cache using Cache Fusion in the normal manner. Figure 2.
PAGE 7
The complex tasks of managing and linking business priorities to the appropriate resource allocations are handled by the highly integrated components of the VSE portfolio of solutions: • HP Serviceguard and SGeRAC • HP Partitioning Continuum • HP-UX Workload Manager (WLM) and HP Global Workload Manager (gWLM) • HP Instant Capacity and Temporary Instant Capacity HP SGeRAC brings data protection, application availability, and ease of management to servers and server partitions to create an enterprise cluster
PAGE 8
Utilizing its intelligent policy engine, the WLM component of the VSE allows the real-time allocation of assets throughout the virtual resource pool—yielding enhanced server utilization, increasing return on IT investment, and dramatically improving the enterprise’s ability to accommodate business volatility. If an entire data center is lost, the remaining data center continues to function during the rerouting of users to the functioning environment.
PAGE 9
Figure 3. Two-data center Extended Cluster for RAC—up to 100 km currently-supported configuration Test architecture The test configuration for the 100-km evaluation followed the supported configuration for all subsequent SGeRAC implementations. Supported hardware configuration • Two-node cluster (PA-RISC or HP Integrity servers, not mixed). – A two-, four-, six- or eight-node cluster is supported up to 10 km with VERITAS Cluster Volume Manager (CVM).
PAGE 10
• Cluster arbitration: dual cluster lock disks (Logical Volume Manager (LVM) volume groups) or Quorum Server. – Note: Three-site configuration is supported using Quorum Server to prevent split-brain, the condition in which two equal-sized subgroups of cluster nodes re-form a cluster independent of each other. • Nortel OPTera DWDM switches were used for initial testing and certification. Supported software configuration • Operating system: HP-UX 11.11 or HP-UX 11i v2.
PAGE 11
complexity that were executed online and queued for deferred execution. TPC-C is widely acknowledged as providing one of the most realistic loading simulations within a comprehensive computing environment. Failover test description Multiple tests were performed to simulate the wide variety of scenarios that could impact a data center.
PAGE 12
traffic could be separated from other TCP/IP and Fibre Channel traffic. Moreover, adding Ethernet and Fibre Channel I/O cards to the servers better distributed the I/O loads and resulted in increased performance.
PAGE 13
Conclusions HP has successfully shown the viability of the Extended Cluster for RAC in a virtualized environment over distance. In particular, HP demonstrated the feasibility of a SGeRAC configuration deployed across two discrete data centers separated by 100 km. The 100-km distance significantly diminishes the likelihood of a single disaster impacting more than one data center at any one time.
PAGE 14
For more information • http://www.hp.com/go/ha • http://www.hp.com/go/virtualization © 2005 Hewlett-Packard Development Company, L.P. The information contained herein is subject to change without notice. The only warranties for HP products and services are set forth in the express warranty statements accompanying such products and services. Nothing herein should be construed as constituting an additional warranty. HP shall not be liable for technical or editorial errors or omissions contained herein.