SAN clarity in a virtual cloud

Posted on February 02, 2009

RssImageAltText

As the number of virtual servers sharing the physical FC HBA ports of a VOE server increase, SAN fan-out is no longer just a switch issue: It becomes a server HBA issue that mandates holistic management of SAN infrastructure from switchesAs.

By Jack Fegreus

For IT administrators, all of the popular HBAs, whether from Brocade, Emulex or QLogic, provide a GUI-based management application: Brocade Host Connectivity Manager (HCM), QLogic SANsurfer, and Emulex HBAnyware. Each of these applications has a very similar hierarchy of managed objects, which makes what each application can monitor and manage very similar. The important issue then becomes the ease and quickness with which IT administrators manipulate those managed-object hierarchies when performing SAN maintenance and problem discovery tasks.

At issue is how well these tools empower IT administrators to quickly assess SAN traffic problems, accurately correlate problems with the performance of business applications, and resolve processing disruptions. That's why SAN managers view HBA management within the context of holistic fabric management. How well HBA utilities manage their object hierarchies within a unified fabric context directly impacts productivity of IT administrators.

The importance of the impact that these HBA utilities have on system and storage administrators is underscored by an important IT heuristic: In the first year of operation, operating costs associated with managing storage hardware are often greater than the capital costs of acquiring that hardware. While many think of Fibre Channel (FC) HBAs as commodity items, differences in the design and behavior of the HBA utilities will impact workflow and productivity for IT administrators.

To support business processes, IT must be able to quickly diagnose and resolve infrastructure events and issues that involve interdependencies among storage devices, hosts, and SAN switches. To simplify SAN connectivity, Brocade's Data Center Fabric (DCF) architecture provides an end-to-end framework that logically unifies SAN HBAs, switches, and directors. The key component of Brocade's DCF architecture, Data Center Fabric Manager (DCFM) Enterprise, is the primary tool used by many SAN managers to assess data center fabrics—from storage ports to HBAs attached to either physical or virtual servers. DCFM's unified perspective provides administrators a significant advantage in maintaining, optimizing, and auditing a SAN fabric.

That unified perspective is all the more important given the explosive growth in the adoption of Virtual Operating Environments (VOEs). The limitations of software I/O profiles and the practice of isolating critical applications on dedicated servers left SAN fabrics with multiple servers for every storage device. Dubbed the fan-out ratio, with a high number of servers to storage devices, throughput at storage devices became a key bottleneck metric. Consolidation via server virtualization, however, radically changes that SAN topology.

With VOE servers hosting eight or more virtual machines (VMs), an HBA in a VOE server can no longer be regarded as a simple commodity product. As the number of virtual servers sharing the physical FC HBA ports of a VOE server increase, SAN fan-out is no longer just a switch issue: It becomes a server HBA issue as well.

By extending the DCFM SAN management tool to HCM, the Brocade management tool for HBAs, Brocade also extends a well-established fabric management paradigm to the host side. As a result, IT administrators can apply Brocade's unique Quality of Service (QoS) Traffic Prioritization, which comes entirely out of the fabric, to each VM. Through unified host- and fabric-based Adaptive Networking services, Brocade HBAs provide support for policy-based data management and application service levels.

To assess the functionality and ease of use of server HBAs, openBench Labs focused on the ease with which an initial working SAN fabric can be configured and managed. Initial setup of new infrastructure is very important within a small- to medium-size enterprise (SME) environment as the impact of introducing new technology on a small IT staff is proportionally more disruptive. While the ease of initial setup remains important for new infrastructure, ease of setup pales in comparison to the question of how well any new infrastructure will help lower ongoing IT operating costs.

For the foundation of our infrastructure, we set up two Dell PowerEdge 1900 servers. Each server featured 4GB of RAM and a quad-core Intel Xeon E5335 processor. One server ran Microsoft Windows Server 2003, while the other ran Windows Server 2008 with Hyper-V, which in turn supported multiple Windows Server 2008 VMs. We installed three single-port 8Gbps HBAs in each server: A Brocade 815, a QLogic QLE2560, and an Emulex LPe12000. We then installed the GUI-based management application, which is independent of the HBA's throughput speed, for each HBA family: Brocade's Host Connectivity Manager (HCM), QLogic's SANsurfer, and Emulex's HBAnyware.

To reflect the new edge-driven SAN fabric technology, and provide sufficient I/O throughput to meet the demands of our 8Gbps infrastructure, openBench Labs employed a Texas Memory Systems RamSan-400 solid-state disk (SSD) array that was configured with four 4Gbps FC controllers, each capable of handling 100,000 IOPS. We then provisioned one port on each controller with a target LUN. This topology represents a worse-case scenario for encountering potential SAN bottlenecks, as four 4-Gbps data paths from the RamSan SSD converge on each 8Gbps server HBA port.

The small IT staff at an SME site makes the installation and optimization of a SAN a daunting hurdle and the time taken by IT administrators to accomplish diagnostic and maintenance tasks all the more important. How quickly can a SAN fabric be set up and working? How easy is it for system/storage administrators to keep a SAN functioning optimally? Will greater levels of resource abstraction lead to more administrator confusion? These questions shape the SAN evaluation criteria for SME sites.

To install each HBA, IT administrators begin by going to the vendor's web site in order to download the latest versions of all the required software, which includes drivers, firmware, boot code, management software and on-line documentation. It is here that the out-of-box experience for Brocade HBA users diverges from users of QLogic and Emulex HBAs. Installation should be a routine task that borders on the trivial. Only the Brocade HBAs, however, surpassed our expectations.

The Brocade HBA offers one-button simplicity starting right from the initial Web download. Brocade simplifies installation of all of its HBAs via a single foolproof installation process that automatically installs the correct HBA drivers, updates to HBA firmware, and management software. An IT administrator has only two options from which to choose: Either download and burn a complete OS-specific CD image or download and burn a larger multi-OS DVD image.

In sharp contrast, QLogic and Emulex follow traditional practices of FC resource vendors. At each of these vendor's Web sites, HBA software is broken out into lists of multiple independent options, each of which must be selected, downloaded, and installed. That means IT administrators must carefully examine the state of each HBA with respect to firmware, drivers, boot code, and management software.

While the installation of HBA management software is important, installation is just a one-time step towards the end goal of maintaining an optimally functioning SAN and meeting any service level agreements (SLAs) with client departments. How well IT is able to achieve that goal is in part dependent upon how quickly IT administrators are able to diagnose and resolve SAN performance issues. As a result, the value of HBA management software for IT will be determined by how HCM, HBAnyware, and SANsurfer present and manipulate their managed object hierarchies.

To ensure that administrators will perform critical problem-resolution tasks consistently, they should always know what steps to take next with their tool suite. That requires management tools that are easy to learn, easy to remember, and intuitive to use. To support such ease-of-use, HBA management software requires a user interface (UI) that avoids clutter and clarifies information to keeps things simple.

Launching HBAnyware or SANsurfer, administrators are immediately confronted by the UI conundrum that ‘more is less,' when it comes to clarity. All the HBA utilities, including Brocad'se HCM, leverage LAN connectivity to manage any available host's HBA. To facilitate this single-pane-of-glass paradigm, each HBA management utility places a SAN navigation panel along the left-hand side of the GUI. The usefulness of these navigation panels, however, is limited to inspection rather than interaction.

HBAnyware can be configured to poll a range of LAN addresses at start up for the presence of Emulex HBAs. This can be a lengthy process that provides no SAN context, such as zone membership. More importantly, no SAN navigation panel can extend interactive management of HBA features to multiple simultaneous hosts. Since the managed-object hierarchy of each HBA utility starts with a host server, IT administrators can interactively manage one host at a time.

On the other hand, SANsurfer exploits LAN connectivity to launch multiple batch commands that update basic HBA configuration parameters on multiple hosts sequentially via background processes. This is a basic first step towards automating a common enterprise IT management practice of tuning an initial HBA interactively and then using a command line interface to script a batch process to apply that configuration to all other HBAs.

SANsurfer also adds an elaborate topology map that can be displayed for the SAN—all servers to which SANsurfer has been connected—or for any single server. While the end-to-end path data contained in these maps is vital, that information is siloed in this one menu and not actionable from other screens.

Nonetheless, there is renewed interest in providing IT administrators with unified management software and one-button administration of IT resources to simplify management and lower operational costs. Senior IT decision makers now focus on the need to acquire resource management software featuring consistent easy-to-use GUIs. The central premise is to utilize classic quality-improvement techniques on IT processes.

The most important tasks of IT administrators, however, involve problem discovery and analysis, and these tasks are not well defined. That means any plan to transform IT into an internal service provider capable of executing processes consistently, automatically, and correctly every time hinges on creating an environment in which administrators make similar assessments and conclusions when correlating SAN traffic data with service-level policies.

With consistency a key aspect of quality control, an important step in becoming a successful service provider is the adoption of easy-to-use management tools that present data in a consistent format that is easy to understand. With all Brocade software built on top of the company's DCF architecture, all Brocade management offerings provide IT with unified touch points throughout a SAN. More importantly, Brocade's DCF architecture provides the blueprint for the company's HBAs to lay a foundation that will include servers within an end-to-end service paradigm.

To meet those objectives, Brocade's HCM utilizes a construct commonly found in the GUIs of SAN switches: a global option to use descriptive device names in place of hexadecimal worldwide name (WWN) IDs throughout all of the HCM screens and menus. Brocade HCM is unique in the application of this technique to make HBA management software easy to learn, easy to remember, and intuitive. This GUI feature of HCM makes it easier for administrators to quickly launch HCM and to intuitively obtain complete and actionable information.

 

For our local host, we used HCM to associate intuitively descriptive names for SAN resources in our test bed in place of unique hexadecimal WWN names. We then set a global option to display our names in place of WWN names. That action changed the navigation panel and propagated through all HCM menus.

HCM further empowers IT administrators by simplifying menu structures to reduce tedious navigation and optimize the display of information. Just as in managing an FC switch, Brocade HCM minimizes the number of menus and maximizes the amount of information displayed on each screen. For example, all configurable HBA port options are displayed on a single properties menu page. To clarify the relative importance of such a large amount of data, HCM screens have three panels: one for navigation, one for data, and one for event log alerts. This combination enhances the ability to quickly discover anomalies in HBA operation.

Just as in managing an FC switch, Brocade HCM minimizes the number of menus and maximizes the amount of information displayed on each screen. All configurable HBA port options are displayed on a single properties menu page. To clarify the relative importance of the data, screens have three panels for navigation, data, and event logs. This enhances the ability to quickly discover anomalies in HBA operation. For ease of use, there are just four options in the HCM menu for an HBA port.

More importantly, server virtualization is radically transforming fundamental heuristic regarding I/O between servers and storage. Long-standing metrics for SAN fabric topology regarding the ratio of server to storage connections require a new level of sophisticated planning. With servers hosting multiple virtual machines, the role of a server HBA by necessity begins to take on the characteristics of a switch, which is a strength of Brocade. The company's HBAs are capable of extending full QoS support to virtualized workloads on host VMs throughout the fabric in a manner that inherently supports and guarantees any SLA associated with business processes, even as that VM is arbitrarily migrated around the data center, from one VOE server to the next.

Jack Fegreus is CTO of openBench Labs.

********

OPENBENCH LABS SCENARIO

UNDER EXAMINATION: HBA management software

WHAT WE TESTED

Brocade 815 8Gbps HBA
Brocade Host Connectivity Manager (HCM)

HOW WE TESTED

Emulex LPe12000 8Gbps HBA
Emulex HBAnyware

QLogic QLE2580 8Gbps HBA
QLogic SANsurfer

(2) Dell 1900 PowerEdge Servers
-- Quad-core Xeon CPU
-- 4GB RAM
-- Windows Server 2003 Server 
-- Windows Server 2008
-- Hyper-V

Brocade 300 8Gbps switch

Texas Memory Systems RamSan 400
-- (4) dual-port 4Gbps HBAs
-- 32GB RAM

KEY FINDINGS

-- HCM provides single installation download that includes all software and firmware for a unified installation to accelerate the-out-of-box experience.

-- Brocade's DCF architecture unifies common constructs used in HBA and switch management software.

-- Brocade HBA and switch management tools minimize menus and provide an event log alerts panel to facilitate SAN management as a service.


Comment and Contribute
(Maximum characters: 1200). You have
characters left.