Pass the Pure Storage FAIS FlashArray-Implementation-Specialist Questions and answers with CertsForce

The FlashArray//XL series (such as the XL130R5) utilizes a modern backend connectivity architecture for its expansion shelves, specifically the DirectFlash Shelf (DFS). Unlike older generations that might have used SAS (Serial Attached SCSI) for shelf connectivity, the //XL architecture relies on high-speed Ethernet with RoCE (RDMA over Converged Ethernet) to communicate with external media shelves. This ensures that the NVMe drives in the shelf perform with the same low latency as those in the head unit.

To attach a DirectFlash Shelf to a FlashArray//XL130R5, the chassis must be populated with specific PCIe interface cards designated for shelf back-end connectivity. The correct part for this is the FA-XL-100G Ethernet/RoCE 2-Port card. This card provides the necessary 100 Gigabit Ethernet bandwidth and RoCE protocol support required for the NVMe-oF (NVMe over Fabrics) backend fabric that Pure Storage uses.

It is crucial to distinguish this from host-facing cards. While an "iSCSI/RoCE" card exists, the shelf connectivity specifically utilizes the "Ethernet/RoCE" designation in the BOM to differentiate backend fabric ports from frontend host ports. The 200G options are generally reserved for host connectivity or inter-array clustering in specific high-performance setups, but the standard validated card for connecting the DFS to the //XL130R5 is the 100G Ethernet/RoCE adapter. Verifying this line item on the BOM prevents onsite delays where the engineer might otherwise find themselves with incompatible ports for the expansion shelves.

Drive or shelf evacuation is a resource-intensive, background data mobility process within the Purity operating system. When an Implementation Engineer issues an evacuation command via the CLI (e.g., puredrive evacuate) or the GUI, the array begins transparently reading data blocks from the targeted DirectFlash Modules, recalculating parity, and destaging those blocks onto the remaining free capacity in the chassis or a connected swing shelf.

According to strict Pure Storage Implementation guidelines, only one evacuation process can be actively running on a FlashArray at any given time . The system architecture does not support queuing multiple, simultaneous drive or shelf evacuations, nor does it allow an administrator to arbitrarily inject new drives into an active evacuation job.

If an engineer attempts to issue a second evacuation command while the first is still running, the Purity operating system will immediately reject the command and return an error stating that an evacuation is already in progress. While it is technically possible to cancel an evacuation, doing so forces the array to halt its progress and leaves the data fragmented across the old and new drives, wasting time. The only supported and safe method is to let the current evacuation reach 100% completion, physically remove the evacuated drives, and then initiate a completely separate, new evacuation job for the second data pack.

Understanding the default network port assignments on a standard 3U Pure Storage FlashArray (which encompasses models like the //X10, //X20, //X50, //X70, and //X90) is a fundamental requirement for any Implementation Engineer. The rear of the controllers features a standardized set of integrated Ethernet ports that are logically predefined by the Purity operating system upon factory initialization.

The first two ports, explicitly labeled eth0 and eth1 , are 1GbE Base-T copper ports. These are strictly reserved and dedicated by default for management traffic (GUI, CLI, SSH, API, and Call Home telemetry to Pure1). They are not designed to handle high-throughput storage workloads.

The next two ports, eth2 and eth3 , are high-speed 10GbE/25GbE optical/Twinax ports. By default, Purity provisions these specifically for asynchronous and synchronous replication traffic (including ActiveCluster), as well as IP-based block storage protocols like iSCSI if the customer is not using Fibre Channel. Utilizing eth2 and eth3 ensures that heavy data mobility workloads have the required bandwidth and are physically isolated from lightweight management traffic. Ports like eth4 and eth5 (if present via PCIe expansion cards) are typically configured manually for additional frontend host I/O or File Services, rather than acting as the default replication interfaces.

DirectFlash Shelves (DFS) connect to the FlashArray controllers using high-speed protocols (typically RoCE - RDMA over Converged Ethernet) that require high-fidelity signal integrity. Due to the high bandwidth (50Gb or 100Gb speeds) and low latency requirements of the NVMe-oF (NVMe over Fabrics) protocol used for backend connectivity, the physical cabling length is strictly limited.

Pure Storage officially supports a maximum cable length of 3 meters for connecting DirectFlash Shelves to the controller or for daisy-chaining shelves (where supported). Cables longer than 3 meters (such as 5m or 7m) introduce signal attenuation and latency that can destabilize the backend fabric, leading to CRC errors, path flapping, or drive disconnections.

Implementation Engineers must ensure that the rack layout allows the shelves to be placed within this 3-meter radius of the controllers. Typically, shelves are racked immediately above or below the controller chassis to minimize cable run distance. Attempting to span across multiple racks using longer, unsupported cables will result in an unsupported configuration and likely immediate I/O errors.

=========

After a complex operation like a Hardware Non-Disruptive Upgrade (HWNDU), the Purity health services may occasionally stall or report generic errors like "health not responding." Standard alert commands (purealert list) might be empty or show generic "service unavailable" messages because the alerting service itself depends on the health system.

To troubleshoot this, the Implementation Engineer should dig deeper into the system's internal message log using puremessage list --open --hidden .

puremessage accesses the raw message bus of the array, which captures lower-level events than standard alerts.

--hidden is the critical flag here; it reveals internal system messages that are typically suppressed from the standard user view to avoid noise.

These hidden messages often contain the specific error codes or service failure reasons (e.g., "timeout waiting for daemon X") that explain why the health status is hanging. Providing this output to Pure Support significantly accelerates the root cause analysis. purearray diagnose is not a standard command for this purpose, and purealert watcher is for configuring notification recipients, not viewing log contents.

When upgrading from a FlashArray//X to a FlashArray//XL, the hardware migration often involves handling DirectMemory Modules (DMMs) differently than standard data drives. DMMs are high-performance cache modules that reside in the controller chassis.

In this specific scenario—migrating a fully populated //X90R3 to an //XL that already has its own set of DirectFlash Modules (DFM-Ds)—the DMMs from the old chassis need to be moved to the new chassis to preserve their cache function or be properly decommissioned.

The correct procedure is to Evacuate DMMs as a datapack then install into any slot in //XL .

DMMs cannot be simply "hot-swapped" randomly while the system is live in a way that disrupts the cache map.

They must be logically grouped and evacuated (conceptually "vacated" of active data) so they can be safely removed from the old chassis.

Once removed, they can be installed into the new //XL chassis. The //XL architecture supports DMMs in specific slots, and Purity will detect and re-incorporate them into the cache pool.

This ensures that the expensive SCM (Storage Class Memory) hardware is reused in the new system without causing data integrity issues during the transition.

=========

The output "Ping successful with CCM" is a specific success message returned by the puresupport test or purearray test connectivity checks. CCM stands for Cloud Connection Manager , which is the internal service or endpoint responsible for mediating the secure connection between the local FlashArray and the Pure1 cloud management platform.

When an Implementation Engineer sees this message, it confirms that the array can successfully resolve and reach the Pure1 infrastructure over the internet (specifically the pure1.purestorage.com or associated regional endpoints). This validates that:

DNS is functioning correctly (resolving the CCM hostname).

Firewall rules are permitting outbound HTTPS (port 443) traffic.

The array's management interface is routing correctly.

This connection is vital for "Phone Home" logs, Remote Assist sessions, and fleet management via the Pure1 mobile app or dashboard. It is distinct from the Fusion Fleet Coordinator (which manages fleet logic) and the cross-controller interconnect (which is internal hardware communication).

=========

During complex maintenance procedures like a controller upgrade or replacement (puresetup replace), it is often necessary to verify the physical hardware identity of the chassis to ensure compatibility with the new controllers or software image.

The command hwconfig --model is the specific CLI tool used at the engineering/boot level to return the chassis model string (e.g., FA-X50R3 or FA-XL170). This confirms the hardware platform identity.

hwconfig --all would dump a massive amount of verbose configuration data, making it difficult to quickly identify just the model.

pureversion -a displays the version of the Purity operating system software, not the physical hardware model of the chassis.

Therefore, hwconfig --model is the correct and most efficient command for the Implementation Engineer to validate the hardware platform identity during the upgrade workflow.

=========

For a Pure Storage FlashArray to fully utilize its predictive support capabilities, it must maintain a persistent, secure outbound connection to the Pure1 cloud infrastructure. This allows the array's Callhome Connection Manager (CCM) to transmit telemetry data, hardware alerts, and heartbeat signals. However, in many enterprise environments, storage management networks do not have direct, unfiltered access to the public internet. Instead, all outbound HTTP/HTTPS traffic must be routed through a corporate proxy server.

To facilitate this, the Implementation Engineer must configure the FlashArray to tunnel its Call Home traffic through the customer's proxy. The officially supported Purity CLI command to achieve this is purearray setattr --proxy https:// < proxy_address > : < port > .

By executing this command, the system modifies its global network attributes. Purity immediately updates the internal routing daemon, instructing it to encapsulate all outgoing Pure1 management traffic and direct it to the specified proxy IP or hostname on the designated port (e.g., port 8080 or 3128). Options B, C, and D are fabricated commands that do not exist within the Purity CLI framework. Once the proxy is set, the engineer should always validate the configuration by running purearray test phonehome to ensure the proxy is properly allowing the traffic to pass through to the Pure Storage cloud endpoints.

Before performing a physical card addition (I/O expansion) on a specific controller, it should be in the Secondary state.

The procedure for adding hardware to a FlashArray is a sequential, non-disruptive process. You cannot add a card to the Primary controller because it is actively handling host I/O; opening it would cause a service outage. Therefore, the Implementation Engineer must first verify the cluster health and, if necessary, perform a manual failover (pureadm make --secondary) to ensure the target controller is Secondary .

Once the controller is Secondary (passing no I/O), the engineer proceeds to stop the Purity software (pureadm stop) and/or power down the controller to safely install the PCIe card. While the physical work happens when the controller is powered off/inactive, "Secondary" is the correct operational starting state required to begin the maintenance workflow safely. "Standby" is often used to refer to a controller that is powered on but not running Purity, which is a subsequent step, not the initial prerequisite state relative to the cluster role.