FE Basics
FE Basics
All flash storage array
Scale out solution - add more nodes to increase power
x-brick - 2 storage controllers / DAE / 2 Battery backup units
There are 2 generations of XtremIO, the first generation being designated X1 and the second generation being X2. This is not to be confused with the numbering of the Xbricks in a multi-brick cluster.
- 2 Infini band switches are added once scaled out from 1 x-brick
Replacements are all script based, there are no simple hot swap components.
DAE controllers (LCC) - script based replacement
- If a controller fails it will report the storage controller as failed as well, due to communication breakdown between the two.
Storage controllers - 1U supermicro units running CentOS
- Gen2 controllers have iSCSI ports, Gen1 does not.
- SAS connections go to the DAE
DAE 25 SSD's, always fully loaded
- Disk replacement is run with a script and once started, there is no dummy replacement. The machine will track the serial number and will not allow for a dummy replacement
Infiniband switches only used with multiple x-brick clusters
Configuration for x-brick cluster is 1, 2, 4, 8
Able to monitor and control several arrays from one management server. Always double check how many clusters are controlled by the XMS
XMS functions like an HMC, purely management
- Originally a 1U server
- Today runs as a VM
- XMCLI lives here
- Graphical interface
- Can not manage an Extreme I/O without an XMS
OVA is freely available for the XMS, no contract is needed (used to stand up a virtual XMS)
admin user is only for the gui
xmsadmin is used to log in through ssh
Next user: tech
- tech port is not accessible after a certain code level | every tech port has the same IP, DO NOT connect them via a HUB or put on the network*
user: xinstall
GUI is needed to configure ExpressConnect Monitoring
Notifications - Events - Errors
Serial number should be added into Contact details of email alerting
Hardware tab shows serial number (Older code names serial number PSNT)
- Hardware Tab
- Visual picture of the system
- X1 and X2 nomenclature is numbering the bricks, not the generation
- Interactive view of components
- Part numbers can also be read from the GUI
Only 2 high density units can be managed from 1 XMS
Local disks are disks in the storage controllers and not the DAE
Audit - Obtained through XMS (Xtremio Management Server)
- Collect a Log Bundle
Logs
- System event log -
- an intel based event log (error, fault, critical)
- ipmitool_fru_list (...\latest\X1-SC1\system\ipmitool)
- lists the FRU part numbers
Password to enter BIOS after pressing F6: emcbios (might be all caps)
Disk numbering starts at 0 ( 0 - 24, [8 disks | 9 disks | 8 disks] )
Old GUI interface has an arrow to the far right which can show more details regarding the items on the page you're viewing
how is the network connected.

System Overview:
The XtremIO Storage Array is an all-flash system, based on a scale-out architecture.
The system uses building blocks, called X-Bricks, which can be clustered together to
grow performance and capacity as required, as shown in Figure 2.
The system operation is controlled via a stand-alone dedicated Linux-based server,
called the XtremIO Management Server (XMS). Each XtremIO cluster requires its own
XMS host, which can be either a physical or a virtual server. The array continues
operating if it is disconnected from the XMS, but cannot be configured or monitored.
XtremIO's array architecture is specifically designed to deliver the full performance
potential of flash, while linearly scaling all resources such as CPU, RAM, SSDs, and
host ports in a balanced manner. This allows the array to achieve any desired
performance level, while maintaining consistency of performance that is critical to
predictable application behavior.
The XtremIO Storage System provides a very high level of performance that is
consistent over time, system conditions and access patterns. It is designed for true
random I/O.
The system's performance level is not affected by its capacity utilization level,
number of volumes, or aging effects. Moreover, performance is not based on a
"shared cache" architecture and therefore it is not affected by the dataset size or data
access pattern.
Due to its content-aware storage architecture, XtremIO provides:
• Even distribution of data blocks, inherently leading to maximum performance and
minimal flash wear
• Even distribution of metadata
• No data or metadata hotspots
• Easy setup and no tuning
• Advanced storage functionality, including Inline Data Reduction (deduplication
and data compression), thin provisioning, advanced data protection (XDP),
snapshots, and more