Showing posts with label EMC STORAGE. Show all posts
Showing posts with label EMC STORAGE. Show all posts

In the current storage markets and technology, storage tiers are defined by availability, functionality, performance and costs. In fact data can move up and down tiers as time and business required.

Tier "0" is not new in storage market but for implementation purposes it has been difficult to accommodate because it requires best performance and lowest latency. Enterprise Flash disks (Solid State Disks) capable to meet this requirement. It is possible to get more performance for company most critical applications. The performance can be gained through using Flash drives supported in VMAX and DMX-4 systems. One Flash drive can deliver IOPS equivalent to 30 15K RPM hard disk drives with approximately 1 ms application response time. Flash memory achieves performance and the lowest latency ever available in the enterprise class storage array.

Tier “0” application can be closely coupled with other storage tier within Symetrix series for consistency and efficiency, reducing cost of company for manual data layout or data migration from old disk to new high speed disk.

Tier “0” storage can be used to accelerate online transaction processing, accelerating performance with large indices and frequently accessed database tables i.e. Oracle, DB2 databases and SAP R/3. Tier 0 can also improve performance in batch processing and shorten batch processing in windows environments.

Tier “0” storage performance will help application that needs the lowest latency and response time possible. The following applications can get benefited through using Tier 0 storage:

- Algorithmic trading
- Data modeling
- Trade optimization
- Realtime data/feed processing
- Contextual web advertising
- Other realtime transaction systems
- Currency exchange and arbitrage

Tier “0” storage is most beneficial with random read miss application. If random read miss percentage is low, application will not see any performance difference since writes and sequential reads/writes already leverage Symmetrix cache to achieve the lowest possible response time.

For example, if the read hit percentage is high >90 % as compared to read misses, such application like DSS, Streaming media, improvements provided by Tier 0 storage will not likely be enough to be cost-effective.

EMC announced Symmetrix V-Max recently which is based on virtual matrix. Symmetrix V-Max runs on latest Enginuity 5874. The 5874 plateform support Symmetricx V-Max Emulation level 121 and service processor level 102. The modular design of V-Max series Enginuity 5874 ensure flow and integrity between hardware component. Symmetrix Management Console 7.0 (SMC) integrated in service processor. SMC allows you to provision in 5 steps. Enginuity 5874 provides following enhanced feature:

RAID Virtual Architecture :-Enginuity 5874 introduces a new RAID implementation infrastructure. This enhancement increases configuration options in SRDF environments by reducing the number of mirror positions for RAID 1 and RAID 5 devices. This enhancement also provides additional configuration options, for example, allowing LUN migrations in a Concurrent or Cascaded SRDF environment. You can migrate device between raid level/tier level.

Large Volume :-Support Enginuity 5874 increases the maximum volume size to approximately 240 GB for open systems environments and 223 GB for mainframe environments. DMX-4 allows max only 65 GB hyper.

512 Hyper Volumes per Physical Drive :- Enginuity 5874 supports up to 512 hyper volumes on a single drive, twice as much as Enginuity 5773(DMX-3/4). You can improve flexibility and capacity utilization by configuring more granular volumes that more closely meet their space requirements and leave less space unused.

Autoprovisioning Groups :- Auto provisioning Groups reduce the complexity of Symmetrix device masking by allowing the creation of groups of host initiators, front-end ports and storage volumes. This provides the ability to mask storage to multiple paths instead of one path at a time, reducing the time required and potential for error for consolidated and virtualized server environments. You can script and schedule batch operation using SMC 7.0.

Concurrent Provisioning and Scripts :- Concurrent configuration changes provide the ability to run scripts concurrently instead of serially, improving system management efficiency. Uses for concurrent configuration changes include parallel device mapping, unmapping, metavolume form and dissolve from different hosts.

Dynamic Provisioning Enhancements :- Dynamic configuration changes allow the dynamic setting of the BCV and dynamic SRDF device attributes and decrease the impact to hosts I/O during the corresponding configuration manager operations.

New Management Integration :- With Enginuity 5874, the Symmetrix Management Console (SMC) and SMI-S provider are available on the Symmetrix system's Service Processor. This frees host resources and simplifies Symmetrix system management; by attaching the Service Processor to your network, you can open SMC and manage the Symmetrix system from anywhere in their enterprise.

Enhanced Virtual LUN :- With Enginuity 5874, Virtual LUN technology provides the ability to non disruptively change the physical location on disk, and/or the protection type of Symmetrix logical volumes and allows the migration of open systems, Mainframe and System i volumes to unallocated storage or to existing volumes. Organizations can respond more easily to changing business requirements when using tiered storage in the array.
Enhanced Virtual Provisioning Draining:- With Enginuity 5874, Virtual Provisioning support for draining of data devices allows the nondisruptive removal of one or more data devices from a thin device pool, without losing the data that belongs to the thin devices. This feature allows for improved capacity utilization.
Enhanced Virtual Provisioning:- Support for all RAID Types With Enginuity 5874, Virtual Provisioning no longer restricts RAID 5 data devices. Virtual Provisioning now supports all data device RAID types.

The following rules and recommendations CX systems:
1)
You cannot use any of the disks 000 through 004 (enclosure 0, loop 0, disks 0-4) as a hot spare in a CX-Series system.
2) The hardware reserves several gigabytes on each of disks 000 through 004 for the cache vault and internal tables. To conserve disk space, you should avoid binding any other disk into a RAID Group that includes any of these disks. Any disk you include in a RAID Group with a cache disk 000-004 is bound to match the lower unreserved capacity, resulting in lost storage of several gigabytes per disk.
3) Each disk in the RAID Group should have the same capacity. All disks in a Group are bound to match the smallest capacity disk, and you could waste disk space. The first five drives (000-004) should always be the same size.
4) You cannot mix ATA (Advanced Technology Attachment) and Fibre Channel disk drives within a RAID Group.
5) Hot spares for Fibre Channel drives must be Fibre Channel drives; ATA drives require ATA hot spares.
6) If a storage system will use disks of different speeds (for example, 10K and 15K rpm), then EMC recommends that you use disks of the same speed throughout each 15-disk enclosure. For any enclosure, the hardware allows one speed change within an enclosure, so if need be, you may use disks of differing speeds. Place the higher speed drives in the first (leftmost) drive slot(s).
7) You should always use disks of the same speed and capacity in any RAID Group.
8) Do not use ATA drives to store boot images of an operating system. You must boot host operating systems from a Fibre Channel drive.

Veritas Disk Group Configuration Guidelines:-

1) Use multiple Disk Groups—preferably a minimum of four; place the DATA, REDO, TEMP, UNDO, and FRA archive logs in different (separate) Veritas Disk Groups

2) Optimally, use RAID 1 for tier 1 storage

3) Configure Disk Groups so that each contains LUNs of the same size and performance characteristics

Distribute Veritas Disk Group members over as many spindles as is practical for the site’s configuration and operational needs

Data Striping and Load Balancing:-

1) Veritas software level striping: layout=stripe ncols=10 stripeunit=128k

2) Storage-level striping further parallelizes the individual I/O requests within storage

3) Using the storage RAID protection, the amount of I/O traffic (host to storage) is reduced

4) EMC PowerPath should be used for load balancing and path failover

5) Use of metavolumes is optional

a) There is an upper limit on the number of LUNs that a host can address—typically ranging from 256 to 1,024 per HBA.

b) When these limits are reached, metavolumes are a convenient way to access more Symmetrix hypervolume.


Volume Configuration with Veritas (Hypervolumes):


1) Created 5 Veritas Disk Groups

2) Five Disk Groups are used because this number provides better granularity for performance planning

3) The use of five Disk Groups also provides increased flexibility when planning for the utilization of EMC replication technology within the context of an enterprise-scale workload

4) Having five Disk Groups permits the placement of data onto different storage tiers if desired

Hypervolume

Purpose

Size

1

DATA

32 GB

2

REDO

400 MB

3

DATA

32 GB

4

FRA

30 GB

5

TEMP

10 GB

6

FRA

30 GB

Average Disk Utilization for Raid 1 should be below 150 IOPS per disk and should not go above 200 IOPS per disk as per below configuration.

-- 80 physical disks (40 mirrored pairs)

-- 240 devices visible to Veritas

-- Average user count ~ 16,000

About Me

My photo
Sr. Solutions Architect; Expertise: - Cloud Design & Architect - Data Center Consolidation - DC/Storage Virtualization - Technology Refresh - Data Migration - SAN Refresh - Data Center Architecture More info:- diwakar@emcstorageinfo.com
Blog Disclaimer: “The opinions expressed here are my personal opinions. Content published here is not read or approved in advance by EMC and does not necessarily reflect the views and opinions of EMC.”
EMC Storage Product Knowledge Sharing