存储数据保护Raid技术DDP说明

Staggering amounts of data to store, protect, access
Some sites have thousands of large-capacity drives Drive failures are continual, particularly with NL-SAS drives
10
Dynamic Disk Pools Overview
DDP dynamically distributes data, spare capacity, and parity information across a pool of SSDs
– All drives are active (no idle hot spares) – Spare capacity is available to all volumes
Data Parity Parity Data
RAID 6 (P+Q) – data disks and rotating dual parity
Data Data Data
Data Data Parity Q Parity Data Parity Q Parity Data Parity Q Parity Data Data
All volumes in that group are significantly impacted
24-drive system with 2 10-drive groups (8+2) and 4 hot spares
5
The Problem
The Large-Disk-Drive Challenge
Data is dynamically recreated/redistributed whenever pools grows or shrinks
NetApp Confidential
11
DDP: Simplicity, Performance, Protection
Simplified administration
存储高级 数据保护技术DDP说明
1
SANtricity RAID Protection
Host LUNs Volumes
Volume Groups SSDs
Volume groups
– RAID 0, 1, 10, 5, 6 – Intermix RAID levels – Various group sizes
Easy: No RAID or idle spares to manage— active spare capacity on all drives.
“With Dynamic Disk Pools, you can add or lose disk drives without impact, reconfiguration, or headaches.”
– No RAID sets or hot spares to manage – Data is automatically balanced within pool – Flexible disk pool sizing optimizes capacity utilization
Data is striped across multiple
SSDs.
RAID 1 uses mirroring to write data to two duplicate
SSDs simultaneously.
RAID 10 uses striping to stripe data across a set of
RAID 0 – striped
Data Data Data Data
RAID 1 (10) – mirrored and striped
Data Data
Mirror Mirror
RAID 5 – data disks and rotating parity
Data Data
Data Data
Flexible: Add ANY* number of drives for additional capacity— system automatically rebalances data for optimal performance.
* After the minimum of 11.
Combining effort: All drives in the pool sustain the workload— perfect for virtual mixed workloads or fast reconstruction if needed.
Good for reads, small IOPS, many concurrent IOPS and random I/Os. Parity utilizes small portion of raw capacity.
Good for reads, small IOPS, many concurrent IOPS and random I/Os. Parity utilizes small portion of raw capacity.
Block-level striping with a distributed parity
NetApp Confidential
3
Traditional RAID Volumes
Disk drives organized into RAID groups Volumes reside across the drives in a RAID group
4
Traditional RAID—Drive Failure
Data is reconstructed onto hot spare
Single drive responsible for all writes (bottleneck) Reconstruction happens linearly (one stripe at a time)
mirrored SSD pairs
SSDs operated independently with user data
and redundant information (parity) are striped across the SSDs. The equivalent capacity of one SSD is used for redundant information.
Business Impact
RAID
Time
DDP
40
DDP RAID 6
Business Impact
99% Exposure Improvement
1.3 Days
2.5 Days More than 4 Days
20
0 Hours
96 Minutes
300GB Dr(ivEestima9te00dG) B Drive
SSDs operated independently with user data
and redundant information (dual parity) are striped across the SSDs. The
equivalent capacity of two SSDs is used for redundant
4TB+
Drive transfer rates have not kept up with capacities
Larger drives equal longer rebuilds—anywhere from 10+ hours to several days
6
Dynamic Disk Pools
Large pool of spindles for every volume reduces hot spots
Each volume spread across all drives in pool
Dynamic distribution/redistribution is a nondisruptive background operation
IOPS
IOPS | MB/s
IOPS | MB/s
Advantages
Performance due to parallel operation
of the access
Performance as multiple requests can be fulfilled simultaneously. Also offers the highest data availability
7
ITnrnaodvitaiotinvael DRyAnIDamTieccDhnisokloPgoyols
Balanced: Algorithm randomly spreads data across all drives, balancing workload and rebuilding if necessary.
Host LUNs Volumes Disk Pool SSDs
Dynamic disk pools
– Min 11 SSDs – Max 120 SSDs – Up to 10 disk pools
per system
NetApp Confidential
2
SANtricity RAID Levels
8
Data Rebalancing in Minutes vs. Days
Maintain business
SLAs with a drive1fa2i0lure