[不断更新]存储上的一些基本概念

术语	展开或缩写	原文解释	翻译和解释	备注
Block		A unit of contiguous fixed-size space on a disk drive.	磁盘驱动器上固定大小的空间连续的一个单元	一般format时, block的大小是512个字节, 即0.5KB
Strip		A group of contiguously addressed blocks within each disk of a RAID set.	RAID集合中的一块盘中的地址连续的block的一个组.	即Stripe element, 其大小推荐是128个blocks, 即64KB. 最好不要修改这项指标.
Stripe		A set of aligned strips that spans all the disks within a RAID set.	跨RAID集合里的所有盘的排整齐的strips的集合.	Stripe Element * data disks = Stripe size.
LUN	Logical Unit Number	An identifier of a logical storage unit presented to a host for storing and accessing data on those units.	呈现给宿主机用于存放和访问数据的一个逻辑上的存储单元
Volume			卷. 人们把硬件层次生成的虚拟磁盘，统一称为“LUN”. 而由软件生成的虚拟磁盘，统一称为“卷”
MetaLUN		A logical unit that is expanded by aggregating multiple logical units.	聚合了多个逻辑单位的来达到扩展目的一个逻辑单位	MetaLUN允许我们将I/O分散到许多磁盘上. 假设我们有四个RAID Group, 每个RAID group中有5块盘. 那么跨着四个RADI Group的MetaLUN可以让20块盘同时响应该LUN上的IO. MetaLUN仅在RAID Group而存在.
Pool LUN				Pool LUN的精髓在于逐步地消耗资源的同时自动地平衡每个user LUN上的pool resource.
Thin LUN		The LUN provisioned by Thin Provisioning. Thin provisioning is a technology that allows you to create LUNs or Volumes on a storage device such that the LUN/Volume(s) appear to the host or client to be larger than they actually are.	使用Thin Provisioning技术创建出来的LUN. Thin Provisioning是一种让你的存储设备创建出实际划分的大小比从主机或客户端看上去要小得多的技术.	这使得你可以精确地满足应用程序所需要的空间, 但你有不需要提前把所有的
Thick LUN	Traditional LUN		看上去是多大, 实际就是多大的LUN.
watermark		On the basis of the I/O access rate and pattern, high and low levels called watermarks are set in cache to manage the flushing process.	Cache的使用程度的标记. 这标记是可以设置的, 用于控制将cache中的数据写回磁盘(flush)的过程.
High watermark	HWM	High watermark (HWM) is the cache utilization level at which the storage system starts highspeed flushing of cache data.	处于或高于high watermark水平, 说明cache使用率比较高, 需要启动high watermark flushing来写回数据到磁盘上. 当cache使用率达到百分百(或者一个设置的高于HWM的值)的时候, 会触发forced flushing.
Low watermark	LWM	Low watermark (LWM) is the point at which the storage system stops the high-speed or forced flushing and returns to idle flush behavior.	处于该水平的cache使用率比较低, 存储系统会使用持续发生的, 适中的频率来flush, 叫做idle flushing.
Throughput		I/O per second(IOPS), suitable for measuring OLTP-type applications.	每秒钟发生的读写次数, 适用于衡量OLTP类型的应用程序.
Bandwidth		How much data, in megabytes, is being transferred per second. It is important for measuring media streaming, large file databases, backups.	每秒种传输的数据量, 已MB为单位. 对于流媒体, 大数据库文件, 备份这类应用程序存储方面的性能衡量比较适用.
Response time		Amount of time a system or functional unit takes to react to a given input.	系统或功能单元用来对一个输入进行响应所需的时间.	一个存储系统可能可以提供非常大的IOPS, 但response time却很长.
Parity		A mathematical construct that enables re-creation of the missing segment of data.	一个数学结构, 可以重新创建丢失的数据.	这是一种预防丢失一个磁盘的保护数据的方式.
Page		Unit of allocation in cache memory	缓存内存中的分配单位
Vault		Reserved data to correct disk location (normal cache function)	存储系统中在磁盘上保留的区域, 用于写cache dumping的.
Disk Array Enclosure	DAE	Disk Array Enclosure (DAE) are the key modular building blocks of a CLARiiON. A DAE enclosure contains up to 15 disk drives, two link control cards (LCCs), two power supplies, and two fan modules.	磁盘阵列盒, 是存储
Disk Processor Enclosure	DPE

 

 

参考资料

<<Information Storage Management>>

 

Capacity vs. Performance : Thin Provisioning

http://storagesavvy.com/2009/06/30/capacity-vs-performance-thin-provisioning/