Switch-based acceleration of computer data storage employing aggregations of disk arrays
    12.
    发明授权
    Switch-based acceleration of computer data storage employing aggregations of disk arrays 有权
    基于开关的加速计算机数据存储采用磁盘阵列的聚合

    公开(公告)号:US06801960B1

    公开(公告)日:2004-10-05

    申请号:US09670933

    申请日:2000-09-28

    CPC classification number: H04L67/1097 H04L69/329

    Abstract: There is disclosed apparatus and methodology for enhancing computer system data transfer when writing to network attached storage systems employing FC-2 fibrechannel protocol by dynamically reconfiguring a fibrechannel switch in response to map/unmap command controls issued by a disk drive aggregator. The reconfiguration involves fabrication of a dynamic map table having sets of fibrechannel FC-2 header fields and their corresponding new or proxy destination IDs (which correspond to the switch's output ports), and fabrication of both an input frame header buffer for temporary storage purposes and a frame header field selector (which can be a frame header mask) containing only relevant information. The input frame header is temporarily stored in the buffer and the field selector is used to obtain a “distilled” input header which is compared with the dynamic map table of stored header fields to obtain a match. If one of the sets of header fields matches the distilled input header, its corresponding proxy destination or source ID is substituted into the corresponding FC-2 input frame header's destination ID field, whereby write command data transfers are accomplished between host computer and a particular disk drive directly, avoiding the aggregator and latency otherwise introduced by the aggregator. Similar disclosure is provided for read command data.

    Abstract translation: 公开了用于在写入使用FC-2光纤通道协议的网络连接的存储系统时,通过响应由磁盘驱动器集成器发出的映射/取消映射命令控制来动态重新配置光纤通道交换机来增强计算机系统数据传输的装置和方法。 重新配置涉及制造具有纤维信道FC-2报头字段及其对应的新的或代理目的地ID(其对应于交换机的输出端口)的动态映射表,以及用于临时存储目的的输入帧报头缓冲器的制造,以及 一个仅包含相关信息的帧头字段选择器(它可以是帧头掩码)。 输入帧头被临时存储在缓冲器中,并且使用字段选择器来获得与所存储的头字段的动态映射表进行比较以获得匹配的“蒸馏”输入头。 如果标题字段集合中的一个与蒸馏的输入标题匹配,则将其相应的代理目的地或源ID替换为对应的FC-2输入帧标题的目的地ID字段,由此在主计算机和特定盘之间完成写入命令数据传送 直接驱动,避免聚合器和聚合器引入的延迟。 为读命令数据提供了类似的公开。

    System and method for expanding a log structure in a disk array
    13.
    发明授权
    System and method for expanding a log structure in a disk array 有权
    用于扩展磁盘阵列中的日志结构的系统和方法

    公开(公告)号:US06507890B1

    公开(公告)日:2003-01-14

    申请号:US09676222

    申请日:2000-09-29

    Abstract: A system and method for expanding a log structure in a disk array, the disk array being expanded from M-width to N-width, the disk array including a storage level, the log structure including one or more sequential used segments, the one or more sequential used segments including live data, locates one or more sequential used segments, writes live data from the one or more located segments to the storage level, enlarges the size of the one or more located segments from M-width to N-width, and places the one or more enlarged segments on a first free segment list.

    Abstract translation: 一种用于扩展磁盘阵列中的日志结构的系统和方法,所述磁盘阵列从M宽扩展到N-width,所述磁盘阵列包括存储级别,所述逻辑结构包括一个或多个顺序使用的段,所述一个或多个 更多连续使用的段,包括实时数据,定位一个或多个顺序使用的段,将实时数据从一个或多个定位段写入存储级别,将一个或多个定位的段的大小从M宽扩大到N宽, 并将一个或多个放大的段放在第一个空闲段列表上。

    High performance data path with XOR on the fly
    14.
    发明授权
    High performance data path with XOR on the fly 失效
    高性能的数据路径,XOR即时运行

    公开(公告)号:US6161165A

    公开(公告)日:2000-12-12

    申请号:US815193

    申请日:1997-03-11

    CPC classification number: G06F11/1076 G06F2211/1054

    Abstract: A high performance data path for performing XOR on the fly. A first memory is connected to a first bus and a second memory is connected to a second bus selectively coupled to the first bus. Logic for performing an XOR can be switched into connection with the first and second bus for XORing data in a buffer with the data passed from one of the memories to the other memory. The result is replaced into the buffer to permit successive XORing. When reading from an interrelated group of disks such as a RAID 3 group, the data path permits an N-1 and go mode in which a read does not wait for data from the last disk to retrieve its data sector. If the last disk contains data (as opposed to parity) the data is obtained from the XORed data in the XOR buffer of the high performance data path. For writing data, the XOR on the fly generates the parity sector for writing at the completion of a write to an interrelated group of disks.

    Abstract translation: 用于执行XOR的高性能数据路径。 第一存储器连接到第一总线,第二存储器连接到选择性地耦合到第一总线的第二总线。 用于执行XOR的逻辑可以切换成与第一和第二总线连接,用于将数据从一个存储器传递到另一个存储器的缓冲器中的数据进行异或运算。 结果被替换为缓冲区以允许连续的异或。 当从相互关联的诸如RAID 3组的磁盘组读取数据路径时,数据路径允许N-1和去模式,其中读取不等待来自最后一个磁盘的数据来检索其数据扇区。 如果最后一个磁盘包含数据(与奇偶校验相反),则从高性能数据路径的XOR缓冲区中的异或数据获取数据。 对于写入数据,XOR在写入到相互关联的一组磁盘完成时,将产生用于写入的奇偶校验扇区。

Patent Agency Ranking