公开(公告)号：EP1031928B1

公开(公告)日：2005-05-18

申请号：EP00111252.3

申请日：1994-06-02

申请人： Network Appliance, Inc.

发明人： Hitz, David ,  Malcolm, Michael ,  Lau, James ,  Rakitzis, Byron

IPC分类号： G06F11/10

CPC分类号： G06F11/1076 ,  G06F2211/1059 ,  G06F2211/1061 ,  G11B20/1833

摘要： The present invention is a method for providing error correction for an array of disks (828) using non-volatile random access memory (NV-RAM) (816). Non-volatile RAM (816) is used to increase the speed or RAID recovery from a disk error(s). This is done by listing of all blocks for which the parity is possibly inconsistent. This list of blocks is much smaller than the total number of parity blocks (820) in the RAID. The total number of parity blocks (820) in the RAID (828) is in the range of hundreds of thousands. Knowledge of the number of parity blocks that are possibly inconsistent makes it possible to fix only those few blocks, identified in the list, resulting in a significant time savings. The technique for safely writing to a RAID with a broken disk is complicated. In this technique, data that can become corrupted is copied into NV-RAM (816) before the potentially corrupting operation is performed.

公开(公告)号：EP1197836A3

公开(公告)日：2009-06-17

申请号：EP02000858.7

申请日：1994-06-02

申请人： Network Appliance, Inc.

发明人： Hitz, David ,  Malcolm, Michael ,  Lau, James ,  Rakitzis, Byron

IPC分类号： G06F3/06 ,  G06F17/30

CPC分类号： G06F11/1076 ,  G06F3/0601 ,  G06F3/0613 ,  G06F3/0643 ,  G06F3/0689 ,  G06F2003/0697 ,  Y10S707/99955

摘要： The present invention is a method for integrating a file system with a RAID array (1030) that exports precise information about the arrangement of data blocks in the RAID subsystem (1030). The system uses explicit knowledge of the underlying RAID disk layout to schedule disk allocation. The present invention uses separate current-write location (CWL) pointers for each disk (1022) in the disk array (1030) where the pointers simply advance through disks (1022) as writes occur. The algorithm used has two primary goals. The first goal is to keep the CWL pointers as close together as possible, thereby improving RAID (1030) efficiency by writing to multiple blocks in the stripe simultaneously. The second goal is to allocate adjacent blocks of a file on the same disk (1022), thereby improving read back performance. The first goal is satisfied by always writing on the disk (1022) with the lowest CWL pointer. For the second goal, another disk (1024) is chosen only when the algorithm starts allocating space for a new file, or when it has allocated N blocks on the same disk (1022) for a single file. The result is that CWL pointers are never more than N blocks apart on different disks (1024), and large files have N consecutive blocks on the same disk (1022).

公开(公告)号：EP1031928A2

公开(公告)日：2000-08-30

申请号：EP00111252.3

申请日：1994-06-02

申请人： Network Appliance, Inc.

发明人： Hitz, David ,  Malcolm, Michael ,  Lau, James ,  Rakitzis, Byron

IPC分类号： G06F11/10

CPC分类号： G06F11/1076 ,  G06F2211/1059 ,  G06F2211/1061 ,  G11B20/1833

摘要： The present invention is a method for providing error correction for an array of disks (828) using non-volatile random access memory (NV-RAM) (816). Non-volatile RAM (816) is used to increase the speed or RAID recovery from a disk error(s). This is done by listing of all blocks for which the parity is possibly inconsistent. This list of blocks is much smaller than the total number of parity blocks (820) in the RAID. The total number of parity blocks (820) in the RAID (828) is in the range of hundreds of thousands. Knowledge of the number of parity blocks that are possibly inconsistent makes it possible to fix only those few blocks, identified in the list, resulting in a significant time savings. The technique for safely writing to a RAID with a broken disk is complicated. In this technique, data that can become corrupted is copied into NV-RAM (816) before the potentially corrupting operation is performed.

摘要翻译： 本发明是在磁盘使用非易失性随机存取存储器（NV-RAM）（816）（828）的阵列，用于提供误差校正的方法。 非易失性RAM（816）被用于增加从磁盘错误（多个）的速度或RAID恢复。 这是由所有块为其平价可能是不一致的上市做。 块的这个列表是比在RAID奇偶校验块（820）的总数小得多。 在RAID（828）的奇偶校验块（820）的总数是在千狗红色的范围内。 做奇偶校验块的数量的知识都可能不一致，能够解决那些只有几个街区，在列表中标识，在显著节省时间所致。 与破盘安全地写入RAID技术是复杂的。 在这种技术中，数据可能会被破坏并在执行可能腐败手术前复制到NV-RAM（816）。

公开(公告)号：EP1197836A2

公开(公告)日：2002-04-17

申请号：EP02000858.7

申请日：1994-06-02

申请人： Network Appliance, Inc.

发明人： Hitz, David ,  Malcolm, Michael ,  Lau, James ,  Rakitzis, Byron

IPC分类号： G06F3/06 ,  G06F17/30

CPC分类号： G06F11/1076 ,  G06F3/0601 ,  G06F3/0613 ,  G06F3/0643 ,  G06F3/0689 ,  G06F2003/0697 ,  Y10S707/99955

摘要： The present invention is a method for integrating a file system with a RAID array (1030) that exports precise information about the arrangement of data blocks in the RAID subsystem (1030). The system uses explicit knowledge of the underlying RAID disk layout to schedule disk allocation. The present invention uses separate current-write location (CWL) pointers for each disk (1022) in the disk array (1030) where the pointers simply advance through disks (1022) as writes occur. The algorithm used has two primary goals. The first goal is to keep the CWL pointers as close together as possible, thereby improving RAID (1030) efficiency by writing to multiple blocks in the stripe simultaneously. The second goal is to allocate adjacent blocks of a file on the same disk (1022), thereby improving read back performance. The first goal is satisfied by always writing on the disk (1022) with the lowest CWL pointer. For the second goal, another disk (1024) is chosen only when the algorithm starts allocating space for a new file, or when it has allocated N blocks on the same disk (1022) for a single file. The result is that CWL pointers are never more than N blocks apart on different disks (1024), and large files have N consecutive blocks on the same disk (1022).

摘要翻译： 本发明是用于将文件系统与导出关于RAID子系统（1030）中的数据块的布置的精确信息的RAID阵列（1030）进行集成的方法。 系统使用基础RAID磁盘布局的显式知识来计划磁盘分配。 本发明对于磁盘阵列（1030）中的每个磁盘（1022）使用单独的电流写入位置（CWL）指针，其中当发生写入时，指针简单地前进通过磁盘（1022）。 所使用的算法有两个主要目标。 第一个目标是使CWL指针尽可能靠近，从而通过同时写入条带中的多个块来提高RAID（1030）的效率。 第二个目标是将文件的相邻块分配在同一个磁盘上（1022），从而提高回读性能。 总是用最低CWL指针写在磁盘（1022）上来满足第一个目标。 对于第二个目标，只有当算法开始为新文件分配空间时，或者当分配了单个文件的同一个磁盘上的N个块（1022）时，才选择另一个磁盘（1024）。 结果是CWL指针在不同的磁盘（1024）上绝对不超过N个块，而大文件在同一磁盘上具有N个连续的块（1022）。

公开(公告)号：EP1031928A3

公开(公告)日：2000-11-15

申请号：EP00111252.3

申请日：1994-06-02

申请人： Network Appliance, Inc.

发明人： Hitz, David ,  Malcolm, Michael ,  Lau, James ,  Rakitzis, Byron

IPC分类号： G06F11/10

CPC分类号： G06F11/1076 ,  G06F2211/1059 ,  G06F2211/1061 ,  G11B20/1833

摘要： The present invention is a method for providing error correction for an array of disks (828) using non-volatile random access memory (NV-RAM) (816). Non-volatile RAM (816) is used to increase the speed or RAID recovery from a disk error(s). This is done by listing of all blocks for which the parity is possibly inconsistent. This list of blocks is much smaller than the total number of parity blocks (820) in the RAID. The total number of parity blocks (820) in the RAID (828) is in the range of hundreds of thousands. Knowledge of the number of parity blocks that are possibly inconsistent makes it possible to fix only those few blocks, identified in the list, resulting in a significant time savings. The technique for safely writing to a RAID with a broken disk is complicated. In this technique, data that can become corrupted is copied into NV-RAM (816) before the potentially corrupting operation is performed.

摘要翻译： 本发明是在磁盘使用非易失性随机存取存储器（NV-RAM）（816）（828）的阵列，用于提供误差校正的方法。 非易失性RAM（816）被用于增加从磁盘错误（多个）的速度或RAID恢复。 这是由所有块为其平价可能是不一致的上市做。 块的这个列表是比在RAID奇偶校验块（820）的总数小得多。 在RAID（828）的奇偶校验块（820）的总数是在千狗红色的范围内。 做奇偶校验块的数量的知识都可能不一致，能够解决那些只有几个街区，在列表中标识，在显著节省时间所致。 与破盘安全地写入RAID技术是复杂的。 在这种技术中，数据可能会被破坏并在执行可能腐败手术前复制到NV-RAM（816）。

公开(公告)号：EP1003103B1

公开(公告)日：2008-10-01

申请号：EP99120949.5

申请日：1994-06-02

申请人： Network Appliance, Inc.

发明人： Hitz, David ,  Malcolm, Michael ,  Lau, James ,  Rakitzis, Byron

IPC分类号： G06F11/14

CPC分类号： G06F17/3015 ,  G06F11/1435 ,  G06F2201/84 ,  Y10S707/99953 ,  Y10S707/99954

摘要： The present invention provides a method for keeping a file system in a consistent state and for creating read-only copies of a file system. Changes to the file system are tightly controlled. The file system progresses from one consistent state to another. The set of self-consistent blocks on disk that is rooted by the root inode is referred to as a consistency point. To implement consistency points, new data is written to unallocated blocks on disk. A new consistency point occurs when the fsinfo block (2440) is updated by writing a new root inode for the inode file (1210) into it. Thus, as long as the root inode is not updated, the state of the file system represented on disk does not change. The present invention also creates snapshots (Figure 22) that are read-only copies of the file system. A snapshot uses no disk space when it is initially created. It is designed so that many different snap shots can be created for the same file system. Unlike prior art file systems that create a clone by duplicating the entire inode file and all of the indirect blocks, the present invention duplicates only the inode that describes the inode file. A multi-bit free-block map file (1630) is used to prevent data from being overwritten on disk.

公开(公告)号：EP1003103A3

公开(公告)日：2007-08-15

申请号：EP99120949.5

申请日：1994-06-02

申请人： Network Appliance, Inc.

发明人： Hitz, David ,  Malcolm, Michael ,  Lau, James ,  Rakitzis, Byron

IPC分类号： G06F11/14

CPC分类号： G06F17/3015 ,  G06F11/1435 ,  G06F2201/84 ,  Y10S707/99953 ,  Y10S707/99954

摘要： The present invention provides a method for keeping a file system in a consistent state and for creating read-only copies of a file system. Changes to the file system are tightly controlled. The file system progresses from one consistent state to another. The set of self-consistent blocks on disk that is rooted by the root inode is referred to as a consistency point. To implement consistency points, new data is written to unallocated blocks on disk. A new consistency point occurs when the fsinfo block (2440) is updated by writing a new root inode for the inode file (1210) into it. Thus, as long as the root inode is not updated, the state of the file system represented on disk does not change. The present invention also creates snapshots (Figure 22) that are read-only copies of the file system. A snapshot uses no disk space when it is initially created. It is designed so that many different snap shots can be created for the same file system. Unlike prior art file systems that create a clone by duplicating the entire inode file and all of the indirect blocks, the present invention duplicates only the inode that describes the inode file. A multi-bit free-block map file (1630) is used to prevent data from being overwritten on disk.