公开(公告)号：US20170235673A1

公开(公告)日：2017-08-17

申请号：US15581800

申请日：2017-04-28

Applicant: NetApp, Inc.

Inventor： Dhaval Patel ,  Manish Swaminathan ,  Edward D. McClanahan ,  John Muth

IPC: G06F12/02

CPC classification number: G06F12/0253 ,  G06F3/0608 ,  G06F3/061 ,  G06F3/0619 ,  G06F3/0641 ,  G06F3/0656 ,  G06F3/0688 ,  G06F12/0246 ,  G06F2212/1016 ,  G06F2212/1024 ,  G06F2212/1044 ,  G06F2212/702 ,  G06F2212/7201 ,  G06F2212/7205

Abstract: A rate matching technique may be configured to adjust a rate of cleaning of one or more selected segments of the storage array to accommodate a variable rate of incoming workload processed by a storage input/output (I/O) stack executing on one or more nodes of a cluster. An extent store layer of the storage I/O stack may clean a segment in accordance with segment cleaning which, illustratively, may be embodied as a segment cleaning process. The rate matching technique may be implemented as a feedback control mechanism configured to adjust the segment cleaning process based on the incoming workload. Components of the feedback control mechanism may include one or more weight schedulers and various accounting data structures, e.g., counters, configured to track the progress of segment cleaning and free space usage. The counters may also be used to balance the rates of segment cleaning and incoming I/O workload, which may change depending upon an incoming I/O rate. When the incoming I/O rate changes, the rate of segment cleaning may be adjusted accordingly to ensure that rates are substantially balanced.

公开(公告)号：US20160357743A1

公开(公告)日：2016-12-08

申请号：US14728482

申请日：2015-06-02

Applicant: NetApp, Inc.

Inventor： Manish Swaminathan ,  Dhaval Patel ,  Edward D. McClanahan ,  Jeffrey S. Kimmel

IPC: G06F17/30

CPC classification number: G06F17/3033 ,  G06F12/0246 ,  G06F12/0261 ,  G06F17/30194 ,  G06F17/30914

Abstract: A technique reduces an amount of metadata stored in a memory of a node in a cluster. An extent store layer of a storage input/output (I/O) stack executing on the node stores key-value pairs in a plurality of data structures, e.g., cuckoo hash tables, resident in the memory. The cuckoo hash table embodies metadata that describes an extent and, as such, may be organized to associate a location on disk with a value that identifies the location on disk. The value may be embodied as a locator that includes a reference count used to support deduplication functionality of the extent store layer with respect to the extent. The reference count is divided into two portions: a delta count portion stored in memory for each slot of the hash table and an overflow count portion stored on disk in a header of each extent. One bit of the delta count portion is reserved as an overflow bit that indicates whether the in-memory reference count has overflowed. Another bit of the delta count portion is reserved as a sign bit that indicates whether the value of the remaining delta count portion, which stores the “delta” of the reference count, is positive or negative. Overflow updates to the overflow count portion on disk are postponed until all of the bits of the delta count portion are consumed as negative/positive transitions.

Abstract translation: 一种技术减少了存储在群集中的节点的存储器中的元数据量。 在节点上执行的存储输入/输出（I / O）堆栈的盘区存储层将密钥值对存储在驻留在存储器中的多个数据结构（例如，布谷鸟哈希表）中。 杜鹃哈希表体现了描述范围的元数据，因此可以被组织以将磁盘上的位置与标识磁盘上的位置的值相关联。 该值可以体现为定位器，其包括用于相对于该范围支持扩展存储层的重复数据删除功能的引用计数。 引用计数被分为两部分：存储在哈希表的每个时隙的存储器中的增量计数部分和存储在每个盘区的标题中的盘上的溢出计数部分。 增量计数部分的一位被保留为指示内存中引用计数是否溢出的溢出位。 增量计数部分的另一位被保留为符号位，其指示存储引用计数的“delta”的剩余增量计数部分的值是正还是负。 推迟到磁盘溢出计数部分的溢出更新，直到增量计数部分的所有位被消耗为负/正转移。

公开(公告)号：US20160077745A1

公开(公告)日：2016-03-17

申请号：US14484565

申请日：2014-09-12

Applicant: NetApp, Inc.

Inventor： Dhaval Patel ,  Manish Swaminathan ,  Edward D. McClanahan ,  John Muth

IPC: G06F3/06 ,  G06F12/02

CPC classification number: G06F12/0253 ,  G06F3/0608 ,  G06F3/061 ,  G06F3/0619 ,  G06F3/0641 ,  G06F3/0656 ,  G06F3/0688 ,  G06F12/0246 ,  G06F2212/1016 ,  G06F2212/1024 ,  G06F2212/1044 ,  G06F2212/702 ,  G06F2212/7201 ,  G06F2212/7205

Abstract: A rate matching technique may be configured to adjust a rate of cleaning of one or more selected segments of the storage array to accommodate a variable rate of incoming workload processed by a storage input/output (I/O) stack executing on one or more nodes of a cluster. An extent store layer of the storage I/O stack may clean a segment in accordance with segment cleaning which, illustratively, may be embodied as a segment cleaning process. The rate matching technique may be implemented as a feedback control mechanism configured to adjust the segment cleaning process based on the incoming workload. Components of the feedback control mechanism may include one or more weight schedulers and various accounting data structures, e.g., counters, configured to track the progress of segment cleaning and free space usage. The counters may also be used to balance the rates of segment cleaning and incoming I/O workload, which may change depending upon an incoming I/O rate. When the incoming I/O rate changes, the rate of segment cleaning may be adjusted accordingly to ensure that rates are substantially balanced.

Abstract translation: 速率匹配技术可以被配置为调整存储阵列的一个或多个所选段的清理速率，以适应由在一个或多个节点上执行的存储输入/输出（I / O）栈处理的进入工作负载的可变速率 的集群。 存储I / O堆栈的盘区存储层可以根据段清洁来清洁段，其示例性地可以被实现为段清理过程。 速率匹配技术可以被实现为反馈控制机制，其被配置为基于输入的工作负载来调整段清除过程。 反馈控制机构的组件可以包括一个或多个权重调度器和各种会计数据结构，例如计数器，其被配置为跟踪段清洁和可用空间使用的进度。 这些计数器也可用于平衡段清除和输入I / O工作负载的速率，这可能会根据传入的I / O速率而改变。 当进入的I / O速率变化时，可以相应地调节段清洁的速率，以确保速率基本平衡。

公开(公告)号：US10762070B2

公开(公告)日：2020-09-01

申请号：US15895593

申请日：2018-02-13

Applicant: NetApp, Inc.

Inventor： Manish Swaminathan ,  Dhaval Patel ,  Edward D. McClanahan ,  Jeffrey S. Kimmel

IPC: G06F16/22 ,  G06F12/02 ,  G06F16/84 ,  G06F16/182

Abstract: A technique reduces an amount of metadata stored in a memory of a node in a cluster. An extent store layer of a storage input/output (I/O) stack executing on the node stores key-value pairs in a plurality of data structures, e.g., cuckoo hash tables, resident in the memory. The cuckoo hash table embodies metadata that describes an extent and, as such, may be organized to associate a location on disk with a value that identifies the location on disk. The value may be embodied as a locator that includes a reference count used to support deduplication functionality of the extent store layer with respect to the extent. The reference count is divided into two portions: a delta count portion stored in memory for each slot of the hash table and an overflow count portion stored on disk in a header of each extent. One bit of the delta count portion is reserved as an overflow bit that indicates whether the in-memory reference count has overflowed. Another bit of the delta count portion is reserved as a sign bit that indicates whether the value of the remaining delta count portion, which stores the “delta” of the reference count, is positive or negative. Overflow updates to the overflow count portion on disk are postponed until all of the bits of the delta count portion are consumed as negative/positive transitions.

公开(公告)号：US10210082B2

公开(公告)日：2019-02-19

申请号：US15581800

申请日：2017-04-28

Applicant: NetApp, Inc.

Inventor： Dhaval Patel ,  Manish Swaminathan ,  Edward D. McClanahan ,  John Muth

IPC: G06F12/02 ,  G06F3/06

Abstract: A rate matching technique may be configured to adjust a rate of cleaning of one or more selected segments of the storage array to accommodate a variable rate of incoming workload processed by a storage input/output (I/O) stack executing on one or more nodes of a cluster. An extent store layer of the storage I/O stack may clean a segment in accordance with segment cleaning which, illustratively, may be embodied as a segment cleaning process. The rate matching technique may be implemented as a feedback control mechanism configured to adjust the segment cleaning process based on the incoming workload. Components of the feedback control mechanism may include one or more weight schedulers and various accounting data structures, e.g., counters, configured to track the progress of segment cleaning and free space usage. The counters may also be used to balance the rates of segment cleaning and incoming I/O workload, which may change depending upon an incoming I/O rate. When the incoming I/O rate changes, the rate of segment cleaning may be adjusted accordingly to ensure that rates are substantially balanced.

公开(公告)号：US09934264B2

公开(公告)日：2018-04-03

申请号：US14728482

申请日：2015-06-02

Applicant: NetApp, Inc.

Inventor： Manish Swaminathan ,  Dhaval Patel ,  Edward D. McClanahan ,  Jeffrey S. Kimmel

IPC: G06F7/00 ,  G06F17/30 ,  G06F12/02

CPC classification number: G06F17/3033 ,  G06F12/0246 ,  G06F12/0261 ,  G06F17/30194 ,  G06F17/30914

Abstract: A technique reduces an amount of metadata stored in a memory of a node in a cluster. An extent store layer of a storage input/output (I/O) stack executing on the node stores key-value pairs in a plurality of data structures, e.g., cuckoo hash tables, resident in the memory. The cuckoo hash table embodies metadata that describes an extent and, as such, may be organized to associate a location on disk with a value that identifies the location on disk. The value may be embodied as a locator that includes a reference count used to support deduplication functionality of the extent store layer with respect to the extent. The reference count is divided into two portions: a delta count portion stored in memory for each slot of the hash table and an overflow count portion stored on disk in a header of each extent. One bit of the delta count portion is reserved as an overflow bit that indicates whether the in-memory reference count has overflowed. Another bit of the delta count portion is reserved as a sign bit that indicates whether the value of the remaining delta count portion, which stores the “delta” of the reference count, is positive or negative. Overflow updates to the overflow count portion on disk are postponed until all of the bits of the delta count portion are consumed as negative/positive transitions.

公开(公告)号：US09671960B2

公开(公告)日：2017-06-06

申请号：US14484565

申请日：2014-09-12

Applicant: NetApp, Inc.

Inventor： Dhaval Patel ,  Manish Swaminathan ,  Edward D. McClanahan ,  John Muth

IPC: G06F3/06 ,  G06F12/02

CPC classification number: G06F12/0253 ,  G06F3/0608 ,  G06F3/061 ,  G06F3/0619 ,  G06F3/0641 ,  G06F3/0656 ,  G06F3/0688 ,  G06F12/0246 ,  G06F2212/1016 ,  G06F2212/1024 ,  G06F2212/1044 ,  G06F2212/702 ,  G06F2212/7201 ,  G06F2212/7205

Abstract: A rate matching technique may be configured to adjust a rate of cleaning of one or more selected segments of the storage array to accommodate a variable rate of incoming workload processed by a storage input/output (I/O) stack executing on one or more nodes of a cluster. An extent store layer of the storage I/O stack may clean a segment in accordance with segment cleaning which, illustratively, may be embodied as a segment cleaning process. The rate matching technique may be implemented as a feedback control mechanism configured to adjust the segment cleaning process based on the incoming workload. Components of the feedback control mechanism may include one or more weight schedulers and various accounting data structures, e.g., counters, configured to track the progress of segment cleaning and free space usage. The counters may also be used to balance the rates of segment cleaning and incoming I/O workload, which may change depending upon an incoming I/O rate. When the incoming I/O rate changes, the rate of segment cleaning may be adjusted accordingly to ensure that rates are substantially balanced.

公开(公告)号：US10133511B2

公开(公告)日：2018-11-20

申请号：US14484820

申请日：2014-09-12

Applicant: NetApp, Inc.

Inventor： John Muth ,  Edward D. McClanahan ,  Dhaval Patel ,  Manish Swaminathan

IPC: G06F3/06

Abstract: An optimized segment cleaning technique is configured to efficiently clean one or more selected portions or segments of a storage array coupled to one or more nodes of a cluster. A bottom-up approach of the segment cleaning technique is configured to read all blocks of a segment to be cleaned (i.e., an “old” segment) to locate extents stored on the SSDs of the old segment and examine extent metadata to determine whether the extents are valid and, if so, relocate the valid extents to a segment being written (i.e., a “new” segment). A top-down approach of the segment cleaning technique obviates reading of the blocks of the old segment to locate the extents and, instead, examines the extent metadata to determine the valid extents of the old segment. A hybrid approach may extend the top-down approach to include only full stripe read operations needed for relocation and reconstruction of blocks as well as retrieval of valid extents from the stripes, while also avoiding any unnecessary read operations of the bottom-down approach.

公开(公告)号：US20180173703A1

公开(公告)日：2018-06-21

申请号：US15895593

申请日：2018-02-13

Applicant: NetApp, Inc.

Inventor： Manish Swaminathan ,  Dhaval Patel ,  Edward D. McClanahan ,  Jeffrey S. Kimmel

IPC: G06F17/30 ,  G06F12/02

CPC classification number: G06F16/2255 ,  G06F12/0246 ,  G06F12/0261 ,  G06F16/182 ,  G06F16/84

Abstract: A technique reduces an amount of metadata stored in a memory of a node in a cluster. An extent store layer of a storage input/output (I/O) stack executing on the node stores key-value pairs in a plurality of data structures, e.g., cuckoo hash tables, resident in the memory. The cuckoo hash table embodies metadata that describes an extent and, as such, may be organized to associate a location on disk with a value that identifies the location on disk. The value may be embodied as a locator that includes a reference count used to support deduplication functionality of the extent store layer with respect to the extent. The reference count is divided into two portions: a delta count portion stored in memory for each slot of the hash table and an overflow count portion stored on disk in a header of each extent. One bit of the delta count portion is reserved as an overflow bit that indicates whether the in-memory reference count has overflowed. Another bit of the delta count portion is reserved as a sign bit that indicates whether the value of the remaining delta count portion, which stores the “delta” of the reference count, is positive or negative. Overflow updates to the overflow count portion on disk are postponed until all of the bits of the delta count portion are consumed as negative/positive transitions.

公开(公告)号：US20160077746A1

公开(公告)日：2016-03-17

申请号：US14484820

申请日：2014-09-12

Applicant: NetApp, Inc.

Inventor： John Muth ,  Edward D. McClanahan ,  Dhaval Patel ,  Manish Swaminathan

IPC: G06F3/06

CPC classification number: G06F3/0652 ,  G06F3/0608 ,  G06F3/061 ,  G06F3/0644 ,  G06F3/0673 ,  G06F3/0688 ,  G06F2212/7205

Abstract: An optimized segment cleaning technique is configured to efficiently clean one or more selected portions or segments of a storage array coupled to one or more nodes of a cluster. A bottom-up approach of the segment cleaning technique is configured to read all blocks of a segment to be cleaned (i.e., an “old” segment) to locate extents stored on the SSDs of the old segment and examine extent metadata to determine whether the extents are valid and, if so, relocate the valid extents to a segment being written (i.e., a “new” segment). A top-down approach of the segment cleaning technique obviates reading of the blocks of the old segment to locate the extents and, instead, examines the extent metadata to determine the valid extents of the old segment. A hybrid approach may extend the top-down approach to include only full stripe read operations needed for relocation and reconstruction of blocks as well as retrieval of valid extents from the stripes, while also avoiding any unnecessary read operations of the bottom-down approach.

Abstract translation: 经优化的段清洁技术被配置为有效地清洁耦合到群集的一个或多个节点的存储阵列的一个或多个选定部分或段。 分段清洁技术的自下而上的方法被配置为读取待清理的段的所有块（即，“旧”段））以定位存储在旧段的SSD上的区段，并检查扩展元数据以确定是否 范围是有效的，如果是，将有效范围重定位到正在写入的段（即“新”段）。 段清除技术的自上而下的方法避免了读取旧段的块以定位范围，而是检查元数据的大小以确定旧段的有效范围。 混合方法可以扩展自上而下的方法，以仅包括块的重定位和重建所需的全条带读取操作以及从条带检索有效范围，同时还避免了自下而上的方法的任何不必要的读操作。