Netapp, Inc.

Matthew Fontaine Curtis-Maury

Vinay Devadas

Ananthan Subramanian

Ram Kesavan

Abdul Basit

Aditya Kulkarni

Mark Smith

Yash Hetal Trivedi

Bulli Venkata Rajesh Vipperla

Rupa Natarajan

Peter Denz

Peter Scott Wyckoff

Techniques are provided for forwarding operations to bypass persistent memory. A modify operation, targeting an object, may be received at a persistent memory tier of a node. If a forwarding policy indicates that forwarding is not enabled for the modify operation and the target object, then the modify operation is executed through a persistent memory file system. If the forwarding policy indicates that forwarding is enabled for the modify operation and the target object, then the modify operation is forwarded to a file system tier as a forwarded operation for execution through a storage file system.

Forwarding operations to bypass persistent memory

Techniques are provided for block allocation for persistent memory during aggregate transition. In a high availability pair including first and second nodes, the first node makes a determination that control of a first aggregate is to transition from the first node to the second node. A portion of available free storage space is allocated from a first persistent memory of the first node as allocated pages within the first persistent memory. Metadata information for the allocated pages is updated with an identifier of the first aggregate to create updated metadata information reserving the allocated pages for the first aggregate. The updated metadata information is mirrored to the second node, so that the second node also reserves those pages. Control of the first aggregate is transitioned to the second node. As a result, the nodes do not attempt allocating the same free pages to different aggregates during a transition.

Block allocation for persistent memory during aggregate transition

Techniques are provided for data management across a persistent memory tier and a file system tier. A block within a persistent memory tier of a node is determined to have up-to-date data compared to a corresponding block within a file system tier of the node. The corresponding block may be marked as a dirty block within the file system tier. Location information of a location of the block within the persistent memory tier is encoded into a container associated with the corresponding block. In response to receiving a read operation, the location information is obtained from the container. The up-to-date data is retrieved from the block within the persistent memory tier using the location information for processing the read operation.

Data management across a persistent memory tier and a file system tier

Techniques are provided for maintaining and recomputing reference counts in a persistent memory file system of a node. Primary reference counts are maintained for pages within persistent memory of the node. In response to receiving a first operation to link a page into a persistent memory file system of the persistent memory, a primary reference count of the page is incremented before linking the page into the persistent memory file system. In response to receiving a second operation to unlink the page from the persistent memory file system, the page is unlinked from the persistent memory file system before the primary reference count is decremented. Upon the node recovering from a crash, the persistent memory file system is traversed in order to update shadow reference counts for the pages with correct reference count values, which are used to overwrite the primary reference counts with the correct reference count values.

Maintaining and recomputing reference counts in a persistent memory file system

Techniques are provided for implementing a persistent memory storage tier to manage persistent memory of a node. The persistent memory is managed by the persistent memory storage tier at a higher level within a storage operating system storage stack than a level at which a storage file system of the node is managed. The persistent memory storage tier intercepts an operation targeting the storage file system. The persistent memory storage tier retargets the operation from targeting the storage file system to targeting the persistent memory. The operation is transmitted to the persistent memory.

Persistent memory architecture

Techniques are provided for coordinating snapshot operations across multiple file systems. A notification may be received that a snapshot of data stored across a persistent memory file system and a storage file system is to be generated. Forwarding, of modify operations from a persistent memory tier to a file system tier for execution through the storage file system, may be enabled. Framing may be initiated to notify the storage file system of blocks within the persistent memory file system that comprise more up-to-date data than corresponding blocks within the storage file system. In response to the framing completing, a consistency point operation is performed to create the snapshot and to create a snapshot image as part of the snapshot.

Coordinating snapshot operations across multiple file systems

Techniques are provided for implementing write ordering for persistent memory. A set of actions are identified for commitment to persistent memory of a node for executing an operation upon the persistent memory. An episode is created to comprise a first subset of actions of the set of actions that can be committed to the persistent memory in any order with respect to one another such that a consistent state of the persistent memory can be reconstructed in the event of a crash of the node during execution of the operation. The first subset of actions within the episode are committed to the persistent memory and further execution of the operation is blocked until the episode completes.

Write ordering for persistent memory

Techniques are provided for compacting indirect blocks. For example, an object is represented as a structure including data blocks within which data of the object is stored and indirect blocks including block numbers of where the data blocks are located in storage. Block numbers within a set of indirect blocks are compacted into a compacted indirect block including a base block number, a count of additional block numbers after the base block number in the compacted indirect block, and a pattern of the block numbers in the compacted indirect block. The compacted indirect block is stored into memory for processing access operations to the object. Storing compacted indirect blocks into memory allows for more block numbers to be stored within memory.

File system format for persistent memory

Presented herein are methods, non-transitory computer readable media, and devices for optimizing thread assignment to schedulers, avoid starvation of individual data partitions, and maximize parallelism in the presence of hierarchical data partitioning are disclosed, which include: partitioning, by a network storage server, a scheduler servicing a data partitioned system into a plurality of autonomous schedulers; determining what fraction of thread resources in the data partitioned system at least one of the plurality of autonomous schedulers is to receive; and determining, with minimal synchronization, when it is time to allow the at least one of the plurality of autonomous schedulers servicing a coarse hierarchy to run.

Efficient distributed scheduler for a data partitioned system

Techniques are provided for persistent memory file system reconciliation. As part of the persistent memory file system reconciliation, high level file system metadata associated with a persistent memory file system of persistent memory is reconciled. Client access to the persistent memory file system is inaccessible until reconciliation of the high level file system metadata has completed. A first scanner is executed to traverse pages of the persistent memory in order to fix local inconsistencies associated with the pages. A local inconsistency of a first set of metadata or data of a page is fixed using a second set of metadata or data of the page. The first scanner is executed asynchronously in parallel with processing client I/O directed to the persistent memory file system.

Persistent memory file system reconciliation

Techniques are provided for supporting a lookup structure for a file system implementing hierarchical reference counting. A write operation to write data to a page maintained by the file system is received. A lookup within a lookup structure is performed using information related to the page in order to identify a lookup entry within the lookup structure. A hash generation count within the lookup entry is compared to a file system info generation count within a file system info object for a volume associated with the page. In response to the lookup entry generation count not matching the file system info generation count, a file system tree of the file system is traversed to determine a reference count for the page, and the write operation is implemented based upon the reference count. Otherwise, the lookup entry is utilized to access the page for processing the write operation.

Supporting a lookup structure for a file system implementing hierarchical reference counting

Presented herein are methods, non-transitory computer readable media, and devices for integrating a hybrid model of fine-grained locking and data-partitioning wherein fine-grained locking is added to existing systems that are based on hierarchical data-partitioning in order in increase parallelism with minimal code re-write. Methods for integrating a hybrid model of fine-grained locking and data-partitioning are disclosed which include: creating, by a network storage server, a plurality of domains for execution of processes of the network storage server, the plurality of domains including a domain; creating a hierarchy of storage filesystem subdomains within the domain, wherein each of the subdomains corresponds to one or more types of processes, wherein at least one of the storage filesystem subdomains maps to a data object that is locked via fine-grained locking; and assigning processes for simultaneous execution by the storage filesystem subdomains within the domain and the at least one subdomain that maps to the data object locked via fine-grained locking.

Hybrid model of fine-grained locking and data partitioning

Techniques are provided for atomic writes for persistent memory. In response to receiving a write operation, a new per-page structure with a new page block number is allocated. New data of the write operation is persisted to a new page of the persistent memory having the new page block number, and the new per-page structure is persisted to the persistent memory. If the write operation targets a hole after the new data and the new per-page structure have been persisted, then a new per-page structure identifier of the new per-page structure is inserted into a parent indirect page of a page comprising the new data. If the write operation targets old data after the new data and the new per-page structure have been persisted, then an old per-page structure of the old data is updated with the new page block number.

Growing community of inventors

Apex, NC, United States of America

Matthew Fontaine Curtis-Maury