Vmware, Inc.

Vmwre, Inc.

Rohan Pasalkar

Prasanna Aithal

Mahesh Shivanagouda Hiregoudar

Prasad Rao Jangam

Srinivasa Shantharam

Asit Desai

Bryan Branstetter

Pradeep H Krishnamurthy

Srikanth Mahabalarao

Raghavan Pichai

A method of synchronously executing input/output operations (IOs) for a plurality of applications using a storage device with a file system includes the steps of: receiving a first write IO including an instruction to write first data at a first address of the file system; determining that, within a first range of the file system comprising the first address, there are no pending unmap IOs for deallocating storage space of the storage device from files of the plurality of applications; after determining that there are no pending unmap IOs within the first range, locking the first range to prevent incoming unmap IOs from deallocating storage space within the first range from the files of the plurality of applications; after locking the first range, writing the first data to the storage device at the first address; and after writing the first data, unlocking the first range.

Avoiding data inconsistency in a file system using 2-level synchronization

An example method of handling, at a hypervisor on a host in a virtualized computing system, a write input/output (IO) operation to a file on a storage device having a virtual machine file system (VMFS) is described. The method includes: generating logical transactions for the write IO operation having updates to metadata of the VMFS for the file; estimating, for the logical transactions, common space reservations for those of the updates to common fields in the metadata for the file; estimating, for the logical transactions, exclusive space reservations for those of the updates to exclusive fields in the metadata for the file; batching the logical transactions into a physical transaction, which includes a single reservation of space in a journal of the VMFS based on the common space reservations and a reservations of space in the journal for each of the exclusive space reservations, respectively.

Journal space reservations for virtual disks in a virtualized computing system

A method of deleting a first pointer block of a plurality of pointer blocks of a file system from a storage device used by a plurality of applications, wherein the plurality of pointer blocks are each subdivided into sub-blocks, includes the steps of: determining that a first sub-block of the first pointer block is marked as being empty of any addresses of the file system at which storage space is allocated to files of the applications; determining that a second sub-block of the first pointer block has not been marked as being empty; in response to the determining that the second sub-block has not been marked as being empty, determining that the second sub-block does not contain any addresses of the file system at which storage space is allocated to the files of the applications; and deleting the first pointer block from the storage device.

Optimal method for deleting sub-blocks of a pointer block that do not have on-disk metadata headers for addresses

An example method of handling, at a hypervisor on a host in a virtualized computing system, a write input/output (IO) operation to a file on a storage device having a virtual machine file system (VMFS) is described. The method includes: sorting, at the hypervisor, a scatter-gather array for the write IO operation into sets of scatter-gather elements, each of the sets including at least one scatter-gather element targeting a common file block address; resolving offsets of the sets of scatter-gather elements to identify a first scatter-gather array of transaction-dependent scatter-gather elements; generating logical transactions for the first scatter-gather array having updates to metadata of the VMFS for the file; batching the logical transactions into a physical transaction; and executing the physical transaction to commit the updates to the metadata of the VMFS on the storage device for the file.

Write input/output optimization for virtual disks in a virtualized computing system

A method of deleting a first pointer block of a plurality of pointer blocks of a file system from a storage device used by a plurality of applications, wherein the plurality of pointer blocks are each subdivided into sub-blocks, includes the steps of: determining that a first sub-block of the first pointer block is marked as being empty of any addresses of the file system at which storage space is allocated to files of the applications, determining that a second sub-block of the first pointer block has not been marked as being empty; in response to the determining that the second sub-block has not been marked as being empty, determining that the second sub-block does not contain any addresses of the file system at which storage space is allocated to the files of the applications; and deleting the first pointer block from the storage device.

Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for reclaiming one or more portions of storage resources in a computer system serving one or more virtual computing instances, where the storage resources in the computer system are organized in clusters of storage blocks. In one aspect, a method includes maintaining a respective block tracking value for each storage block that indicates whether a call to reclaim the storage block is outstanding; determining, from the block tracking values, a respective cluster priority value for each of the clusters based on a count of storage blocks in the respective cluster for which a call to reclaim is outstanding; and reclaiming a first portion of storage resources in the computer system in accordance with the cluster priority values.

Reclaiming storage resources

The systems described herein are configured to enhance the efficiency of memory usage and access in a VM file system data store with respect to allocating memory in large and small file block clusters using affinity metadata and propagating and maintaining the affinity metadata in support of the described allocation. In order to maintain affinity metadata of the large file block cluster, affinity generation values stored on the large file block cluster are read and cached affinity generation values for each small file block cluster are read from an in-memory cache associated with the large file block cluster. When the stored affinity generation values and the cached affinity generation values do not match, affinity metadata from all the small file block clusters associated with the large file block cluster is used to update the affinity metadata of the large file block cluster and the associated cache.

Propagating affinity data to large file block clusters in a file system

The systems described herein are configured to enhance the efficiency of memory usage and access in a VM file system data store with respect to allocating memory in large and small file block clusters using affinity metadata and propagating and maintaining the affinity metadata in support of the described allocation. During storage of file data, an affinity identifier of the file data is determined. The affinity identifier is used to identify a large file block cluster and a small file block cluster within the identified large file block cluster. The file data is stored in the selected small file block cluster and affinity metadata of the selected small file block cluster is updated to reflect the storage of the file data.

Allocating memory resources in a file system based on affinity data

A distributed file system may be configured with file blocks of a first type and file blocks of a second type, from allocation units that comprise a logical volume containing the file system. File blocks of the second type may be defined from one or more file blocks of the first type. A thick file may be instantiated with a number of allocation units totaling a size greater than or equal to a specified file size of the thick file. The allocation units may be allocated to the thick file in units of file blocks of the first type or file blocks of the second type, depending on the specified file size of the thick file.

Method and system for thick files in a distributed file system

Exemplary methods, apparatuses, and systems determine whether a skip optimization process can be used to store a file in a storage space. When it is determined that the skip optimization can be performed, a file stored in the storage space can be referenced in a file metadata data structure using direct addressing of file blocks storing the file instead of through indirect addressing (e.g., pointer addresses stored in pointer blocks).

Minimizing file creation and access times using skip optimization

The systems described herein are configured to enhance the efficiency of memory in a host file system with respect to hosted virtual file systems. In situations when the hosted virtual file systems use smaller file block sizes than the file block sizes of the host file system. During storage of a file, a file block is assigned a block address and unmapping bits. The block address and unmapping bits are stored in a pointer block or other similar data structure associated with the file. Particularly, the block address is stored in a first address block and the unmapping bits are stored in at least one additional address block located in proximity to the block address, such that the unmap granularity of the file is not limited by the fixed size of address blocks in the system.

Growing community of inventors

Palo Alto, CA, United States of America

Rohan Pasalkar