公开(公告)号：US10545927B2

公开(公告)日：2020-01-28

申请号：US15081651

申请日：2016-03-25

Applicant: Amazon Technologies, Inc.

Inventor： Jacob A. Strauss ,  Jocob David Luszcz ,  Peter Jones ,  Michael Robert Frasca ,  Neal John Charbonneau

IPC: G06F17/30 ,  G06F16/18

Abstract: A distributed file storage services (DFSS) that provides low latency (LL) and high throughput (HT) modes for file systems. A HT metadata subsystem (HTMS) may use a distributed transaction system for data and metadata reads and writes for file systems in HT mode. A LL metadata subsystem (LLMS) may process metadata requests for file systems in LL mode. For metadata read requests, the LLMS may locally cache at least some of the file system metadata. For metadata write requests, the LLMS may write entries to a journal and notify the access node after the entries are committed to the journal. Data reads and writes for file systems in LL mode may be handled similarly to data reads and writes for file systems in HT mode. A file system may be converted from LL to HT mode, or from HT to LL mode.

公开(公告)号：US11061865B2

公开(公告)日：2021-07-13

申请号：US16678969

申请日：2019-11-08

Applicant: Amazon Technologies, Inc.

Inventor： Jacob A. Strauss ,  Michael Robert Frasca ,  Neal John Charbonneau

IPC: G06F16/17 ,  G06F3/06 ,  G06F16/182

Abstract: An LL server (LLS) may process metadata requests for a file system in LL mode in a distributed file storage services (DFSS). For requests that require allocating blocks to file system objects in the backing store, instead of relying on distributed transactions used for file systems in high throughput (HT) mode, a pool of blocks may be pre-allocated for the LL file system in the backing store, and a free block list may be maintained in local memory of the LLS. When a metadata operation requires blocks to be allocated, the blocks are assigned to the respective object from the blocks in the pool. A background process may allocate new blocks in the pool upon the number of blocks dropping below a threshold, or upon block allocation rate for the file system increasing.

公开(公告)号：US10474636B2

公开(公告)日：2019-11-12

申请号：US15081652

申请日：2016-03-25

Applicant: Amazon Technologies, Inc.

Inventor： Jacob A. Strauss ,  Michael Robert Frasca ,  Neal John Charbonneau

IPC: G06F12/00 ,  G06F16/17 ,  G06F3/06 ,  G06F16/182

Abstract: An LL server (LLS) may process metadata requests for a file system in LL mode in a distributed file storage services (DFSS). For requests that require allocating blocks to file system objects in the backing store, instead of relying on distributed transactions used for file systems in high throughput (HT) mode, a pool of blocks may be pre-allocated for the LL file system in the backing store, and a free block list may be maintained in local memory of the LLS. When a metadata operation requires blocks to be allocated, the blocks are assigned to the respective object from the blocks in the pool. A background process may allocate new blocks in the pool upon the number of blocks dropping below a threshold, or upon block allocation rate for the file system increasing.

公开(公告)号：US10140312B2

公开(公告)日：2018-11-27

申请号：US15081647

申请日：2016-03-25

Applicant: Amazon Technologies, Inc.

Inventor： Jacob A. Strauss ,  Mark Allen Fogleman ,  Edward William Naim ,  Jacob David Luszcz ,  Michael Robert Frasca ,  Daniel Nussbaum ,  Peter Jones ,  Xiaobin Wu ,  John McClain ,  Neal John Charbonneau ,  Wayne William Duso

IPC: G06F17/30

Abstract: A low latency metadata subsystem for file systems in low latency (LL) mode in a distributed file storage service (DFSS). An LL server (LLS) may receive metadata requests from an access node of the DFSS. For read operations, the LLS may check a local cache of metadata and, for cache hits, retrieve the metadata from the cache. For cache misses, the metadata may be fetched from the storage subsystem of the DFSS and cached. For write operations, the LLS may write entries into a journal for the file system and notify the access node after the journal entries are committed to the journal; the journal entries are asynchronously committed in the storage subsystem. The access node may communicate with the storage subsystem to perform data reads and writes for the LL file system.