# US 2019/0317925 A1 · Quick initialization of data regions in a distributed storage system

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 2019/0317925 A1
- Document ID: US20190317925A1
- Status: Published application
- Kind: A1
- Application number: 16/455,570
- Filed: 2019-06-27
- Published: 2019-10-17
- Earliest claimed: 2014-09-30
- Assignees: International Business Machines Corporation
- Applicants: International Business Machines Corporation
- Inventors: Dean Hildebrand; Frank B. Schmuck
- Web page: https://patentgrep.com/patent/US20190317925A1

## CPC

- G06F 16/1844: {Management specifically adapted to replicated file systems}
- G06Q 10/00: Administration; Management
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)
- G06Q: INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR

## Abstract

A method includes integrating a file system recovery log layer in a file system. The file system buffers data in a cyclical manner, and transforms all incoming random requests into a series of synchronous sequential updates. The method determines a length value of a write transaction byte-range for a received write transaction. Upon the length value exceeding a threshold value, data for the write transaction byte-range is written to permanent storage in the file system. Upon the length value being less than the threshold value, the data for the write transaction byte-range is written to a recovery log that is stored in the file system recovery log layer. The threshold value is changed dynamically while the file system is mounted.

## Claims

### Claim 1

A method comprising:
integrating a file system recovery log layer in a file system, wherein the file system buffers data in a cyclical manner, transforming all incoming random requests into a series of synchronous sequential updates;
determining a length value of a write transaction byte-range for a received write transaction;
upon the length value exceeding a threshold value, writing data for the write transaction byte-range to permanent storage in the file system;
upon the length value being less than the threshold value, writing the data for the write transaction byte-range to a recovery log that is stored in the file system recovery log layer,
wherein the threshold value is changed dynamically while the file system is mounted.

### Claim 2 (depends on 1)

The method of claim 1, wherein the file system recovery log layer comprises a non-volatile storage layer of the file system.

### Claim 3 (depends on 2)

The method of claim 2, further comprising:
upon dynamically reducing the threshold value, stopping logging the data for the write transaction byte-range to the recovery log for byte-ranges length value exceeding the threshold value.

### Claim 4 (depends on 3)

The method of claim 3, further comprising:
upon dynamically increasing the threshold value, logging the data for the write transaction byte-range with byte-ranges length values being less than the threshold value in the recovery log.

### Claim 5 (depends on 2)

The method of claim 2, further comprising:
upon determining not to place the data for the write transaction byte-range in the recovery log, and the byte-range overlaps with a byte-range for a file system block that has already been placed in a non-volatile layer of the file system, writing all dirty byte-ranges for the file system block to primary storage in the file system and placing a marker in the non-volatile layer indicating that all previous updates to the file system block are skipped upon recovery upon a node failure.

### Claim 6 (depends on 5)

The method of claim 5, further comprising:
tracking byte-ranges that have been logged in the recovery log using a committed bit, wherein committed bits track which byte-ranges are in the recovery log such that a same byte-range is not logged to the recovery log again.

### Claim 7 (depends on 6)

The method of claim 6, wherein the byte ranges to log in the recovery log are not yet marked using the committed bit and have a length value less than the threshold value.

### Claim 8 (depends on 7)

The method of claim 7, further comprising:
creating a bit array that is an XOR of committed bits and dirty bits; and
performing an AND process with the dirty bits to determine the byte-ranges to log in the recovery log.

### Claim 9

A computer program product for quick initialization using storage and replication, the computer program product comprising a computer readable storage medium having program code embodied therewith, the program code executable by a processor to:
integrate a file system recovery log layer in a file system, wherein the file system buffers data in a cyclical manner, and transforms all incoming random requests into a series of synchronous sequential updates;
determine, by the processor, a length value of a write transaction byte-range for a received write transaction;
upon the length value exceeding a threshold value, write, by the processor, data for the write transaction byte-range to permanent storage in the file system;
upon the length value being less than the threshold value, write, by the processor, the data for the write transaction byte-range to a recovery log that is stored in the file system recovery log layer,
wherein the threshold value is changed dynamically while the file system is mounted.

### Claim 10 (depends on 9)

The computer program product of claim 9, wherein the file system recovery log layer comprises a non-volatile storage layer of the file system.

### Claim 11 (depends on 10)

The computer program product of claim 10, wherein the program code is further executable by the processor to:
upon dynamically reducing the threshold value, stop logging the data for the write transaction byte-range to the recovery log for byte-ranges length value exceeding the threshold value.

### Claim 12 (depends on 11)

The computer program product of claim 11, wherein the program code is further executable by the processor to:
upon dynamically increasing the threshold value, log the data for the write transaction byte-range with byte-ranges length values being less than the threshold value in the recovery log.

### Claim 13 (depends on 12)

The computer program product of claim 12, wherein the program code is further executable by the processor to:
upon determining not to place the data for the write transaction byte-range in the recovery log, and the byte-range overlaps with a byte-range for a file system block that has already been placed in a non-volatile layer of the file system, write all dirty byte-ranges for the file system block to primary storage in the file system and placing a marker in the non-volatile layer indicating that all previous updates to the file system block are skipped upon recovery upon a node failure.

### Claim 14 (depends on 13)

The computer program product of claim 13, wherein the program code is further executable by the processor to:
track byte-ranges that have been logged in the recovery log using a committed bit, wherein committed bits track which byte-ranges are in the recovery log such that a same byte-range is not logged to the recovery log again.

### Claim 15 (depends on 14)

The computer program product of claim 14, wherein the byte ranges to log in the recovery log are not yet marked using the committed bit and have a length value less than the threshold value.

### Claim 16 (depends on 15)

The computer program product of claim 15, wherein the program code is further executable by the processor to:
create a bit array that is an XOR of committed bits and dirty bits; and
perform an AND process with the dirty bits to determine the byte-ranges to log in the recovery log.

### Claim 17

A system comprising:
a file system including a primary storage device; and
a client node device coupled with a recovery log and a first memory device, the client node including a process that:
integrates a file system recovery log layer in the file system, buffers data in a cyclical manner, and transforms all incoming random requests into a series of synchronous sequential updates;
determines a length value of a write transaction byte-range for a received write transaction;
upon the length value exceeding a threshold value, write data for the write transaction byte-range to permanent storage in the file system;
upon the length value being less than the threshold value, write the data for the write transaction byte-range to a recovery log that is stored in the file system recovery log layer, wherein the threshold value is changed dynamically while the file system is mounted.

### Claim 18 (depends on 17)

The system of claim 17, wherein the process further:
upon dynamically reducing the threshold value, stops logging the data for the write transaction byte-range to the recovery log for byte-ranges length value exceeding the threshold value; and
upon dynamically increasing the threshold value, logs the data for the write transaction byte-range with byte-ranges length values being less than the threshold value in the recovery log,
wherein the file system recovery log layer comprises a non-volatile storage layer of the file system.

### Claim 19 (depends on 18)

The system of claim 18, wherein the process further:
upon determining not to place the data for the write transaction byte-range in the recovery log, and the byte-range overlaps with a byte-range for a file system block that has already been placed in a non-volatile layer of the file system, writes all dirty byte-ranges for the file system block to primary storage in the file system and placing a marker in the non-volatile layer indicating that all previous updates to the file system block are skipped upon recovery upon a node failure; and
tracks byte-ranges that have been logged in the recovery log using a committed bit, wherein committed bits track which byte-ranges are in the recovery log such that a same byte-range is not logged to the recovery log again;
wherein the byte ranges to log in the recovery log are not yet marked using the committed bit and have a length value less than the threshold value.

### Claim 20 (depends on 19)

The system of claim 19, wherein the process further:
creates a bit array that is an XOR of committed bits and dirty bits; and
performs an AND process with the dirty bits to determine the byte-ranges to log in the recovery log.
