# US 2022/0066996 A1 · "bouncing" io pattern for replication protocols

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

- Number: US 2022/0066996 A1
- Document ID: US20220066996A1
- Status: Published application
- Kind: A1
- Application number: 17/007,972
- Filed: 2020-08-31
- Published: 2022-03-03
- Earliest claimed: 2020-08-31
- Assignees: Oracle International Corporation
- Applicants: Oracle International Corporation
- Inventors: Andrey Efimov
- Web page: https://patentgrep.com/patent/US20220066996A1

## CPC

- G06F 16/184: {implemented as replicated file system}
- G06F 16/27: Replication, distribution or synchronisation of data between databases or within a distributed database system; Distributed database system architectures therefor
- G06F 3/0604: {Improving or facilitating administration, e.g. storage management}
- G06F 3/065: {Replication mechanisms}
- G06F 3/0655: {Vertical data movement, i.e. input-output transfer; data movement between one or more hosts and one or more storage devices}
- G06F 3/067: {Distributed or networked storage systems, e.g. storage area networks [SAN], network attached storage [NAS]}
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)

## Abstract

a first request to replicate a first transaction and execute a batching process to replicate the first transaction. The batching process can include selecting a first server for replication of the first transaction, determining that a pending acknowledgement from the selected first server has not been identified, adding the first transaction to a first batch for the first server, and sending the first batch including only the first transaction. The master controller can receive a second request to replicate a second transaction, execute the batching process with the master controller to replicate the second transaction, which executing of the batching process includes adding the second transaction to a second batch including a plurality of transactions, receive an acknowledgement indicative of completion of replication, and send the second batch upon receipt of the acknowledgement indicative of completion of replication.

## Claims

### Claim 1

A method comprising:
receiving a first request to replicate a first transaction at a master controller from a replication requestor;
executing a batching process with the master controller to replicate the first transaction on at least some of a plurality of servers in a replication cluster, the batching process comprising:
selecting with the master controller a first server for replication of the first transaction from the replication cluster;
determining that a pending acknowledgement from the selected first server has not been identified;
adding the first transaction to a new first batch for the first server; and
sending the first batch to the first server selected for replication of the first transaction, wherein the first transaction is an only transaction in the first batch; and
receiving a second request to replicate a second transaction at the master controller;
executing the batching process with the master controller to replicate the second transaction on at least some of the plurality of servers in the replication cluster, wherein executing the batching process to replicate the second transaction on at least some of the plurality of servers in the replication cluster comprises adding the second transaction to a second batch for the first server, the second batch comprising a plurality of transactions;
receiving with the master controller an acknowledgement indicative of completion of replication from each of the at least some of the plurality of servers in the replication cluster; and
sending the second batch, wherein the sending of the second batch is triggered by receipt of the acknowledgement indicative of completion of replication.

### Claim 2 (depends on 1)

The method of claim 1, further comprising sending with the master controller a response to the replication requestor indicating completion of the replication.

### Claim 3 (depends on 2)

The method of claim 2, further comprising determining completion of the replication when a value associated with the received acknowledgment indicative of completion of replication meets or exceeds a threshold value.

### Claim 4 (depends on 1)

The method of claim 1, wherein the batching process is executed by the master controller for each of the plurality of servers in the replication cluster.

### Claim 5 (depends on 4)

The method of claim 4, wherein executing the batching process causes the master controller to, for each of the plurality of servers in the replication cluster, send the first transaction in a batch to each of the plurality of servers in the replication cluster.

### Claim 6 (depends on 5)

The method of claim 5, wherein at least some of the batches sent to different servers in the plurality of servers in the replication cluster are non-identical.

### Claim 7 (depends on 1)

The method of claim 1, further comprising: determining that no current unsent batch is available for the first server; and creating the first batch for the first server.

### Claim 8 (depends on 7)

The method of claim 7, wherein the plurality of transactions included in the second batch are received subsequent to the sending of the first batch to the first server selected for replication of the first transaction.

### Claim 9 (depends on 8)

The method of claim 8, wherein the batching process for the second request further comprises:
selecting with the master controller the first server for replication of the second transaction from the replication cluster;
determining that an acknowledgement of completion of previous batch processing has been received from the selected first server; and
identifying the second batch for the first server, wherein the second batch comprises a current unsent batch.

### Claim 10 (depends on 9)

The method of claim 9, wherein a size of the second batch varies based on a timing of receipt of the acknowledgement indicative of completion of replication.

### Claim 11 (depends on 9)

The method of claim 9, wherein the second batch is not full when sent to the first server.

### Claim 12 (depends on 9)

The method of claim 9, wherein adding the second transaction to the second batch for the first server comprises determining that the adding of the second transaction to the second batch does not increase a size of the second batch beyond a maximum size.

### Claim 13 (depends on 12)

The method of claim 12, wherein adding the second transaction to the second batch for the first server comprises:
identifying a maximum size for the second batch;
identifying the size of the second batch after the adding of the second transaction;
determining that the adding of the second transaction to the second batch does not exceed the maximum size for the second batch; and
adding the second transaction to the second batch.

### Claim 14 (depends on 13)

The method of claim 13, wherein identifying the maximum size for the second batch comprises retrieving information identifying a maximum batch size for the first server.

### Claim 15 (depends on 13)

The method of claim 13, wherein identifying the maximum size for the second batch comprises:
determining a hardware attribute of the first server; and
identifying a maximum batch size based on the hardware attribute of the first server.

### Claim 16 (depends on 15)

The method of claim 15, wherein the hardware attribute comprises an amount of random access memory of the first server.

### Claim 17 (depends on 1)

The method of claim 1, wherein the master controller is a subsystem within one of the plurality of servers in the replication cluster.

### Claim 18 (depends on 17)

The method of claim 17, wherein the first server comprises the one of the plurality of servers in the replication cluster containing the master controller.

### Claim 19

A non-transitory computer-readable storage medium storing a plurality of instructions executable by one or more processors, the plurality of instructions when executed by the one or more processors cause the one or more processors to:
receive a first request to replicate a first transaction at a master controller from a replication requestor;
execute a batching process with the master controller to replicate the first transaction on at least some of a plurality of servers in a replication cluster, the batching process comprising:
selecting with the master controller a first server for replication of the first transaction from the replication cluster;
determining that a pending acknowledgement from the selected first server has not been identified;
adding the first transaction to a new first batch for the first server; and
sending the first batch to the first server selected for replication of the first transaction, wherein the first transaction is an only transaction in the first batch;
receive a second request to replicate a second transaction at the master controller;
execute the batching process with the master controller to replicate the second transaction on at least some of the plurality of servers in the replication cluster, wherein executing the batching process to replicate the second transaction on at least some of the plurality of servers in the replication cluster comprises adding the second transaction to a second batch for the first server, the second batch comprising a plurality of transactions;
receive with the master controller an acknowledgement indicative of completion of replication from each of the at least some of the plurality of servers in the replication cluster; and
send the second batch, wherein the sending of the second batch is triggered by receipt of the acknowledgement indicative of completion of replication.

### Claim 20

A system comprising:
a replication cluster comprising:
a plurality of servers; and
a master controller configured to:
receive a first request to replicate a first transaction from a replication requestor;
execute a batching process to replicate the first transaction on at least some of the plurality of servers in the replication cluster, the batching process comprising:
selecting a first server for replication of the first transaction from the replication cluster;
determining that a pending acknowledgement from the selected first server has not been identified;
adding the first transaction to a first batch for the first server; and
sending the first batch to the first server selected for replication of the first transaction, wherein the first transaction is an only transaction in the first batch;
receive a second request to replicate a second transaction at the master controller;
execute the batching process with the master controller to replicate the second transaction on at least some of the plurality of servers in the replication cluster, wherein executing the batching process to replicate the second transaction on at least some of the plurality of servers in the replication cluster comprises adding the second transaction to a second batch for the first server, the second batch comprising a plurality of transactions;
receive an acknowledgement indicative of completion of replication from each of the at least some of the plurality of servers in the replication cluster; and
send the second batch, wherein the sending of the second batch is triggered by receipt of the acknowledgement indicative of completion of replication.
