REPLICATING DATA ACROSS DATA CENTERS

• US 20140067759A1
• Filed: 08/31/2012
• Published: 03/06/2014
• Est. Priority Date: 08/31/2012
• Status: Active Grant

• Current Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Original Assignee: Microsoft Corporation
• Inventors: Aguilera, Marcos Kawazoe, Cho, Brian
• Granted Patent: US 9,870,374 B2
• Time in Patent Office: Days
• US Class Current: 707/610
• CPC Class Codes: G06F 11/2094 Redundant storage or storage space G06F11/2056 takes precedence
• CPC Class Codes: G06F 11/2097 maintaining the standby controller/processing unit updated initialisation or re-synchronisation thereof G06F11/1658 and subgroups
• CPC Class Codes: G06F 16/184 implemented as replicated file system
• CPC Class Codes: H04L 67/1095 Replication or mirroring of data, e.g. scheduling or transport for data synchronisation between network nodes
• CPC Class Codes: H04L 67/60 Scheduling or organising the servicing of application requests, e.g. requests for application data transmissions using the analysis and optimisation of the required network resources admission control or resource allocation H04L47/70

Abstract

The present techniques prioritize transmission of feature information associated with data copies in data transmission, and selectively transmit the data copies when necessary. As the size of the feature information is small compared with the data copies, and as feature information is transmitted using prioritized messages, delays caused by congestion in the network are reduced. Based on the use of prioritized messages, the present techniques provide solutions for replicating data across data centers when conducting various data operations including reading, writing, and modifying data. The present techniques also replicate data across data centers while providing consistency, access locality, and disaster tolerance.

Claims

1. A method comprising:

separating a data copy at a computing device from its associated feature information, the feature information including an update indicator that indicates update information of the data copy;

transmitting a prioritized message including the feature information apart from the data copy; and

determining that the data copy is qualified for transmission at least partly in response to determining that the data copy is a latest data copy at least partly based on the feature information.

2. The method as recited in claim 1, wherein the determining that the data copy is qualified for transmission is further in response to determining that the computing device is a local computing device relative to a computing system that requests the data copy.

3. The method as recited in claim 1, wherein the transmitting the prioritized message comprises:

transmitting the prioritized message from the computing device to another computing device via a privileged path; and

propagating the data copy from the computing device to another computing device via a non-privileged path.

4. The method as recited in claim 1, wherein the transmitting the prioritized message comprising transmitting the prioritized message ahead of the data copy at a path between two data centers.

5. A method comprising:

receiving, at a computing device, multiple prioritized messages from multiple computing devices, each of the multiple prioritized message including a respective update indicator indicating update information of a respective data copy stored at a respective computing device; and

finding, by the computing device, a first update indicator that indicates presently latest update information from multiple indicators included in the multiple prioritized messages.

6. The method as recited in claim 5, wherein a size of the respective prioritized message is smaller than a size of the respective data copy.

7. The method as recited in claim 5, wherein the respective update indicator includes a timestamp that indicates when the respective data copy was last updated at the respective computing device.

8. The method as recited in claim 5, wherein the finding the first update indicator comprises:

ranking the multiple update indicators received from the multiple prioritized messages based on their respective update information included in the multiple update indicators; and

finding the first indicator that has a highest ranking.

9. The method as recited in claim 5, further comprising requesting, by the computing device, at least one computing device to send a data copy stored at the at least one computing device if the data copy is associated with a second update indicator indicating update information that is at least as up-to-date as that of the first update indicator.

10. The method as recited in claim 9, wherein the requesting at least one computing device to send the data copy comprises:

sending the first update indicator to a plurality of computing devices; and

requesting each of the plurality of computing devices to send a stored data copy if its update indicator includes update information at least as up-to-date as that of the first update indicator

11. The method as recited in claim 9, wherein the requesting at least one computing device to send the data copy comprises:

determining one or more computing devices from the multiple computing devices that store one or more data copies associated with the first update indicator;

determining whether the one or more computing devices includes a local computing device;

if there is at least one local computing device, requesting a data copy from one of the at least one local computing device; and

if there is no local computing device in the one or more computing devices, selecting a remote computing device from the one or more computing devices from which to request a data copy stored at the remote computing device.

12. The method as recited in claim 11, wherein the selecting the remote computing device from the one or more computing devices comprises:

ranking transmission latencies of the one or more computing devices;

selecting a remote computing device that has a transmission latency less than a threshold; and

requesting the selected remote sever to send a data copy stored at the select remote computing device.

13. The method as recited in claim 9, further comprising writing a latest update indicator to a plurality of computing devices.

14. The method as recited in claim 5, further comprising

requesting, by the computing device, at least one computing device to send a data copy stored at the at least one computing device if the data copy is associated with a second update indicating update information that is at least as up-to-date as that of the first update indicator;

applying one or more modification commands to the data copy to obtain a modified data copy;

associating a new update indicator with the modified data copy; and

storing the modified data copy and the new update indicator at a local computing device.

15. The method as recited in claim 14, further comprising propagating the modified data copy and associated new update indicator from the local computing device to one or more remote computing devices.

16. The method as recited in claim 14, wherein:

the requesting the multiple prioritized messages comprises requesting the multiple prioritized messages via a privileged path;

the requesting the at least one computing device to send the data copy comprises requesting the at least one computing device to send the data copy via the privileged path; and

propagating the modified data copy and associated new update indicator from the local computing device to one or more remote computing devices comprises propagating the modified data copy and associated new update indicator from the local computing device to one or more remote computing devices via a non-privileged path.

17. The method as recited in claim 5, further comprising:

determining one or more computing devices from the multiple computing devices that store one or more data copies associated with the first update indicator;

sending one or more modification commands and a new update indicator to at least one of the remote computing devices; and

requesting the at least one of the remote computing devices to apply the one or more modification commands to its stored respective data copy to obtain a modified data copy and associate the new update indicator with the modified data copy.

18. A method comprising:

obtaining new data and a new update indicator;

generating a prioritized message associated with the new data, the prioritized message including at least the new update indicator that indicates update information of the new data;

storing one or more copies of the prioritized message and the new data at one or more local computing devices respectively; and

sending the prioritized message to a plurality of computing devices including one or more remote computing devices apart from the new data.

19. The method as recited in claim 18, wherein the storing one or more copies of the prioritized message and the new data at one or more local computing devices respectively comprises:

receiving an acknowledgment from a respective local computing device when the respective local computing device stores a respective copy of the new data; and

in response to a result of determining that a number of local computing devices that send the acknowledgment is not more than a threshold, waiting to receive another acknowledgement from another respective local computing device before sending the prioritized message to the plurality of computing devices.

20. The method as recited in claim 18, further comprising propagating copies of the new data from the one or more local computing devices to one or more remote computing devices.