Zone consistency

• US 10,496,671 B1
• Filed: 06/30/2014
• Issued: 12/03/2019
• Est. Priority Date: 05/05/2014
• Status: Active Grant

• Current Assignee: Emc IP Holding Company LLC (Dell Technologies Inc.)
• Original Assignee: Emc IP Holding Company LLC (Dell Technologies Inc.)
• Inventors: Srivastav, Shashwat, Sankaran, Sriram, Gaddamadugu, Subba, Musial, Peter, Robertson, Andrew, Yuan, Huapeng, Zhang, Qi, Luo, Jun, Shah, Vishrut, Wang, Chen
• Primary Examiner(s): Burke, Jeff A
• Assistant Examiner(s): Dewan, Kamal K
• Application Number:
  US14/319,113
• Time in Patent Office: 1,982 Days
• Field of Search: 707611, 707E1722, 711108, 711114, 711165, 714 411, 714E11101, 714E11107
• CPC Class Codes: G06F 12/0831 using a bus scheme, e.g. with bus monitoring or watching means
• CPC Class Codes: G06F 16/13 File access structures, e.g. distributed indices arrangements of input from, or output to, record carriers G06F3/06
• CPC Class Codes: G06F 16/2246 Trees, e.g. B+trees
• CPC Class Codes: G06F 16/273 Asynchronous replication or reconciliation
• CPC Class Codes: G06F 16/275 Synchronous replication
• CPC Class Codes: G06F 3/0604 Improving or facilitating administration, e.g. storage management
• CPC Class Codes: G06F 3/0611 in relation to response time
• CPC Class Codes: G06F 3/0614 Improving the reliability of storage systems
• CPC Class Codes: G06F 3/0619 in relation to data integrity, e.g. data losses, bit errors
• CPC Class Codes: G06F 3/0626 Reducing size or complexity of storage systems
• CPC Class Codes: G06F 3/0638 Organizing or formatting or addressing of data
• CPC Class Codes: G06F 3/065 Replication mechanisms
• CPC Class Codes: G06F 3/0653 Monitoring storage devices or systems
• CPC Class Codes: G06F 3/0655 Vertical data movement, i.e. input-output transfer; data movement between one or more hosts and one or more storage devices
• CPC Class Codes: G06F 3/067 Distributed or networked storage systems, e.g. storage area networks [SAN], network attached storage [NAS]
• CPC Class Codes: G06F 3/0689 Disk arrays, e.g. RAID, JBOD
• CPC Class Codes: G06F 9/5061 Partitioning or combining of resources
• CPC Class Codes: H04L 67/1095 Replication or mirroring of data, e.g. scheduling or transport for data synchronisation between network nodes

Abstract

A computer implemented method, system, and computer program product for enabling strong consistency of unique objects between zones comprising enabling consistency of an unique data object between in zones by switching between consistency techniques to keep the unique data object consistent between the zones; wherein read and write access is enabled to the unique object in the zones.

Claims

1. A computer implemented method-comprising:

creating strong consistency for a unique data object directly accessible by a client in both of two zones sharing a common file system namespace, each zone representing a different network partition;

wherein the unique data object appears to the client to be the same data object in each of the zones;

wherein the unique data object has a unique way to be accessed by the client within the file system namespace;

wherein strong consistency ensures that if the unique data object is accessed at either zone in the namespace, the data of the unique data object appears to the client to be the same across zones in the namespace whether the unique data object is accessed in a first zone of the two zones or a second zone of the two zones by switching between consistency techniques to keep the unique data object consistent between the two zones;

wherein direct read and write access by the client is enabled to the unique data object in each of the two zones;

wherein the consistency technique includes rules governing access to the unique data object across the two zones;

wherein the consistency techniques include application of synchronous and asynchronous copying of the unique data object from the first zone to the second zone;

wherein the consistency techniques include configuring each of the first zone and the second zone to send each other respective first and second periodic heartbeats, each respective periodic heartbeat configured to ensure its respective recipient zone that the respective sender of the respective periodic heartbeat knows that there has not been a network partition between the first and second zones, wherein the first and second respective zones are each assured that each has the latest data as long as each is receiving its respective heartbeat from the other zone; and

wherein different techniques are applied to each of the unique data objects being synchronized based on the number of read and write requests to the each object at each zone; and

determining, based on the consistency techniques, including at least the first and second heartbeats, and in response to a read request to a specified zone, whether the unique data object in the specified zone has the most up to date information; and

if the specified zone is determined to have the most up to date information, then servicing the read request; and

if the specified zone is determined not to have the most up to date information, at least one of redirecting the read request to another zone or failing the read request.

2. The method of claim 1 wherein each zone of the zones is a data center and the zones are connected by a wide area connection.

3. The method of claim 1 further comprising:

observing access requests to a set of unique data objects accessible in the zones;

determining a synchronization technique for each unique data object in the set of unique data objects;

based on the determining, applying a synchronous synchronization technique to a first unique data object of the set of unique objects; and

based on the determining, applying an asynchronous synchronization technique to a second unique data object of the set of unique data objects.

12. The method of claim 1 wherein the unique data object has an owner;

wherein the owner is in the first zone;

wherein the data in the first zone has the most up to date information;

establishing a first lease between the first zone and the second zone;

wherein the first lease is renewed by a third respective heartbeat;

periodically sending the third respective heartbeat from the first zone to the second zone;

wherein the second zone is determined to not have the most up to date data if the second zone has not received the third respective heartbeat within a predetermined period of time; and

wherein the second zone is determined to have the most up to date data if the third respective heartbeat is received at the second zone is within the predetermined period of time.

17. The computer program product of claim 12, further comprising:

breaking the first lease between the first zone and the second zone by sending a message from the first zone to the second zone that the first lease is not valid;

wherein when the first lease is not valid the determination for the unique object is that the second zone does not have the most up to date information.

18. The computer program product of claim 12, wherein the predetermined period time comprises at least one of:

a fixed period of time;

a period of time dynamically determined based on observations of network traffic in a network where the two zones are operating; and

a period of time dynamically determined based on information about at least one failure in a network where the two zones are operating.

19. The method of claim 1, wherein at least one of the first and second zones continues to send its respective first or second heartbeat even if it is not receiving the respective heartbeat from the other of the first and second zones.

20. The method of claim 1, wherein at least one of the first and second zones stops sending its respective first or second heartbeat once it stops receiving the respective heartbeat from the other of the first and second zones.

4. A system comprising:

one or more processors;

zones, including a different storage device at each zone of the zones;

a unique data object stored in the zones; and

computer-executable program code operating in memory, wherein the computer-executable program code is configured to cause the one or more processors to execute;

creating strong consistency for the unique data object directly accessible by a client in both of two zones in a file system namespace;

wherein the unique data object appears to be the same data object in each of the zones;

wherein the unique data object has a unique way to be accessed by the client within the file system namespace;

wherein strong consistency ensures that if the unique data object is accessed at either zone in the file system namespace, the data of the unique data object appears to be the same across zones in the namespace whether the unique object is accessed in a first zone of the two zones or a second zone of the two zones by switching between consistency techniques to keep the unique data object consistent between the two zones;

wherein direct read and write access by the client is enabled to the unique data object in each of the two zones;

wherein the consistency technique includes rules governing access to the unique data object across the two zones;

wherein the consistency techniques include application of synchronous and asynchronous copying of the unique data object from the first zone to the second zone;

wherein the consistency techniques include configuring the first zone and the second zone to each send each other respective first and second periodic heartbeats, each respective periodic heartbeat configured to ensure that each of the first and second zones knows that there has not been a network partition between the first and second zones and that the respective zone is assured that it has the latest data as long as it is receiving its respective heartbeat from the other zone; and

wherein different techniques are applied to each of the unique data objects being synchronized based on the number of read and write requests to the each data object at each zone;

wherein the computer-executable program code further enables one or more processors to execute;

determining, based on the consistency techniques, including at least the first and second heartbeats, and in response to a read request to a specified zone, whether the unique data object in the specified zone has the most up to date information;

if the specified zone is determined to have the most up to date information, then servicing the read request; and

if the specified zone is determined not to have the most up to date information, at least one of redirecting the read request to another zone or failing the read request.

5. The system of claim 4 wherein each zone of the zones is a data center and the zones are connected by a wide area connection.

6. The system of claim 5 wherein the program code is further configured to enable the one or more processors to execute:

observing access requests to a set of unique data objects accessible in the zones;

determining a synchronization technique for each unique data object in the set of unique objects;

based on the determining, applying a synchronous synchronization technique to a first unique data object of the set of unique data objects; and

based on the determining, applying an asynchronous synchronization technique to a second unique data object of the set of unique data objects.

13. The system of claim 4 wherein the unique data object has an owner;

wherein the owner is in the first zone;

wherein the data in the first zone has the most up to date information, and wherein the computer-executable program code is further configured to cause the one or more processors to execute;

establishing a first lease between the first zone and the second zone;

wherein the first lease is renewed by a third respective heartbeat;

periodically sending the third respective heartbeat from the first zone to the second zone;

wherein the second zone is determined to not have the most up to date data if the second zone has not received the third respective heartbeat within a predetermined period of time; and

wherein the second zone is determined to have the most up to date data if the third respective heartbeat is received at the second zone is within the predetermined period of time.

14. The system of claim 13, wherein the predetermined period time comprises at least one of:

a fixed period of time;

a period of time dynamically determined based on observations of network traffic in a network where the two zones are operating; and

a period of time dynamically determined based on information about at least one failure in a network where the two zones are operating.

15. The system of claim 13, wherein the computer-executable program code is further configured to cause the one or more processors to execute:

breaking the first lease between the first zone and the second zone by sending a message from the first zone to the second zone that the first lease is not valid;

wherein when the first lease is not valid the determination for the unique object is that the second zone does not have the most up to date information.

7. A computer program product comprising:

a non-transitory computer-readable storage medium encoded with computer-executable program code enabling one or more processors to execute;

creating strong consistency for a unique data object accessible by a client in both of two zones in a file system namespace;

wherein the unique data object appears to be the same data object in each of the zones;

wherein the unique data object has a unique way to be accessed within the file system namespace;

wherein strong consistency ensures that if the unique data object is accessed at either zone in the namespace, the data of the unique data object appears to be the same across zones in the file system namespace whether the unique data object is accessed in a first zone of the two zones or a second zone of the two zones by switching between consistency techniques to keep the unique data object consistent between the two zones;

wherein direct read and write access by the client is enabled to the unique data object in each of the two zones;

wherein the consistency technique includes rules governing access to the unique data object;

wherein the consistency techniques include application of synchronous and asynchronous copying of the unique data object from the first zone to the second zone;

wherein the consistency techniques include configuring the first zone and the second zone to each send each other respective first and second periodic heartbeats, each respective periodic heartbeat configured to ensure that each of the first and second zones knows that there has not been a network partition between the first and second zones and that the respective zone is assured that it has the latest data as long as it is receiving its respective heartbeat from the other zone; and

wherein different techniques are applied to each of the unique data objects being synchronized based on the number of read and write requests to the each data object at each zone;

determining, based on the consistency techniques, including at least the first and second heartbeats, and in response to a read request to a specified zone, whether the unique data object in the specified zone has the most up to date information;

if the specified zone is determined to have the most up to date information, then servicing the read request;

if the specified zone is determined not to have the most up to date information, at least one of redirecting the read request to another zone or failing the read request.

8. The computer product of claim 7 wherein each zone of the zones is a data center and the zones are connected by a wide area connection.

9. The computer product of claim 8 wherein the computer-executable program code further enables one or more processors to execute:

observing access requests to a set of unique data objects accessible in the zones;

determining a synchronization technique for each unique data object in the set of unique objects;

based on the determining, applying a synchronous synchronization technique to a first unique data object of the set of unique objects; and

based on the determining, applying an asynchronous synchronization technique to a second unique data object of the set of unique data objects.

10. The computer program product of claim 7 wherein the unique data object has an owner;

wherein the owner is in the first zone;

wherein the data in the first zone has the most up to date information;

wherein the computer-executable program code further enables one or more processors to execute;

establishing a first lease between the first zone and the second zone;

wherein the first lease is renewed by a third respective heartbeat and has a first respective lease period;

periodically sending the third respective heartbeat from the first zone to the second zone;

wherein the second zone is determined to not have the most up to date data if the second zone has not received the third respective heartbeat within a predetermined period of time; and

wherein the second zone is determined to have the most up to date data if the third respective heartbeat is received at the second zone is within the predetermined period of time.

11. The computer program product of claim 10 wherein the computer-executable program code further enables one or more processors to execute:

breaking the first lease between the first zone and the second zone by sending a message from the first zone to the second zone that the first lease is not valid;

wherein when the first lease is not valid the determination for the unique object is that the second zone does not have the most up to date information.

16. The computer program product of claim 10, wherein the predetermined period time comprises at least one of:

a fixed period of time;

a period of time dynamically determined based on observations of network traffic in a network where the two zones are operating; and

a period of time dynamically determined based on information about at least one failure in a network where the two zones are operating.