Method and system for providing coordinated checkpointing to a group of independent computer applications

• US 9,389,959 B1
• Filed: 06/20/2014
• Issued: 07/12/2016
• Est. Priority Date: 08/26/2005
• Status: Active Grant

• Current Assignee: International Business Machines Corporation
• Original Assignee: Open Invention Network LLC
• Inventors: Backensto, Keith Richard, Havemose, Allan
• Primary Examiner(s): Lottich, Joshua P
• Application Number:
  US14/310,573
• Time in Patent Office: 753 Days
• Field of Search: 709/213, 709/223, 714/4, 714/7, 714/15, 714/4.1, 714/6.3, 714/38.1, 717/128, 717/170, 717/171, 719/320
• US Class Current: 1/1
• CPC Class Codes: G06F 11/1407 Checkpointing the instruction stream
• CPC Class Codes: G06F 11/1438 Restarting or rejuvenating
• CPC Class Codes: G06F 11/1451 by selection of backup contents
• CPC Class Codes: G06F 11/1471 involving logging of persistent data for recovery
• CPC Class Codes: G06F 11/1482 by means of middleware or OS functionality
• CPC Class Codes: G06F 11/203 using migration
• CPC Class Codes: G06F 2201/805 Real-time
• CPC Class Codes: G06F 2201/84 Using snapshots, i.e. a logical point-in-time copy of the data
• CPC Class Codes: G06F 2201/85 Active fault masking without idle spares
• CPC Class Codes: G06F 9/30145 Instruction analysis, e.g. decoding, instruction word fields
• CPC Class Codes: G06F 9/461 Saving or restoring of program or task context
• CPC Class Codes: G06F 9/4843 by program, e.g. task dispatcher, supervisor, operating system
• CPC Class Codes: G06F 9/4856 resumption being on a different machine, e.g. task migration, virtual machine migration G06F9/5088 takes precedence

Abstract

A system and method thereof for performing loss-less migration of an application group. In an exemplary embodiment, the system may include a high-availability services module structured for execution in conjunction with an operating system, and one or more computer nodes of a distributed system upon which at least one independent application can be executed upon. The high-availability services module may be structured to be executable on the one or more computer nodes for loss-less migration of the one or more independent applications, and is operable to perform checkpointing of all state in a transport connection.

Claims

1. A system, comprising:

interceptors configured to intercept fork( ) and exec( );

a checkpointer structured to checkpoint applications that use fork( ) and exec( );

one or more computer nodes upon which one or more applications can be loaded and executed;

a shared memory comprising one or more shared memory locations; and

wherein said checkpointer is configured to store in said shared memory at least one of a global application state including checkpoint barrier information having a barrier semaphore ID, a Virtual PID table, a Pipe table, a Semaphore ID table, and a “

System V shared memory Segment ID”

table;

wherein the system is configured to, upon an exec call by an application being issued, pass control of the application to the interceptors, call, by the interceptors, an operating system exec( ), use an environment variable to preserve across exec( ) a number of times a process has exec'"'"'ed, and run said interceptors for fork( ) and exec( ) in user-space;

wherein the system is configured to call the application'"'"'s entry point to run the application; and

wherein a custom_init( ) function is preloaded.

2. The system according to claim 1 comprising a high-availability services module is structured to be executable on the one or more computer nodes and is operable to perform checkpointing of all state in a transport connection, wherein the high-availability services module is operable to coordinate the checkpointing of the state of the transport connection across an application group comprised of the one or more independent applications.

3. The system according to claim 2, wherein the high-availability services module is operable to restore all states in the transport connection to the state they were in at a last checkpoint.

4. The system according to claim 3, wherein the high-availability services module is operable to coordinate recovery within a restore procedure that is coupled to the transport connection.

5. A method, comprising:

migrating an application group comprising one or more independent applications each executing on a primary node from the respective primary nodes of the one or more independent applications to at least one backup node;

installing interceptors for fork( ) and exec( );

preloading a custom_init( ) function;

upon issuing an exec( ) call by an independent application, passing control of the independent application to the interceptors, calling, by the interceptors, an operating system exec( ), using an environment variable to preserve across exec( ) a number of times a process has exec'"'"'ed, and running said interceptors for fork( ) and exec( ) in user-space; and

calling an independent application'"'"'s entry point to run the independent application;

wherein said one or more independent applications can use both fork( ) and exec( );

wherein said checkpoints store in a shared memory at least one of a global application state including checkpoint barrier information having a barrier semaphore ID, a Virtual PID table, a Pipe table, a Semaphore ID table, and a “

System V shared memory segment ID”

table.

6. The method according to claim 5, comprising flushing and halting the transport connection during a taking of the checkpoints.

7. The method according to claim 5, comprising maintaining transparency to a client connected to an independent application on a primary node over a transport connection, wherein the transparency is maintained by automatically coordinating transparent recovery of distributed applications of an application group comprised of the one or more independent applications.

8. A method, comprising:

installing interceptors for fork( ) and exec( );

preloading a custom_init( ) function;

loading and running an independent application wherein said independent application is a member of an application group comprised of one or more independent applications;

calling, by the interceptors, an operating system fork( ), creating a new application process from a parent process, passing control of the application back to the interceptors; and

upon the application issuing an exec call, passing control of the application to the interceptors;

calling, by the interceptors, an operating system exec( ) passing control of the application back to the interceptors, and running said interceptors for fork( ) and exec( ) in user-space;

calling an application'"'"'s entry point to run the application; and

storing in a shared memory at least one of a global application state including checkpoint barrier information having a barrier semaphore ID, a Virtual PID table, a Pipe table, a Semaphore ID table, and a “

System V shared memory segment ID”

table.

9. The method according to claim 8, comprising registering the new application process and updating process information for the parent process.

10. The method according to claim 9, comprising resuming execution of the parent process and executing a child process.

11. The method according to claim 10, comprising terminating and unregistering the parent process and the child process.

12. The method according to claim 11, comprising terminating the application.

13. A method, comprising:

preloading a custom_init( ) function;

loading an independent application;

installing interceptors for fork( ) and exec( );

storing in shared memory at least one of a global application state including checkpoint barrier information having a barrier semaphore ID, a Virtual PID table, a Pipe table, a Semaphore ID table, and a “

System V shared memory segment ID”

table; and

calling the independent application'"'"'s entry point to run the independent application;

upon the application issuing an exec call, passing control of the application to the interceptors, calling, by the interceptors, an operating system exec( ), and running said interceptors for fork( ) and exec( ) in user-space.

14. The method according to claim 13, comprising overlaying a new application image onto an existing application process and initializing the new image by registering the new image, restoring internal state from shared memory, and executing the new image.

15. A method, comprising:

installing interceptors for fork( ) and exec( );

storing in a shared memory at least one of a global application state including checkpoint barrier information having a barrier semaphore ID, a Virtual PID table, a Pipe table, a Semaphore ID table, and a “

System V shared memory segment ID”

table; and

upon issuing an exec call by an independent application, calling, by the interceptors, an operating system exec( ), overlaying a new image onto an existing application process, and using an environment variable to preserve across exec( ) a number of times a process has exec'"'"'ed.

16. The method according to claim 15 comprising initializing the new image and executing the new image.

17. The method according to claim 15 comprising upon issuing an exec call by an independent application, passing control of the application to the interceptors.

18. The method according to claim 15, wherein a shared memory ID of said shared memory and CPENV_EXEC are both written to an environment and used for re-initialization.

19. The method according to claim 15, comprising using said shared memory to preserve key system states across the exec( ) and the fork( ), wherein said shared memory is configured to be outside an address space of the independent application.

20. A method, comprising:

installing interceptors for fork( ) and exec( );

initializing an application image, restoring all internal state from a first shared memory, and executing the application image;

storing in a second shared memory at least one of a global application state including checkpoint barrier information having a barrier semaphore ID, a Virtual PID table, a Pipe table, a Semaphore ID table, and a “

System V shared memory segment ID”

table; and

upon an application issuing an exec call, passing control of the application to the interceptors, calling, by the interceptors, an operating system exec( ), and using an environment variable to preserve, across exec, a number of times a process must exec prior to restoring its data;

wherein said interceptors for fork( ) and exec( ) are configured to operate in user-space.