Migration of unified table metadata graph nodes

• US 10,474,648 B2
• Filed: 11/25/2014
• Issued: 11/12/2019
• Est. Priority Date: 11/25/2014
• Status: Active Grant

• Current Assignee: SAP SE
• Original Assignee: SAP SE
• Inventors: Schreter, Ivan, Thomsen, Dirk
• Primary Examiner(s): Gurmu, Muluemebet
• Application Number:
  US14/553,571
• Publication Number:
  US 20160147819A1
• Time in Patent Office: 1,813 Days
• Field of Search: 707707, 707701
• CPC Class Codes: G06F 16/214 Database migration support

Abstract

Metadata is stored within a database for each of a plurality of objects in different frames associated with a structure descriptor (e.g., a container directory entry, etc.). The frames are part of a metadata page and each comprising an object and a header specifying a version identifier for the object and a size of the object. The structure descriptor initially is built for a first build identifier. Thereafter, upon the structure descriptor changing from the first build identifier to a second build identifier, at least one of the objects that require migration is identified. The identification is based on the version identifier for the object being different from the second build identifier. In response, the identified objects are migrated from their corresponding frame to a new frame. The new frame includes the objects and new headers that include a version identifier equal to the second build identifier.

Claims

1. A method comprising:

storing, within an in-memory database, a metadata page describing a composition of a unified table, the unified table comprising a plurality of columns of data, each column having a column type, data for each column stored in at least one page chain, the metadata page comprising a plurality of structure descriptors forming a tree of metadata corresponding to the structure of the unified table, the metadata page further comprising metadata for each of a plurality of objects in different frames associated with one of the plurality of structure descriptors describing a database structure of the corresponding object, the different frames being part of the metadata page, each different frame comprising an object and a header specifying a version identifier for the object and a size of the object, the plurality of structure descriptors initially being for a first build identifier, wherein the plurality of objects comprises columns of data;

identifying, upon the plurality of structure descriptors changing from the first build identifier to a second build identifier, at least one of the objects that requires migration, the identification being based on the version identifier for the object being different from the second build identifier;

migrating only the objects from their corresponding frame to a new frame in the in-memory database, the new frame including the objects and new headers that include a version identifier equal to the second build identifier, wherein each object is migrated from its corresponding frame to the new frame by generating a corresponding new object in the new frame that is larger than the object, and subsequently populating data encapsulated in the object to the new object in the new frame; and

deactivating the different frames from which the objects have been migrated after completion of the migration.

2. The method of claim 1 further comprising:

modifying the objects to be compatible with the second build identifier.

3. The method of claim 2, wherein the objects are modified prior to the migration.

4. The method of claim 2, wherein the objects are modified as part of the migration.

5. The method of claim 1, wherein the version identifier for the object is less than the second build identifier.

6. The method of claim 1, wherein the in-memory database is a column-oriented database that stores data tables as sections of columns.

14. The method of claim 1, wherein the plurality of structure descriptors describing a database structure of the corresponding object comprises at least one of:

a number of columns, a type of column, a location in the database structure, a pointer to another one of the plurality of structure descriptors, and a pointer to a page chain.

7. A non-transitory computer program product storing instructions which, when executed by at least one hardware data processor forming part of at least one computing system, result in operations comprising:

storing, within an in-memory database, a metadata page describing a composition of a unified table, the unified table comprising a plurality of columns of data, each column having a column type, data for each column stored in at least one page chain, the metadata page comprising a plurality of structure descriptors forming a tree of metadata corresponding to the structure of the unified table, the metadata page further comprising metadata for each of a plurality of objects in different frames associated with one of the plurality of structure descriptors describing a database structure of the corresponding object, the different frames being part of the metadata page, each different frame comprising an object and a header specifying a version identifier for the object and a size of the object, the plurality of structure descriptors initially being for a first build identifier, wherein the plurality of objects comprises columns of data;

identifying, upon the plurality of structure descriptors changing from the first build identifier to a second build identifier, at least one of the objects that requires migration, the identification being based on the version identifier for the object being different from the second build identifier;

migrating only the objects from their corresponding frame to a new frame in the in-memory database, the new frame including the objects and new headers that include a version identifier equal to the second build identifier, wherein each object is migrated from its corresponding frame to the new frame by generating a corresponding new object in the new frame that is larger than the object, and subsequently populating data encapsulated in the object to the new object in the new frame; and

deactivating the different frames from which the objects have been migrated after completion of the migration.

8. The non-transitory computer program product of claim 7, wherein the operations further comprise:

modifying the objects to be compatible with the second build identifier.

9. The non-transitory computer program product of claim 8, wherein the objects are modified prior to the migration.

10. The non-transitory computer program product of claim 8, wherein the objects are modified as part of the migration.

11. The non-transitory computer program product of claim 7, wherein the version identifier for the object is less than the second build identifier.

12. The non-transitory computer program product of claim 7, wherein the in-memory database stores data tables as sections of columns.

13. A system comprising:

at least one hardware data processor; and

memory storing instructions which, when executed by the at least one hardware data processor, result in operations comprising;

storing, within an in-memory database, a metadata page describing a composition of a unified table, the unified table comprising a plurality of columns of data, each column having a column type, data for each column stored in at least one page chain, the metadata page comprising a plurality of structure descriptors forming a tree of metadata corresponding to the structure of the unified table, the metadata page further comprising metadata for each of a plurality of objects in different frames associated with one of the plurality of structure descriptors describing a database structure of the corresponding object, the different frames being part of the metadata page, each different frame comprising an object and a header specifying a version identifier for the object and a size of the object, the plurality of structure descriptors initially being for a first build identifier, wherein the plurality of objects comprises columns of data;

identifying, upon the plurality of structure descriptors changing from the first build identifier to a second build identifier, at least one of the objects that requires migration, the identification being based on the version identifier for the object being different from the second build identifier;

migrating only the objects from their corresponding frame to a new frame in the in-memory database, the new frame including the objects and new headers that include a version identifier equal to the second build identifier, wherein each object is migrated from its corresponding frame to the new frame by generating a corresponding new object in the new frame that is larger than the object, and subsequently populating data encapsulated in the object to the new object in the new frame; and

deactivating the different frames from which the objects have been migrated after completion of the migration.