Method and apparatus for parallel execution in terminal database using data partitions

A parallel execution apparatus in a terminal database, comprising:

• a memory comprising instructions;
• and
• a processor coupled to the memory, wherein the instructions cause the processor to be configured to:
• select a set of central processing units (CPUs) from a plurality of CPUs based on a preset degree of parallelism, wherein the preset degree of parallelism indicates a quantity of threads executed in parallel;
• obtain a frequency of each selected CPU;
• calculate a frequency proportion of the selected CPUs;
• divide a to-be-queried data table in the terminal database into data partitions based on the frequency proportion of the selected CPUs, wherein when dividing the to-be-queried data table, the instructions further cause the processor to be configured to:
• read a quantity of data recorded in each subpage in layer-1 subpages in the to-be-queried data table that are connected to an index root page;
• and
• divide, based on the quantity of data recorded in each subpage and according to the frequency proportion of the selected CPUs, data recorded in the layer-1 subpages into N data partitions, wherein N equals to the preset degree of parallelism, and wherein a quantity proportion of the data recorded in the layer-1 subpages in the N data partitions is equal to the frequency proportion of the selected CPUs;
• determine a data partition corresponding to each selected CPU;
• and
• execute, in parallel, a query function on data in a corresponding data partition using each selected CPU.