Disk detection method and apparatus

Abstract

The present invention provides a disk detection method and apparatus. The method includes: collecting a set of N pieces of real-time data that are in a one-to-one correspondence with N input/output I/O-related counters of a disk, where the N I/O-related counters include an I/O response time of the disk and a counter affecting the I/O response time; the I/O response time is a time between delivery of an operation request by an application and reception of a response of the disk to the request; determining, according to the N pieces of real-time data, whether the I/O response time is abnormal; and outputting a detection result if the I/O response time is abnormal, where the detection result is used to represent that the I/O response time is abnormal.

What is claimed is: 
     
         1 . A disk detection method, comprising:
 collecting a set of N pieces of real-time data that are in a one-to-one correspondence with N I/O-related counters of a disk, wherein the N I/O-related counters comprise an I/O response time of the disk and a counter affecting the I/O response time, the I/O response time is a time between delivery of an operation request by an application and reception of a response of the disk to the request, and N is an integer greater than or equal to 2; and   using the N pieces of real-time data as a data point in an N-dimensional coordinate system, wherein N dimensions in the N-dimensional coordinate system are in a one-to-one correspondence with the N I/O-related counters; and   determining whether a first distance from the data point to a clustering center in the N-dimensional coordinate system is greater than a predetermined distance, wherein the clustering center is a central point obtained by performing clustering processing on M N-dimensional data points corresponding to the N I/O-related counters and collected before the N pieces of real-time data are collected, and the predetermined distance is a distance that enables a probability that M distance values from the M N-dimensional data points to the clustering center are greater than the predetermined distance to be less than a user acceptable probability range; and   determining that the I/O response time is abnormal when the first distance is greater than the predetermined distance, wherein the I/O response time being abnormal indicates that the disk is incapable of normally running a service; and   outputting a detection result if the I/O response time is abnormal, wherein the detection result is used to represent that the I/O response time is abnormal.   
     
     
         2 . The method according to  claim 1 , wherein before the determining that the I/O response time is abnormal when the first distance is greater than the predetermined distance, further comprises:
 determining whether real-time data corresponding to the I/O response time exceeds a preset I/O response time threshold, wherein the I/O response time threshold is a threshold that enables a probability that M pieces of data that correspond to the I/O response time and that are of the M N-dimensional data points are greater than the I/O response time threshold to be less than a user acceptable probability range; and, wherein determining that the I/O response time is abnormal when the first distance is greater than the predetermined distance further comprises:   determining that the I/O response time is abnormal when the first distance is greater than the predetermined distance and the real-time data corresponding to the I/O response time exceeds the preset I/O response time threshold.   
     
     
         3 . The method according to  claim 1 , wherein before determining that the I/O response time is abnormal when the first distance is greater than the predetermined distance, further comprises:
 determining whether real-time data corresponding to a counter of the N I/O-related counters, the counter representing a load magnitude, exceeds a preset load range, wherein the preset load range is a full range or a partial range of a range between minimum load and maximum load that the disk is capable of supporting; and, wherein determining that the I/O response time is abnormal when the first distance is greater than the predetermined distance further comprises:   determining that the I/O response time is abnormal when the first distance is greater than the predetermined distance and the real-time data corresponding to the counter that represents a load magnitude is in the preset load range.   
     
     
         4 . The method according to  claim 1 , wherein before determining that the I/O response time is abnormal when the first distance is greater than the predetermined distance, further comprises:
 determining whether real-time data corresponding to the I/O response time exceeds a preset I/O response time threshold, wherein the I/O response time threshold enables a probability indicating that M pieces of data of the M N-dimensional data points corresponding to the I/O response time are greater than the I/O response time threshold to be less than a user acceptable probability range; and   determining whether real-time data corresponding to a counter of the N I/O-related counters, the counter representing a load magnitude, exceeds a preset load range, wherein the preset load range is a full range or a partial range of a range between minimum load and maximum load that the disk is capable of supporting; and, wherein determining that the I/O response time is abnormal when the first distance is greater than the predetermined distance further comprises:
 determining that the I/O response time is abnormal when the first distance is greater than the predetermined distance, the real-time data corresponding to the I/O response time exceeds the preset I/O response time threshold, and the real-time data corresponding to the counter that represents a load magnitude is in the preset load range. 
   
     
     
         5 . An electronic device, comprising:
 a memory, configured to store data used by a processor; and   the processor, configured to:   collect a set of N pieces of real-time data that are in a one-to-one correspondence with N input/output I/O-related counters of a disk, wherein the N I/O-related counters comprise an I/O response time of the disk and a counter affecting the I/O response time, wherein the I/O response time is a time between delivery of an operation request by an application and reception of a response of the disk to the request, and N is an integer greater than or equal to 2; and   use the N pieces of real-time data as a data point in an N-dimensional coordinate system, wherein N dimensions in the N-dimensional coordinate system are in a one-to-one correspondence with the N I/O-related counters; and   determine whether a first distance from the data point to a clustering center in the N-dimensional coordinate system is greater than a predetermined distance, wherein the clustering center is a central point obtained by performing clustering processing on M N-dimensional data points corresponding to the N I/O-related counters and collected before the N pieces of real-time data are collected, and the predetermined distance is a distance that enables a probability that M distance values from the M N-dimensional data points to the clustering center are greater than the predetermined distance to be less than a user acceptable probability range; and   determine that the I/O response time is abnormal when the first distance is greater than the predetermined distance, wherein the I/O response time being abnormal indicates that the disk is incapable of normally running a service; and   output a detection result if the I/O response time is abnormal, wherein the detection result is used to represent that the I/O response time is abnormal.   
     
     
         6 . The electronic device according to  claim 5 , wherein the processor is configured to:
 determine whether real-time data corresponding to the I/O response time exceeds a preset I/O response time threshold, wherein the I/O response time threshold enables a probability indicating that M pieces of data of the M N-dimensional data points corresponding to the I/O response time are greater than the I/O response time threshold to be less than a user acceptable probability range; and   determine that the I/O response time is abnormal when the first distance is greater than the predetermined distance and the real-time data corresponding to the I/O response time exceeds the preset I/O response time threshold.   
     
     
         7 . The electronic device according to  claim 5 , wherein the processor is configured to:
 determine whether real-time data corresponding to a counter that represents a load magnitude and that is of the N I/O-related counters exceeds a preset load range, wherein the preset load range is a full range or a partial range of a range between minimum load and maximum load that the disk is capable of supporting; and   determine that the I/O response time is abnormal when the first distance is greater than the predetermined distance and the real-time data corresponding to the counter that represents a load magnitude is in the preset load range.   
     
     
         8 . The electronic device according to  claim 5  wherein the processor is configured to:
 determine whether real-time data corresponding to the I/O response time exceeds a preset I/O response time threshold, wherein the I/O response time threshold enables a probability indicating that M pieces of data of the M N-dimensional data points corresponding to the I/O response time are greater than the I/O response time threshold to be less than a user acceptable probability range; 
 determine whether real-time data corresponding to a counter of the N I/O-related counters exceeds a preset load range, the counter representing a load magnitude, wherein the preset load range is a full range or a partial range of a range between minimum load and maximum load that the disk is capable of supporting; and 
 determine that the I/O response time is abnormal when the first distance is greater than the predetermined distance, the real-time data corresponding to the I/O response time exceeds the preset I/O response time threshold, and the real-time data corresponding to the counter that represents a load magnitude is in the preset load range. 
 
     
     
         9 . A disk system, comprising:
 a disk; and   a disk controller, configured to:   collect a set of N pieces of real-time data that are in a one-to-one correspondence with N input/output I/O-related counters of the disk, wherein the N I/O-related counters comprise an I/O response time of the disk and a counter affecting the I/O response time, wherein the I/O response time is a time between delivery of an operation request by an application and reception of a response of the disk to the request, and N is an integer greater than or equal to 2; and   use the N pieces of real-time data as a data point in an N-dimensional coordinate system, wherein N dimensions in the N-dimensional coordinate system are in a one-to-one correspondence with the N I/O-related counters; and   determine whether a first distance from the data point to a clustering center in the N-dimensional coordinate system is greater than a predetermined distance, wherein the clustering center is a central point obtained by performing clustering processing on M N-dimensional data points that correspond to the N I/O-related counters and that are collected before the N pieces of real-time data are collected, and the predetermined distance is a distance that enables a probability that M distance values from the M N-dimensional data points to the clustering center are greater than the predetermined distance to be less than a user acceptable probability range; and   determine that the I/O response time is abnormal when the first distance is greater than the predetermined distance, wherein the I/O response time being abnormal indicates that the disk is incapable of normally running a service; and   output a detection result if the I/O response time is abnormal, wherein the detection result is used to represent that the I/O response time is abnormal.   
     
     
         10 . The disk system according to  claim 9 , wherein the disk controller is configured to:
 determine whether real-time data corresponding to the I/O response time exceeds a preset I/O response time threshold, wherein the I/O response time threshold enables a probability that M pieces of data of the M N-dimensional data points corresponding to the I/O response time and that are are greater than the I/O response time threshold to be less than a user acceptable probability range; and   determine that the I/O response time is abnormal when the first distance is greater than the predetermined distance and the real-time data corresponding to the I/O response time exceeds the preset I/O response time threshold.   
     
     
         11 . The disk system according to  claim 9 , wherein the disk controller is configured to:
 determine whether real-time data corresponding to a counter of the N I/O-related counters exceeds a preset load range, the counter representing a load magnitude, wherein the preset load range is a full range or a partial range of a range between minimum load and maximum load that the disk is capable of supporting; and   determine that the I/O response time is abnormal when the first distance is greater than the predetermined distance and the real-time data corresponding to the counter that represents a load magnitude is in the preset load range.   
     
     
         12 . The disk system according to  claim 9 , wherein the disk controller is configured to:
 determine whether real-time data corresponding to the I/O response time exceeds a preset I/O response time threshold, wherein the I/O response time threshold enables a probability indicating that M pieces of data of the M N-dimensional data points corresponding to the I/O response time are greater than the I/O response time threshold to be less than a user acceptable probability range;   determine whether real-time data corresponding to a counter that represents a load magnitude and that is of the N I/O-related counters exceeds a preset load range, wherein the preset load range is a full range or a partial range of a range between minimum load and maximum load that the disk is capable of supporting; and   determine that the I/O response time is abnormal when the first distance is greater than the predetermined distance, the real-time data corresponding to the I/O response time exceeds the preset I/O response time threshold, and the real-time data corresponding to the counter that represents a load magnitude is in the preset load range.