Fault positioning method and device for storage system

• Main Authors: WEIHUANG WANG, KANG UK, SONG HONGYI, CHEN WANGBIN
• Format: Patent
• Language: Chinese; English
• Published: 01.03.2022
• Subjects: CALCULATING; COMPUTING; COUNTING; ELECTRIC COMMUNICATION TECHNIQUE; ELECTRIC DIGITAL DATA PROCESSING; ELECTRICITY; PHYSICS; TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHICCOMMUNICATION

The invention discloses a fault positioning method and device for a storage system, which can be used in the financial field or other fields. The method comprises the steps of obtaining IO stack time-consuming data of a storage system according to a preset information collection period and a preset period number, and determining stage time-consuming data according to the IO stack time-consuming data; determining a host failure rate ratio, a network failure rate ratio and a storage failure rate ratio according to the stage time consumption data and the period number; and obtaining a fault prediction curve according to the host fault rate ratio, the network fault rate ratio and the storage fault rate ratio, and obtaining a fault positioning result by using the fault prediction curve. According to the method, the fault prediction curve is formed by using the fault rate proportion of each stage of the IO stack, and the fault positioning range is reduced from the whole IO stack to three stages of a host, a network