Abstract: A storage unit access method includes receiving an access request that includes an access address, where the access address includes one or more original addresses of at least one storage unit in a storage apparatus; identifying, based on global repair information, whether a failed unit exists in the storage unit to which the access address points, where the global repair information includes original addresses of all failed units and a redundant address of a redundant unit configured to replace each failed unit; when it is identified that a first failed unit exists, replacing an original address that is in the access address and that points to the first failed unit with a redundant address of a first redundant unit corresponding to the first failed unit; and sending an access request obtained after replacing the original address with the redundant address.

Abstract: A storage apparatus includes a first memory disposed in a first die and configured to store data, a second memory disposed in a second die and configured to store an error correcting code corresponding to the data. The error correcting code may be used to perform data protection on the data. A storage controller is configured to write the data into the first memory, and read the data from the first memory.

Abstract: A spring mechanism for a rocker assembly is disclosed, the spring mechanism being connected to a rocker mechanism of the rocker assembly to assist a rocker member of the rocker mechanism in returning from a rocking position to a rest position, wherein the spring mechanism comprises two mounting plates opposed at a spacing and two springs connected between the two mounting plates, each of the mounting plates being provided with holding structures for holding each of the springs in place on the mounting plate, wherein a spacer is provided between each mounting plate and each spring to avoid the mounting plate from contacting at least one turn of the spring.

Abstract: A method and an apparatus for implementing round robin scheduling are provided. The method includes: acquiring, from a queue, original location information of elements in the queue; performing location mapping processing on the original location information of the elements in the queue based on a set algorithm to obtain mapped location information of the elements in the queue, where the set algorithm or parameters used by the set algorithm change according to a set rule during each time of round robin scheduling; and starting from an element corresponding to a set initial location, performing round robin scheduling according to mapped queue sequences corresponding to the mapped location information of the elements. The method and the apparatus for implementing round robin scheduling can reduce the cost of storage devices and can ensure a balance in scheduling of elements in a service queue.

Abstract: The present invention discloses a delay request processing method and apparatus that are based on a token bucket and relates to the field of communications technologies, where the method and the apparatus are invented to shorten a scanning period when a delay request is processed. The method includes: receiving a delay request message of a queue corresponding to a token bucket, where the delay request message includes delay request time; determining, according to the delay request time, whether the delay request message needs to be processed preferentially; processing the delay request message in a preferentially processing manner when it is determined that the delay request message needs to be processed preferentially. The present invention may be applied to a delay request processing technology.

Abstract: The embodiments of the present invention disclose a token bucket-based traffic limiting method, including: when a packet is received, triggering a filling operation of filling each token bucket in a token bucket set under a scheduling node corresponding to the packet, where the token bucket set includes at least two token buckets; determining the number of tokens filled in each token bucket in the token bucket set according to a moment when the packet is received and a timestamp shared by the token bucket set; and if the number of tokens in a token bucket corresponding to the packet exceeds a length of the packet, allowing the packet to pass through the scheduling node and removing the number of tokens, corresponding to the length of the packet, from the token bucket corresponding to the packet.

Abstract: The present invention discloses a delay request processing method and apparatus that are based on a token bucket and relates to the field of communications technologies, where the method and the apparatus are invented to shorten a scanning period when a delay request is processed. The method includes: receiving a delay request message of a queue corresponding to a token bucket, where the delay request message includes delay request time; determining, according to the delay request time, whether the delay request message needs to be processed preferentially; processing the delay request message in a preferentially processing manner when it is determined that the delay request message needs to be processed preferentially. The present invention may be applied to a delay request processing technology.

Abstract: A method and an apparatus for implementing round robin scheduling are provided. The method includes: acquiring, from a queue, original location information of elements in the queue; performing location mapping processing on the original location information of the elements in the queue based on a set algorithm to obtain mapped location information of the elements in the queue, where the set algorithm or parameters used by the set algorithm change according to a set rule during each time of round robin scheduling; and starting from an element corresponding to a set initial location, performing round robin scheduling according to mapped queue sequences corresponding to the mapped location information of the elements. The method and the apparatus for implementing round robin scheduling can reduce the cost of storage devices and can ensure a balance in scheduling of elements in a service queue.

Abstract: The embodiments of the present invention disclose a token bucket-based traffic limiting method, including: when a packet is received, triggering a filling operation of filling each token bucket in a token bucket set under a scheduling node corresponding to the packet, where the token bucket set includes at least two token buckets; determining the number of tokens filled in each token bucket in the token bucket set according to a moment when the packet is received and a timestamp shared by the token bucket set; and if the number of tokens in a token bucket corresponding to the packet exceeds a length of the packet, allowing the packet to pass through the scheduling node and removing the number of tokens, corresponding to the length of the packet, from the token bucket corresponding to the packet.