Fault-tolerant distributed information handling systems and methods
Fault-tolerant distributed information handling systems and methods, including a method in a system including: a first host configured to store a first fragment of data, a second host configured to store a second fragment of data, a third host configured to store a third fragment of data, and a fourth host configured to store a first code derived at least from the first fragment of data, the second fragment of data, and the third fragment of data, are provided. The method includes: the first agent transmitting via a multicast operation an updated second fragment of data to the second host and the fourth host; a second agent corresponding to the second host transmitting via a unicast operation the second fragment of data to the fourth host; and generating a second code derived from the first code, the second fragment of data, and the updated second fragment of data.
1. A method in an information handling system (IHS) comprising: (1) N hosts, wherein N is a positive integer, and wherein each of the N hosts is configured to store at least one fragment of data, (2) an N+1 host configured to store at least a first code derived from at least one fragment of data stored by each of a subset of the N hosts, (3) an N+2 host configured to store at least a second code derived from at least one fragment of data stored by each of the subset of the N hosts, the method comprising:
in response to receiving a request by a first agent corresponding to any of the N hosts regarding a first fragment of data stored by a second host from among the at least the subset of the N hosts:
the first agent transmitting via a multicast operation an updated first fragment of data to the second host, the N+1 host, and the N+2 host;
a second agent corresponding to the second host transmitting via a multicast operation the first fragment of data to the N+1 host and N+2 host;
an N+1 agent corresponding to the N+1 host generating a third code derived from at least the first code, the first fragment of data, and the updated first fragment of data; and
an N+2 agent corresponding to the N+2 host generating a fourth code derived from at least the second code, the first fragment of data, and the updated first fragment of data.
2. The method of claim 1 further comprising the second agent overwriting the first fragment of data with the updated first fragment of data.
3. The method of claim 1 further comprising: (1) the N+1 agent writing the third code to a storage disk associated with the N+1 host and (2) the N+2 agent writing the fourth code to a storage disk associated with the N+2 host.
4. The method of claim 1 , wherein the at least the first code is generated by performing an exclusive-OR operation using each one of the at least one fragment of data stored by each of the subset of the N hosts.
5. The method of claim 1 , wherein the third code is generated by performing an exclusive-OR operation using the at least the first code and each one of the at least one fragment of data stored by each of the subset of the N hosts.
6. The method of claim 1 further comprising in response to receiving the request by the first agent regarding the first fragment of data, the first agent transmitting a request to a cluster coordination module to determine: (1) a location of a disk corresponding to the first fragment of data, (2) a location of a disk corresponding to the at least the first code, and (3) a location of each of any other fragments of data requiring modification.
7. The method of claim 1 , wherein each of the at least the first code and the at least the second code is an erasure code, wherein the erasure code adds redundancy to the IHS to tolerate at least one failure in storage disks associated with the at least the subset of the N hosts.
8. A n information handling system (IHS) comprising:
N hosts, wherein N is a positive integer, and wherein each of the N hosts is configured to store at least one fragment of data;
an N+1 host configured to store at least a first code derived from at least one fragment of data stored by each of a subset of the N hosts;
a first agent corresponding to any of the N hosts configured to, in response to a request regarding a first fragment of data stored by a second host from among the at least a subset of the N hosts, transmit via a multicast operation an updated first fragment of data to the N+1 host;
a second agent corresponding to the second host configured to transmit via a unicast operation the updated first fragment of data to the N+1 host; and
an N+1 agent corresponding to the N+1 host configured to generate a second code derived from the at least the first code, the updated first fragment of data, and at least one fragment of data stored by each of the subset of the N hosts.
9. The IHS of claim 8 , wherein the second agent is further configured to overwrite the first fragment of data with the updated first fragment of data.
10. The IHS of claim 8 , wherein the N+1 agent is further configured to write the third code to a storage disk associated with the N+1 host.
11. The IHS of claim 8 , wherein the N+1 agent is configured to generate the at least the first code by performing an exclusive-OR operation using each one of the at least one fragment of data stored by each of the subset of the N hosts.
12. The IHS of claim 8 , wherein the N+1 agent is configured to generate the second code by performing an exclusive-OR operation using the at least the first code and each one of the at least one fragment of data stored by each of the subset of the N hosts.
13. The IHS of claim 8 further comprising a cluster coordination module configured to receive a request from the first agent to determine: (1) a location of a disk corresponding to the updated first fragment of data, (2) a location of a disk corresponding to the at least the first code, and (3) a location of each of any other fragments of data requiring modification.