Resource Monitoring in a Distributed Storage System
A distributed electronic storage system (DESS) comprises a plurality of computing devices communicatively coupled via one or more network links and having a file system distributed among them. The DESS comprises management circuitry that resides on the first computing device. The management circuitry is operable to generate an indication of a load on a first resource that resides on the first computing device. The management circuitry is operable to receive, via the one or more network links, an indication of a load on a second resource that resides on a second computing device of the plurality of computing devices. The management circuitry is operable to determine a condition of the DESS based on the indication of the load on the first resource and the indication of the load on the second resource.
1 - 22 . (canceled)
23 . A method for managing a distributed electronic storage system (DESS), the method comprising:
generating, via a first network adapter, an indication of a load on a first set of one or more resources;
receiving, via a network link, an indication of a load on a second set of one or more resources;
receiving an indication of a performance over the network link;
determining a condition of the DESS based on the performance over the network link, the indication of the load on the first set of one or more resources and the indication of the load on the second set of one or more resources, wherein a first computing device is operable to determine the condition as an overperformance condition.
24 . The method of claim 23 , wherein the first set of one or more resources resides on the first computing device.
25 . The method of claim 23 , wherein the first set of one or more resources comprises the first network adapter.
26 . The method of claim 23 , wherein the first network adapter is operable to store DESS traffic in a virtual container
27 . The method of claim 23 , wherein the second set of one or more resources resides on a second computing device
28 . The method of claim 27 , wherein the second set of one or more resources comprises a second network adapter operable to store DESS traffic.
29 . The method of claim 23 , wherein the condition is adaptable over time.
30 . The method of claim 23 , wherein the method comprises:
reducing a network congestion by changing a priority of DESS traffic according to the condition of the DESS.
31 . The method of claim 23 , wherein the method comprises:
adjusting, according to the condition of the DESS, one or more of:
a read batch timing setting,
a read batch size setting,
a write batch timing setting, and
a write batch size setting.
32 . The method of claim 23 , wherein the method comprises:
in response to the condition of the DESS being the overperformance condition, performing automatic provisioning of additional network bandwidth for use by the DESS, wherein the automatic provisioning of additional resources comprises one or more of:
automatic provisioning of an additional processing core for use by the DESS;
automatic provisioning of additional memory for use by the DESS; and
automatic provisioning of additional nonvolatile storage for use by the DESS.
33 . A system for managing a distributed electronic storage system (DESS), the system comprising:
a first computing device operable to:
generate, via a first network adapter, an indication of a load on a first set of one or more resources;
receive, via a network link, an indication of a load on a second set of one or more resources;
receive an indication of a performance over the network link;
determine a condition of the DESS based on the performance over the network link, the indication of the load on the first set of one or more resources and the indication of the load on the second set of one or more resources, wherein the first computing device is operable to determine the condition as an overperformance condition.
34 . The system of claim 33 , wherein the first set of one or more resources resides on the first computing device.
35 . The system of claim 33 , wherein the first set of one or more resources comprises the first network adapter.
36 . The system of claim 33 , wherein the first network adapter is operable to store DESS traffic in a virtual container
37 . The system of claim 33 , wherein the second set of one or more resources resides on a second computing device
38 . The system of claim 37 , wherein the second set of one or more resources comprises a second network adapter operable to store DESS traffic.
39 . The system of claim 33 , wherein the first computing device is operable adapt the condition over time.
40 . The system of claim 33 , wherein the first computing device is operable to reduce a network congestion by changing a priority of DESS traffic according to the condition of the DESS.
41 . The system of claim 33 , wherein the first computing device is operable to adjust, according to the condition of the DESS, one or more of:
a read batch timing setting,
a read batch size setting,
a write batch timing setting, and
a write batch size setting.
42 . The system of claim 33 , wherein the he first computing device is operable to, in response to the condition of the DESS being the overperformance condition, perform automatic provisioning of additional network bandwidth for use by the DESS, wherein the automatic provisioning of additional resources comprises one or more of:
automatic provisioning of an additional processing core for use by the DESS;
automatic provisioning of additional memory for use by the DESS; and
automatic provisioning of additional nonvolatile storage for use by the DESS.