Monitoring inter-site bandwidth for rebuilding
First Claim
1. A method for use in a dispersed storage network (DSN), the method comprising:
- monitoring a plurality physical sites communicatively coupled via a data link having a data link bandwidth, each of the plurality of physical sites hosting a plurality of distributed storage (DS) units hosted by a DSN memory;
determining a data loss rate associated with a particular physical site of the plurality of physical sites, wherein the data loss rate associated with the particular physical site includes data loss attributable to the plurality of DS units hosted at the particular physical site;
determining a threshold communication bandwidth associated with the particular physical site, the threshold communication bandwidth indicating a maximum portion of the data link bandwidth allocated to the particular physical site for slice rebuilding;
determining that the data loss rate associated with the particular individual physical site exceeds the threshold communication bandwidth associated with the particular physical site, wherein determining the data loss rate includes;
determining an average DS unit failure rate for DS units operating at the particular physical site;
multiplying capacities of the DS units operating at the particular physical site by the average DS unit failure rate; and
transmitting an alert message in response to determining that the data loss rate exceeds the threshold communication bandwidth.
1 Assignment
0 Petitions
Accused Products
Abstract
A dispersed storage network (DSN) includes a DSN memory employing multiple distributed storage (DS) units, e.g., memory devices, operating at multiple different physical sites, with each site having one or more of the memory devices. A monitoring entity can monitor the sites to determine a data loss rate and a threshold communication bandwidth, e.g., a bandwidth available for rebuilding encoded data slices, associated with particular sites. If the data loss rate of a particular site exceeds the threshold communication bandwidth, the monitoring unit can send an alert message notifying, for example, a DSN controller, an integrity processing unit, the DSN memory, about the determination, so that corrective action can be taken.
93 Citations
14 Claims
-
1. A method for use in a dispersed storage network (DSN), the method comprising:
-
monitoring a plurality physical sites communicatively coupled via a data link having a data link bandwidth, each of the plurality of physical sites hosting a plurality of distributed storage (DS) units hosted by a DSN memory; determining a data loss rate associated with a particular physical site of the plurality of physical sites, wherein the data loss rate associated with the particular physical site includes data loss attributable to the plurality of DS units hosted at the particular physical site; determining a threshold communication bandwidth associated with the particular physical site, the threshold communication bandwidth indicating a maximum portion of the data link bandwidth allocated to the particular physical site for slice rebuilding; determining that the data loss rate associated with the particular individual physical site exceeds the threshold communication bandwidth associated with the particular physical site, wherein determining the data loss rate includes; determining an average DS unit failure rate for DS units operating at the particular physical site; multiplying capacities of the DS units operating at the particular physical site by the average DS unit failure rate; and transmitting an alert message in response to determining that the data loss rate exceeds the threshold communication bandwidth. - View Dependent Claims (2, 3, 4, 5)
-
-
6. A processing system configured to implement a managing unit, the managing unit comprising:
-
a computing core including associated memory; a network interface configured to couple the managing unit to a dispersed storage network (DSN) including one or more DSN memory devices; the computing core configured to; monitor a plurality physical sites communicatively coupled via a data link having a data link bandwidth, each of the plurality of physical sites hosting a plurality of distributed storage (DS) units hosted by a particular DSN memory device; determine a data loss rate associated with a particular physical site, wherein the data loss rate associated with the particular physical site includes data loss attributable to the plurality of DS units hosted at the particular physical site, wherein determining the data loss rate includes; determining an average DS unit failure rate for DS units operating at the particular physical site; multiplying capacities of the DS units operating at the particular physical site by the average DS unit failure rate; compare the data loss rate associated with a particular physical site to a threshold communication bandwidth associated with the particular physical site, the threshold communication bandwidth indicating a maximum portion of the data link bandwidth allocated to the particular physical site for slice rebuilding; and transmit an alert message in response to determining that the data loss rate exceeds the threshold communication bandwidth. - View Dependent Claims (7, 8, 9, 10)
-
-
11. A dispersed storage network (DSN) comprising:
-
a DSN memory including a plurality of memory devices located at a particular physical site; at least one processing core implementing an integrity processing unit configured to rebuild encoded data slices; at least one processing core implementing a managing unit configured to; monitor a plurality physical sites communicatively coupled via a data link having a data link bandwidth, each of the plurality of physical sites hosting a plurality of distributed storage (DS) units hosted by a particular DSN memory device; determine a data loss rate associated with a particular physical site, wherein the data loss rate associated with the particular physical site includes data loss attributable to the plurality of DS units hosted at the particular physical site, wherein determining the data loss rate includes; determining an average DS unit failure rate for DS units operating at the particular physical site; multiplying capacities of the DS units operating at the particular physical site by the average DS unit failure rate; compare the data loss rate associated with a particular physical site to a threshold communication bandwidth associated with the particular physical site, the threshold communication bandwidth indicating a maximum portion of the data link bandwidth allocated to the particular physical site for slice rebuilding; and transmit an alert message in response to determining that the data loss rate exceeds the threshold communication bandwidth. - View Dependent Claims (12, 13, 14)
-
Specification