Validating workload distribution in a storage area network
An information system identifies redundant communication paths between a server and a storage device in a storage area network and classifies the state of the paths according to the distribution of workload amongst them. To make the classification, the information system pairs up active paths. For each pair of active paths, the information system identifies traffic data of the two paths. The information system compares the traffic data of the two paths. Based on the comparison, the information system determines whether workload is balanced or imbalanced between the two paths.
1. A computer-implemented method comprising:
identifying an active path between a server and a storage device in a storage area network, the active path having associated with it first traffic data, the first traffic data including a plurality of first data points;
selecting from a plurality of paths between the server and the storage device, a paired path having associated with it second traffic data, the second traffic data including a plurality of second data points;
comparing, by a processing device, each data point in a first subset of the first data points with a corresponding second data point in a second subset of the second data points to determine a percentage difference between the compared data points, wherein the compared data points each represent traffic data on one of the active path or the paired path at a same point in time;
classifying each of the compared data points as balanced or imbalanced based on the percentage difference;
determining, based on the comparison, a measure indicating whether the active path is balanced with respect to the paired path; and
transmitting the determined measure to a user device for display to a user.
2. The method of claim 1 , wherein the paired path is selected from among the plurality of paths based on the paired path being on a different switch fabric than the active path.
3. The method of claim 1 , wherein the paired path is selected from among the plurality of paths based on a similarity between the first traffic data and the second traffic data.
4. The method of claim 1 , wherein the first traffic data describes network traffic on the active path and the second traffic data describes network traffic on the paired path.
5. The method of claim 1 , wherein the first data points are data transmission rates of the active path at various times and the second data points are data transmission rates of the paired path at various times.
6. The method of claim 1 , wherein the first subset of the first data points are data points above a noise threshold and the second subset of the data points are second data points above the noise threshold.
7. The method of claim 1 , wherein compared data points are classified as balanced responsive to the percentage difference between the compared data points being below a classification threshold.
8. The method of claim 1 , wherein the compared data points are classified as imbalanced responsive to the percentage difference between the compared data points being above a classification threshold.
9. The method of claim 1 , wherein the measure is determined based on the classification of each of the compared data points.
10. The method of claim 1 , wherein determining the measure comprises:
classifying the active path and the paired path as balanced responsive to each of the compared data points being classified as balanced.
11. The method of claim 1 , wherein determining the measure comprises:
classifying the active path and the paired path as balanced responsive to:
a percentage of data points classified as imbalanced being less than a first number;
a difference between a percentage of data points classified as balanced and the percentage of data points classified as imbalanced being greater than a second number; and
a difference between an average value of the data points classified as balanced and an average value of the data points classified as imbalanced being greater than a third number.
12. The method of claim 1 , wherein determining the measure of balance comprises:
classifying the active path as imbalanced with respect to the paired path responsive to one or more of the following not being true:
a percentage of data points classified as imbalanced being less than a first number;
a difference between a percentage of data points classified as balanced and the percentage of data points classified as imbalanced being greater than a second number; and
a difference between an average value of the data points classified as balanced and an average value of the data points classified as imbalanced being greater than a third number.
13. The method of claim 1 , further comprising:
responsive to determining that workload is imbalanced between the active path and the paired path, determining whether the active path and the paired path recently became imbalanced.
14. The method of claim 1 , further comprising:
responsive to determining that workload is imbalanced between the active path and the paired path, determining whether the active path and the paired path recently became balanced.
15. The method of claim 1 , further comprising:
determining a redundancy score for the active path and paired path based on whether the paired path is on a different switch fabric than the active path.
16. A computer-implemented method comprising:
identifying a first entity that processes network traffic, the first entity having associated with it first traffic data, the first traffic data including a plurality of first data points;
selecting from a plurality of additional entities that process network traffic, a second entity having associated with it second traffic data, the second traffic data including a plurality of second data points;
comparing, by a processing device, each data point in a first subset of the first data points with a corresponding second data point in a second subset of the second data points to determine a percentage difference between the compared data points, wherein the compared data points each represent traffic data associated with one of the first entity or the second entity at a same point in time;
classifying each of the compared data points as balanced or imbalanced based on the percentage difference;
determining, based on the comparison, a measure indicating whether the first entity is balanced with respect to the second entity; and
transmitting the determined measure to a user device for display to a user.
17. A computer-implemented method comprising:
identifying a first path in a network, the first path having associated with it first traffic data, the first traffic data including a plurality of first data points;
selecting from a plurality of paths in the network, a second path having associated with it second traffic data, the second traffic data including a plurality of second data points;
comparing, by a processing device, each data point in a first subset of the first data points with a corresponding second data point in a second subset of the second data points to determine a percentage difference between the compared data points, wherein the compared data points each represent traffic data on one of the first path or the second path at a same point in time;
classifying each of the compared data points as balanced or imbalanced based on the percentage difference;
determining, based on the comparison, a measure indicating whether the first path is balanced with respect to the second path; and
transmitting the determined measure to a user device for display to a user.
18. The method of claim 17 , wherein the first traffic data describes network traffic on the first path and the second traffic data describes network traffic on the second path.
19. The method of claim 17 , wherein the second path is selected from among the plurality of paths based on a similarity between the first traffic data and the second traffic data.