Storage paths
A method for controlling data traffic within a storage area network can be provided. The method can comprise analyzing data for a path in a storage area network to determine whether the path should be identified as a less preferred path, and controlling data traffic routing to avoid use of a path identified as a less preferred path. In some embodiments, the data can be obtained from a host bus adaptor in the path. In some embodiments, the controlling can comprise throttling traffic over a path identified as a less preferred path.
1. A method for controlling data traffic in a storage area network, the method comprising:
a computer system storing one or more tables identifying a plurality of paths between the computer system and a logical storage unit in the storage area network;
the computer system analyzing a first set of one or more statistics of a first path of the plurality of paths;
in response to the first set of statistics satisfying a first threshold:
the computer system storing a first indication in the one or more tables, wherein the first indication identifies the first path as being a less preferred path;
the computer system reducing I/O traffic provided to the logical storage unit via the first path;
the computer system increasing I/O traffic provided to the logical storage unit via a second path of the plurality of paths;
after reducing the I/O traffic provided to the logical storage unit via the first path for a predetermined time period, the computer system initiating a restoration process, including analyzing a second set of one or more statistics of the first path by generating test traffic and transmitting the test traffic to the logical storage unit via the first path;
in response to the second set of statistics satisfying a second threshold:
the computer system storing a second indication in the one or more tables, wherein the second indication identifies the first path as being a preferred path;
the computer system increasing I/O traffic provided to the logical storage unit via the first path.
2. The method of claim 1 , wherein satisfying the second threshold includes determining that a time for completing an I/O request is below a predetermined amount of time.
3. The method of claim 1 , wherein satisfying the second threshold includes determining that a number of outstanding I/O requests is below a predetermined queue threshold.
4. The method of claim 1 , wherein the test traffic is transmitted using FibreChannel, InfiniBand, ATA over Ethernet (AoE), or iSCSI (Internet Small Computer System Interface).
5. The method of claim 1 , wherein increasing the I/O traffic provided to the storage device via the second path includes rescheduling pending I/O requests provided via the first path for transmission via the second path.
6. The method of claim 1 , wherein satisfying the second threshold includes determining that a level of detected errors is below a predetermined error threshold.
7. The method of claim 1 , wherein the first and second thresholds are the same.
8. The method of claim 1 , wherein the first and second threshold are different from one another.
9. The method of claim 1 , wherein the first and second sets of statistics include one or more of the following statistics: a start time of an I/O request, an end time of an I/O request, a size of an I/O request, or a number of outstanding I/O requests.
10. The method of claim 1 , wherein the logical storage unit is a logical unit number (LUN).
11. A computing system comprising:
one or more processors;
memory storing program instructions executable by the one or more processors to:
store information identifying a plurality of paths between the computer system and a logical storage unit in a storage area network;
analyze a first set of one or more statistics of a first path of a plurality of paths;
in response to the first set of statistics satisfying a first threshold:
indicate in the stored information that the first path is a less preferred path;
reduce I/O traffic provided to the logical storage unit via the first path;
increase I/O traffic provided to the logical storage unit via a second path of the plurality of paths;
after reducing the I/O traffic provided to the logical storage unit via the first path for a predetermined time period, initiate a restoration process, including analyzing a second set of one or more statistics of the first path by generating test traffic and transmitting the test traffic to the logical storage unit via the first path;
in response to the second set of statistics satisfying a second threshold:
indicate in the stored information that the first path is a preferred path; and
increase I/O traffic provided to the logical storage unit via the first path.
12. The computing system of claim 11 , wherein satisfying the second threshold includes determining that a time for completing an I/O request is below a predetermined timeout threshold.
13. The computing system of claim 11 , wherein satisfying the second threshold includes determining that a level of detected errors is below a predetermined error threshold.
14. The computing system of claim 11 , wherein satisfying the second threshold includes determining that a number of pending I/O requests is below a predetermined queue threshold.
15. The computing system of claim 11 , wherein the first and second thresholds are.
16. The computer system of claim 11 , wherein the first and second threshold are different from one another.
17. The computer system of claim 11 , wherein the first and second sets of statistics include one or more of the following statistics: a start time of an I/O request, an end time of an I/O request, a size of an I/O request, or a number of outstanding I/O requests.
18. The computer system of claim 11 , wherein the first and second sets of statistics include information obtained from one or more switches along the first path, and wherein the obtained information includes a number of dropped packets or a number of transmission errors.
19. The computer system of claim 11 , wherein the restoration process is configured to transmit the test traffic using FibreChannel, InfiniBand, ATA over Ethernet (AoE), or iSCSI (Internet Small Computer System Interface).
20. The computer system of claim 11 , wherein the restoration process is configured to generate the test traffic and transmit the test traffic until the second set of statistics has satisfied the second threshold for at least a predetermined time period.