Adaptively tuning polling intervals of control hosts in distributed storage systems

Patent metadata

Field	Value
Publication number	US-11099780-B2
Application number	US-201916384412-A
Country	US
Kind code	B2
Filing date	Apr 15, 2019
Priority date	Apr 15, 2019
Publication date	Aug 24, 2021
Grant date	Aug 24, 2021

Abstract

The described technology is generally directed towards adaptively tuning storage systems. According to an embodiment, a system can comprise a processor and computer executable components that can comprise an interval determiner to determine a polling interval based on an estimate of a workload of a shared data store on a data storage array, based on a change activity detected by the system. Further, a host controller can receive transactions from a host application, wherein the transactions perform one or more of updating the local data store, or querying the local data store for results, and a daemon process that, at the polling interval, performs one or more of, polling the data storage array for updates to the local data store based on the shared data store, or updating the shared data store based on the local data store.

First claim

What is claimed is:

1. A system, comprising:
a memory that stores computer executable components; and
a processor that executes the computer executable components stored in the memory, wherein the computer executable components comprise:
an interval determiner to determine a polling interval based on an estimate of a workload of a shared data store on a data storage array, based on a change activity detected by the system, wherein the change activity detected by the system comprises a rate of change of a size of a local data store in comparison to a first threshold;
a host controller to receive transactions from a host application, wherein the transactions perform one or more of updating the local data store, or querying the local data store for results; and
a daemon process that, at the polling interval, performs one or more of:
polling the data storage array for updates to the local data store based on the shared data store, or
updating the shared data store based on the local data store.

2. The system of claim 1 , wherein the change activity detected by the system further comprises a number of transactions received from the host application in comparison to a second threshold.

3. The system of claim 1 , wherein the host controller further receives transactions from one or more additional host applications, and wherein the change activity detected by the system further comprises a change in a total number of host applications from which transactions are received in comparison to a second threshold.

4. The system of claim 1 , wherein the daemon process measures a time for response from the data storage array for the polling for updates to the local data store and the updating the shared data store based on the local data store, and wherein the change activity detected by the system further comprises the time for response in comparison to a second threshold.

5. The system of claim 1 , wherein the change activity detected by the system further comprises an error in one or more of, the polling the data storage array for updates and the updating the shared data store based on the local data store, and wherein the change activity detected by the system further comprises a second of errors detected in comparison to a second threshold.

6. The system of claim 5 , wherein the interval determiner further determines a pause interval based on the polling interval, and wherein upon detection of the error, the system reduces activity based on the pause interval.

7. The system of claim 1 , wherein the data storage array comprises a group name server.

8. A computer-implemented method, comprising:
updating, by a data storage array comprising a processor, a shared data store, based on an update request received from a management host device;
receiving, by the data storage array, a polling request from the management host device, wherein the polling request is received at a polling interval determined by the management host device based on an estimate, by the management host device, of a workload of the shared data store, wherein the estimate of the workload of the shared data store is based on a change activity detected by the management host device, wherein the change activity detected by the host management device comprises a rate of change of a size of a local data store in comparison to a first threshold; and
responding, by the data storage array, to the polling request.

9. The computer-implemented method of claim 8 , wherein the change activity detected by the system further comprises a number of transactions received from host application in comparison to a second threshold.

10. The computer-implemented method of claim 8 , wherein host controller further receives transactions from one or more additional host applications, and wherein the change activity detected by the system further comprises a change in a total number of host applications from which transactions are received in comparison to a second threshold.

11. The computer-implemented method of claim 8 , wherein the daemon process further measures a time for response from the data storage array for the polling for updates to the local data store and the updating the shared data store based on the local data store, and wherein the change activity detected by the system further comprises the time for response in comparison to a second threshold.

12. The computer-implemented method of claim 8 , wherein the change activity detected by the system further comprises an error in one or more of, the polling the data storage device for updates and the updating the shared data store based on the data storage array.

13. The computer-implemented method of claim 12 , wherein the interval determiner further determines a pause interval based on the polling interval, and wherein upon detection of the error, the system reduces activity based on the pause interval.

14. A non-transitory machine-readable medium, comprising executable instructions that, when executed by a processor of a network device, facilitate performance of operations, comprising:
determining a polling interval based on an estimate of a workload of a shared data store on a data storage array, based on a change activity detected by the system, wherein the change activity comprises a rate of change of a size of a local data store in comparison to a first threshold;
receiving transactions from a host application, wherein the transactions perform one or more of updating the local data store, or querying the local data store for results; and
performing, by a daemon process at the polling interval, one or more of:
polling the data storage array for updates to the local data store based on the shared data store, or
updating the shared data store based on the local data store.

15. The non-transitory machine-readable medium of claim 14 , wherein the change activity further comprises a number of transactions received from the host application in comparison to a second threshold.

16. The non-transitory machine-readable medium of claim 14 , wherein the change activity further comprises a number of transactions received from the host application in comparison to a second threshold.

17. The non-transitory machine-readable storage medium of claim 14 , wherein the change activity further comprises a number of transactions received from a host application in comparison to a second threshold.

18. The non-transitory machine-readable medium of claim 14 , wherein the daemon process further measures a time for response from the data storage array for the polling for updates to the local data store and the updating the shared data store based on the local data store, and wherein the change activity detected by the system further comprises the time for response in comparison to a second threshold.

19. The non-transitory machine-readable medium of claim 14 , wherein the change activity further comprises an error.

20. The non-transitory machine-readable medium of claim 19 , wherein the operations further comprise:
determining, by an interval determiner, a pause interval based on the polling interval, wherein, upon detection of the error, the system reduces activity based on the pause interval.

Assignees

• Emc Ip Holding Co Llc

Inventors

• Jiang Xuedong
• Kinney Daryl F
• Copley John S
• Specht Michael E

Classifications

• G06F3/0689

  Disk arrays, e.g. RAID, JBOD · CPC title

• G06F3/067

  Distributed or networked storage systems, e.g. storage area networks [SAN], network attached storage [NAS] · CPC title

• G06F3/0604

  Improving or facilitating administration, e.g. storage management · CPC title

• G06F3/0659 Primary

  Command handling arrangements, e.g. command buffers, queues, command scheduling · CPC title