Preventing input/output (I/O) traffic overloading of an interconnect channel in a distributed data storage system

Patent metadata

Field	Value
Publication number	US-9916275-B2
Application number	US-201514641889-A
Country	US
Kind code	B2
Filing date	Mar 9, 2015
Priority date	Mar 9, 2015
Publication date	Mar 13, 2018
Grant date	Mar 13, 2018

Abstract

Methods, computing systems and computer program products implement embodiments of the present invention that include configuring distributed storage system resources for a distributed storage system. Examples of the storage system resources include a plurality of network segments, one or more network devices coupled to the network, and multiple nodes coupled to the network, the nodes including both frontend and backend nodes. Upon receiving, by a given frontend node in the distributed storage system, an input/output (I/O) request, one or more of the distributed storage system resources required to process the I/O request are identified, and a respective load that the I/O request will generate on each of the identified distributed storage system resources is calculated. The distributed storage system processes the I/O request upon detecting that the respective loads are less than respective available capacities of the identified distributed storage system resources.

First claim

The invention claimed is:

1. A method, comprising:
configuring distributed storage system resources for a distributed storage system, the distributed storage system resources comprising a network comprising a plurality of network segments, multiple nodes coupled to the network, and one or more network devices coupled to the network;
receiving, by a given node of the distributed storage system, an input/output (I/O) request;
identifying one or more of the distributed storage system resources required to process the I/O request;
calculating a respective load that the I/O request will generate on each of the identified distributed storage system resources; and
processing the I/O request upon detecting that the respective loads are less than respective available capacities of the identified distributed storage system resources; wherein a respective capacity is defined for each of the distributed storage system resources; and further wherein detecting that the respective loads are less than respective available capacities of the distributed storage system resources comprises identifying, by the given node, one or more processes currently employing the identified distributed storage system resources, and determining, for each of the one or more processes, a respective utilization for each of the identified distributed storage system resources.

2. The method according to claim 1 , wherein each of the nodes is selected from a list consisting of a frontend node and a backend node, and wherein the given node comprises a given frontend node.

3. The method according to claim 1 , and comprising determining a respective amount of time each of the processes will be employing each of the identified distributed storage system resources.

4. The method according to claim 3 , and comprising, upon detecting that the respective loads are greater than respective available capacities of the identified distributed storage system resources, determining, based on the respective amounts of time, a subsequent time when the respective loads will be less than respective available capacities of the identified distributed storage system resources, and scheduling the I/O request for processing at the subsequent time.

5. A distributed storage system, comprising:
multiple distributed storage system resources comprising a network of multiple network segments, multiple nodes coupled to the network, and one or more network devices coupled to the network, a given node being configured:
to receive an input/output (I/O) request;
to identify one or more of the distributed storage system resources required to process the I/O request;
to calculate a respective load that the I/O request will generate on each of the identified one or more distributed storage system resources; and
to process the I/O request upon detecting that the respective one or more loads are less than respective one or more available capacities of the one or more identified distributed storage system resources; wherein a respective capacity is defined for each of the distributed storage system resources; and further wherein the given node is configured to detect that the respective loads are less than respective available capacities of the distributed storage system resources by identifying, by the given node, one or more processes currently employing the identified distributed storage system resources, and determining, for each of the one or more processes, a respective utilization for each of the identified distributed storage system resources.

6. The distributed storage system according to claim 5 , wherein each of the nodes is selected from a list consisting of a frontend node and a backend node, and wherein the given node comprises a given frontend node.

7. The distributed storage system according to claim 5 , wherein the given node is configured to determine a respective amount of time each of the processes will be employing each of the identified distributed storage system resources.

8. The distributed storage system according to claim 7 , wherein, upon detecting that the respective loads are greater than respective available capacities of the identified distributed storage system resources, the given node is configured to determine, based on the respective amounts of time, a subsequent time when the respective loads will be less than respective available capacities of the identified distributed storage system resources, and to schedule the I/O request for processing at the subsequent time.

9. A computer program product, the computer program product comprising:
a non-transitory computer readable storage medium having computer readable program code embodied therewith, the computer readable program code comprising:
computer readable program code configured to arrange distributed storage system resources for a distributed storage system, the distributed storage system resources comprising a network comprising a plurality of network segments, multiple nodes coupled to the network, and one or more network devices coupled to the network;
computer readable program code configured to receive, by a given node, an input/output (I/O) request;
computer readable program code configured to identify one or more of the distributed storage system resources required to process the I/O request;
computer readable program code configured to calculate a respective load that the I/O request will generate on each of the identified distributed storage system resources; and
computer readable program code configured to processing the I/O request upon detecting that the respective loads are less than respective available capacities of the identified distributed storage system resources; wherein a respective capacity is defined for each of the distributed storage system resources; and further wherein the computer readable program code is configured to detect that the respective loads are less than respective available capacities of the distributed storage system resources by identifying, by the given node, one or more processes currently employing the identified distributed storage system resources, and determining, for each of the one or more processes, a respective utilization for each of the identified distributed storage system resources.

10. The computer program product according to claim 9 , wherein each of the nodes is selected from a list consisting of a frontend node and a backend node, and wherein the given node comprises a given frontend node.

11. The computer program product according to claim 9 , and comprising computer readable program code configured to determine a respective amount of time each of the processes will be employing each of the identified distributed storage system resources, and, upon detecting that the respective loads are greater than respective available capacities of the identified distributed storage system resources, to determine, based on the respective amounts of time, a subsequent time when the respective loads will be less than respective available capacities of the identified distributed storage system resources, and to schedule the I/O request for processing at the subsequent time.

Assignees

• IBM

Inventors

• Barzik Zah
• Chen Lior
• Cohen Dan
• Shasha Osnat

Classifications

• G06F2206/1012

  Load balancing · CPC title

• G06F3/0635

  by changing the path, e.g. traffic rerouting, path reconfiguration · CPC title

• G06F3/0611

  in relation to response time · CPC title

• G06F13/4221 Primary

  being an input/output bus, e.g. ISA bus, EISA bus, PCI bus, SCSI bus · CPC title

• G06F3/067

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