Shaping I/O traffic by managing queue depth in fractional increments

• US 9,575,667 B2
• Filed: 03/28/2016
• Issued: 02/21/2017
• Est. Priority Date: 06/20/2014
• Status: Active Grant

• Current Assignee: Dell International LLC (Dell Technologies Inc.)
• Original Assignee: Dell International LLC (Dell Technologies Inc.)
• Inventors: Oelke, Dan
• Primary Examiner(s): BAYOU, YONAS A
• Application Number:
  US15/082,043
• Publication Number:
  US 20160210059A1
• Time in Patent Office: 330 Days
• US Class Current: 1/1
• CPC Class Codes: G06F 11/1446 Point-in-time backing up or restoration of persistent data
• CPC Class Codes: G06F 11/3034 where the computing system component is a storage system, e.g. DASD based or network based digital input from or digital output to record carriers G06F3/06; digital recording or reproducing G11B20/18; for distributed storage of data in networks, e.g. transport arrangements for network file system [NFS], storage area networks [SAN] or network attached storage [NAS], H04L67/1097
• CPC Class Codes: G06F 11/3048 where the topology of the computing system or computing system component explicitly influences the monitoring activity, e.g. serial, hierarchical systems
• CPC Class Codes: G06F 11/3419 by assessing time
• CPC Class Codes: G06F 11/3433 for load management allocation of a server based on load conditions G06F9/505; load rebalancing G06F9/5083; redistributing the load in a network by a load balancer H04L67/1029
• CPC Class Codes: G06F 11/3452 Performance evaluation by statistical analysis
• CPC Class Codes: G06F 11/3485 for I/O devices
• CPC Class Codes: G06F 12/145 the protection being virtual, e.g. for virtual blocks or segments before a translation mechanism
• CPC Class Codes: G06F 13/161 with latency improvement
• CPC Class Codes: G06F 13/1642 with request queuing
• CPC Class Codes: G06F 2201/875 Monitoring of systems including the internet
• CPC Class Codes: G06F 3/0611 in relation to response time
• CPC Class Codes: G06F 3/0619 in relation to data integrity, e.g. data losses, bit errors
• CPC Class Codes: G06F 3/0665 at area level, e.g. provisioning of virtual or logical volumes
• CPC Class Codes: G06F 3/0689 Disk arrays, e.g. RAID, JBOD
• CPC Class Codes: H04L 43/0888 Throughput
• CPC Class Codes: H04L 63/0807 using tickets, e.g. Kerberos cryptographic mechanisms or cryptographic arrangements for entity authentication using tickets or tokens H04L9/3213

Abstract

A method for managing input/output (I/O) traffic in an information handling system. The method may include receiving electronic I/O requests from a network-attached server, determining a queue depth limit, monitoring latency of processed electronic I/O requests, and processing received electronic I/O requests. The number of electronic I/O requests permitted to be processed over a period of time may be based on a mathematical combination of the queue depth limit and a latency of processed electronic I/O requests. The determined queue depth limit may be a fractional value.

Claims

1. A method for managing input/output (I/O) traffic in an information handling system, the method comprising:

receiving electronic I/O requests from a network-attached server;

determining a queue depth limit;

monitoring latency of processed electronic I/O requests; and

processing received electronic I/O requests by;

managing a virtual bucket comprising a number of virtual tokens, each token representative of authorization for an I/O request to be processed; and

permitting a received I/O request to be processed if the virtual bucket comprises a number of virtual tokens greater than zero, and decrementing the number of virtual tokens by at least one;

wherein the number of electronic I/O requests permitted to be processed over a period of time is based on a mathematical combination of the queue depth limit and a latency of processed electronic I/O requests.

2. The method of claim 1, wherein the virtual tokens are added to the virtual bucket at any given time t_x according to the equation:

Tokens(t_x)=QueueDepthLimit*TimeElapsed(t_x−

t_x-1)/Latency

wherein Tokens(t_x) gives a value corresponding to a number of virtual tokens to be added to the virtual bucket at time t_x;

QueueDepthLimit is the determined queue depth limit;

TimeElapsed(t_x−

t_x-1) is an amount of time elapsed between time t_x and a time t_x-1, where t_x-1 is a point in time prior to time t_x; and

Latency is a latency of processed electronic I/O requests that have completed during the time elapsed between time t_x and a time t_x-1.

3. The method of claim 2, wherein Tokens(t_x) is calculated at periodic intervals.

4. The method of claim 3, wherein Tokens(t_x) is additionally calculated when an I/O request is received.

5. The method of claim 2, wherein Tokens(t_x) is calculated at random intervals.

6. The method of claim 2, wherein Tokens(t_x) is calculated when an I/O request is received.

7. The method of claim 2, wherein the QueueDepthLimit is a fractional value.

8. The method of claim 1, wherein the queue depth limit is a fractional value.

9. The method of claim 1, wherein processing received I/O requests further comprises waiting to process a received I/O request if the virtual bucket comprises a number of virtual tokens less than zero until the virtual bucket receives additional virtual tokens.

10. A method for managing input/output (I/O) traffic in an information handling system, the method comprising:

receiving electronic I/O requests from a plurality of network-attached servers;

determining a queue depth limit for each of the plurality of network-attached servers;

monitoring latency of processed electronic I/O requests; and

for each of the network-attached servers, processing received electronic I/O requests for that network-attached server by;

managing a virtual bucket comprising a number of virtual tokens, each token representative of authorization for an I/O request from at least that network-attached server to be processed; and

permitting a received I/O request from that network-attached server to be processed if the virtual bucket comprises a number of virtual tokens greater than zero, and decrementing the number of virtual tokens by at least one;

wherein the number of electronic I/O requests permitted to be processed for a given network-attached server over a period of time is based on a mathematical combination of the queue depth limit determined for that network-attached server and a latency of processed electronic I/O requests.

11. The method of claim 10, wherein the queue depth limit for one of the plurality of network-attached servers is different than at least one other of the plurality of network-attached servers.

12. The method of claim 10, wherein the virtual tokens are added to the virtual bucket at any given time t_x according to the equation:

Tokens(t_x)=QueueDepthLimit*TimeElapsed(t_x−

t_x-1)/Latency

wherein Tokens(t_x) gives a value corresponding to a number of virtual tokens to be added to the virtual bucket at time t_x;

QueueDepthLimit is the determined queue depth limit for that network-attached server;

TimeElapsed(t_x−

t_x-1) is an amount of time elapsed between time t_x and a time t_x-1, where t_x-1 is a point in time prior to time t_x; and

Latency is a latency of processed electronic I/O requests that have completed during the time elapsed between time t_x and a time t_x-1.

13. The method of claim 12, wherein Tokens(t_x) is calculated for each network-attached server when an I/O request is received from that network-attached server.

14. The method of claim 12, wherein Tokens(t_x) is calculated for each network-attached server at periodic intervals.

15. The method of claim 12, wherein the QueueDepthLimit for at least one of the network-attached servers is a fractional value.

16. The method of claim 10, wherein the queue depth limit for at least one of the network-attached servers is a fractional value.

17. An information handling system comprising:

a data storage system receiving I/O requests from two or more network-attached servers; and

a controller managing the data storage system, including;

storing a queue depth limit for each of the plurality of network-attached servers;

monitoring latency of processed I/O requests; and

for each of the network-attached servers, processing received I/O requests for that network-attached server by;

managing a virtual bucket comprising a number of virtual tokens, each token representative of authorization for an I/O request from at least that network-attached server to be processed; and

permitting a received I/O request from that network-attached server to be processed if the virtual bucket comprises a number of virtual tokens greater than zero, and decrementing the number of virtual tokens by at least one;

wherein the number of I/O requests permitted to be processed for a given network-attached server over a period of time is based on a mathematical combination of the queue depth limit determined for that network-attached server and a latency of processed I/O requests.

18. The information handling system of claim 17, wherein the queue depth limit for at least one of the plurality of network-attached servers is a fractional value.