WO2015085313A1 - System and method for dynamically load balancing storage media devices based on a mid-range performance level - Google Patents
System and method for dynamically load balancing storage media devices based on a mid-range performance level Download PDFInfo
- Publication number
- WO2015085313A1 WO2015085313A1 PCT/US2014/069143 US2014069143W WO2015085313A1 WO 2015085313 A1 WO2015085313 A1 WO 2015085313A1 US 2014069143 W US2014069143 W US 2014069143W WO 2015085313 A1 WO2015085313 A1 WO 2015085313A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- storage media
- storage
- commands
- media device
- load
- Prior art date
Links
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/01—Protocols
- H04L67/10—Protocols in which an application is distributed across nodes in the network
- H04L67/1097—Protocols in which an application is distributed across nodes in the network 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]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
- G06F3/06—Digital input from, or digital output to, record carriers, e.g. RAID, emulated record carriers or networked record carriers
- G06F3/0601—Interfaces specially adapted for storage systems
- G06F3/0602—Interfaces specially adapted for storage systems specifically adapted to achieve a particular effect
- G06F3/061—Improving I/O performance
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
- G06F3/06—Digital input from, or digital output to, record carriers, e.g. RAID, emulated record carriers or networked record carriers
- G06F3/0601—Interfaces specially adapted for storage systems
- G06F3/0628—Interfaces specially adapted for storage systems making use of a particular technique
- G06F3/0655—Vertical data movement, i.e. input-output transfer; data movement between one or more hosts and one or more storage devices
- G06F3/0659—Command handling arrangements, e.g. command buffers, queues, command scheduling
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
- G06F3/06—Digital input from, or digital output to, record carriers, e.g. RAID, emulated record carriers or networked record carriers
- G06F3/0601—Interfaces specially adapted for storage systems
- G06F3/0668—Interfaces specially adapted for storage systems adopting a particular infrastructure
- G06F3/0671—In-line storage system
- G06F3/0683—Plurality of storage devices
- G06F3/0685—Hybrid storage combining heterogeneous device types, e.g. hierarchical storage, hybrid arrays
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/01—Protocols
- H04L67/10—Protocols in which an application is distributed across nodes in the network
- H04L67/1001—Protocols in which an application is distributed across nodes in the network for accessing one among a plurality of replicated servers
- H04L67/1004—Server selection for load balancing
- H04L67/1008—Server selection for load balancing based on parameters of servers, e.g. available memory or workload
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/01—Protocols
- H04L67/10—Protocols in which an application is distributed across nodes in the network
- H04L67/1001—Protocols in which an application is distributed across nodes in the network for accessing one among a plurality of replicated servers
- H04L67/1029—Protocols in which an application is distributed across nodes in the network for accessing one among a plurality of replicated servers using data related to the state of servers by a load balancer
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/50—Network services
- H04L67/56—Provisioning of proxy services
Definitions
- the present invention relates generally to the field of storage. More specifically, the present invention is related to system and method for dynamically load balancing storage media devices based on a mid-range performance level.
- NCQ Native Command Queuing
- NCQ Native Command Queuing
- storage systems having such NCQ supported drives do not view the storage system holistically as existing techniques, such as Native Command Queuing (NCQ) or storage media device head movement time minimization, look at a single host - slave in a vacuum (i.e., a single storage media device).
- NCQ Native Command Queuing
- FIG. 1 What is absent in the prior art is a system and method that brings load balancing methodologies typically applied at a macro level (to networks outside of the storage systems or compute systems) down to the micro level within the storage system itself and applied across the storage media devices within that system using criteria specific to storage media devices.
- Embodiments of the present invention are an improvement over prior art systems and methods.
- the present invention provides a storage system comprising: a plurality of storage media devices, each storage media device comprising one or more addressable storage regions, each region assigned a different weight based on at least a fast access rate, a mid-range access rate or a slow access rate, respectively; a storage controller controlling the plurality of storage media devices, the storage controller: receives one or more commands from a queue representing a load; identifies a set of weighted storage regions having the mid-range access rate to target a mid-range performance level that is enough to service the load; and distributes the load based on the mid-range performance level by utilizing only the set of weighted storage regions having the mid-range access rate thereby targeting the mid-range performance level that is enough to service the load.
- the present invention provides a storage system comprising: a plurality of storage media devices, each storage media device comprising one or more addressable storage regions, each region assigned a different weight based on at least a fast access rate or a slow access rate, respectively; a storage controller controlling the plurality of storage media devices, the storage controller: receives one or more commands from a queue representing a load; derives a mid-range access rate that is a function of the fast access rate and the slow access rate, where the mid-range access rate is achieved by alternating the fast access rate and the slow access rate; and distributes the load based on the mid-range performance level that is enough to service the load.
- the present invention provides a method as implemented in a storage system comprising a plurality of storage media devices, each storage media device comprising one or more addressable storage regions, each region assigned a different weight based on at least a fast access rate, a mid-range access rate or a slow access rate, respectively, a storage controller controlling the plurality of storage media devices, the method comprising: receiving one or more commands from a queue representing a load; identifying a set of weighted storage regions having the mid-range access rate to target a mid-range performance level that is enough to service the load; and distributing the load based on the mid-range performance level by utilizing only the set of weighted storage regions having the mid-range access rate thereby targeting the mid-range performance level that is enough to service the load.
- the present invention provides a method as implemented in storage system comprising: a plurality of storage media devices, each storage media device comprising one or more addressable storage regions, each region assigned a different weight based on at least a fast access rate or a slow access rate, respectively; a storage controller controlling the plurality of storage media devices, the method comprising: receiving one or more commands from a queue representing a load; deriving a mid-range access rate that is a function of the fast access rate and the slow access rate, where the mid-range access rate is achieved by alternating the fast access rate and the slow access rate; and distributing the load based on the mid-range performance level that is enough to service the load.
- the present invention provides a non-transitory, computer accessible memory medium storing program instructions for performing a method as implemented in a storage system comprising a plurality of storage media devices, each storage media device comprising one or more addressable storage regions, each region assigned a different weight based on at least a fast access rate, a mid-range access rate or a slow access rate, respectively, a storage controller controlling the plurality of storage media devices, wherein the program instructions are executable by a processor to: receive one or more commands from a queue representing a load; identify a set of weighted storage regions having the mid-range access rate to target a mid-range performance level that is enough to service the load; and distribute the load based on the mid-range performance level by utilizing only the set of weighted storage regions having the mid-range access rate thereby targeting the mid-range performance level that is enough to service the load.
- the present invention provides a non-transitory, computer accessible memory medium storing program instructions for performing a method as implemented in a storage system comprising a plurality of storage media devices, each storage media device comprising one or more addressable storage regions, each region assigned a different weight based on at least a fast access rate or a slow access rate, respectively; a storage controller controlling the plurality of storage media devices, wherein the program instructions are executable by a processor to: receive one or more commands from a queue representing a load; derive a mid-range access rate that is a function of the fast access rate and the slow access rate, where the mid-range access rate is achieved by alternating the fast access rate and the slow access rate; and distribute the load based on the mid-range performance level that is enough to service the load.
- the present invention provides a storage system comprising: a plurality of storage media devices; at least one storage controller controlling the plurality of storage media devices; a load balancer in communication with the storage controller to balance storage load across the storage media devices; an optional memory shared between the load balancer and the storage controller; and the load balancer receiving a set of commands for execution in at least one storage media device among the plurality of storage media devices, optionally storing the set of commands in the shared memory, assigning either a positive or negative bias to each of the commands; and distributing load amongst the storage media devices as a function of the assigned positive or negative bias.
- the present invention provides a storage system comprising: a plurality of storage media devices comprising at least a first storage media device and a second storage media device; at least one storage controller controlling the first and second storage media devices; a queue storing a set of commands to be executed in the first or second storage media devices; wherein the storage controller: computes a first apparent load associated with the first storage media device as a function of the set of commands, a first bias associated with execution of the set of commands in the first storage media device, and at least one time factor associated with execution of the set of commands in the first storage media device; computes a second apparent load associated with the second storage media device as a function of the set of commands, a second bias associated with execution of the set of commands in the second storage media device, and at least one time factor associated with execution of the set of commands in the second storage media device; the first apparent load less than the second apparent load when the first bias and the second bias are set to a neutral, unbiased value indicating potential execution of said set of commands in the first storage media device; negatively biase
- the present invention provides a method as implemented in a storage system comprising a plurality of storage media devices comprising at least a first storage media device and a second storage media device, at least one storage controller controlling the first and second storage media devices, a queue storing a set of commands to be executed in the first or second storage media devices, the method comprising: computing a first apparent load associated with the first storage media device as a function of the set of commands, a first bias associated with execution of the set of commands in the first storage media device, and at least one time factor associated with execution of the set of commands in the first storage media device; computing a second apparent load associated with the second storage media device as a function of the set of commands, a second bias associated with execution of the set of commands in the second storage media device, and at least one time factor associated with execution of the set of commands in the second storage media device; the first apparent load less than the second apparent load when the first bias and the second bias are set to a neutral, unbiased value indicating potential execution of said set of commands in the first storage media device; negatively
- the present invention provides for a non-transitory, computer accessible memory medium storing program instructions for performing a method as implemented in a storage system comprising a plurality of storage media devices comprising at least a first storage media device and a second storage media device, at least one storage controller controlling the first and second storage media devices, a queue storing a set of commands to be executed in the first or second storage media devices, wherein the program instructions are executable by a processing element to: compute a first apparent load associated with the first storage media device as a function of the set of commands, a first bias associated with execution of the set of commands in the first storage media device, and at least one time factor associated with execution of the set of commands in the first storage media device; compute a second apparent load associated with the second storage media device as a function of the set of commands, a second bias associated with execution of the set of commands in the second storage media device, and at least one time factor associated with execution of the set of commands in the second storage media device; the first apparent load less than the second apparent load when the first bias and the
- the present invention provides a storage system comprising: a plurality of storage media devices comprising at least a first storage media device and a second storage media device; at least one storage controller controlling the first and second storage media devices; a queue storing a set of commands to be executed in the first or second storage media devices; wherein the storage controller: computes a first apparent load associated with the first storage media device as a function of the set of commands, a first bias associated with execution of the set of commands in the first storage media device, and at least one time factor associated with execution of the set of commands in the first storage media device; computes a second apparent load associated with the second storage media device as a function of the set of commands, a second bias associated with execution of the set of commands in the second storage media device, and at least one time factor associated with execution of the set of commands in the second storage media device; the first apparent load less than the second apparent load when the first bias and the second bias are set to a neutral, unbiased value indicating potential execution of said set of commands in the first storage media device; positively biase
- the present invention provides a method as implemented in a storage system comprising a plurality of storage media devices comprising at least a first storage media device and a second storage media device, at least one storage controller controlling the first and second storage media devices, a queue storing a set of commands to be executed in the first or second storage media devices, the method comprising: computing a first apparent load associated with the first storage media device as a function of the set of commands, a first bias associated with execution of the set of commands in the first storage media device, and at least one time factor associated with execution of the set of commands in the first storage media device; computing a second apparent load associated with the second storage media device as a function of the set of commands, a second bias associated with execution of the set of commands in the second storage media device, and at least one time factor associated with execution of the set of commands in the second storage media device; the first apparent load less than the second apparent load when the first bias and the second bias are set to a neutral, unbiased value indicating potential execution of said set of commands in the first storage media device; positively
- the present invention provides for a non-transitory, computer accessible memory medium storing program instructions for performing a method as implemented in a storage system comprising a plurality of storage media devices comprising at least a first storage media device and a second storage media device, at least one storage controller controlling the first and second storage media devices, a queue storing a set of commands to be executed in the first or second storage media devices, wherein the program instructions are executable by a processing element to: compute a first apparent load associated with the first storage media device as a function of the set of commands, a first bias associated with execution of the set of commands in the first storage media device, and at least one time factor associated with execution of the set of commands in the first storage media device; compute a second apparent load associated with the second storage media device as a function of the set of commands, a second bias associated with execution of the set of commands in the second storage media device, and at least one time factor associated with execution of the set of commands in the second storage media device; the first apparent load less than the second apparent load when the first bias and the
- the present invention provides a storage system comprising: a plurality of storage media devices comprising at least a first storage media device and a second storage media device; at least one storage controller controlling the first and second storage media devices; a queue storing a set of commands to be executed in the first or second storage media devices; wherein the storage controller: computes a first apparent load associated with the first storage media device as a function of the set of commands, a first bias associated with execution of the set of commands in the first storage media device, and at least one time factor associated with execution of the set of commands in the first storage media device; computes a second apparent load associated with the second storage media device as a function of the set of commands, a second bias associated with execution of the set of commands in the second storage media device, and at least one time factor associated with execution of the set of commands in the second storage media device; the first apparent load greater than the second apparent load when the first bias and the second bias are set to a neutral, unbiased value indicating potential execution of said set of commands in the second storage media device; negatively biase
- the present invention provides a method as implemented in a storage system comprising a plurality of storage media devices comprising at least a first storage media device and a second storage media device, at least one storage controller controlling the first and second storage media devices, a queue storing a set of commands to be executed in the first or second storage media devices, the method comprising: computing a first apparent load associated with the first storage media device as a function of the set of commands, a first bias associated with execution of the set of commands in the first storage media device, and at least one time factor associated with execution of the set of commands in the first storage media device; computing a second apparent load associated with the second storage media device as a function of the set of commands, a second bias associated with execution of the set of commands in the second storage media device, and at least one time factor associated with execution of the set of commands in the second storage media device; the first apparent load greater than the second apparent load when the first bias and the second bias are set to a neutral, unbiased value indicating potential execution of said set of commands in the second storage media device; negatively
- the present invention provides for a non-transitory, computer accessible memory medium storing program instructions for performing a method as implemented in a storage system comprising a plurality of storage media devices comprising at least a first storage media device and a second storage media device, at least one storage controller controlling the first and second storage media devices, a queue storing a set of commands to be executed in the first or second storage media devices, wherein the program instructions are executable by a processing element to: compute a first apparent load associated with the first storage media device as a function of the set of commands, a first bias associated with execution of the set of commands in the first storage media device, and at least one time factor associated with execution of the set of commands in the first storage media device; compute a second apparent load associated with the second storage media device as a function of the set of commands, a second bias associated with execution of the set of commands in the second storage media device, and at least one time factor associated with execution of the set of commands in the second storage media device; the first apparent load greater than the second apparent load when the first bias and the
- the present invention provides a storage system comprising: a plurality of storage media devices comprising at least a first storage media device and a second storage media device; at least one storage controller controlling the first and second storage media devices; a queue storing a set of commands to be executed in the first or second storage media devices; wherein the storage controller: computes a first apparent load associated with the first storage media device as a function of the set of commands, a first bias associated with execution of the set of commands in the first storage media device, and at least one time factor associated with execution of the set of commands in the first storage media device; computes a second apparent load associated with the second storage media device as a function of the set of commands, a second bias associated with execution of the set of commands in the second storage media device, and at least one time factor associated with execution of the set of commands in the second storage media device; the first apparent load greater than the second apparent load when the first bias and the second bias are set to a neutral, unbiased value indicating potential execution of said set of commands in the second storage media device; positively biase
- the present invention provides a method as implemented in a storage system comprising a plurality of storage media devices comprising at least a first storage media device and a second storage media device, at least one storage controller controlling the first and second storage media devices, a queue storing a set of commands to be executed in the first or second storage media devices, the method comprising: computing a first apparent load associated with the first storage media device as a function of the set of commands, a first bias associated with execution of the set of commands in the first storage media device, and at least one time factor associated with execution of the set of commands in the first storage media device; computing a second apparent load associated with the second storage media device as a function of the set of commands, a second bias associated with execution of the set of commands in the second storage media device, and at least one time factor associated with execution of the set of commands in the second storage media device; the first apparent load greater than the second apparent load when the first bias and the second bias are set to a neutral, unbiased value indicating potential execution of said set of commands in the second storage media device; positively
- the present invention provides for a non-transitory, computer accessible memory medium storing program instructions for performing a method as implemented in a storage system comprising a plurality of storage media devices comprising at least a first storage media device and a second storage media device, at least one storage controller controlling the first and second storage media devices, a queue storing a set of commands to be executed in the first or second storage media devices, wherein the program instructions are executable by a processing element to: compute a first apparent load associated with the first storage media device as a function of the set of commands, a first bias associated with execution of the set of commands in the first storage media device, and at least one time factor associated with execution of the set of commands in the first storage media device; compute a second apparent load associated with the second storage media device as a function of the set of commands, a second bias associated with execution of the set of commands in the second storage media device, and at least one time factor associated with execution of the set of commands in the second storage media device; the first apparent load greater than the second apparent load when the first bias and the
- the teachings of the present invention equally apply to a plurality of storage controllers, including multiple, distributed, storage controllers.
- the system is described as being within a chassis, it should be noted that the entire system need not be co-located within one chassis or physical location, as one or more individual elements may be located as part of a different chassis/location.
- the system may also have parent and child storage controllers, where a parent storage controller makes decisions to balance across child storage controllers, who may then make decisions to balance across their child storage controllers, etc. (eventually reaching storage media devices connected to last storage controller(s) in the chain).
- FIG. 1 depicts a storage controller controlling storage media devices having regions of varying access rates.
- FIG. 2A-B and FIG. 3 illustrates examples of the present invention's method to distribute load based on mid-range performance level.
- FIG. 4A, FIG. 5A, FIG. 6A, and FIG. 7A illustrate various embodiments of the system of the present invention for either positively or negatively biasing the apparent load.
- FIG. 4B, FIG. 5B, FIG. 6B, and FIG. 7B illustrate methods associated with the various embodiments of the present invention for either positively or negatively biasing the apparent load.
- references to “one embodiment” or “an embodiment” mean that the feature being referred to is included in at least one embodiment of the invention. Further, separate references to “one embodiment” in this description do not necessarily refer to the same embodiment; however, neither are such embodiments mutually exclusive, unless so stated and except as will be readily apparent to those of ordinary skill in the art. Thus, the present invention can include any variety of combinations and/or integrations of the embodiments described herein.
- the present invention views the storage system holistically. Whereas existing techniques, such as Native Command Queuing (NCQ) or storage media device head movement time minimization, look at a single host - slave in a vacuum (i.e., a single storage media device).
- NCQ Native Command Queuing
- This invention brings load balancing methodologies typically applied at a macro level (to networks outside of the storage systems or compute systems) down to the micro level within the storage system itself and applied across the storage media devices within that system using criteria specific to storage media devices.
- the present invention's system and method maintains a balance of storage media devices accessing fast regions of their media and storage media devices accessing slow regions of their media to produce a sustained throughput higher than that of randomly accessing the storage media devices, thus targeting the average throughput of a storage media device (e.g., between fast access location and slow access location).
- DR Storage Media Device and a Region within
- DRs are computed by assigning weights for all storage media devices and their sub regions within a storage system based physical characteristics. These regions may be a series of sequential sectors. Other components of the weights are based on recorded historical performance trends and real time actual performance. Then, based on the DRs calculated, one may distribute load across the storage system based upon these DR weights.
- One distribution scheme would be to target a minimum performance level, in which lower value (lower performance) DRs may be used before higher value DRs to hold high value DRs in reserve, to be used as needed to meet that minimum performance level.
- Another scheme would be to maximize performance and distribute load across the highest available DRs at all times.
- An example region-weighting scheme would be to start with a reference region and assigning that a weight of 1.0, typically the lowest performing region would be selected as the reference. Every other regions' weight is assigned as a ratio of its performance to that of the reference. If a region were 50% higher performance than that of the reference its weight would be assigned 1.5. If a region were 10% lower performance than that of the reference its weight would be assigned 0.9.
- a DR applies to non-rotational storage media devices as well, simply different weights and regions are defined based on the technology.
- a DR may include regions based on access type (e.g., access type may be based on read or write, such as the case of a solid-state storage media device where fast and slow access rates may correspond to read or write rates and the solid-state storage media device may have overlapping read and write regions), to account for differing performance levels of each.
- access type may be based on read or write, such as the case of a solid-state storage media device where fast and slow access rates may correspond to read or write rates and the solid-state storage media device may have overlapping read and write regions
- some such devices may also be considered a hybrid of differing technologies, such as solid-state and rotational, whereas the performance of each technology differs and in some instances differs further within each technology.
- rotational hard drives must mechanically move an arm and heads across spinning platters to locate a data block (seek time) and the supported data rates vary with the data's location on the spinning platter such that data closer to the outer diameter of the platter flows faster to and from such spinning platter. In this scenario it is often desirable to minimize the movement of the heads as well as locate data on the outer circumference of the platters.
- This invention assigns weightings to commands based on many factors, including but not limited to the limitations of the underlying storage media device. It then views the command queue fullness / load from that perspective rather than simply the number of commands outstanding, to determine the "apparent load" of a storage media device.
- the invention also discloses the use of a positive bias and a negative bias to artificially influence the apparent load. This bias may be based on what is expected or about to be destined for the storage media device (such as load reservation and load predictions), what is already committed / pending, or what is desired. The difference between a reservation and a commitment is that a reservation can be changed or reallocated based upon new information. Predictions may be based on historical trends or knowledge base of specific types of traffic. Non-limiting prediction examples include:
- Bias is useful to distribute the data volume across storage media devices of varying capacities to insure any given storage media device does not prematurely fill, be subsequently unavailable for further writes, and thus reduce the number of storage media devices that a given write load may be distributed across. It is also useful to maintain a certain sustainable data rate for a storage system by holding some bandwidth or load capability in reserve, to be used when needed to increase instantaneous data rate in order to maintain that sustainable data rate average (much like a regulator). Without bias, faster storage media devices would naturally get more load by default since they would appear to be less heavily loaded (i.e. they are capable of handling more data faster), but this is not always desired and can be corrected with bias.
- Bias allows for "traffic shaping" of the data flow, which can intentionally shape the load on the storage media devices as well as the load seen on the attached network to match a desired profile.
- the Bias may also vary based upon the type of data (i.e. type of data traffic) or to follow a given Quality of Service (QoS) scheme.
- QoS Quality of Service
- the apparent load may be used solely for monitoring purposes, meaning that it could be used as an indicator of system performance without being used to modify the load in any way.
- apparent load may include the "whole path" from the point where a command is issued all the way to the point at which the response is received.
- Prior art looks at a storage media device itself, alone, assuming negligible time for transport and movement to/from memory/memories.
- the transport layer may be important (such as when through a network or distributed system where the storage controller and storage media devices have physical separation) as well as the movement of data to/from a storage media device and memory/memories.
- the performance of a storage media device will be impacted if data cannot flow to or be carried away from the storage media device fast enough, a condition not typically under the direct control of the storage media device, which will cause data pushback or starvation.
- the impact of one or more caches in the path would then be included within the apparent load.
- Tmin minimal time possible for any single command for the storage media device, from issuance to completion.
- Tcmd time for the specific command to issue, from issuance to completion. This is dependent upon the actual command. For example, in some storage media devices, a write may require a different period of time to complete than a read. Also, if the path contains one or more caches, the time to complete the command may vary at different times.
- QueueCapacity the maximum number of commands that the queue can hold.
- Bias the desired artificial influence applied to each command. A number ranging from 0.0 -> 10.0; for example, neutral bias would be 1.0, positive bias would be a value below 1.0 (to artificially lower the apparent load), while negative bias would be a value greater than 1.0 (to artificially increase the apparent load).
- RequiredSeekTime The estimated or actual storage media device seek time, based upon lookup or historical performance or calculation, for this command from the previous command.
- Both T min and T cmd are system values. These values may vary based on the class of storage media device (such as rotational, solid state, or hybrid). They may be treated as static or dynamic based on measured system characteristics in real-time and / or historical values. Such measurements may include temperature monitoring (when the completion times vary with temperature) or current cache contents.
- each specific storage media device to be used in the system may be "qualified” and the values of Tmin and T cm d determined and used for accesses to that specific storage media device. As an alternative, a sampling of similar storage media devices may be "qualified” and averaged to produce values for that class of storage media device.
- time factor refers to the required seek time, Tmin, Tcmd, combinations thereof, or functions based on various combinations thereof.
- Some non-limiting example usages of the apparent load include, but are not limited to
- the described storage media device is not a separate physical device, as it may be memory used for storage, embedded within another device.
- the present invention provides a storage system comprising: a plurality of storage media devices; at least one storage controller controlling the plurality of storage media devices; a load balancer in communication with the storage controller to balance storage load across the storage media devices; an optional memory shared between the load balancer and the storage controller; and the load balancer receiving a plurality of commands for execution in at least one storage media device among the plurality of storage media devices, optionally storing the commands in the shared memory, assigning either a positive or negative bias to each of the commands; and distributing load amongst the storage media devices as a function of the assigned positive or negative bias.
- FIG. 1 provides a system-level diagram to understand the principles of the present invention.
- the present invention's system comprises a storage controller 102 that controls a plurality of storage media devices represented by 104 and 106.
- Storage media device 104 comprises regions of varying access rates. For example, if storage media device 104 were a rotational disk drive, the outermost region of storage media device 104 is the fast access region as this refers to a region that provides fastest read/write access rates.
- the inner-most region of storage media device 104 is a slow access region as this refers to a region that provides slowest read/write access rates. There also may be regions between the fast access rate regions and the slow access rate regions, which we refer to as the mid-range access rate region.
- FIG. 1 two storage media devices are shown in FIG. 1 only for the sake of simplicity, and that the present invention covers instances where there are more than two storage media devices, as is the case with most network attached storage (NAS) devices or storage devices that are part of a storage area network (SAN).
- NAS network attached storage
- SAN storage area network
- the storage media device 104 has three access rate regions shown, a fast access region 108, a mid-range access region 110, and a slow access region 112. It should also be noted that while a three-tier access region (i.e., fast access region 108, mid-range access region 110, and slow access region 112) is disclosed in FIG. 1, the same teachings can be expanded to a multi-tier region where there are a plurality of access rate regions between the fast access rate region 108 and the slow access rate region 112 shown in FIG. 1. In FIG. 1, fast access region 108 of storage media device 104 is further subdivided into a plurality of fast access regions shown as D ⁇ R° , D y R , etc.
- mid- range access region 110 of storage media device 104 is further subdivided into a plurality of regions shown as , D y R 2 , etc. and slow access region 112 of storage media device 104 is further subdivided into a plurality of regions shown as , D y R 2 c , etc.
- fast access region 108 of storage media device 106 is further subdivided into a plurality of fast access regions shown as D 2 R , D 2 R 2 , etc.
- mid- range access region 110 of storage media device 106 is further subdivided into a plurality of regions shown as D 2 R( , D 2 R ⁇ , etc.
- slow access region 112 of storage media device 106 is further subdivided into a plurality of regions shown as D 2 R , D 2 R 2 , etc.
- the present invention provides a storage system comprising: a plurality of storage media devices, each storage media device comprising one or more addressable storage regions, each region assigned a different weight based on at least a fast access rate, a mid-range access rate or a slow access rate, respectively; a storage controller controlling the plurality of storage media devices, the storage controller: receives one or more commands from a queue representing a load; identifies a set of weighted storage regions having the mid-range access rate to target a mid-range performance level that is enough to service the load; and distributes the load based on the mid-range performance level by utilizing only the set of weighted storage regions having the mid-range access rate thereby targeting the mid-range performance level that is enough to service the load.
- the present invention provides a storage system comprising: a plurality of storage media devices, each storage media device comprising one or more addressable storage regions, each region assigned a different weight based on at least a fast access rate or a slow access rate, respectively; a storage controller controlling the plurality of storage media devices, the storage controller: receives one or more commands from a queue representing a load; derives a mid-range access rate that is a function of the fast access rate and the slow access rate, where the mid-range access rate is achieved by alternating the fast access rate and the slow access rate; and distributes the load based on the mid-range performance level that is enough to service the load.
- Non-limiting examples of storage media devices are any of, or a combination of, the following: solid-state drive, rotational hard disk drive, hybrid disk drive, or PCI-Express slot disk drive.
- the storage media devices may be part of a storage area network (SAN) or may be part of a network attached storage (NAS) device.
- SAN storage area network
- NAS network attached storage
- the present invention provides a method as implemented in a storage system comprising a plurality of storage media devices, each storage media device comprising one or more addressable storage regions, each region assigned a weight based on at least a fast or slow access rate, where regions having fast access rate are weighted differently than regions having slow access rate (e.g., regions having fast access rate having higher weights than regions having slow access rate or regions having slow access rate having higher weights than regions having fast access rate), a storage controller controlling the plurality of storage media devices, the method comprising: receiving one or more commands from a queue representing a load - step 201; identifying a minimum performance level required for the load - step 203; identifying a first set of weighted storage regions having a slow access rate across the plurality of storage media devices and a second set of weighted storage regions having a fast access rate in the plurality of storage media devices - step 205; identifying a subset of storage regions within the first set of weighted
- the present invention provides a method as implemented in a storage system comprising a storage system comprising a plurality of storage media devices, each storage media device comprising one or more addressable storage regions, each region assigned a different weight based on at least a fast access rate, a mid-range access rate or a slow access rate, respectively, a storage controller controlling the plurality of storage media devices, the method comprising: receiving one or more commands from a queue representing a load - step 202; identifying a set of weighted storage regions having the mid-range access rate to target a mid-range performance level that is enough to service the load - step 204; and distributing the load based on the mid-range performance level by utilizing only the set of weighted storage regions having the mid-range access rate thereby targeting the mid-range performance level that is enough to service the load - step 206.
- Figs. 2 A and 2B are not meant to be limiting as the embodiments may be extended to computing an optimal sustained performance level as function of the first set of weighted storage regions having the slow access rate and the second set of weighted storage regions having the fast access rate; and distributing load based on the computed optimal sustained performance level.
- One example sustained performance level determined would be to examine the sets of weighted storage regions presented and take the average, this average being used to distribute the load by alternating weighted storage regions as necessary to maintain that average over time.
- Another example sustained performance level determined would be to examine the sets of weighted storage regions presented and take the average then apply a discount to that average to allow for operational margin, this discounted average being used to distribute the load by alternating weighted storage regions as necessary to maintain that discounted average over time.
- the embodiments may be further extended to identifying one or more weighted fast access storage regions within the addressable storage regions across the plurality of storage media devices having the fast access rate and distributing load by utilizing only the weighted fast access storage regions within the addressable storage regions across the plurality of storage media devices having the fast access rate.
- the present invention provides a method as implemented in storage system comprising: a plurality of storage media devices, each storage media device comprising one or more addressable storage regions, each region assigned a different weight based on at least a fast access rate or a slow access rate, respectively; a storage controller controlling the plurality of storage media devices, the method comprising: receiving one or more commands from a queue representing a load - step 302; deriving a mid-range access rate that is a function of the fast access rate and the slow access rate - step 304, where the mid-range access rate is achieved by alternating the fast access rate and the slow access rate; and distributing the load based on the mid-range performance level that is enough to service the load - step 306.
- the present invention provides a storage system comprising: a plurality of storage media devices comprising at least a first storage media device 402 and a second storage media device 404; at least one storage controller 406 controlling the first and second storage media devices 402 and 404, respectively; a queue 408 storing a set of commands 409 to be executed in the first or second storage media devices; wherein the storage controller 406: computes a first apparent load 410 associated with the first storage media device 402 as a function of the set of commands 409, a first bias associated with execution of the set of commands in the first storage media device, and at least one time factor (e.g., seek time) associated with execution of the set of commands 409 in the first storage media device 402; computes a second apparent load 412 associated with the second storage media device 404 as a function of the set of commands 409, a second bias associated with execution of the set of commands in the second storage media device, and at least one time factor (e.g.
- the present invention provides a method as implemented in a storage system comprising a plurality of storage media devices comprising at least a first storage media device and a second storage media device, at least one storage controller controlling the first and second storage media devices, a queue storing a set of commands to be executed in the first or second storage media devices, the method comprising: computing a first apparent load associated with the first storage media device as a function of the set of commands, a first bias associated with execution of the set of commands in the first storage media device, and at least one time factor associated with execution of the set of commands in the first storage media device - step 416; computing a second apparent load associated with the second storage media device as a function of the set of commands, a second bias associated with execution of the set of commands in the second storage media device, and at least one time factor associated with execution of the set of commands in the second storage media device - step 418; the first apparent load less than the second apparent load when the first bias and the second bias are set to
- the present invention also provides for a non-transitory, computer accessible memory medium storing program instructions for performing a method as implemented in a storage system comprising a plurality of storage media devices comprising at least a first storage media device and a second storage media device, at least one storage controller controlling the first and second storage media devices, a queue storing a set of commands to be executed in the first or second storage media devices, wherein the program instructions are executable by a processing element to: compute a first apparent load associated with the first storage media device as a function of the set of commands, a first bias associated with execution of the set of commands in the first storage media device, and at least one time factor associated with execution of the set of commands in the first storage media device; compute a second apparent load associated with the second storage media device as a function of the set of commands, a second bias associated with execution of the set of commands in the second storage media device, and at least one time factor associated with execution of the set of commands in the second storage media device; the first apparent load less than the second apparent load when the
- the present invention provides a storage system comprising: a plurality of storage media devices comprising at least a first storage media device 502 and a second storage media device 504; at least one storage controller 206 controlling the first and second storage media devices 502 and 504, respectively; a queue 508 storing a set of commands 509 to be executed in the first or second storage media devices; wherein the storage controller 506: computes a first apparent load 510 associated with the first storage media device as a function of the set of commands 509, a first bias associated with execution of the set of commands 509 in the first storage media device 502, and at least one time factor (e.g., seek time) associated with execution of the set of commands 509 in the first storage media device 502; computes a second apparent load 512 associated with the second storage media device 504 as a function of the set of commands 509, a second bias associated with execution of the set of commands 509 in the second storage media device 504, and at least one time factor (e
- the present invention provides a method as implemented in a storage system comprising a plurality of storage media devices comprising at least a first storage media device and a second storage media device, at least one storage controller controlling the first and second storage media devices, a queue storing a set of commands to be executed in the first or second storage media devices, the method comprising: computing a first apparent load associated with the first storage media device as a function of the set of commands, a first bias associated with execution of the set of commands in the first storage media device, and at least one time factor associated with execution of the set of commands in the first storage media device - step 516; computing a second apparent load associated with the second storage media device as a function of the set of commands, a second bias associated with execution of the set of commands in the second storage media device, and at least one time factor associated with execution of the set of commands in the second storage media device - step 518; the first apparent load less than the second apparent load when the first bias and the second bias are set to
- the present invention also provides for a non-transitory, computer accessible memory medium storing program instructions for performing a method as implemented in a storage system comprising a plurality of storage media devices comprising at least a first storage media device and a second storage media device, at least one storage controller controlling the first and second storage media devices, a queue storing a set of commands to be executed in the first or second storage media devices, wherein the program instructions are executable by a processing element to: compute a first apparent load associated with the first storage media device as a function of the set of commands, a first bias associated with execution of the set of commands in the first storage media device, and at least one time factor associated with execution of the set of commands in the first storage media device; compute a second apparent load associated with the second storage media device as a function of the set of commands, a second bias associated with execution of the set of commands in the second storage media device, and at least one time factor associated with execution of the set of commands in the second storage media device; the first apparent load less than the second apparent load when the
- the present invention provides a storage system comprising: a plurality of storage media devices comprising at least a first storage media device 602 and a second storage media device 604; at least one storage controller 306 controlling the first and second storage media devices 602 and 604, respectively; a queue 608 storing a set of commands 609 to be executed in the first or second storage media devices; wherein the storage controller 606: computes a first apparent load 610 associated with the first storage media device 602 as a function of the set of commands 609, a first bias associated with execution of the set of commands 309 in the first storage media device 602, and at least one time factor (e.g., seek time) associated with execution of the set of commands 609 in the first storage media device 602; computes a second apparent load 612 associated with the second storage media device 604 as a function of the set of commands 609, a second bias associated with execution of the set of commands 609 in the second storage media device 604, and at least one time factor
- the present invention provides a method as implemented in a storage system comprising a plurality of storage media devices comprising at least a first storage media device and a second storage media device, at least one storage controller controlling the first and second storage media devices, a queue storing a set of commands to be executed in the first or second storage media devices, the method comprising: computing a first apparent load associated with the first storage media device as a function of the set of commands, a first bias associated with execution of the set of commands in the first storage media device, and at least one time factor associated with execution of the set of commands in the first storage media device - step 616; computing a second apparent load associated with the second storage media device as a function of the set of commands, a second bias associated with execution of the set of commands in the second storage media device, and at least one time factor associated with execution of the set of commands in the second storage media device - step 618; the first apparent load greater than the second apparent load when the first bias and the second bias are set to
- the present invention also provides for a non-transitory, computer accessible memory medium storing program instructions for performing a method as implemented in a storage system comprising a plurality of storage media devices comprising at least a first storage media device and a second storage media device, at least one storage controller controlling the first and second storage media devices, a queue storing a set of commands to be executed in the first or second storage media devices, wherein the program instructions are executable by a processing element to: compute a first apparent load associated with the first storage media device as a function of the set of commands, a first bias associated with execution of the set of commands in the first storage media device, and at least one time factor associated with execution of the set of commands in the first storage media device; compute a second apparent load associated with the second storage media device as a function of the set of commands, a second bias associated with execution of the set of commands in the second storage media device, and at least one time factor associated with execution of the set of commands in the second storage media device; the first apparent load greater than the second apparent load when the
- the present invention provides a storage system comprising: a plurality of storage media devices comprising at least a first storage media device 702 and a second storage media device 704; at least one storage controller 706 controlling the first and second storage media devices 702 and 704, respectively; a queue 708 storing a set of commands 709 to be executed in the first or second storage media devices; wherein the storage controller 706: computes a first apparent load 710 associated with the first storage media device 702 as a function of the set of commands 709, a first bias associated with execution of the set of commands 709 in the first storage media device 702, and at least one time factor (e.g., seek time) associated with execution of the set of commands 709 in the first storage media device 702; computes a second apparent load 712 associated with the second storage media device 704 as a function of the set of commands 709, a second bias associated with execution of the set of commands 709 in the second storage media device 704, and at least one time factor
- the present invention also provides a method as implemented in a storage system comprising a plurality of storage media devices comprising at least a first storage media device and a second storage media device, at least one storage controller controlling the first and second storage media devices, a queue storing a set of commands to be executed in the first or second storage media devices, the method comprising: computing a first apparent load associated with the first storage media device as a function of the set of commands, a first bias associated with execution of the set of commands in the first storage media device, and at least one time factor associated with execution of the set of commands in the first storage media device - step 716; computing a second apparent load associated with the second storage media device as a function of the set of commands, a second bias associated with execution of the set of commands in the second storage media device, and at least one time factor associated with execution of the set of commands in the second storage media device - step 718; the first apparent load greater than the second apparent load when the first bias and the second bias are set to
- the embodiments may integrate specific use cases where the load balancing is achieved based on temperatures, temperature ranges, fill percentages, write rate, read rate, and data type in conjunction with the biasing.
- the temperatures, temperature ranges, fill percentages, write rate, read rate, and data type for the corresponding media devices may be monitored, measured or tracked through known means in some embodiments.
- the present invention provides a method as a non-transitory, computer accessible memory medium storing program instructions for performing a method as implemented in a storage system comprising a storage system comprising a plurality of storage media devices, each storage media device comprising one or more addressable storage regions, each region assigned a different weight based on at least a fast access rate, a mid- range access rate or a slow access rate, respectively, a storage controller controlling the plurality of storage media devices, wherein the program instructions are executable by a processor to: receive one or more commands from a queue representing a load; identify a set of weighted storage regions having the mid-range access rate to target a mid-range performance level that is enough to service the load; and distribute the load based on the mid- range performance level by utilizing only the set of weighted storage regions having the mid- range access rate thereby targeting the mid-range performance level that is enough to service the load.
- the present invention provides a non-transitory, computer accessible memory medium storing program instructions for performing a method as implemented in a storage system comprising a plurality of storage media devices, each storage media device comprising one or more addressable storage regions, each region assigned a different weight based on at least a fast access rate or a slow access rate, respectively; a storage controller controlling the plurality of storage media devices, wherein the program instructions are executable by a processor to: receive one or more commands from a queue representing a load; derive a mid-range access rate that is a function of the fast access rate and the slow access rate, where the mid-range access rate is achieved by alternating the fast access rate and the slow access rate; and distribute the load based on the mid-range performance level that is enough to service the load.
- the teachings of the present invention equally applies to a plurality of storage controllers, including multiple, distributed, storage controllers.
- the system is described as being within a chassis, it should be noted that the entire system need not be co-located within one chassis or physical location, as one or more individual elements may be located as part of a different chassis/location.
- the system may also have parent and child storage controllers, where a parent storage controller makes decisions to balance across child storage controllers, who may then make decisions to balance across their child storage controllers, etc. (eventually hitting storage media devices connected to last storage controller(s) in the chain.
- a storage controller may balance load across a chassis having a plurality of storage media devices, where a master storage controller may be connected to a plurality of such storage controllers to perform load balancing across a plurality of such chassis, each having a plurality of storage media devices.
- the above-described features and applications can be implemented as software processes that are specified as a set of instructions recorded on a computer readable storage medium (also referred to as computer readable medium).
- a computer readable storage medium also referred to as computer readable medium.
- processing element(s) e.g., one or more processors, cores of processors, or other processing elements
- Embodiments within the scope of the present disclosure may also include tangible and/or non-transitory computer-readable storage media for carrying or having computer-executable instructions or data structures stored thereon.
- Such non- transitory computer-readable storage media can be any available media that can be accessed by a general purpose or special purpose computer, including the functional design of any special purpose processor.
- non-transitory computer-readable media can include flash memory, RAM, ROM, EEPROM, CD-ROM or other optical disk storage, magnetic disk storage or other magnetic storage devices, or any other medium which can be used to carry or store desired program code means in the form of computer-executable instructions, data structures, or processor chip design.
- the computer readable media does not include carrier waves and electronic signals passing wirelessly or over wired connections.
- Computer-executable instructions include, for example, instructions and data which cause a general purpose computer, special purpose computer, or special purpose processing device to perform a certain function or group of functions.
- Computer-executable instructions also include program modules that are executed by computers in stand-alone or network environments.
- program modules include routines, programs, components, data structures, objects, and the functions inherent in the design of special-purpose processors, etc. that perform particular tasks or implement particular abstract data types.
- Computer- executable instructions, associated data structures, and program modules represent examples of the program code means for executing steps of the methods disclosed herein. The particular sequence of such executable instructions or associated data structures represents examples of corresponding acts for implementing the functions described in such steps.
- a computer program (also known as a program, software, software application, script, or code) can be written in any form of programming language, including compiled or interpreted languages, declarative or procedural languages, and it can be deployed in any form, including as a stand-alone program or as a module, component, subroutine, object, or other unit suitable for use in a computing environment.
- a computer program may, but need not, correspond to a file in a file system.
- a program can be stored in a portion of a file that holds other programs or data (e.g., one or more scripts stored in a markup language document), in a single file dedicated to the program in question, or in multiple coordinated files (e.g., files that store one or more modules, sub programs, or portions of code).
- a computer program can be deployed to be executed on one computer or on multiple computers that are located at one site or distributed across multiple sites and interconnected by a communication network.
- Some implementations include electronic components, for example microprocessors, storage and memory that store computer program instructions in a machine-readable or computer-readable medium (alternatively referred to as computer-readable storage media, machine-readable media, or machine-readable storage media).
- computer-readable media include RAM, ROM, read-only compact discs (CD-ROM), recordable compact discs (CD-R), rewritable compact discs (CD-RW), read-only digital versatile discs (e.g., DVD-ROM, dual-layer DVD-ROM), a variety of recordable/rewritable DVDs (e.g., DVD-RAM, DVD-RW, DVD+RW, etc.), flash memory (e.g., SD cards, mini-SD cards, micro-SD cards, etc.), magnetic or solid state hard drives, read-only and recordable Blu-Ray ® discs, ultra density optical discs, any other optical or magnetic media, and floppy disks.
- CD-ROM compact discs
- CD-R recordable compact discs
- the computer-readable media can store a computer program that is executable by at least one processing element and includes sets of instructions for performing various operations.
- Examples of computer programs or computer code include machine code, for example is produced by a compiler, and files including higher-level code that are executed by a computer, an electronic component, or a microprocessor using an interpreter.
- the terms "computer”, “server”, “processor”, and “memory” all refer to electronic or other technological devices. These terms exclude people or groups of people.
- display or displaying means displaying on an electronic device.
- computer readable medium and “computer readable media” are entirely restricted to tangible, physical objects that store information in a form that is readable by a computer. These terms exclude any wireless signals, wired download signals, and any other ephemeral signals.
- Embodiments may be practiced in network computing environments with many types of computer system configurations, including personal computers, hand-held devices, multi-processor systems, ASIC -based systems, FPGA-based systems, microprocessor-based or programmable consumer electronics, network PCs, minicomputers, mainframe computers, and the like.
- Embodiments may also be practiced in distributed computing environments where tasks are performed by local and remote processing devices that are linked (either by hardwired links, wireless links, or by a combination thereof) through a communications network.
- program modules may be located in both local and remote memory storage devices.
- any specific order or hierarchy of steps in the processes disclosed is an illustration of example approaches. Based upon design preferences, it is understood that the specific order or hierarchy of steps in the processes may be rearranged, or that all illustrated steps be performed. Some of the steps may be performed simultaneously. For example, in certain circumstances, multitasking and parallel processing may be advantageous. Moreover, the separation of various system components illustrated above should not be understood as requiring such separation, and it should be understood that the described program components and systems can generally be integrated together in a single software product or packaged into multiple software products. Various modifications to these aspects will be readily apparent, and the generic principles defined herein may be applied to other aspects.
- a phrase, for example, an "aspect” does not imply that the aspect is essential to the subject technology or that the aspect applies to all configurations of the subject technology.
- a disclosure relating to an aspect may apply to all configurations, or one or more configurations.
- a phrase, for example, an aspect may refer to one or more aspects and vice versa.
- a phrase, for example, a “configuration” does not imply that such configuration is essential to the subject technology or that such configuration applies to all configurations of the subject technology.
- a disclosure relating to a configuration may apply to all configurations, or one or more configurations.
- a phrase, for example, a configuration may refer to one or more configurations and vice versa.
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- General Engineering & Computer Science (AREA)
- Human Computer Interaction (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Computer Hardware Design (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
- Automatic Disk Changers (AREA)
Abstract
A storage controller controlling said plurality of storage media devices receives one or more commands from a queue representing a load, identifies a set of weighted storage regions having the mid-range access rate to target a mid-range performance level that is enough to service the load; and distributes the load based on the mid-range performance level by utilizing only the set of weighted storage regions having the mid-range access rate thereby targeting the mid-range performance level that is enough to service the load.
Description
SYSTEM AND METHOD FOR DYNAMICALLY LOAD BALANCING
STORAGE MEDIA DEVICES BASED ON A MID-RANGE PERFORMANCE LEVEL
BACKGROUND OF THE INVENTION
Field of Invention
The present invention relates generally to the field of storage. More specifically, the present invention is related to system and method for dynamically load balancing storage media devices based on a mid-range performance level.
Discussion of Related Art
Native Command Queuing (NCQ) are known in the prior art for optimizing the order in which commands (i.e., read and/or write) are executed in a single drive, where the optimization is localized within the single drive. However, storage systems having such NCQ supported drives do not view the storage system holistically as existing techniques, such as Native Command Queuing (NCQ) or storage media device head movement time minimization, look at a single host - slave in a vacuum (i.e., a single storage media device). What is absent in the prior art is a system and method that brings load balancing methodologies typically applied at a macro level (to networks outside of the storage systems or compute systems) down to the micro level within the storage system itself and applied across the storage media devices within that system using criteria specific to storage media devices.
Embodiments of the present invention are an improvement over prior art systems and methods.
SUMMARY OF THE INVENTION
In one embodiment, the present invention provides a storage system comprising: a plurality of storage media devices, each storage media device comprising one or more addressable storage regions, each region assigned a different weight based on at least a fast access rate, a mid-range access rate or a slow access rate, respectively; a storage controller controlling the plurality of storage media devices, the storage controller: receives one or more commands from a queue representing a load; identifies a set of weighted storage regions having the mid-range access rate to target a mid-range performance level that is enough to service the load; and distributes the load based on the mid-range performance level by
utilizing only the set of weighted storage regions having the mid-range access rate thereby targeting the mid-range performance level that is enough to service the load.
In another embodiment, the present invention provides a storage system comprising: a plurality of storage media devices, each storage media device comprising one or more addressable storage regions, each region assigned a different weight based on at least a fast access rate or a slow access rate, respectively; a storage controller controlling the plurality of storage media devices, the storage controller: receives one or more commands from a queue representing a load; derives a mid-range access rate that is a function of the fast access rate and the slow access rate, where the mid-range access rate is achieved by alternating the fast access rate and the slow access rate; and distributes the load based on the mid-range performance level that is enough to service the load.
In another embodiment, the present invention provides a method as implemented in a storage system comprising a plurality of storage media devices, each storage media device comprising one or more addressable storage regions, each region assigned a different weight based on at least a fast access rate, a mid-range access rate or a slow access rate, respectively, a storage controller controlling the plurality of storage media devices, the method comprising: receiving one or more commands from a queue representing a load; identifying a set of weighted storage regions having the mid-range access rate to target a mid-range performance level that is enough to service the load; and distributing the load based on the mid-range performance level by utilizing only the set of weighted storage regions having the mid-range access rate thereby targeting the mid-range performance level that is enough to service the load.
In another embodiment, the present invention provides a method as implemented in storage system comprising: a plurality of storage media devices, each storage media device comprising one or more addressable storage regions, each region assigned a different weight based on at least a fast access rate or a slow access rate, respectively; a storage controller controlling the plurality of storage media devices, the method comprising: receiving one or more commands from a queue representing a load; deriving a mid-range access rate that is a function of the fast access rate and the slow access rate, where the mid-range access rate is achieved by alternating the fast access rate and the slow access rate; and distributing the load based on the mid-range performance level that is enough to service the load.
In another embodiment, the present invention provides a non-transitory, computer accessible memory medium storing program instructions for performing a method as implemented in a storage system comprising a plurality of storage media devices, each storage media device comprising one or more addressable storage regions, each region assigned a different weight based on at least a fast access rate, a mid-range access rate or a slow access rate, respectively, a storage controller controlling the plurality of storage media devices, wherein the program instructions are executable by a processor to: receive one or more commands from a queue representing a load; identify a set of weighted storage regions having the mid-range access rate to target a mid-range performance level that is enough to service the load; and distribute the load based on the mid-range performance level by utilizing only the set of weighted storage regions having the mid-range access rate thereby targeting the mid-range performance level that is enough to service the load.
In another embodiment, the present invention provides a non-transitory, computer accessible memory medium storing program instructions for performing a method as implemented in a storage system comprising a plurality of storage media devices, each storage media device comprising one or more addressable storage regions, each region assigned a different weight based on at least a fast access rate or a slow access rate, respectively; a storage controller controlling the plurality of storage media devices, wherein the program instructions are executable by a processor to: receive one or more commands from a queue representing a load; derive a mid-range access rate that is a function of the fast access rate and the slow access rate, where the mid-range access rate is achieved by alternating the fast access rate and the slow access rate; and distribute the load based on the mid-range performance level that is enough to service the load.
The present invention provides a storage system comprising: a plurality of storage media devices; at least one storage controller controlling the plurality of storage media devices; a load balancer in communication with the storage controller to balance storage load across the storage media devices; an optional memory shared between the load balancer and the storage controller; and the load balancer receiving a set of commands for execution in at least one storage media device among the plurality of storage media devices, optionally storing the set of commands in the shared memory, assigning either a positive or negative bias to each of the commands; and distributing load amongst the storage media devices as a function of the assigned positive or negative bias.
The present invention provides a storage system comprising: a plurality of storage media devices comprising at least a first storage media device and a second storage media device; at least one storage controller controlling the first and second storage media devices; a queue storing a set of commands to be executed in the first or second storage media devices; wherein the storage controller: computes a first apparent load associated with the first storage media device as a function of the set of commands, a first bias associated with execution of the set of commands in the first storage media device, and at least one time factor associated with execution of the set of commands in the first storage media device; computes a second apparent load associated with the second storage media device as a function of the set of commands, a second bias associated with execution of the set of commands in the second storage media device, and at least one time factor associated with execution of the set of commands in the second storage media device; the first apparent load less than the second apparent load when the first bias and the second bias are set to a neutral, unbiased value indicating potential execution of said set of commands in the first storage media device; negatively biases the first bias until the first apparent load is greater than the second apparent load; and executes the set of commands in the second storage media device.
The present invention provides a method as implemented in a storage system comprising a plurality of storage media devices comprising at least a first storage media device and a second storage media device, at least one storage controller controlling the first and second storage media devices, a queue storing a set of commands to be executed in the first or second storage media devices, the method comprising: computing a first apparent load associated with the first storage media device as a function of the set of commands, a first bias associated with execution of the set of commands in the first storage media device, and at least one time factor associated with execution of the set of commands in the first storage media device; computing a second apparent load associated with the second storage media device as a function of the set of commands, a second bias associated with execution of the set of commands in the second storage media device, and at least one time factor associated with execution of the set of commands in the second storage media device; the first apparent load less than the second apparent load when the first bias and the second bias are set to a neutral, unbiased value indicating potential execution of said set of commands in the first storage media device; negatively biasing the first bias until the first apparent load is greater
than the second apparent load; and executing the set of commands in the second storage media device.
The present invention provides for a non-transitory, computer accessible memory medium storing program instructions for performing a method as implemented in a storage system comprising a plurality of storage media devices comprising at least a first storage media device and a second storage media device, at least one storage controller controlling the first and second storage media devices, a queue storing a set of commands to be executed in the first or second storage media devices, wherein the program instructions are executable by a processing element to: compute a first apparent load associated with the first storage media device as a function of the set of commands, a first bias associated with execution of the set of commands in the first storage media device, and at least one time factor associated with execution of the set of commands in the first storage media device; compute a second apparent load associated with the second storage media device as a function of the set of commands, a second bias associated with execution of the set of commands in the second storage media device, and at least one time factor associated with execution of the set of commands in the second storage media device; the first apparent load less than the second apparent load when the first bias and the second bias are set to a neutral, unbiased value indicating potential execution of said set of commands in the first storage media device; negatively bias the first bias until the first apparent load is greater than the second apparent load; and execute the set of commands in the second storage media device.
The present invention provides a storage system comprising: a plurality of storage media devices comprising at least a first storage media device and a second storage media device; at least one storage controller controlling the first and second storage media devices; a queue storing a set of commands to be executed in the first or second storage media devices; wherein the storage controller: computes a first apparent load associated with the first storage media device as a function of the set of commands, a first bias associated with execution of the set of commands in the first storage media device, and at least one time factor associated with execution of the set of commands in the first storage media device; computes a second apparent load associated with the second storage media device as a function of the set of commands, a second bias associated with execution of the set of commands in the second storage media device, and at least one time factor associated with execution of the set of commands in the second storage media device; the first apparent load less than the second
apparent load when the first bias and the second bias are set to a neutral, unbiased value indicating potential execution of said set of commands in the first storage media device; positively biases the second bias until the first apparent load is greater than the second apparent load; and executes the set of commands in the second storage media device.
The present invention provides a method as implemented in a storage system comprising a plurality of storage media devices comprising at least a first storage media device and a second storage media device, at least one storage controller controlling the first and second storage media devices, a queue storing a set of commands to be executed in the first or second storage media devices, the method comprising: computing a first apparent load associated with the first storage media device as a function of the set of commands, a first bias associated with execution of the set of commands in the first storage media device, and at least one time factor associated with execution of the set of commands in the first storage media device; computing a second apparent load associated with the second storage media device as a function of the set of commands, a second bias associated with execution of the set of commands in the second storage media device, and at least one time factor associated with execution of the set of commands in the second storage media device; the first apparent load less than the second apparent load when the first bias and the second bias are set to a neutral, unbiased value indicating potential execution of said set of commands in the first storage media device; positively biasing the second bias until the first apparent load is greater than the second apparent load; and executing the set of commands in the second storage media device.
The present invention provides for a non-transitory, computer accessible memory medium storing program instructions for performing a method as implemented in a storage system comprising a plurality of storage media devices comprising at least a first storage media device and a second storage media device, at least one storage controller controlling the first and second storage media devices, a queue storing a set of commands to be executed in the first or second storage media devices, wherein the program instructions are executable by a processing element to: compute a first apparent load associated with the first storage media device as a function of the set of commands, a first bias associated with execution of the set of commands in the first storage media device, and at least one time factor associated with execution of the set of commands in the first storage media device; compute a second apparent load associated with the second storage media device as a function of the set of
commands, a second bias associated with execution of the set of commands in the second storage media device, and at least one time factor associated with execution of the set of commands in the second storage media device; the first apparent load less than the second apparent load when the first bias and the second bias are set to a neutral, unbiased value indicating potential execution of said set of commands in the first storage media device; positively bias the second bias until the first apparent load is greater than the second apparent load; and execute the set of commands in the second storage media device.
The present invention provides a storage system comprising: a plurality of storage media devices comprising at least a first storage media device and a second storage media device; at least one storage controller controlling the first and second storage media devices; a queue storing a set of commands to be executed in the first or second storage media devices; wherein the storage controller: computes a first apparent load associated with the first storage media device as a function of the set of commands, a first bias associated with execution of the set of commands in the first storage media device, and at least one time factor associated with execution of the set of commands in the first storage media device; computes a second apparent load associated with the second storage media device as a function of the set of commands, a second bias associated with execution of the set of commands in the second storage media device, and at least one time factor associated with execution of the set of commands in the second storage media device; the first apparent load greater than the second apparent load when the first bias and the second bias are set to a neutral, unbiased value indicating potential execution of said set of commands in the second storage media device; negatively biases the second bias until the second apparent load is greater than the first apparent load; and executes the set of commands in the first storage media device.
The present invention provides a method as implemented in a storage system comprising a plurality of storage media devices comprising at least a first storage media device and a second storage media device, at least one storage controller controlling the first and second storage media devices, a queue storing a set of commands to be executed in the first or second storage media devices, the method comprising: computing a first apparent load associated with the first storage media device as a function of the set of commands, a first bias associated with execution of the set of commands in the first storage media device, and at least one time factor associated with execution of the set of commands in the first storage media device; computing a second apparent load associated with the second storage media
device as a function of the set of commands, a second bias associated with execution of the set of commands in the second storage media device, and at least one time factor associated with execution of the set of commands in the second storage media device; the first apparent load greater than the second apparent load when the first bias and the second bias are set to a neutral, unbiased value indicating potential execution of said set of commands in the second storage media device; negatively biasing the second bias until the second apparent load is greater than the first apparent load; and executing the set of commands in the first storage media device.
The present invention provides for a non-transitory, computer accessible memory medium storing program instructions for performing a method as implemented in a storage system comprising a plurality of storage media devices comprising at least a first storage media device and a second storage media device, at least one storage controller controlling the first and second storage media devices, a queue storing a set of commands to be executed in the first or second storage media devices, wherein the program instructions are executable by a processing element to: compute a first apparent load associated with the first storage media device as a function of the set of commands, a first bias associated with execution of the set of commands in the first storage media device, and at least one time factor associated with execution of the set of commands in the first storage media device; compute a second apparent load associated with the second storage media device as a function of the set of commands, a second bias associated with execution of the set of commands in the second storage media device, and at least one time factor associated with execution of the set of commands in the second storage media device; the first apparent load greater than the second apparent load when the first bias and the second bias are set to a neutral, unbiased value indicating potential execution of said set of commands in the second storage media device; negatively bias the second bias until the second apparent load is greater than the first apparent load; and execute the set of commands in the first storage media device.
The present invention provides a storage system comprising: a plurality of storage media devices comprising at least a first storage media device and a second storage media device; at least one storage controller controlling the first and second storage media devices; a queue storing a set of commands to be executed in the first or second storage media devices; wherein the storage controller: computes a first apparent load associated with the first storage media device as a function of the set of commands, a first bias associated with execution of
the set of commands in the first storage media device, and at least one time factor associated with execution of the set of commands in the first storage media device; computes a second apparent load associated with the second storage media device as a function of the set of commands, a second bias associated with execution of the set of commands in the second storage media device, and at least one time factor associated with execution of the set of commands in the second storage media device; the first apparent load greater than the second apparent load when the first bias and the second bias are set to a neutral, unbiased value indicating potential execution of said set of commands in the second storage media device; positively biases the first bias until the second apparent load is greater than the first apparent load; and executes the set of commands in the first storage media device.
The present invention provides a method as implemented in a storage system comprising a plurality of storage media devices comprising at least a first storage media device and a second storage media device, at least one storage controller controlling the first and second storage media devices, a queue storing a set of commands to be executed in the first or second storage media devices, the method comprising: computing a first apparent load associated with the first storage media device as a function of the set of commands, a first bias associated with execution of the set of commands in the first storage media device, and at least one time factor associated with execution of the set of commands in the first storage media device; computing a second apparent load associated with the second storage media device as a function of the set of commands, a second bias associated with execution of the set of commands in the second storage media device, and at least one time factor associated with execution of the set of commands in the second storage media device; the first apparent load greater than the second apparent load when the first bias and the second bias are set to a neutral, unbiased value indicating potential execution of said set of commands in the second storage media device; positively biasing the first bias until the second apparent load is greater than the first apparent load; and executing the set of commands in the first storage media device.
The present invention provides for a non-transitory, computer accessible memory medium storing program instructions for performing a method as implemented in a storage system comprising a plurality of storage media devices comprising at least a first storage media device and a second storage media device, at least one storage controller controlling the first and second storage media devices, a queue storing a set of commands to be executed
in the first or second storage media devices, wherein the program instructions are executable by a processing element to: compute a first apparent load associated with the first storage media device as a function of the set of commands, a first bias associated with execution of the set of commands in the first storage media device, and at least one time factor associated with execution of the set of commands in the first storage media device; compute a second apparent load associated with the second storage media device as a function of the set of commands, a second bias associated with execution of the set of commands in the second storage media device, and at least one time factor associated with execution of the set of commands in the second storage media device; the first apparent load greater than the second apparent load when the first bias and the second bias are set to a neutral, unbiased value indicating potential execution of said set of commands in the second storage media device; positively bias the first bias until the second apparent load is greater than the first apparent load; and execute the set of commands in the first storage media device.
It should be noted that while the specification refers to at least one storage controller, the teachings of the present invention equally apply to a plurality of storage controllers, including multiple, distributed, storage controllers. Also, while, for the sake of simplicity, the system is described as being within a chassis, it should be noted that the entire system need not be co-located within one chassis or physical location, as one or more individual elements may be located as part of a different chassis/location. Additionally, the system may also have parent and child storage controllers, where a parent storage controller makes decisions to balance across child storage controllers, who may then make decisions to balance across their child storage controllers, etc. (eventually reaching storage media devices connected to last storage controller(s) in the chain).
While the specification refers to positive and negative biases as notations to either artificially lower or artificially increase the load, it should be noted that the opposite notation is also within the scope of the present invention (e.g., positive bias referring to artificially increasing the load and negative bias referring to artificially lowering the load).
BRIEF DESCRIPTION OF THE DRAWINGS
The present disclosure, in accordance with one or more various examples, is described in detail with reference to the following figures. The drawings are provided for purposes of illustration only and merely depict examples of the disclosure. These drawings are provided
to facilitate the reader's understanding of the disclosure and should not be considered limiting of the breadth, scope, or applicability of the disclosure. It should be noted that for clarity and ease of illustration these drawings are not necessarily made to scale.
FIG. 1 depicts a storage controller controlling storage media devices having regions of varying access rates.
FIG. 2A-B and FIG. 3 illustrates examples of the present invention's method to distribute load based on mid-range performance level.
FIG. 4A, FIG. 5A, FIG. 6A, and FIG. 7A illustrate various embodiments of the system of the present invention for either positively or negatively biasing the apparent load.
FIG. 4B, FIG. 5B, FIG. 6B, and FIG. 7B illustrate methods associated with the various embodiments of the present invention for either positively or negatively biasing the apparent load.
DESCRIPTION OF THE PREFERRED EMBODIMENTS
While this invention is illustrated and described in a preferred embodiment, the invention may be produced in many different configurations. There is depicted in the drawings, and will herein be described in detail, a preferred embodiment of the invention, with the understanding that the present disclosure is to be considered as an exemplification of the principles of the invention and the associated functional specifications for its construction and is not intended to limit the invention to the embodiment illustrated. Those skilled in the art will envision many other possible variations within the scope of the present invention.
Note that in this description, references to "one embodiment" or "an embodiment" mean that the feature being referred to is included in at least one embodiment of the invention. Further, separate references to "one embodiment" in this description do not necessarily refer to the same embodiment; however, neither are such embodiments mutually exclusive, unless so stated and except as will be readily apparent to those of ordinary skill in the art. Thus, the present invention can include any variety of combinations and/or integrations of the embodiments described herein.
The present invention views the storage system holistically. Whereas existing techniques, such as Native Command Queuing (NCQ) or storage media device head movement time minimization, look at a single host - slave in a vacuum (i.e., a single storage media device). This invention brings load balancing methodologies typically applied at a
macro level (to networks outside of the storage systems or compute systems) down to the micro level within the storage system itself and applied across the storage media devices within that system using criteria specific to storage media devices.
In one embodiment, the present invention's system and method maintains a balance of storage media devices accessing fast regions of their media and storage media devices accessing slow regions of their media to produce a sustained throughput higher than that of randomly accessing the storage media devices, thus targeting the average throughput of a storage media device (e.g., between fast access location and slow access location).
In another embodiment consider a unit of measure called DR (Storage Media Device and a Region within) and applied to rotational storage media devices. In this example DRs are computed by assigning weights for all storage media devices and their sub regions within a storage system based physical characteristics. These regions may be a series of sequential sectors. Other components of the weights are based on recorded historical performance trends and real time actual performance. Then, based on the DRs calculated, one may distribute load across the storage system based upon these DR weights. One distribution scheme would be to target a minimum performance level, in which lower value (lower performance) DRs may be used before higher value DRs to hold high value DRs in reserve, to be used as needed to meet that minimum performance level. Another scheme would be to maximize performance and distribute load across the highest available DRs at all times. An example region-weighting scheme would be to start with a reference region and assigning that a weight of 1.0, typically the lowest performing region would be selected as the reference. Every other regions' weight is assigned as a ratio of its performance to that of the reference. If a region were 50% higher performance than that of the reference its weight would be assigned 1.5. If a region were 10% lower performance than that of the reference its weight would be assigned 0.9.
The DR applies to non-rotational storage media devices as well, simply different weights and regions are defined based on the technology. In some such devices, a DR may include regions based on access type (e.g., access type may be based on read or write, such as the case of a solid-state storage media device where fast and slow access rates may correspond to read or write rates and the solid-state storage media device may have overlapping read and write regions), to account for differing performance levels of each. In addition, some such devices may also be considered a hybrid of differing technologies, such
as solid-state and rotational, whereas the performance of each technology differs and in some instances differs further within each technology.
Different storage media devices have different features and limitations. For example, rotational hard drives must mechanically move an arm and heads across spinning platters to locate a data block (seek time) and the supported data rates vary with the data's location on the spinning platter such that data closer to the outer diameter of the platter flows faster to and from such spinning platter. In this scenario it is often desirable to minimize the movement of the heads as well as locate data on the outer circumference of the platters.
This invention assigns weightings to commands based on many factors, including but not limited to the limitations of the underlying storage media device. It then views the command queue fullness / load from that perspective rather than simply the number of commands outstanding, to determine the "apparent load" of a storage media device. The invention also discloses the use of a positive bias and a negative bias to artificially influence the apparent load. This bias may be based on what is expected or about to be destined for the storage media device (such as load reservation and load predictions), what is already committed / pending, or what is desired. The difference between a reservation and a commitment is that a reservation can be changed or reallocated based upon new information. Predictions may be based on historical trends or knowledge base of specific types of traffic. Non-limiting prediction examples include:
• video streaming, which generally maintains a given average rate;
• known or measured bandwidth limitations of either the source or destination, such as destination X cannot accept data faster than lGbps for example; and
• adjustments made based on the type of traffic, such as its bursty nature.
When the storage system is viewed holistically, one can cause certain storage media devices to get less of the load by negative bias (arbitrarily causing a certain storage media device to "appear" more heavily loaded), thus forcing other storage media devices to pick up additional load. One may also increase a storage media device's load by adding positive bias (arbitrarily causing a certain storage media device to "appear" less heavily loaded). It may be desirable to reduce the load on a storage media device in order to reduce power consumption or operating temperatures. Alternatively, if a given storage media device thermal profile is desired (such as desiring higher operating temperatures for operation in cold weather extremes or space-based equipment), increasing the load and consequently the temperature
may be desirable as well. Bias is useful to distribute the data volume across storage media devices of varying capacities to insure any given storage media device does not prematurely fill, be subsequently unavailable for further writes, and thus reduce the number of storage media devices that a given write load may be distributed across. It is also useful to maintain a certain sustainable data rate for a storage system by holding some bandwidth or load capability in reserve, to be used when needed to increase instantaneous data rate in order to maintain that sustainable data rate average (much like a regulator). Without bias, faster storage media devices would naturally get more load by default since they would appear to be less heavily loaded (i.e. they are capable of handling more data faster), but this is not always desired and can be corrected with bias. Bias allows for "traffic shaping" of the data flow, which can intentionally shape the load on the storage media devices as well as the load seen on the attached network to match a desired profile. The Bias may also vary based upon the type of data (i.e. type of data traffic) or to follow a given Quality of Service (QoS) scheme.
In one embodiment, the apparent load may be used solely for monitoring purposes, meaning that it could be used as an indicator of system performance without being used to modify the load in any way.
In another embodiment, apparent load may include the "whole path" from the point where a command is issued all the way to the point at which the response is received. Prior art looks at a storage media device itself, alone, assuming negligible time for transport and movement to/from memory/memories. However, when dealing with a given sustained data rate, the transport layer may be important (such as when through a network or distributed system where the storage controller and storage media devices have physical separation) as well as the movement of data to/from a storage media device and memory/memories. The performance of a storage media device will be impacted if data cannot flow to or be carried away from the storage media device fast enough, a condition not typically under the direct control of the storage media device, which will cause data pushback or starvation. The impact of one or more caches in the path would then be included within the apparent load.
For clarity, the following is a non-limiting apparent load calculation:
N
M. * Bias.
ApparentLoad = for N commands in the queue
i=0 QueueCapacity
^ _ R quiredSeekTime Tcmd
T T
Where min min
Tmin = minimal time possible for any single command for the storage media device, from issuance to completion.
Tcmd = time for the specific command to issue, from issuance to completion. This is dependent upon the actual command. For example, in some storage media devices, a write may require a different period of time to complete than a read. Also, if the path contains one or more caches, the time to complete the command may vary at different times.
QueueCapacity = the maximum number of commands that the queue can hold.
Bias = the desired artificial influence applied to each command. A number ranging from 0.0 -> 10.0; for example, neutral bias would be 1.0, positive bias would be a value below 1.0 (to artificially lower the apparent load), while negative bias would be a value greater than 1.0 (to artificially increase the apparent load).
RequiredSeekTime = The estimated or actual storage media device seek time, based upon lookup or historical performance or calculation, for this command from the previous command.
Both Tmin and Tcmd are system values. These values may vary based on the class of storage media device (such as rotational, solid state, or hybrid). They may be treated as static or dynamic based on measured system characteristics in real-time and / or historical values. Such measurements may include temperature monitoring (when the completion times vary with temperature) or current cache contents. In addition, each specific storage media device to be used in the system may be "qualified" and the values of Tmin and Tcmd determined and used for accesses to that specific storage media device. As an alternative, a sampling of similar storage media devices may be "qualified" and averaged to produce values for that class of storage media device.
It should be noted that the time factor as used herein refers to the required seek time, Tmin, Tcmd, combinations thereof, or functions based on various combinations thereof.
Some non-limiting example usages of the apparent load include, but are not limited to
• reordering commands in a queue;
• influencing the power consumption and thermal profile of a storage media device;
• removing commands from a queue;
• reallocating commands from the queue of one storage media device to another;
• minimizing or maximizing storage media device seek time;
• controlling the fill rate of a storage media device; and / or
• passively monitoring system performance.
In one embodiment, the described storage media device is not a separate physical device, as it may be memory used for storage, embedded within another device.
The present invention provides a storage system comprising: a plurality of storage media devices; at least one storage controller controlling the plurality of storage media devices; a load balancer in communication with the storage controller to balance storage load across the storage media devices; an optional memory shared between the load balancer and the storage controller; and the load balancer receiving a plurality of commands for execution in at least one storage media device among the plurality of storage media devices, optionally storing the commands in the shared memory, assigning either a positive or negative bias to each of the commands; and distributing load amongst the storage media devices as a function of the assigned positive or negative bias.
FIG. 1 provides a system-level diagram to understand the principles of the present invention. In this non- limiting example, the present invention's system comprises a storage controller 102 that controls a plurality of storage media devices represented by 104 and 106. Storage media device 104 comprises regions of varying access rates. For example, if storage media device 104 were a rotational disk drive, the outermost region of storage media device 104 is the fast access region as this refers to a region that provides fastest read/write access rates. Along the same lines, the inner-most region of storage media device 104 is a slow access region as this refers to a region that provides slowest read/write access rates. There also may be regions between the fast access rate regions and the slow access rate regions, which we refer to as the mid-range access rate region.
It should be noted that two storage media devices are shown in FIG. 1 only for the sake of simplicity, and that the present invention covers instances where there are more than two storage media devices, as is the case with most network attached storage (NAS) devices or storage devices that are part of a storage area network (SAN).
In the example shown in FIG. 1, the storage media device 104 has three access rate regions shown, a fast access region 108, a mid-range access region 110, and a slow access region 112. It should also be noted that while a three-tier access region (i.e., fast access region 108, mid-range access region 110, and slow access region 112) is disclosed in FIG. 1, the same teachings can be expanded to a multi-tier region where there are a plurality of access rate regions between the fast access rate region 108 and the slow access rate region 112 shown in FIG. 1. In FIG. 1, fast access region 108 of storage media device 104 is further subdivided into a plurality of fast access regions shown as D^R° , DyR , etc. Similarly, mid- range access region 110 of storage media device 104 is further subdivided into a plurality of regions shown as
, DyR2 , etc. and slow access region 112 of storage media device 104 is further subdivided into a plurality of regions shown as , DyR2 c , etc.
Also, shown in FIG. 1, fast access region 108 of storage media device 106 is further subdivided into a plurality of fast access regions shown as D2R , D2R2 , etc. Similarly, mid- range access region 110 of storage media device 106 is further subdivided into a plurality of regions shown as D2R( , D2R{ , etc. and slow access region 112 of storage media device 106 is further subdivided into a plurality of regions shown as D2R , D2R2 , etc.
In one embodiment, the present invention provides a storage system comprising: a plurality of storage media devices, each storage media device comprising one or more addressable storage regions, each region assigned a different weight based on at least a fast access rate, a mid-range access rate or a slow access rate, respectively; a storage controller controlling the plurality of storage media devices, the storage controller: receives one or more commands from a queue representing a load; identifies a set of weighted storage regions having the mid-range access rate to target a mid-range performance level that is enough to service the load; and distributes the load based on the mid-range performance level by utilizing only the set of weighted storage regions having the mid-range access rate thereby targeting the mid-range performance level that is enough to service the load.
In another embodiment, the present invention provides a storage system comprising: a plurality of storage media devices, each storage media device comprising one or more addressable storage regions, each region assigned a different weight based on at least a fast access rate or a slow access rate, respectively; a storage controller controlling the plurality of storage media devices, the storage controller: receives one or more commands from a queue representing a load; derives a mid-range access rate that is a function of the fast access rate and the slow access rate, where the mid-range access rate is achieved by alternating the fast access rate and the slow access rate; and distributes the load based on the mid-range performance level that is enough to service the load.
Non-limiting examples of storage media devices are any of, or a combination of, the following: solid-state drive, rotational hard disk drive, hybrid disk drive, or PCI-Express slot disk drive.
Further, the storage media devices may be part of a storage area network (SAN) or may be part of a network attached storage (NAS) device.
In another embodiment, as depicted in FIG. 2A, the present invention provides a method as implemented in a storage system comprising a plurality of storage media devices, each storage media device comprising one or more addressable storage regions, each region assigned a weight based on at least a fast or slow access rate, where regions having fast access rate are weighted differently than regions having slow access rate (e.g., regions having fast access rate having higher weights than regions having slow access rate or regions having slow access rate having higher weights than regions having fast access rate), a storage controller controlling the plurality of storage media devices, the method comprising: receiving one or more commands from a queue representing a load - step 201; identifying a minimum performance level required for the load - step 203; identifying a first set of weighted storage regions having a slow access rate across the plurality of storage media devices and a second set of weighted storage regions having a fast access rate in the plurality of storage media devices - step 205; identifying a subset of storage regions within the first set of weighted storage regions having a slow access rate that satisfies the identified minimum performance level - step 207; and distributing the load based on the identified minimum performance level by utilizing only the subset of storage regions within the first set of weighted storage
regions having the slow access rate and holding the second storage region having the fast access rate in reserve - step 209.
In another embodiment, as depicted in FIG. 2B, the present invention provides a method as implemented in a storage system comprising a storage system comprising a plurality of storage media devices, each storage media device comprising one or more addressable storage regions, each region assigned a different weight based on at least a fast access rate, a mid-range access rate or a slow access rate, respectively, a storage controller controlling the plurality of storage media devices, the method comprising: receiving one or more commands from a queue representing a load - step 202; identifying a set of weighted storage regions having the mid-range access rate to target a mid-range performance level that is enough to service the load - step 204; and distributing the load based on the mid-range performance level by utilizing only the set of weighted storage regions having the mid-range access rate thereby targeting the mid-range performance level that is enough to service the load - step 206.
The embodiments of Figs. 2 A and 2B are not meant to be limiting as the embodiments may be extended to computing an optimal sustained performance level as function of the first set of weighted storage regions having the slow access rate and the second set of weighted storage regions having the fast access rate; and distributing load based on the computed optimal sustained performance level. One example sustained performance level determined would be to examine the sets of weighted storage regions presented and take the average, this average being used to distribute the load by alternating weighted storage regions as necessary to maintain that average over time. Another example sustained performance level determined would be to examine the sets of weighted storage regions presented and take the average then apply a discount to that average to allow for operational margin, this discounted average being used to distribute the load by alternating weighted storage regions as necessary to maintain that discounted average over time. The embodiments may be further extended to identifying one or more weighted fast access storage regions within the addressable storage regions across the plurality of storage media devices having the fast access rate and distributing load by utilizing only the weighted fast access storage regions within the addressable storage regions across the plurality of storage media devices having the fast access rate.
In another embodiment, as depicted in FIG. 3, the present invention provides a method as implemented in storage system comprising: a plurality of storage media devices, each storage media device comprising one or more addressable storage regions, each region
assigned a different weight based on at least a fast access rate or a slow access rate, respectively; a storage controller controlling the plurality of storage media devices, the method comprising: receiving one or more commands from a queue representing a load - step 302; deriving a mid-range access rate that is a function of the fast access rate and the slow access rate - step 304, where the mid-range access rate is achieved by alternating the fast access rate and the slow access rate; and distributing the load based on the mid-range performance level that is enough to service the load - step 306.
In one embodiment, as depicted in FIG. 4A, the present invention provides a storage system comprising: a plurality of storage media devices comprising at least a first storage media device 402 and a second storage media device 404; at least one storage controller 406 controlling the first and second storage media devices 402 and 404, respectively; a queue 408 storing a set of commands 409 to be executed in the first or second storage media devices; wherein the storage controller 406: computes a first apparent load 410 associated with the first storage media device 402 as a function of the set of commands 409, a first bias associated with execution of the set of commands in the first storage media device, and at least one time factor (e.g., seek time) associated with execution of the set of commands 409 in the first storage media device 402; computes a second apparent load 412 associated with the second storage media device 404 as a function of the set of commands 409, a second bias associated with execution of the set of commands in the second storage media device, and at least one time factor (e.g., seek time) associated with execution of the set of commands 409 in the second storage media device 404; the first apparent load 410 less than the second apparent load 412 when the first bias and the second bias are set to a neutral, unbiased value indicating potential execution of said set of commands in the first storage media device; negatively biases 414 the first bias until the first apparent load 410 is greater than the second apparent load 412; and executes the set of commands 409 in the second storage media device 404.
In another embodiment, as depicted in FIG. 4B, the present invention provides a method as implemented in a storage system comprising a plurality of storage media devices comprising at least a first storage media device and a second storage media device, at least one storage controller controlling the first and second storage media devices, a queue storing a set of commands to be executed in the first or second storage media devices, the method comprising: computing a first apparent load associated with the first storage media device as a function of the set of commands, a first bias associated with execution of the set of
commands in the first storage media device, and at least one time factor associated with execution of the set of commands in the first storage media device - step 416; computing a second apparent load associated with the second storage media device as a function of the set of commands, a second bias associated with execution of the set of commands in the second storage media device, and at least one time factor associated with execution of the set of commands in the second storage media device - step 418; the first apparent load less than the second apparent load when the first bias and the second bias are set to a neutral, unbiased value - step 420 indicating potential execution of said set of commands in the first storage media device; negatively biasing the first bias until the first apparent load is greater than the second apparent load - step 422; and executing the set of commands in the second storage media device - step 424.
In another embodiment, the present invention also provides for a non-transitory, computer accessible memory medium storing program instructions for performing a method as implemented in a storage system comprising a plurality of storage media devices comprising at least a first storage media device and a second storage media device, at least one storage controller controlling the first and second storage media devices, a queue storing a set of commands to be executed in the first or second storage media devices, wherein the program instructions are executable by a processing element to: compute a first apparent load associated with the first storage media device as a function of the set of commands, a first bias associated with execution of the set of commands in the first storage media device, and at least one time factor associated with execution of the set of commands in the first storage media device; compute a second apparent load associated with the second storage media device as a function of the set of commands, a second bias associated with execution of the set of commands in the second storage media device, and at least one time factor associated with execution of the set of commands in the second storage media device; the first apparent load less than the second apparent load when the first bias and the second bias are set to a neutral, unbiased value indicating potential execution of said set of commands in the first storage media device; negatively bias the first bias until the first apparent load is greater than the second apparent load; and execute the set of commands in the second storage media device.
In another embodiment, as depicted in FIG. 5A, the present invention provides a storage system comprising: a plurality of storage media devices comprising at least a first
storage media device 502 and a second storage media device 504; at least one storage controller 206 controlling the first and second storage media devices 502 and 504, respectively; a queue 508 storing a set of commands 509 to be executed in the first or second storage media devices; wherein the storage controller 506: computes a first apparent load 510 associated with the first storage media device as a function of the set of commands 509, a first bias associated with execution of the set of commands 509 in the first storage media device 502, and at least one time factor (e.g., seek time) associated with execution of the set of commands 509 in the first storage media device 502; computes a second apparent load 512 associated with the second storage media device 504 as a function of the set of commands 509, a second bias associated with execution of the set of commands 509 in the second storage media device 504, and at least one time factor (e.g., seek time) associated with execution of the set of commands 509 in the second storage media device 504; the first apparent load 510 less than the second apparent load 512 when the first bias and the second bias are set to a neutral, unbiased value indicating potential execution of said set of commands in the first storage media device; positively biases 514 the second bias until the first apparent load 510 is greater than the second apparent load 512; and executes the set of commands 509 in the second storage media device 504.
In another embodiment, as depicted in FIG. 5B, the present invention provides a method as implemented in a storage system comprising a plurality of storage media devices comprising at least a first storage media device and a second storage media device, at least one storage controller controlling the first and second storage media devices, a queue storing a set of commands to be executed in the first or second storage media devices, the method comprising: computing a first apparent load associated with the first storage media device as a function of the set of commands, a first bias associated with execution of the set of commands in the first storage media device, and at least one time factor associated with execution of the set of commands in the first storage media device - step 516; computing a second apparent load associated with the second storage media device as a function of the set of commands, a second bias associated with execution of the set of commands in the second storage media device, and at least one time factor associated with execution of the set of commands in the second storage media device - step 518; the first apparent load less than the second apparent load when the first bias and the second bias are set to a neutral, unbiased value - step 520 indicating potential execution of said set of commands in the first storage media device; positively biasing the second bias until the first apparent load is greater than
the second apparent load - step 522; and executing the set of commands in the second storage media device - step 524.
In another embodiment, the present invention also provides for a non-transitory, computer accessible memory medium storing program instructions for performing a method as implemented in a storage system comprising a plurality of storage media devices comprising at least a first storage media device and a second storage media device, at least one storage controller controlling the first and second storage media devices, a queue storing a set of commands to be executed in the first or second storage media devices, wherein the program instructions are executable by a processing element to: compute a first apparent load associated with the first storage media device as a function of the set of commands, a first bias associated with execution of the set of commands in the first storage media device, and at least one time factor associated with execution of the set of commands in the first storage media device; compute a second apparent load associated with the second storage media device as a function of the set of commands, a second bias associated with execution of the set of commands in the second storage media device, and at least one time factor associated with execution of the set of commands in the second storage media device; the first apparent load less than the second apparent load when the first bias and the second bias are set to a neutral, unbiased value indicating potential execution of said set of commands in the first storage media device; positively bias the second bias until the first apparent load is greater than the second apparent load; and execute the set of commands in the second storage media device.
In another embodiment, as depicted in FIG. 6A, the present invention provides a storage system comprising: a plurality of storage media devices comprising at least a first storage media device 602 and a second storage media device 604; at least one storage controller 306 controlling the first and second storage media devices 602 and 604, respectively; a queue 608 storing a set of commands 609 to be executed in the first or second storage media devices; wherein the storage controller 606: computes a first apparent load 610 associated with the first storage media device 602 as a function of the set of commands 609, a first bias associated with execution of the set of commands 309 in the first storage media device 602, and at least one time factor (e.g., seek time) associated with execution of the set of commands 609 in the first storage media device 602; computes a second apparent load 612 associated with the second storage media device 604 as a function of the set of commands
609, a second bias associated with execution of the set of commands 609 in the second storage media device 604, and at least one time factor (e.g., seek time) associated with execution of the set of commands 609 in the second storage media device 604; the first apparent load 610 greater than the second apparent load 612 when the first bias and the second bias are set to a neutral, unbiased value indicating potential execution of said set of commands in the second storage media device; negatively biases 614 the second bias until the second apparent load 612 is greater than the first apparent load 610; and executes the set of commands 609 in the first storage media device 602.
In another embodiment, as depicted in FIG. 6B, the present invention provides a method as implemented in a storage system comprising a plurality of storage media devices comprising at least a first storage media device and a second storage media device, at least one storage controller controlling the first and second storage media devices, a queue storing a set of commands to be executed in the first or second storage media devices, the method comprising: computing a first apparent load associated with the first storage media device as a function of the set of commands, a first bias associated with execution of the set of commands in the first storage media device, and at least one time factor associated with execution of the set of commands in the first storage media device - step 616; computing a second apparent load associated with the second storage media device as a function of the set of commands, a second bias associated with execution of the set of commands in the second storage media device, and at least one time factor associated with execution of the set of commands in the second storage media device - step 618; the first apparent load greater than the second apparent load when the first bias and the second bias are set to a neutral, unbiased value - step 620 indicating potential execution of said set of commands in the second storage media device; negatively biasing the second bias until the second apparent load is greater than the first apparent load - step 622; and executing the set of commands in the first storage media device - step 624.
In another embodiment, the present invention also provides for a non-transitory, computer accessible memory medium storing program instructions for performing a method as implemented in a storage system comprising a plurality of storage media devices comprising at least a first storage media device and a second storage media device, at least one storage controller controlling the first and second storage media devices, a queue storing a set of commands to be executed in the first or second storage media devices, wherein the
program instructions are executable by a processing element to: compute a first apparent load associated with the first storage media device as a function of the set of commands, a first bias associated with execution of the set of commands in the first storage media device, and at least one time factor associated with execution of the set of commands in the first storage media device; compute a second apparent load associated with the second storage media device as a function of the set of commands, a second bias associated with execution of the set of commands in the second storage media device, and at least one time factor associated with execution of the set of commands in the second storage media device; the first apparent load greater than the second apparent load when the first bias and the second bias are set to a neutral, unbiased value indicating potential execution of said set of commands in the second storage media device; negatively bias the second bias until the second apparent load is greater than the first apparent load; and execute the set of commands in the first storage media device.
In another embodiment, as depicted in FIG. 7 A, the present invention provides a storage system comprising: a plurality of storage media devices comprising at least a first storage media device 702 and a second storage media device 704; at least one storage controller 706 controlling the first and second storage media devices 702 and 704, respectively; a queue 708 storing a set of commands 709 to be executed in the first or second storage media devices; wherein the storage controller 706: computes a first apparent load 710 associated with the first storage media device 702 as a function of the set of commands 709, a first bias associated with execution of the set of commands 709 in the first storage media device 702, and at least one time factor (e.g., seek time) associated with execution of the set of commands 709 in the first storage media device 702; computes a second apparent load 712 associated with the second storage media device 704 as a function of the set of commands 709, a second bias associated with execution of the set of commands 709 in the second storage media device 704, and at least one time factor (e.g., seek time) associated with execution of the set of commands 709 in the second storage media device 704; the first apparent load 710 greater than the second apparent load 712 when the first bias and the second bias are set to a neutral, unbiased value indicating potential execution of said set of commands in the second storage media device; positively biases 714 the first bias until the second apparent load 712 is greater than the first apparent load 710; and executes the set of commands 709 in the first storage media device 704.
In another embodiment, as depicted in FIG. 7B, the present invention also provides a method as implemented in a storage system comprising a plurality of storage media devices comprising at least a first storage media device and a second storage media device, at least one storage controller controlling the first and second storage media devices, a queue storing a set of commands to be executed in the first or second storage media devices, the method comprising: computing a first apparent load associated with the first storage media device as a function of the set of commands, a first bias associated with execution of the set of commands in the first storage media device, and at least one time factor associated with execution of the set of commands in the first storage media device - step 716; computing a second apparent load associated with the second storage media device as a function of the set of commands, a second bias associated with execution of the set of commands in the second storage media device, and at least one time factor associated with execution of the set of commands in the second storage media device - step 718; the first apparent load greater than the second apparent load when the first bias and the second bias are set to a neutral, unbiased value - step 720 indicating potential execution of said set of commands in the second storage media device; positively biasing the first bias until the second apparent load is greater than the first apparent load - step 722; and executing the set of commands in the first storage media device - step 724.
The embodiments may integrate specific use cases where the load balancing is achieved based on temperatures, temperature ranges, fill percentages, write rate, read rate, and data type in conjunction with the biasing. The temperatures, temperature ranges, fill percentages, write rate, read rate, and data type for the corresponding media devices may be monitored, measured or tracked through known means in some embodiments.
In another embodiment, the present invention provides a method as a non-transitory, computer accessible memory medium storing program instructions for performing a method as implemented in a storage system comprising a storage system comprising a plurality of storage media devices, each storage media device comprising one or more addressable storage regions, each region assigned a different weight based on at least a fast access rate, a mid- range access rate or a slow access rate, respectively, a storage controller controlling the plurality of storage media devices, wherein the program instructions are executable by a processor to: receive one or more commands from a queue representing a load; identify a set of weighted storage regions having the mid-range access rate to target a mid-range performance level that is enough to service the load; and distribute the load based on the mid- range performance level by utilizing only the set of weighted storage regions having the mid-
range access rate thereby targeting the mid-range performance level that is enough to service the load.
In another embodiment, the present invention provides a non-transitory, computer accessible memory medium storing program instructions for performing a method as implemented in a storage system comprising a plurality of storage media devices, each storage media device comprising one or more addressable storage regions, each region assigned a different weight based on at least a fast access rate or a slow access rate, respectively; a storage controller controlling the plurality of storage media devices, wherein the program instructions are executable by a processor to: receive one or more commands from a queue representing a load; derive a mid-range access rate that is a function of the fast access rate and the slow access rate, where the mid-range access rate is achieved by alternating the fast access rate and the slow access rate; and distribute the load based on the mid-range performance level that is enough to service the load.
It should be noted that while the specification refers to at least one storage controller, the teachings of the present invention equally applies to a plurality of storage controllers, including multiple, distributed, storage controllers. Also, while, for the sake of simplicity, the system is described as being within a chassis, it should be noted that the entire system need not be co-located within one chassis or physical location, as one or more individual elements may be located as part of a different chassis/location. Additionally, the system may also have parent and child storage controllers, where a parent storage controller makes decisions to balance across child storage controllers, who may then make decisions to balance across their child storage controllers, etc. (eventually hitting storage media devices connected to last storage controller(s) in the chain. As a non-limiting example, a storage controller may balance load across a chassis having a plurality of storage media devices, where a master storage controller may be connected to a plurality of such storage controllers to perform load balancing across a plurality of such chassis, each having a plurality of storage media devices.
The above-described features and applications can be implemented as software processes that are specified as a set of instructions recorded on a computer readable storage medium (also referred to as computer readable medium). When these instructions are executed by one or more processing element(s) (e.g., one or more processors, cores of processors, or other processing elements), they cause the processing element(s) to perform the
actions indicated in the instructions. Embodiments within the scope of the present disclosure may also include tangible and/or non-transitory computer-readable storage media for carrying or having computer-executable instructions or data structures stored thereon. Such non- transitory computer-readable storage media can be any available media that can be accessed by a general purpose or special purpose computer, including the functional design of any special purpose processor. By way of example, and not limitation, such non-transitory computer-readable media can include flash memory, RAM, ROM, EEPROM, CD-ROM or other optical disk storage, magnetic disk storage or other magnetic storage devices, or any other medium which can be used to carry or store desired program code means in the form of computer-executable instructions, data structures, or processor chip design. The computer readable media does not include carrier waves and electronic signals passing wirelessly or over wired connections.
Computer-executable instructions include, for example, instructions and data which cause a general purpose computer, special purpose computer, or special purpose processing device to perform a certain function or group of functions. Computer-executable instructions also include program modules that are executed by computers in stand-alone or network environments. Generally, program modules include routines, programs, components, data structures, objects, and the functions inherent in the design of special-purpose processors, etc. that perform particular tasks or implement particular abstract data types. Computer- executable instructions, associated data structures, and program modules represent examples of the program code means for executing steps of the methods disclosed herein. The particular sequence of such executable instructions or associated data structures represents examples of corresponding acts for implementing the functions described in such steps.
A computer program (also known as a program, software, software application, script, or code) can be written in any form of programming language, including compiled or interpreted languages, declarative or procedural languages, and it can be deployed in any form, including as a stand-alone program or as a module, component, subroutine, object, or other unit suitable for use in a computing environment. A computer program may, but need not, correspond to a file in a file system. A program can be stored in a portion of a file that holds other programs or data (e.g., one or more scripts stored in a markup language document), in a single file dedicated to the program in question, or in multiple coordinated files (e.g., files that store one or more modules, sub programs, or portions of code). A
computer program can be deployed to be executed on one computer or on multiple computers that are located at one site or distributed across multiple sites and interconnected by a communication network.
These functions described above can be implemented in digital electronic circuitry, in computer software, firmware or hardware. The techniques can be implemented using one or more computer program products. The processes and logic flows can be performed by one or more programmable processors and by one or more programmable logic circuitry. General and special purpose computing devices and storage devices can be interconnected through communication networks.
Some implementations include electronic components, for example microprocessors, storage and memory that store computer program instructions in a machine-readable or computer-readable medium (alternatively referred to as computer-readable storage media, machine-readable media, or machine-readable storage media). Some examples of such computer-readable media include RAM, ROM, read-only compact discs (CD-ROM), recordable compact discs (CD-R), rewritable compact discs (CD-RW), read-only digital versatile discs (e.g., DVD-ROM, dual-layer DVD-ROM), a variety of recordable/rewritable DVDs (e.g., DVD-RAM, DVD-RW, DVD+RW, etc.), flash memory (e.g., SD cards, mini-SD cards, micro-SD cards, etc.), magnetic or solid state hard drives, read-only and recordable Blu-Ray® discs, ultra density optical discs, any other optical or magnetic media, and floppy disks. The computer-readable media can store a computer program that is executable by at least one processing element and includes sets of instructions for performing various operations. Examples of computer programs or computer code include machine code, for example is produced by a compiler, and files including higher-level code that are executed by a computer, an electronic component, or a microprocessor using an interpreter.
While the above discussion primarily refers to microprocessor or multi-core processors that execute software, some implementations are performed by one or more integrated circuits, for example application specific integrated circuits (ASICs) or field programmable gate arrays (FPGAs). In some implementations, such integrated circuits execute instructions that are stored on/within the circuit itself. In some implementations, such as with FPGAs, software may be used to describe hardware circuits, an example of which are FPGA programming files. Such FPGA programming files may also include
computer programs, machine code, microcode, firmware, and other software. The FPGA programming files may be stored within an FPGA, ASIC, computer-readable storage media, machine-readable media, or machine-readable storage media.
As used in this specification and any claims of this application, the terms "computer", "server", "processor", and "memory" all refer to electronic or other technological devices. These terms exclude people or groups of people. For the purposes of the specification, the terms display or displaying means displaying on an electronic device. As used in this specification and any claims of this application, the terms "computer readable medium" and "computer readable media" are entirely restricted to tangible, physical objects that store information in a form that is readable by a computer. These terms exclude any wireless signals, wired download signals, and any other ephemeral signals.
Those of skill in the art will appreciate that other embodiments of the disclosure may be practiced in network computing environments with many types of computer system configurations, including personal computers, hand-held devices, multi-processor systems, ASIC -based systems, FPGA-based systems, microprocessor-based or programmable consumer electronics, network PCs, minicomputers, mainframe computers, and the like. Embodiments may also be practiced in distributed computing environments where tasks are performed by local and remote processing devices that are linked (either by hardwired links, wireless links, or by a combination thereof) through a communications network. In a distributed computing environment, program modules may be located in both local and remote memory storage devices.
It is understood that any specific order or hierarchy of steps in the processes disclosed is an illustration of example approaches. Based upon design preferences, it is understood that the specific order or hierarchy of steps in the processes may be rearranged, or that all illustrated steps be performed. Some of the steps may be performed simultaneously. For example, in certain circumstances, multitasking and parallel processing may be advantageous. Moreover, the separation of various system components illustrated above should not be understood as requiring such separation, and it should be understood that the described program components and systems can generally be integrated together in a single software product or packaged into multiple software products.
Various modifications to these aspects will be readily apparent, and the generic principles defined herein may be applied to other aspects. Thus, the claims are not intended to be limited to the aspects shown herein, but is to be accorded the full scope consistent with the language claims, where reference to an element in the singular is not intended to mean "one and only one" unless specifically so stated, but rather "one or more." Unless specifically stated otherwise, the term "some" refers to one or more. Pronouns in the masculine (e.g., his) include the feminine and neuter gender (e.g., her and its) and vice versa. Headings and subheadings, if any, are used for convenience only and do not limit the subject technology.
A phrase, for example, an "aspect" does not imply that the aspect is essential to the subject technology or that the aspect applies to all configurations of the subject technology. A disclosure relating to an aspect may apply to all configurations, or one or more configurations. A phrase, for example, an aspect may refer to one or more aspects and vice versa. A phrase, for example, a "configuration" does not imply that such configuration is essential to the subject technology or that such configuration applies to all configurations of the subject technology. A disclosure relating to a configuration may apply to all configurations, or one or more configurations. A phrase, for example, a configuration may refer to one or more configurations and vice versa.
The various embodiments described above are provided by way of illustration only and should not be construed to limit the scope of the disclosure. Those skilled in the art will readily recognize various modifications and changes that may be made to the principles described herein without following the example embodiments and applications illustrated and described herein, and without departing from the spirit and scope of the disclosure.
While this specification contains many specific implementation details, these should not be construed as limitations on the scope of any invention or of what may be claimed, but rather as descriptions of features that may be specific to particular embodiments of particular inventions. Certain features that are described in this specification in the context of separate embodiments can also be implemented in combination in a single embodiment. Conversely, various features that are described in the context of a single embodiment can also be implemented in multiple embodiments separately or in any suitable subcombination. Moreover, although features may be described above as acting in certain combinations and even initially claimed as such, one or more features from a claimed combination can in some
cases be excised from the combination, and the claimed combination may be directed to a subcombination or variation of a subcombination.
Similarly, while operations are depicted in the drawings in a particular order, this should not be understood as requiring that such operations be performed in the particular order shown or in sequential order, or that all illustrated operations be performed, to achieve desirable results. In certain circumstances, multitasking and parallel processing may be advantageous. Moreover, the separation of various system components in the embodiments described above should not be understood as requiring such separation in all embodiments, and it should be understood that the described program components and systems can generally be integrated together in a single software product or packaged into multiple software products.
As noted above, particular embodiments of the subject matter have been described, but other embodiments are within the scope of the following claims. For example, the actions recited in the claims can be performed in a different order and still achieve desirable results. As one example, the processes depicted in the accompanying figures do not necessarily require the particular order shown, or sequential order, to achieve desirable results. In certain implementations, multitasking and parallel processing may be advantageous.
CONCLUSION
A system and method has been shown in the above embodiments for the effective implementation of a system, method and article of manufacture for dynamically load balancing of storage media devices based on a mid-range performance level. While various preferred embodiments have been shown and described, it will be understood that there is no intent to limit the invention by such disclosure, but rather, it is intended to cover all modifications falling within the spirit and scope of the invention, as defined in the appended claims. For example, the present invention should not be limited by software/program, computing environment, or specific computing hardware.
Claims
1. A storage system comprising:
a plurality of storage media devices, each storage media device comprising one or more addressable storage regions, each region assigned a different weight based on at least a fast access rate, a mid-range access rate or a slow access rate, respectively;
a storage controller controlling said plurality of storage media devices, said storage controller:
receives one or more commands from a queue representing a load;
identifies a set of weighted storage regions having said mid-range access rate to target a mid-range performance level that is enough to service said load; and
distributes said load based on said mid-range performance level by utilizing only said set of weighted storage regions having said mid-range access rate thereby targeting said mid- range performance level that is enough to service said load.
2. The storage system of claim 1, wherein said storage media devices are any of, or a combination of, the following: solid-state drive, rotational hard disk drive, hybrid disk drive, or PCI-Express slot disk drive.
3. The storage system of claim 1, wherein said storage media devices are part of a storage area network (SAN).
4. The storage system of claim 1, wherein said storage media devices are part of a network attached storage (NAS) device.
5. The storage system of claim 1, wherein at least one command corresponds to a read request.
6. The storage system of claim 1, wherein at least one command corresponds to a write request.
7. A method as implemented in a storage system comprising a storage system comprising a plurality of storage media devices, each storage media device comprising one or more addressable storage regions, each region assigned a different weight based on at least a fast
access rate, a mid-range access rate or a slow access rate, respectively, a storage controller controlling said plurality of storage media devices, said method comprising:
receiving one or more commands from a queue representing a load;
identifying a set of weighted storage regions having said mid-range access rate to target a mid-range performance level that is enough to service said load; and
distributing said load based on said mid-range performance level by utilizing only said set of weighted storage regions having said mid-range access rate thereby targeting said mid- range performance level that is enough to service said load.
8. The method of claim 7, wherein said storage media devices are any of, or a combination of, the following: solid-state drive, rotational hard disk drive, hybrid disk drive, or PCI- Express slot disk drive.
9. The method of claim 7, wherein said storage media devices are part of a storage area network (SAN).
10. The method of claim 7, wherein said storage media devices are part of a network attached storage (NAS) device.
11. The method of claim 7, wherein at least one command corresponds to a read request.
12. The method of claim 7, wherein at least one command corresponds to a write request.
13. A storage system comprising:
a plurality of storage media devices, each storage media device comprising one or more addressable storage regions, each region assigned a different weight based on at least a fast access rate or a slow access rate, respectively;
a storage controller controlling said plurality of storage media devices, said storage controller:
receives one or more commands from a queue representing a load;
deriving a mid-range access rate that is a function of said fast access rate and said slow access rate, where said mid-range access rate is achieved by alternating said fast access rate and said slow access rate; and
distributes said load based on said mid-range performance level that is enough to service said load.
14. The storage system of claim 13, wherein said storage media devices are any of, or a combination of, the following: solid-state drive, rotational hard disk drive, hybrid disk drive, or PCI-Express slot disk drive.
15. The storage system of claim 13, wherein said storage media devices are part of a storage area network (SAN).
16. The storage system of claim 13, wherein said storage media devices are part of a network attached storage (NAS) device.
17. The storage system of claim 13, wherein at least one command corresponds to a read request.
18. The storage system of claim 13, wherein at least one command corresponds to a write request.
Priority Applications (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201480074951.1A CN105981351B (en) | 2013-12-06 | 2014-12-08 | The system and method for dynamic load balancing storage medium device |
EP14867506.9A EP3078184A4 (en) | 2013-12-06 | 2014-12-08 | System and method for dynamically load balancing storage media devices based on a mid-range performance level |
Applications Claiming Priority (22)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
US14/099,848 US9436404B2 (en) | 2013-12-06 | 2013-12-06 | System and method for dynamically load balancing across storage media devices having fast access rates |
US14/099,846 | 2013-12-06 | ||
US14/099,811 | 2013-12-06 | ||
US14/099,807 | 2013-12-06 | ||
US14/099,820 US20150160891A1 (en) | 2013-12-06 | 2013-12-06 | System and method for dynamically load balancing storage media devices based on a minimum performance level |
US14/099,807 US8954617B1 (en) | 2013-12-06 | 2013-12-06 | System, method and article of manufacture for monitoring, controlling and improving storage media system performance based on data type |
US14/099,723 | 2013-12-06 | ||
US14/099,752 US8984172B1 (en) | 2013-12-06 | 2013-12-06 | System, method and article of manufacture for monitoring, controlling and improving storage media system performance based on storage media device fill percentage |
US14/099,723 US8954614B1 (en) | 2013-12-06 | 2013-12-06 | System, method and article of manufacture for monitoring, controlling and improving storage media system performance based on temperature |
US14/099,767 | 2013-12-06 | ||
US14/099,713 | 2013-12-06 | ||
US14/099,820 | 2013-12-06 | ||
US14/099,845 US10048895B2 (en) | 2013-12-06 | 2013-12-06 | System and method for dynamically load balancing storage media devices based on a mid-range performance level |
US14/099,740 | 2013-12-06 | ||
US14/099,767 US8954616B1 (en) | 2013-12-06 | 2013-12-06 | System, method and article of manufacture for monitoring, controlling and improving storage media system performance based on storage media device write rate |
US14/099,846 US10235096B2 (en) | 2013-12-06 | 2013-12-06 | System and method for dynamically load balancing storage media devices based on an average or discounted average sustained performance level |
US14/099,845 | 2013-12-06 | ||
US14/099,713 US9274722B2 (en) | 2013-12-06 | 2013-12-06 | System, method and article of manufacture for monitoring, controlling and improving storage media system performance |
US14/099,740 US8954615B1 (en) | 2013-12-06 | 2013-12-06 | System, method and article of manufacture for monitoring, controlling and improving storage media system performance based on temperature ranges |
US14/099,848 | 2013-12-06 | ||
US14/099,752 | 2013-12-06 | ||
US14/099,811 US8943243B1 (en) | 2013-12-06 | 2013-12-06 | System, method and article of manufacture for monitoring, controlling and improving storage media system performance based on storage media device read rate |
Publications (1)
Publication Number | Publication Date |
---|---|
WO2015085313A1 true WO2015085313A1 (en) | 2015-06-11 |
Family
ID=53274214
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
PCT/US2014/069143 WO2015085313A1 (en) | 2013-12-06 | 2014-12-08 | System and method for dynamically load balancing storage media devices based on a mid-range performance level |
Country Status (3)
Country | Link |
---|---|
EP (1) | EP3078184A4 (en) |
CN (1) | CN105981351B (en) |
WO (1) | WO2015085313A1 (en) |
Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
EP0834878A2 (en) | 1996-10-04 | 1998-04-08 | Sony Corporation | Method and device for controlling access to a disc storage device |
US6327638B1 (en) | 1998-06-30 | 2001-12-04 | Lsi Logic Corporation | Disk striping method and storage subsystem using same |
US20110231458A1 (en) * | 2010-03-01 | 2011-09-22 | Hitachi, Ltd. | File level hierarchical storage management system, method, and apparatus |
US20110246705A1 (en) * | 2010-04-01 | 2011-10-06 | Mudama Eric D | Method and system for wear leveling in a solid state drive |
US20120079318A1 (en) * | 2010-09-28 | 2012-03-29 | John Colgrove | Adaptive raid for an ssd environment |
US8209515B2 (en) * | 2003-01-21 | 2012-06-26 | Dell Products Lp | Storage systems having differentiated storage pools |
US20120297155A1 (en) * | 2008-07-23 | 2012-11-22 | Hitachi, Ltd. | Storage system and method of executing commands by controller |
US8443153B1 (en) | 2010-01-06 | 2013-05-14 | Netapp, Inc. | Dynamic balancing of performance with block sharing in a storage system |
Family Cites Families (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US9207738B2 (en) * | 2008-02-25 | 2015-12-08 | St-Ericsson Sa | Data processing device with adjustable performance level and method of operating such device |
CN101706805B (en) * | 2009-10-30 | 2011-11-09 | 中国科学院计算技术研究所 | Method and system for storing object |
-
2014
- 2014-12-08 EP EP14867506.9A patent/EP3078184A4/en not_active Withdrawn
- 2014-12-08 CN CN201480074951.1A patent/CN105981351B/en not_active Expired - Fee Related
- 2014-12-08 WO PCT/US2014/069143 patent/WO2015085313A1/en active Application Filing
Patent Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
EP0834878A2 (en) | 1996-10-04 | 1998-04-08 | Sony Corporation | Method and device for controlling access to a disc storage device |
US6327638B1 (en) | 1998-06-30 | 2001-12-04 | Lsi Logic Corporation | Disk striping method and storage subsystem using same |
US8209515B2 (en) * | 2003-01-21 | 2012-06-26 | Dell Products Lp | Storage systems having differentiated storage pools |
US20120297155A1 (en) * | 2008-07-23 | 2012-11-22 | Hitachi, Ltd. | Storage system and method of executing commands by controller |
US8443153B1 (en) | 2010-01-06 | 2013-05-14 | Netapp, Inc. | Dynamic balancing of performance with block sharing in a storage system |
US20110231458A1 (en) * | 2010-03-01 | 2011-09-22 | Hitachi, Ltd. | File level hierarchical storage management system, method, and apparatus |
US20110246705A1 (en) * | 2010-04-01 | 2011-10-06 | Mudama Eric D | Method and system for wear leveling in a solid state drive |
US20120079318A1 (en) * | 2010-09-28 | 2012-03-29 | John Colgrove | Adaptive raid for an ssd environment |
Non-Patent Citations (1)
Title |
---|
See also references of EP3078184A4 |
Also Published As
Publication number | Publication date |
---|---|
EP3078184A4 (en) | 2017-07-26 |
EP3078184A1 (en) | 2016-10-12 |
CN105981351B (en) | 2019-08-02 |
CN105981351A (en) | 2016-09-28 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US10216440B2 (en) | Disk management in distributed storage system including grouping disks into cold and hot data disk rings and reducing a spinning rate of disks storing cold data | |
US10042578B2 (en) | Extent migration in multi-tier storage systems | |
US11334398B2 (en) | Learning-based thermal estimation in multicore architecture | |
US20170083474A1 (en) | Distributed memory controller | |
EP3077909A1 (en) | A system and method for dividing and synchronizing a processing task across multiple processing elements/processors in hardware | |
US9747139B1 (en) | Performance-based multi-mode task dispatching in a multi-processor core system for high temperature avoidance | |
KR20150043102A (en) | Apparatus and method for managing data in hybrid memory | |
CN104424106B (en) | The method and system of the resource of distribution storage device is operated for storage optimization | |
US20170177045A1 (en) | Thermal management apparatus and method using dynamic thermal margin, and semiconductor processor device, non-volatile data storage device and access control method using the same | |
US10048895B2 (en) | System and method for dynamically load balancing storage media devices based on a mid-range performance level | |
US9436404B2 (en) | System and method for dynamically load balancing across storage media devices having fast access rates | |
AU2016243416A1 (en) | Systems and methods for improving quality of service within hybrid storage systems | |
US20200104065A1 (en) | Storage capacity usage management | |
US10942784B2 (en) | Database resource scaling | |
US10120575B2 (en) | Dynamic storage tiering | |
US20170277636A1 (en) | Method and device for controlling memory | |
US10235096B2 (en) | System and method for dynamically load balancing storage media devices based on an average or discounted average sustained performance level | |
US9983908B1 (en) | Adjusting allocation of selected resources for capped and uncapped virtual machines | |
US9274722B2 (en) | System, method and article of manufacture for monitoring, controlling and improving storage media system performance | |
US8954614B1 (en) | System, method and article of manufacture for monitoring, controlling and improving storage media system performance based on temperature | |
US20150160891A1 (en) | System and method for dynamically load balancing storage media devices based on a minimum performance level | |
US10289958B1 (en) | Storage system with machine learning based skew prediction | |
CN105224475B (en) | For the method and apparatus for the distribution for adjusting storage device | |
US10209749B2 (en) | Workload allocation based on downstream thermal impacts | |
EP3078184A1 (en) | System and method for dynamically load balancing storage media devices based on a mid-range performance level |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
121 | Ep: the epo has been informed by wipo that ep was designated in this application |
Ref document number: 14867506 Country of ref document: EP Kind code of ref document: A1 |
|
NENP | Non-entry into the national phase |
Ref country code: DE |
|
REEP | Request for entry into the european phase |
Ref document number: 2014867506 Country of ref document: EP |
|
WWE | Wipo information: entry into national phase |
Ref document number: 2014867506 Country of ref document: EP |