Patent Application
20230030168
The present disclosure relates generally to information handling systems. More particularly, the present disclosure relates to protecting input/output (I/O) paths against network partitioning and component failures in non-volatile memory express over fabric (NVMe-oF) environments.
As the value and use of information continues to increase, individuals and businesses seek additional ways to process and store information. One option available to users is information handling systems. An information handling system generally processes, compiles, stores, and/or communicates information or data for business, personal, or other purposes thereby allowing users to take advantage of the value of the information. Because technology and information handling needs and requirements vary between different users or applications, information handling systems may also vary regarding what information is handled, how the information is handled, how much information is processed, stored, or communicated, and how quickly and efficiently the information may be processed, stored, or communicated. The variations in information handling systems allow for information handling systems to be general or configured for a specific user or specific use, such as financial transaction processing, airline reservations, enterprise data storage, or global communications. In addition, information handling systems may include a variety of hardware and software components that may be configured to process, store, and communicate information and may include one or more computer systems, data storage systems, and networking systems.
A Centralized Discovery Controller (CDC) in an IP SAN operating in a standalone mode, e.g., as a virtual machine (VM) on a hypervisor, may lose connectivity to an NVMe entity, such as a host or subsystem for a number of reasons, including network partitioning and component failures on client, server, or networking infrastructure. Once connectivity is lost, if the CDC were to simply remove the NVMe entity from its name server data base, the CDC would send out asynchronous event notifications (AENs) to all relevant entities in the IP SAN. Each impacted entity would then query the name server for the latest information using a Get Log Page command. Upon receiving a response to the query, so-called “well-behaved” NVMe entities may take note of missing NVMe entities in the Get Log Page response and, acting in accordance with existing NVMe protocols, drop open connections with said entities.
Oftentimes, a loss of the connectivity from a CDC to an NVMe entity caused by a control plane issue, such as loss of a TCP connectivity to a particular IP address, is transient in nature. Therefore, simply removing an NVMe entity from the name server each time connectivity is lost negatively impacts traffic in the I/O path between the host and the subsystem, resulting in unnecessary churn in the network. Under certain circumstances, churn may lead to highly undesirable denial-of-service type scenarios.
In comparison, in FC-based SANs, a loss of connectivity between an end-device and a switch automatically results in an immediate removal from the name server since the name server is distributed and operates on the switch where the end-device is attached. As a result, a loss of connectivity always indicates that the end-device is unreachable and that no connection to it should be attempted.
Today, there exist no solutions for the above-mentioned problem for IP-based fabrics that are used for transporting NVMe traffic. Accordingly, it is highly desirable to find new, more efficient ways for IP-based fabrics to increase bandwidth and network availability by reducing unwanted I/O churn, i.e., oftentimes unintended, temporary loss of open connections that must be dropped.
References will be made to embodiments of the disclosure, examples of which may be illustrated in the accompanying figures. These figures are intended to be illustrative, not limiting. Although the accompanying disclosure is generally described in the context of these embodiments, it should be understood that it is not intended to limit the scope of the disclosure to these particular embodiments. Items in the figures may not be to scale.
In the following description, for purposes of explanation, specific details are set forth in order to provide an understanding of the disclosure. It will be apparent, however, to one skilled in the art that the disclosure can be practiced without these details. Furthermore, one skilled in the art will recognize that embodiments of the present disclosure, described below, may be implemented in a variety of ways, such as a process, an apparatus, a system/device, or a method on a tangible computer-readable medium.
Components, or modules, shown in diagrams are illustrative of exemplary embodiments of the disclosure and are meant to avoid obscuring the disclosure. It shall also be understood that throughout this discussion that components may be described as separate functional units, which may comprise sub-units, but those skilled in the art will recognize that various components, or portions thereof, may be divided into separate components or may be integrated together, including, for example, being in a single system or component. It should be noted that functions or operations discussed herein may be implemented as components. Components may be implemented in software, hardware, or a combination thereof.
Furthermore, connections between components or systems within the figures are not intended to be limited to direct connections. Rather, data between these components may be modified, re-formatted, or otherwise changed by intermediary components. Also, additional or fewer connections may be used. It shall also be noted that the terms “coupled,” “connected,” “communicatively coupled,” “interfacing,” “interface,” or any of their derivatives shall be understood to include direct connections, indirect connections through one or more intermediary devices, and wireless connections. It shall also be noted that any communication, such as a signal, response, reply, acknowledgement, message, query, etc., may comprise one or more exchanges of information.
Reference in the specification to “one or more embodiments,” “preferred embodiment,” “an embodiment,” “embodiments,” or the like means that a particular feature, structure, characteristic, or function described in connection with the embodiment is included in at least one embodiment of the disclosure and may be in more than one embodiment. Also, the appearances of the above-noted phrases in various places in the specification do not necessarily all refer to the same embodiment or embodiments.
The use of certain terms in various places in the specification is for illustration and should not be construed as limiting. The terms “include,” “including,” “comprise,” and “comprising” shall be understood to be open terms, and any examples are provided by way of illustration and shall not be used to limit the scope of this disclosure.
A service, function, or resource is not limited to a single service, function, or resource; usage of these terms may refer to a grouping of related services, functions, or resources, which may be distributed or aggregated. The use of memory, database, information base, data store, tables, hardware, cache, and the like may be used herein to refer to system component or components into which information may be entered or otherwise recorded. The terms “data,” “information,” along with similar terms, may be replaced by other terminologies referring to a group of one or more bits, and may be used interchangeably. The terms “packet” or “frame” shall be understood to mean a group of one or more bits.
In one or more embodiments, a stop condition may include: (1) a set number of iterations that has been performed; (2) an amount of processing time has been reached; (3) convergence (e.g., the difference between consecutive iterations is less than a first threshold value); (4) divergence (e.g., the performance deteriorates); and (5) an acceptable outcome has been reached.
It shall be noted that although embodiments described herein may be within the context of SANs, aspects of the present disclosure are not so limited. Accordingly, the aspects of the present disclosure may be applied or adapted for use in other contexts. The term “administrator” may represent any user, such as a network administrator, storage administrator, or other managing entity. The terms “unreachable” and “offline” may be used interchangeably.
Zone management allows a SAN administrator to define access control rules that control communication between host and subsystem interfaces, e.g., such that a host can discover storage ports that it can access. Zoning typically involves creating zones that comprise zone members and that may overlap, i.e., a member of one zone can be a member of any number of other zones. Zone members are allowed to communicate with each other according to their zone membership. Name server entries are filtered to ensure only entities allowed to communicate are returned. When soft zoning methods are employed, the network does not prevent access, and hosts are not prevented from connecting to any subsystem interface. In contrast, when hard zoning is used as the preferred method of zoning, the network does prevent unauthorized access, such that a host can only connect to specific subsystem interfaces with which the host shares a common zone.
The CDC, is typically configured and maintained by an administrator and contains a database that stores zoning information, which defines any number of zones, zone members for each zone, and access control configurations according to zone membership. An administrator can access the CDC to configure zones, e.g., via a management interface (not shown), such as the management interface of one of storage devices 1 through 4.
Once storage 4 in
Various embodiments herein, allow to maintain connections in data paths, e.g., between a host and a subsystem, where there is no operational problem with the data path itself. Advantageously, this reduces churn and disruption in a network, such as SAN 100.
In detail, in one or more embodiments, once a connection from an NVMe entity, such as a host or subsystem, to a CDC is established via any means, e.g., as defined by an NVMe-oF specification (e.g., TP8010), an action, which may be made the default action, is to retain successfully established connections irrespective of a subsequent loss of connectivity with the CDC. Unlike conventional methods that immediately purge NVMe entities from the SAN as soon as connectivity is lost, one or more embodiments herein operate under the assumption that a detected connectivity loss is temporary, e.g., due to ongoing maintenance or similar reasons, and that the connection will be restored in a reasonable amount of time. Herein, such connections are referred to as “sticky” connections.
In one or more embodiments, once a CDC detects a loss of connectivity to an NVMe entity, e.g., the loss of a TCP connection between the CDC and a host or subsystem, the CDC may mark (e.g., in a name server database) those entries that are not reachable as unreachable, rather than removing them. Further, the CDC may withhold generating an AEN that otherwise would solicit a query from impacted entities, e.g., by using a Get Log Page command. For example, in response to an NVMe entity initiating a Get Log Page, e.g., a host that restarts its operation and asks the CDC to list all storage that the host can connect to, the CDC may return all NVMe entities that have been zoned with the querying NVMe entity, irrespective of the CDCs potentially temporary inability to establish a connection with the NVMe entity at that point in time.
In one or more embodiments, entries in a name server database in the CDC that comprise sticky connections may remain in the name server database until the default action is overridden, e.g., by the occurrence of one or more conditions or events, such as an NVMe entity expressly terminating a service that it no longer wants to provide or consume, or until the CDC interprets a lack of communication by an NVMe entity that lasts a certain period of time as an intent by a host or a subsystem as not wanting to provide or consume a service. Once such a condition is present, or such an event has occurred, the CDC may resume sending out AENs to impacted entities to purge information associated with stale entities from its database. Other non-limiting examples of events or conditions for manually or automatically purging entities comprise the following:
(1) a host or subsystem explicitly disconnecting an NVMe entity, e.g., by deregistering it with a CDC or otherwise communicating a termination request according to a network protocol;
(2) detecting a CDC name server move, e.g., based on link layer discovery protocol, multicast domain name system (mDNS) activity, or media access control learning. When the CDC is operating in standalone mode on a virtual appliance, the detection may be based on mDNS activity or by polling networking management data bases on third party switches;
(3) an NVMe entity being replaced on a same physical switch port, which may be detected, e.g., based on LLDP protocol, mDNS activity, or MAC learning. When the CDC is operating in standalone mode on a virtual appliance, the detection may be based on mDNS activity or by polling networking management data bases on third party switches;
(4) forced removal, e.g., by a user explicitly removing an NVMe entity from the CDC name server database;
(5) deletion from a zone database, e.g., by an administrator deleting an NVMe entity reference from all configured zone databases or making related zoning policy changes; or
(6) deletion based on time out, e.g., by a user specifying a timeout value, such that once a CDC loses a connection with an NVMe entity, the CDC may wait according to a pre-configured time-out value prior to removing an offline entry from the CDC.
In one or more embodiments, once the CDC detects the name server has been moved, replaced, forcibly removed, deleted from a zone database, or has timed out, the CDC may send AENs to impacted entities so that when the name server entities such as zone members query the CDC, the get log page response no longer contains the disconnected entities.
In summary, in one or more embodiments herein, a CDC may use built-in intelligence to determine or estimate whether a connection with an NVMe entity, such as a host or subsystem, has been intentionally discontinued, e.g., by user intervention or by the NVMe entity itself initiating removal from a name server database, or whether a connection loss is rather transient, e.g., due to a temporary network issue. In the former case, the CDC may send out notifications, e.g., in the form of AENs and communicate the change, i.e., the absence of the NVMe entity, in a Get Log Page response. In the latter case, the CDC may maintain the entity in the name server database despite the connection loss, refraining from sending out notifications to relevant (or impacted) entities to reduce I/O churn and, optionally, communicate to NVMe entities information regarding its ability to reach an entity in its name server (e.g., via a Get Log Page request), such that the impacted NVMe entities may take appropriate action depending on their particular implementation.
Returning to
In one or more embodiments, the CDC may, e.g., as a default action, generate a sticky entry, or mark an entry as a sticky entry, e.g., according to a policy that may be implemented in an existing protocol (e.g., as a protocol extension), or it may be included in protocols developed in the future. The CDC may use an “unreachability” bit, “unreachable from CDC” bit, or similar, to flag in a database that storage 4 is unreachable or offline and not send out an AEN. In one or more embodiments, the CDC in
In one or more embodiments, the CDC may then send an AEN to host A to cause host A to issue a Get Log Page command and, in response to receiving the Get Log Page command, the CDC may return a log page response that comprises the name server entry “unreachable” for storage 4.
In addition, once the CDC indicates that storage 4 is not reachable, host A may react in various ways. For example, if host A's connection with storage 4 is still operational, host A, having received the name server entry for storage 4, advantageously, may continue to perform I/O operations with storage 4 using the existing connection rather than dropping it and causing I/O churn. In short, absent an indication that any of the subsystems, here, storage 1, 2, and 4 intended to disconnect, the CDC may communicate to host A that host A may continue to detect and directly communicate with storage 1, 2, and 4, even if the CDC is unable to reach storage 4, in effect, assuming that the data path between host A and storage 4 is intact and operational and that the loss of connection is temporary.
It is noted that although an unreachability bit may be purely informational in that it does not carry any expectations on how a notified NVMe entity should act, in one or more embodiments, the information, e.g., in connection with information provided by a host (or a subsystem acting as a host), may be used as a debugging tool, e.g., to narrow down a particular NVMe entity and/or its data paths as the most likely source(s) of a detected CDC connectivity failure. In addition, a sticky entry or other notification by the CDC may comprise information that may be used to directly communicate the content of what has changed in the database, e.g., which NVMe entity has lost communication or went offline. In one or more embodiments, entries may be purged, e.g., by unflagging, removing, or changing a bit in the database, e.g., by a networking component that is different from the CDC and according to a policy, configuration setting, as part of a maintenance procedure.
In addition, as discussed next, the introduction of an unreachability entry in a log page, advantageously, enables a host to distinguish between a CDC connectivity failure and an administrative access control action.
In one or more embodiments, the CDC in
It is noted that, just like entries indicating unreachability, the lack of an entry for storage 4 may be merely informational. In one or more embodiments, a flag in a host registration may be used to indicate to the CDC how the host reacts to administrative access control actions. As a person of skill in the art will appreciate, if an administrator wishes to ensure that a host disconnects from a subsystem (or vice versa) to cease I/O operations, e.g., upon detecting an administrative access control action, hard zoning methods may be implemented to enforce the desired behavior, e.g., to prevent unauthorized access.
In one or more embodiments, the CDC in
It shall be noted that: (1) certain steps herein may optionally be performed; (2) steps may not be limited to the specific order set forth herein; (3) certain steps may be performed in different orders; and (4) certain steps may be done concurrently.
In one or more embodiments, in response to the CDC determining a purging condition for the NVMe entity and the NVMe entity being removed from a database, an AEN may be received (810) from the CDC.
In one or more embodiments, a query may be sent (815) to the CDC. And a query response that does not contain the NVMe entity may be received (820).
Finally, the connection with the NVMe entity may be terminated (825).
In one or more embodiments, aspects of the present patent document may be directed to, may include, or may be implemented on one or more information handling systems (or computing systems). An information handling system/computing system may include any instrumentality or aggregate of instrumentalities operable to compute, calculate, determine, classify, process, transmit, receive, retrieve, originate, route, switch, store, display, communicate, manifest, detect, record, reproduce, handle, or utilize any form of information, intelligence, or data. For example, a computing system may be or may include a personal computer (e.g., laptop), tablet computer, mobile device (e.g., personal digital assistant (PDA), smart phone, phablet, tablet, etc.), smart watch, server (e.g., blade server or rack server), a network storage device, camera, or any other suitable device and may vary in size, shape, performance, functionality, and price. The computing system may include random access memory (RAM), one or more processing resources such as a central processing unit (CPU) or hardware or software control logic, read only memory (ROM), and/or other types of memory. Additional components of the computing system may include one or more drives (e.g., hard disk drives, solid state drive, or both), one or more network ports for communicating with external devices as well as various input and output (I/O) devices, such as a keyboard, mouse, stylus, touchscreen, and/or video display. The computing system may also include one or more buses operable to transmit communications between various hardware components.
As illustrated in
A number of controllers and peripheral devices may also be provided, as shown in
In the illustrated system, all major system components may connect to a bus 916, which may represent more than one physical bus. However, various system components may or may not be in physical proximity to one another. For example, input data and/or output data may be remotely transmitted from one physical location to another. In addition, programs that implement various aspects of the disclosure may be accessed from a remote location (e.g., a server) over a network. Such data and/or programs may be conveyed through any of a variety of machine-readable medium including, for example: magnetic media such as hard disks, floppy disks, and magnetic tape; optical media such as compact discs (CDs) and holographic devices; magneto-optical media; and hardware devices that are specially configured to store or to store and execute program code, such as application specific integrated circuits (ASICs), programmable logic devices (PLDs), flash memory devices, other non-volatile memory (NVM) devices (such as 3D XPoint-based devices), and ROM and RAM devices.
The information handling system 1000 may include a plurality of I/O ports 1005, a network processing unit (NPU) 1015, one or more tables 1020, and a CPU 1025. The system includes a power supply (not shown) and may also include other components, which are not shown for sake of simplicity.
In one or more embodiments, the I/O ports 1005 may be connected via one or more cables to one or more other network devices or clients. The network processing unit 1015 may use information included in the network data received at the node 1000, as well as information stored in the tables 1020, to identify a next device for the network data, among other possible activities. In one or more embodiments, a switching fabric may then schedule the network data for propagation through the node to an egress port for transmission to the next destination.
Aspects of the present disclosure may be encoded upon one or more non-transitory computer-readable media with instructions for one or more processors or processing units to cause steps to be performed. It shall be noted that the one or more non-transitory computer-readable media shall include volatile and/or non-volatile memory. It shall be noted that alternative implementations are possible, including a hardware implementation or a software/hardware implementation. Hardware-implemented functions may be realized using ASIC(s), programmable arrays, digital signal processing circuitry, or the like. Accordingly, the “means” terms in any claims are intended to cover both software and hardware implementations. Similarly, the term “computer-readable medium or media” as used herein includes software and/or hardware having a program of instructions embodied thereon, or a combination thereof. With these implementation alternatives in mind, it is to be understood that the figures and accompanying description provide the functional information one skilled in the art would require to write program code (i.e., software) and/or to fabricate circuits (i.e., hardware) to perform the processing required.
It shall be noted that embodiments of the present disclosure may further relate to computer products with a non-transitory, tangible computer-readable medium that have computer code thereon for performing various computer-implemented operations. The media and computer code may be those specially designed and constructed for the purposes of the present disclosure, or they may be of the kind known or available to those having skill in the relevant arts. Examples of tangible computer-readable media include, for example: magnetic media such as hard disks, floppy disks, and magnetic tape; optical media such as CDs and holographic devices; magneto-optical media; and hardware devices that are specially configured to store or to store and execute program code, such as ASICs, PLDs, flash memory devices, other NVM devices (such as 3D XPoint-based devices), and ROM and RAM devices. Examples of computer code include machine code, such as produced by a compiler, and files containing higher level code that are executed by a computer using an interpreter. Embodiments of the present disclosure may be implemented in whole or in part as machine-executable instructions that may be in program modules that are executed by a processing device. Examples of program modules include libraries, programs, routines, objects, components, and data structures. In distributed computing environments, program modules may be physically located in settings that are local, remote, or both.
One skilled in the art will recognize no computing system or programming language is critical to the practice of the present disclosure. One skilled in the art will also recognize that a number of the elements described above may be physically and/or functionally separated into modules and/or sub-modules or combined together.
It will be appreciated to those skilled in the art that the preceding examples and embodiments are exemplary and not limiting to the scope of the present disclosure. It is intended that all permutations, enhancements, equivalents, combinations, and improvements thereto that are apparent to those skilled in the art upon a reading of the specification and a study of the drawings are included within the true spirit and scope of the present disclosure. It shall also be noted that elements of any claims may be arranged differently including having multiple dependencies, configurations, and combinations.
