This disclosure is generally related to networks, including network I/O (Input/Output) devices, and more particularly to a operating of one or more network cards providing I/O.
A network card refers to an electronic device that connects a computing system to a network. MR-IOV (Multi-Root I/O Virtualization) refers to a technology that enables network devices to be shared by computing systems and operating systems of computing systems. In a current MR-IOV network system, data packets directed to a network card are dropped if a throughput of that network card of the corresponding computing system(s) exceeds a pre-determined threshold. The dropping of data packets may render data incomplete or unusable or unreliable in the current MR-IOV network system due to loss of the dropped data packets.
A method is provided for operating one or more network cards connected to one or more computing systems and connected to one or more networks. The method comprises: detecting resource utilization of all network cards of computing systems connected via the one or more networks; monitoring network statistics of the network, the monitoring the network statistics including: evaluating whether a resource utilization of each network card connected to the one more networks is larger than a threshold; and determining an operation of each network card connected to the network according to and the detected resource utilization and the monitored network statistics.
These and other objects, features and advantages of the present invention will become apparent from the following detailed description of illustrative embodiments thereof, which is to be read in connection with the accompanying drawings, in which:
This disclosure describes that a scalable mechanism in a network system in which packets are received from an external network(s) via one or more network switches with destination addresses set to the IP (Internet Protocol) addresses of network cards that have been suspended, e.g., by using network address aliasing. The network address aliasing enables one or more active network cards to receive those packets directed to the suspended network card.
Each computing system enables a network card to handle data flow transparently through impersonalization, i.e., de-activating one or more network cards whose resource utilization is lower than a threshold. The computing system(s) that are connected to each other via one or more networks disconnect idle network cards because there exists not enough data throughput (e.g., data throughput lower than the threshold, etc.) in the idle network cards.
Before entering the sleep mode, the idle network cards (also called network card to be de-activated) delegate tasks (e.g., receiving data packet(s) from an external network, etc.). The delegation of the tasks includes, but is not limited to: (1) delegating of network addresses of the de-activated network cards to active network cards (i.e., creating of network address alias of network address of the de-activated network cards and enabling one or more active network cards to use the created network address alias when sending or receiving data packets); and (2) updating network addresses of the active network cards in order for the network addresses of the active network cards to include the delegated network addresses of the de-activated network cards.
A network connection and configuration, e.g., network connection and configuration 500 shown in
In one embodiment, no data packet is dropped in the network 500 because data packets to be processed by the network card whose resource utilization is larger than the threshold are processed by the activated network cards.
The network configuration 500 operates as shown in method steps of
At 1230, when an active network card receives a stand-by notification from a next network card along with the IP address that the next network card was using, the former active network card creates a network address alias. In order to create the network address alias, the active network card associates the active network card with one or more network addresses, i.e., IP address(es) currently used by the active network card and the IP address of the next network card, e.g., by using a table that maps the network card(s) to corresponding IP addresses. The created network address alias enables the active network card to respond and to use the one or more network addresses. After creating the network address alias, the active network card informs the network that its MAC address will also be responding for the next network card's IP address. The stand-by notification refers to a notification sent from an idle network card to inform other network cards that the idle network card no longer process data packets and the idle network card stops its operation. Upon sending the stand-by notification, the idle network card suspends all the operation(s) performed by the idle network card.
At 1240, a first network card that uses more than one IP address when entering in the stand-by mode informs an active network of all IP addresses that the first network card is using. At 1250, to handle changes caused by network cards which become idle or active, a master network card integrates a translation table that indicates network routes of returning packets to a correct computing system(s).
The translation table is updated whenever a list of IP addresses of a de-activated network card are included in a list of IP addresses of a currently active network card. The translation table keeps track of all network connections between computing systems and currently active network cards. The translation table 1000 shown in
When a data packet is sent to a network by a network card, a virtual switch of that network card masks this data packet, e.g., by mask bits, and sends only the header information to the primary network card. The primary network card determines, based on the translation table, which network card(s) is connected or installed to a destination computing system(s). In an event of a first active network card being de-activated, a second active network card receives the packets sent to the first active network card. The primary network card monitors the control bus waiting for IP delegation messages and updates the table to route the incoming packets to the correct physical machine. IP delegation messages refer to messages that include network addresses of de-activated network cards and to request one or more currently active network cards to include the network addresses of the de-activated network card in the IP address list of the one or more currently active network card.
When an additional network card is activated on a network by receiving a “RESUME” signal over the control bus, the activated additional network card proceeds with two actions: (1) record its IP (Internet Protocol) address that the additional network card uses in an IP list 910 that lists IP addresses that the additional network card uses; (2) send an ARP (Address Resolution Protocol) messages that include MAC address and IP address of the additional network card. This ARP message announces to network switches and all other devices connected to the network, e.g., the network 900 shown in
The second master network card 625 is a backup network card which perform the tasks, e.g., managing the translation table 905. The second master network card 625 operate when the primary network card loses electric power or when the throughput of the primary secondary network card is higher than a threshold. Other network cards become de-activated (i.e., suspended) or activated (i.e., resumed) via a signal received from computing system(s) through a control bus 615. The network cards process and transfer the data packets to one or more external network(s) or one or more computing system(s). A virtual switch 640 transmits data packets to network cards from the one or more external network(s) or one or more computing system(s) or peripherals. Each network card may also store a list of IP addresses that are used by the each network address.
Primary network card(s) may determine a destination of each data packet, e.g., based on header information of the each data packet. Primary network card(s) sends a data packet, which is directed to the network card whose resource utilization is larger than a threshold, to the one or more activated network cards. The activated network cards share a network address of the network card whose resource utilization is larger than the threshold.
When a first network card receives a “SUSPEND” signal, the first network card stops responding for the packets destined to IP addresses listed in its IP list. At this point, the first network card proceed with a following single action: send over the control bus a message to a currently active network card the IP addresses of the first network card. Then, the currently active network card proceed with two actions: (1) add a network address of the first network card to the IP List of the currently active network card; and (2) create a network address alias of the first network card and sending an ARP message (i.e., a message by using Address Resolution Protocol (ARP)) to inform devices connected to the network that the currently active network card responds to the IP address of the first network card. The currently active network card continue to respond to its IP addresses that have been listed in its IP address list.
When the currently active network card receives a “SUSPEND” signal, the currently active network card (“second network card”) stops responding for the packets destined to its (a) IP addresses listed in its IP address list and to (b) IP address of the first network card. At this point, the second network card proceeds with a following action: send over the control bus a message to another currently active network card. The message includes all the IP addresses the second network card is responsible for. The another currently active network card proceeds with two actions: (1) add the IP address of the first network card and the IP addresses listed in its IP address list of the second network card to the IP list of the another currently active network card; and (2) create network address aliases of network addresses listed in the IP list of the second network card and inform that the another currently active network card is responding for the IP addresses of the first network card and the IP addresses of the second network card. The another active network card continuously responds to the IP addresses listed in its IP address list. This delegation of network cards can continue until only the primary master and secondary master NIC's are activated and currently active network cards process data packets directed to the IP addresses of all the de-activated network cards.
In another embodiment shown in
ARP messages may be static or dynamic, but except for network core infrastructure (backbone, a series of switches, etc.). ARP messages may include dynamic entries with pre-set timeout for the entries. For example, one or more entries in the ARP message may disappear after a particular time-out. In one embodiment, ARP messages entries may be manipulated, e.g., by modifying data of ARP messages through a wireless communication. In one embodiment, packet collisions (i.e., colliding of data packets due to a high rate of data packets being created or transferred) may be avoided, e.g., by preventing network cards to be suspended and to be activated too quickly, e.g., less than 10 seconds after the suspension, in case that a network resource utilization suffers from severe peaks. For example, the computing system(s) keep track of timestamps of the moments a network card is activated and may not suspend that network card in less than a given time from the activation. By delaying the activation of the suspended network card, the computing system(s) may delay responding e.g., by taking more than 10 seconds from the suspension of a network card to the activation of that network card, to a network resource utilization peak and therefore may obviate overloading the network switches with ARP messages and/or data packets. In another embodiment, the computing system(s) may respond, within less than a particular time period, to a network utilization peak and may prevent overloading the network switches with ARP messages.
In one embodiment, the methods shown in
The present invention may be a system, a method, and/or a computer program product. The computer program product may include a computer readable storage medium (or media) having computer readable program instructions thereon for causing a processor to carry out aspects of the present invention.
The computer readable storage medium can be a tangible device that can retain and store instructions for use by a device that runs an instruction. The computer readable storage medium may be, for example, but is not limited to, an electronic storage device, a magnetic storage device, an optical storage device, an electromagnetic storage device, a semiconductor storage device, or any suitable combination of the foregoing. A non-exhaustive list of more specific examples of the computer readable storage medium includes the following: a portable computer diskette, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or Flash memory), a static random access memory (SRAM), a portable compact disc read-only memory (CD-ROM), a digital versatile disk (DVD), a memory stick, a floppy disk, a mechanically encoded device such as punch-cards or raised structures in a groove having instructions recorded thereon, and any suitable combination of the foregoing. A computer readable storage medium, as used herein, is not to be construed as being transitory signals per se, such as radio waves or other freely propagating electromagnetic waves, electromagnetic waves propagating through a waveguide or other transmission media (e.g., light pulses passing through a fiber-optic cable), or electrical signals transmitted through a wire.
Computer readable program instructions described herein can be downloaded to respective computing/processing devices from a computer readable storage medium or to an external computer or external storage device via a network, for example, the Internet, a local area network, a wide area network and/or a wireless network. The network may comprise copper transmission cables, optical transmission fibers, wireless transmission, routers, firewalls, switches, gateway computers and/or edge servers. A network adapter card or network interface in each computing/processing device receives computer readable program instructions from the network and forwards the computer readable program instructions for storage in a computer readable storage medium within the respective computing/processing device.
Computer readable program instructions for carrying out operations of the present invention may be assembler instructions, instruction-set-architecture (ISA) instructions, machine instructions, machine dependent instructions, microcode, firmware instructions, state-setting data, or either source code or object code written in any combination of one or more programming languages, including an object oriented programming language such as Java, Smalltalk, C++ or the like, and conventional procedural programming languages, such as the “C” programming language or similar programming languages. The computer readable program instructions may run entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the latter scenario, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or the connection may be made to an external computer (for example, through the Internet using an Internet Service Provider). In some embodiments, electronic circuitry including, for example, programmable logic circuitry, field-programmable gate arrays (FPGA), or programmable logic arrays (PLA) may run the computer readable program instructions by utilizing state information of the computer readable program instructions to personalize the electronic circuitry, in order to perform aspects of the present invention.
Aspects of the present invention are described herein with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and/or block diagrams, and combinations of blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer readable program instructions.
These computer readable program instructions may be provided to a processor of a general purpose computer, special purpose computer, or other programmable data processing apparatus to produce a machine, such that the instructions, which run via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions/acts specified in the flowchart and/or block diagram block or blocks. These computer readable program instructions may also be stored in a computer readable storage medium that can direct a computer, a programmable data processing apparatus, and/or other devices to function in a particular manner, such that the computer readable storage medium having instructions stored therein comprises an article of manufacture including instructions which implement aspects of the function/act specified in the flowchart and/or block diagram block or blocks.
The computer readable program instructions may also be loaded onto a computer, other programmable data processing apparatus, or other device to cause a series of operational steps to be performed on the computer, other programmable apparatus or other device to produce a computer implemented process, such that the instructions which run on the computer, other programmable apparatus, or other device implement the functions/acts specified in the flowchart and/or block diagram block or blocks.
The flowchart and block diagrams in the Figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of the present invention. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of instructions, which comprises one or more executable instructions for implementing the specified logical function(s). In some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be run substantially concurrently, or the blocks may sometimes be run in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems that perform the specified functions or acts or carry out combinations of special purpose hardware and computer instructions.
This application is a continuation of U.S. patent application Ser. No. 14/247,910, filed Apr. 8, 2014, the entire content and disclosure of which is incorporated herein by reference.
Number | Name | Date | Kind |
---|---|---|---|
6134678 | Mahalingam et al. | Oct 2000 | A |
6314525 | Mahalingham et al. | Nov 2001 | B1 |
6490632 | Vepa | Dec 2002 | B1 |
6512774 | Vepa et al. | Jan 2003 | B1 |
6567377 | Vepa | May 2003 | B1 |
6625169 | Tofano | Sep 2003 | B1 |
6795933 | Wachel | Sep 2004 | B2 |
7159034 | Rai | Jan 2007 | B1 |
7266079 | Fan | Sep 2007 | B2 |
7463595 | Singhal et al. | Dec 2008 | B1 |
7693045 | McGee et al. | Apr 2010 | B2 |
7783784 | Droux et al. | Aug 2010 | B1 |
7788411 | Belgaied et al. | Aug 2010 | B2 |
7830882 | Johnson | Nov 2010 | B2 |
7899848 | Yin et al. | Mar 2011 | B2 |
7907528 | Liu et al. | Mar 2011 | B2 |
7934033 | Malwankar et al. | Apr 2011 | B2 |
7995465 | Abdulla et al. | Aug 2011 | B2 |
8027354 | Portolani | Sep 2011 | B1 |
8265075 | Pandey | Sep 2012 | B2 |
8271604 | Freimuth et al. | Sep 2012 | B2 |
8321616 | Lambert | Nov 2012 | B2 |
8364874 | Schlansker | Jan 2013 | B1 |
8369212 | Howard et al. | Feb 2013 | B2 |
8386762 | Lee | Feb 2013 | B2 |
8412860 | Kishore et al. | Apr 2013 | B2 |
8503468 | Akyol | Aug 2013 | B2 |
8644326 | Naven | Feb 2014 | B2 |
8677023 | Venkataraghavan et al. | Mar 2014 | B2 |
8798067 | Morris | Aug 2014 | B2 |
8817817 | Koenen et al. | Aug 2014 | B2 |
9026640 | Loboz et al. | May 2015 | B2 |
9083611 | Khare et al. | Jul 2015 | B2 |
9083811 | Sharma et al. | Jul 2015 | B2 |
9170976 | Folco et al. | Oct 2015 | B2 |
9178815 | Gasparakis | Nov 2015 | B2 |
9280504 | Ben-Michael | Mar 2016 | B2 |
9419905 | Ara jo | Aug 2016 | B2 |
20060029097 | McGee | Feb 2006 | A1 |
20060227703 | Hung et al. | Oct 2006 | A1 |
20080002714 | Belgaied et al. | Jan 2008 | A1 |
20080304519 | Koenen et al. | Dec 2008 | A1 |
20090276773 | Brown et al. | Nov 2009 | A1 |
20090300209 | Elzur | Dec 2009 | A1 |
20100082874 | Baba et al. | Apr 2010 | A1 |
20100115174 | Akyol et al. | May 2010 | A1 |
20100232443 | Pandey | Sep 2010 | A1 |
20110029695 | Kishore et al. | Feb 2011 | A1 |
20110055433 | Kishore et al. | Mar 2011 | A1 |
20110119423 | Kishore et al. | May 2011 | A1 |
20120096211 | Davis et al. | Apr 2012 | A1 |
20120166690 | Regula | Jun 2012 | A1 |
20130138836 | Cohen et al. | May 2013 | A1 |
20130151685 | Bursell | Jun 2013 | A1 |
20130151750 | Kanigicherla et al. | Jun 2013 | A1 |
20130212440 | Rom et al. | Aug 2013 | A1 |
20140189173 | Folco et al. | Jul 2014 | A1 |
20150029848 | Jain | Jan 2015 | A1 |
20150156124 | Tsuji | Jun 2015 | A1 |
Number | Date | Country |
---|---|---|
101350818 | Jan 2009 | CN |
101383732 | Mar 2009 | CN |
101765176 | Jun 2010 | CN |
2010039729 | Feb 2010 | JP |
Entry |
---|
List of IBM Patents or Patent Applications Treated As Related dated Mar. 8, 2016, 2 pages. |
Office Action dated Jun. 17, 2016, received in parent U.S. Appl. No. 14/247,910, 15 pages. |
Office Action dated Dec. 4, 2015, received in a related U.S. Appl. No. 14/247,910. |
“Junos OS Ethernet Interfaces Configuation Guide”, Published Feb. 12, 2013, Juniper Networks, Inc. |
“Cisco IOS IP Addressing Services Command Reference”, Cisco Systems, Inc., 2013. |
Krause et al., “I/O Virtualization and Sharing”, 2007 PCI-SIG Technology seminar Feb. 26, 2007, http://www.pcisig.com/events/february—seminar; pp. 1-53. |
PCT International Search Report (PCT/ISA/210) dated Apr. 3, 2014, PCT Notification of Transmittal of the International Search Report and the Written Opinion of the International Searching Authority or the Declaration (PCT/ISA/220), and the PCT Written Opinion of the International Searching Authority (PCT/ISA/237), International Application No. PCT/CN2014/070008, 11 pages. |
“PC/1520 Implementation Guide”, Texas Instruments, Application Report, SCPA033, Section 6.3, http://www.ti.com/lit/an/scpa033/scpa033.pdf, Oct. 2002, p. 8. |
Sabhanatarajan, K., et al., “Smart-NICs: Power Proxying for Reduced Power Consumption in Network Edge Devices”, Symposium on VLSI, 2008 (ISVLSI'08), IEEE, Apr. 7-9, 2008, 6 pages. |
Sohan, R., et al., “Characterizing 10 Gbps Network Interface Energy Consumption”, University of Cambridge, Technical Report No. 784, http://www.cl.cam.ac.uk/˜acr31/pubs/sohan-10gbpower.pdf, Jul. 2010, 10 pages. |
Suzuki, J., et al., “Multi-root Share of Single-Root I/O Virtualization (SR-IOV) Compliant PCI Express Device”, 2010 IEEE 18th Annual Symposium on High Performance Interconnects (HOTI), Mountain View, California, Aug. 18-20, 2010, pp. 25-31, Abstract only, 1 page. |
Notice of Allowance dated Jan. 5, 2017 received in parent U.S. Appl. No. 14/247,910, 9 pages. |
Number | Date | Country | |
---|---|---|---|
20150288588 A1 | Oct 2015 | US |
Number | Date | Country | |
---|---|---|---|
Parent | 14247910 | Apr 2014 | US |
Child | 14486438 | US |