DETAILED ACTION
Notice of Pre-AIA or AIA Status
The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA .
Response to Arguments
Applicants’ arguments with respect to claim(s) 1-17 have been considered but are not persuasive.
Argument 1: (Summary of pages 6)
Applicant argues …Froese (US 2022/0166705) in view of Maier (US 2016/0021032), with Marripudi (US 2019/0294513), Ronen (US 2022/0407796), and Tucker (US 2004/0001487) added for certain dependent claims. Notably, the Office has withdrawn its prior § 102 rejections based on Froese alone and no longer relies on the inherency theory previously advanced. For the reasons that follow, Applicant respectfully submits that the new Froese-in-view-of-Maier combination fails to establish a prima facie case of obviousness. Maier does not disclose the claim limitations for which it is cited. Further, the proposed motivation to combine Maier's teachings with Froese lacks the articulated rational underpinning required under KSR Int'l Co. V. Teleflex Inc., 550 U.S. 398 (2007). Because the Marripudi, Ronen, and Tucker references are cited only for particular dependent-claim features and do not remedy the deficiencies of the Froese-Maier combination, the rejections of the dependent claims likewise cannot stand.
Response:
Examiner respectfully disagrees.
In particular, applicant’s claim amendment submitted with the request for continued examination (RCE) on 02/02/2026 require a disclosure where “each switch is assigned to only one set within its VRG”. This amendment further narrowed the claim, necessitating the use of the Maier prior art to disclosure that feature in an obviousness rejection, instead of the prior anticipatory rejection as noted by applicant.
Applicant also argued that “Maier combination fails to establish a prima facie case of obviousness. Maier does not disclose the claim limitations for which it is cited. Further, the proposed motivation to combine Maier's teachings with Froese lacks the articulated rational underpinning required under KSR Int'l Co. V. Teleflex Inc., 550 U.S. 398 (2007)”. However, applicant have not presented any supporting argument to this statement at this time, therefore, no further response is provided.
Argument 2: (Summary of page 7)
Rejection under 35 USC § 103
I. Maier is a Virtual-Switch Reference; the Present Claims Recite a Physical Fabric of
Hardware Switches
The Office Action maps the claim term "switch" onto Maier's "virtual switches" (VSW1, VSW2, VSW3), the claim term "VRG" onto Maier's "virtual system router" (SR1), and the claim term "set" onto Maier's "virtual routers" (VR1 and VR2). This mapping is inconsistent with the broadest reasonable interpretation of the claim terms in light of the specification.
See MPEP § 2111. Maier's own classification confirms it is directed to virtual switches. The Office's Notice of References Cited classifies Maier at CPC subgroup H04L 49/70, which the CPC scheme defines as "Virtual switches." This classification is distinct from the CPC subgroups directed to physical switch fabrics. The present application, by contrast, describes and claims a physical fabric of hardware switches. Paragraph 19 of the specification states:
Response:
Examiner respectfully disagrees.
In particular, the claims of the invention recite in part “a plurality of interconnected virtual routing groups (VRGs)…where each VRG includes a plurality of interconnected switches”. As currently claimed, there is no clear distinction that the switches in the Virtual Routing Groups are physical switches and precludes any grouping of virtual switches. Therefore, consistent with the broadest reasonable interpretation of the claims as currently recited, the virtual switches of Maier are correctly mapped to the switches of the invention and functionally equivalent to the switches of the invention. Furthermore, consistent with applicant’s written disclosure and argument, Maier [0006] discloses that ‘the switches may include physical switches and logical switches such as hypervisor switches”. In [0123] Maier further discloses that during step 214, the controller may generate the paths identified during step 210. The controller may communicate with physical and hypervisor switches in generating the identified paths. For example, the controller may provide flow table entries that direct the physical and hypervisor switches to forward and modify network packets matching the flow table entries along the desired network paths. Therefore, while the switches claimed are currently mapped to Maier virtual switches, Maier disclosure of physical switches that are functionally equivalent and consistent with applicant’s disclosure.
Argument 3: (Summary of pages 9 and 10)
II. Maier Does Not Disclose the Recited Local-Link Ingress Assignment
Independent claim 1 recites, in relevant part:
"wherein the switches include terminal links to compute nodes, local links to
other switches in the same VRG, and global links to switches in other VRGs;
and wherein each of its local links is assigned to either ingress traffic from
terminal links or ingress traffic from global links."
The claim recites three link types with distinct functions and defines them by their
endpoints: terminal links connect switches to compute nodes; local links connect
switches to other switches in the same VRG; and global links connect switches to switches
in other VRGs. The disputed limitation classifies each local link, the intra-VRG switch-to-
switch links, by the source from which its ingress traffic originated (terminal or global).
The Office Action cites Maier 1 0070 as teaching this limitation:
"virtual switch VSW1 may be assigned end host EH3, which establishes a local
ingress link between VSW1 and a terminal/end host EH3. Virtual switch VSW2
may be assigned end hosts EH1 and EH6, and similarly establish local ingress
links between VSW2 and the respective end hosts (EH1 and EH6)."
This passage describes which end hosts (EH1 through EH6) attach to which virtual switches (VSW1, VSW2, VSW3). In the vocabulary of the present application, Maier 1 0070 describes terminal links; the attachments between end hosts and switches. The passage does not describe the classification of any switch-to-switch (local) link by the source of its ingress traffic. The passage does not describe local links at all.
Response:
Examiner respectfully, disagrees.
The network topology claimed by the applicant is a dragonfly network topology which is fully disclosed in [0025 of the primary reference Froese et al. (US 2022/0166705 A1) a Dragonfly network topology is subdivided into groups, with each group containing some number of switches and some number of endpoints. Each switch is an ASIC with many interconnected ports. The ports of each switch are divided between edge ports, local ports, and global ports, Edge ports are where traffic enters and leaves the network. For example, the ports connected to processing nodes are edge ports. Local ports connect to other switches within the same group. Global ports connect to other switches that are in a different group. In a fault-free Dragonfly network, every group is connected to every other group in the network by one or more global links and every switch within a group is connected to every other switch in the same group by one or more local links. Based on Froese’s’ disclosure, the links connecting to the edge ports, local links and global links correspond to the terminal links, local links and the global links, respectively, of applicant’s invention. In the above disclosure, Forese also discloses Edge ports are where traffic enters and leaves the network which corresponds to ingress traffic from terminal or ingress traffic from global links. However, Froese did not explicitly disclose “each switch is assigned to only one set within its VRG”. Fig. 8, of Maier more explicitly disclose “each switch is assigned to only one set within its VRG”. Maier, in [0070] as illustrated in fig. 8, after grouping the switches in the Virtual Routing group (VR1) into two smaller sets (VSW1 and VSW2), virtual switch VSW1 may be assigned end host EH3, which establishes a local ingress link between VSW1 and a terminal/ end host EH3. Virtual switch VSW2 may be assigned end hosts EH1 and EH6 and similarly establish local ingress links between VSW2 and the respective end hosts (EH1 and EH6). Furthermore, virtual switch VSW3 may be assigned end hosts EH2, EH4, and EH5. Similarly local ingress links between VSW3 are established to the respective end hosts (EH2, EH4 and EH5). Therefore, the combination of Froese and Maier disclose all of the limitations of the independent claims.
Argument 4: (Summary of pages 10 and 11)
III. The Proposed Motivation to Combine is Conclusory and Lacks the Required
Articulated Reasoning
Even setting aside the missing-element issues in Sections I and II, the Office Action's
proposed motivation to combine Maier with Froese does not satisfy the standard articulated in KSR and its progeny. The stated motivation, in its entirety, is:
"One of ordinary skill would have been motivated to combine the teachings of Froese, and Maier because these teachings are from the same field of endeavor with respect to controlling virtual system routers to route packets between the virtual routers."
That single sentence does two things and neither of them establishes a proper rationale under KSR. It states that the references are in the same field of endeavor, and it describes Maier's own purpose. Neither articulates a reason why a person of ordinary skill in the art designing a physical dragonfly-topology switch fabric, which is Froese's subject matter, would have looked to Maier's SDN-controller-based virtual network topology and adopted its virtual-router set-assignment scheme.
Response:
Examiner respectfully, disagrees.
See detailed rejections of arguments 1- 3.
Furthermore, applicant agrees that the references are in the same field of endeavor and describes Maier's own purpose but argued that Froese simply “adopted its virtual-router set-assignment scheme”. However, examiner’s response to argument 1 makes it clear that the current recitation of the claims did not make a distinct claim of physical switches. Maier also disclosed physical switches that are functionally equivalent to the switch of the claimed invention. Furthermore, typically, a network administrator is required to manually configure switches in the network to perform desired forwarding operations on network packets. This process can be time-consuming, tedious, and increasingly challenging, especially with increasing network complexity. Maier provide improved systems and methods for configuring a network of switches to perform data forwarding operations.
Argument 5: (Summary of page 12)
IV. The Examiner's Observation Regarding Claims 11 and 13
The Office Action notes on page 2 that the limitation "each switch is assigned to only one set within its VRG," which was added to claim 1 in Applicant's prior submission, is not recited in independent claims 11 and 13. Applicant acknowledges the Examiner's observation. Applicant respectfully submits that no amendment to claims 11 and 13 is required to overcome the present rejection. The Office Action rejects claims 11 and 13 under the same Froese-in-view-of-Maier combination applied to claim 1. As explained above, that combination fails as to claim 1 because Maier does not disclose the local-link ingress classification limitation and because the proposed motivation to combine lacks the required articulation. Both deficiencies apply equally to claims 11 and 13, which recite the same local-link ingress classification limitation. Accordingly, no amendment to claims 11 and 13 are required to overcome the present rejection.
Response:
Examiner respectfully, disagrees.
See detailed rejections of arguments 1- 4.
Argument 6: (Summary of pages 12 - 13)
V. Dependent Claims 5, 10, 12, and 14
Claims 5 and 14 stand rejected under 35 U.S.C. § 103 as unpatentable over Froese in view
of Maier, and further in view of Marripudi. Claim 10 stands rejected under 35 U.S.C. § 103 as
unpatentable over Froese in view of Maier, and further in view of Ronen. Claim 12 stands
rejected under 35 U.S.C. § 103 as unpatentable over Froese in view of Maier, and further in
view of Tucker. Each of these dependent-claim rejections depends on the underlying Froese-in-view-of-Maier combination. Marripudi is cited only for the even-number-of-switches limitation of claims 5 and 14; Ronen only for the virtual-lanes-per-link limitation of claim 10; and Tucker only for the virtual-lane-level-Vlev0 limitation of claim 12. None of Marripudi, Ronen, or Tucker is cited for either the virtual-vs-physical-switch mapping or for the local-link ingress classification limitation discussed above. Accordingly, none remedies the deficiencies of the Froese-in-view-of-Maier combination discussed in Sections I through III.
Response:
Examiner respectfully, disagrees.
See detailed rejections of arguments 1- 4.
Claim Rejections - 35 USC § 103
In the event the determination of the status of the application as subject to AIA 35 U.S.C. 102 and 103 (or as subject to pre-AIA 35 U.S.C. 102 and 103) is incorrect, any correction of the statutory basis (i.e., changing from AIA to pre-AIA ) for the rejection will not be considered a new ground of rejection if the prior art relied upon, and the rationale supporting the rejection, would be the same under either status.
The following is a quotation of 35 U.S.C. 103 which forms the basis for all obviousness rejections set forth in this Office action:
A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made.
The text of those sections of Title 35, U.S. Code not included in this action can be found in a prior Office action.
Claim(s) 1-4, 6-9, 11, 13 and 15-17 is/are rejected under 35 U.S.C. 103 as being unpatentable over Froese et al. (US 2022/0166705 A1), in view of Maier et al. (US 2016/0021032 A1).
Regarding claim 1, Froese discloses a topology (dragonfly network topology) for high performance (fig. 1 - HPC network 114)) computing, the topology comprising (Froese, fig. 9, [0025] discloses a dragonfly network topology for high performance computing network - 114, the topology comprising):
a plurality of interconnected virtual routing groups (VRGs) (Froese, fig. 9, [0025 -0026; 0084] in a dragonfly network topology, the network is subdivided into groups, with each group containing some number of switches and some number of endpoints. In a fault-free Dragonfly network, every group is connected to every other group (interconnected routing groups) in the network by one or more global links and every switch within a group is connected to every other switch in the same group by one or more local links. [0084] each Shaping Queue (SQ) in each of the groups consist of a sets/groups of virtual channels (VCs). That is, the dragonfly network topology consists of interconnected of virtual routing groups (group of switches or routers) with Shaping Queues, where each Shaping Queue consist of a set/group of virtual channels);
wherein each VRG has at least one link to every other VRG (Froese [0025] in a fault-free Dragonfly network, every group is connected to every other group in the network by one or more global links and every switch within a group is connected to every other switch in the same group by one or more local links. That is, global links are used to interconnect each virtual routing group to other virtual routing groups);
wherein each VRG includes a plurality of interconnected switches (Froese [0025] in a fault-free Dragonfly network, every group is connected to every other group in the network by one or more global links and every switch within a group is connected to every other switch in the same group by one or more local links. That is, local links interconnect switches within a group);
wherein the switches include terminal links (local links) to compute nodes (endpoints), local links to other switches in the same VRG (Froese [0025, With the Dragonfly network topology, the network is subdivided into groups, with each group containing some number of switches and some number of endpoints. In a fault-free Dragonfly network, every group is connected to every other group in the network by one or more global links and every switch within a group is connected to every other switch in the same group by one or more local links. [0181] in the situation of three switches, A, B, and C within a group, where each switch is connected to each other switch by four local links) and
global links to switches in other VRGs (Froese [0025] In a fault-free Dragonfly network, every group is connected to every other group in the network by one or more global links and every switch within a group is connected to every other switch in the same group by one or more local links); and
wherein each switch in each VRG is assigned to a particular set within its VRG (Froese [0025-0026] discloses switches that are grouped where every switch within a group is connected to every other switch in the same group by one or more local links. The groups may assign or identify as a source or intermediate or destination group of switches. [0162] a Dragonfly routing is hierarchical, distinguishing between local destinations (those in same group as source) and global destinations. Thus, in a dragonfly network, a switch routes to a destination group and then to a switch within that group using two tables rather than to individual destinations using one large table).
Froese did not explicitly disclose each switch is assigned to only one set within its VRG; and wherein each of its local links is assigned to either ingress traffic from terminal links or ingress traffic from global links.
Maier discloses each switch (VSW1, VSW2 and VSW3) is assigned to only one set (VR1 or VR2) within its VRG (Virtual system router, SR1) (Maier, fig. 8, [0069-0070; 0075] discloses a virtual network topology 120 comprising a virtual system router SR1 which represents a first virtual routing group. Using the controller 18, the virtual switches (VSW1, VSW2 and VSW3) in the virtual routing group SR1 may be grouped into to two different sets. As illustrated in FIG. 8, virtual switches VSW1, and VSW2 are grouped to form virtual router VR1, whereas virtual switch VSW3 is assigned to virtual router VR2),
wherein each of its local links (link between EH3 and VSW1; link between EH6,EH1 and VSW2) is assigned to either ingress traffic from terminal (End host EH1 – EH6) links or ingress traffic from global links (Maier, [0070] as illustrated in fig. 8, after grouping the switches in the Virtual Routing group (VR1) into two smaller sets (VSW1 and VSW2), virtual switch VSW1 may be assigned end host EH3, which establishes a local ingress link between VSW1 and a terminal/ end host EH3. Virtual switch VSW2 may be assigned end hosts EH1 and EH6, and similarly establish local ingress links between VSW2 and the respective end hosts (EH1 and EH6). Furthermore, virtual switch VSW3 may be assigned end hosts EH2, EH4, and EH5. Similarly local ingress links between VSW3 are established to the respective end hosts (EH2, EH4 and EH5).
One of ordinary skill would have been motivated to combine the teachings of Froese, and Maier because these teachings are from the same field of endeavor with respect to controlling virtual system routers to route packets between the virtual routers.
Therefore, before the effective filing date of the invention, it would have been obvious to a person of ordinary skill in the art to incorporate the strategies by Maier into the method by Froese, thereby using a controller to control a virtual network topology by generating respective flow table entries based on identified network policies for each of the virtual routers, virtual system routers, and virtual switches, providing improved systems and methods for configuring a network of switches to perform data forwarding operations Maier, [Abstract].
Regarding claim 2, Froese modified by Maier disclose the topology of claim 1 wherein each switch in each VRG may be an egress switch to a pass-through VRG (Froese [0162] a Dragonfly routing is hierarchical, distinguishing between local destinations (local egress switch) and global destinations (global egress switch). Thus, in a dragonfly network, a switch routes (packets pass through egress/destination group) to a destination group (egress switch group) and then to a switch within that group using two tables rather than to individual destinations using one large table. [0177] during the transmission of network traffic/packet, a hop across a local link is required in both the source/ingress and destination/egress groups. The local link hop in the destination/egress group takes the frame from the destination/egress group switch that is connected to the global link to the egress switch).
The motivation to combine is similar to that of claim 1.
Regarding claim 3, Froese modified by Maier disclose the topology of claim 1 wherein every VRG in the topology has available for routing the same number of pass-through VRGs (Froese [0025-0026] In a fault-free Dragonfly network topology, every group is connected to every other group in the network by one or more global links and every switch within a group is connected to every other switch in the same group by one or more local links. When a packet enters the network at one group (the source group) and leaves the network at a different group the destination group), the packet may be globally routed (routed between its source and destination group) either minimally or non-minimally. The packet takes a global minimal path if it traverses one global link, directly connecting the source group to the destination group. That is, because every group is connected to every other group in the network by one or more global links and every switch within a group is connected to every other switch in the same group by one or more local links ,the Dragonfly topology provides every routing group, access to the same number of pass-through routing groups).
The motivation to combine is similar to that of claim 1.
Regarding claim 4, Froese modified by Maier disclose the topology of claim 1 wherein the VRGs are interconnected as dragonfly (Froese, fig. 9, [0207] in a Dragonfly network topology, the network is divided into groups, with the nodes distributed among the groups).
The motivation to combine is similar to that of claim 1.
Regarding claim 6, Froese modified by Maier disclose the topology of claim 1 wherein each switch includes a switch core configured for intra packet traffic and packets received on terminal links are routed to a switch in the VRG assigned to the same set (Froese [0025-0026] discloses a Dragonfly network topology where switches are grouped. Switches that are grouped where every switch within a group is connected to every other switch in the same group by one or more local links. The switch is configured to transmit packet within and outside a group by transmitting packet between switches in the group using local links and outside to another group using a combination of local and global links).
The motivation to combine is similar to that of claim 1.
Regarding claim 7, Froese modified by Maier disclose the topology of claim 1 wherein each switch includes a switch core configured for intra packet traffic and packets received on global links are routed to a switch in the VRG assigned to a different set (Froese [0025-0026] discloses a Dragonfly network topology where switches are grouped. Switches that are grouped where every switch within a group is connected to every other switch in the same group by one or more local links. The switch is configured to transmit packet within and outside a group by transmitting packet between switches in the group using local links and outside to another group using a combination of local and global links).
The motivation to combine is similar to that of claim 1.
Regarding claim 8, Froese modified by Maier disclose the topology (Dragonfly network topology) of claim 7 wherein each switch is assigned to one of two sets (local source or destination groups within a group of switches) and packets received on terminal links (local links within a group) are routed to a switch assigned to the same set in the VRG (Froese [0025-0026] discloses switches that are grouped where every switch within a group is connected to every other switch in the same group by one or more local links. The switches are assigned or identified as a source or intermediate or destination group of switches. [0162] a Dragonfly routing is hierarchical, distinguishing between local destinations (those in same group as source) and global destinations. Thus, in a dragonfly network, a switch routes to a destination group and then to a switch within that group using two tables rather than to individual destinations using one large table).
The motivation to combine is similar to that of claim 1.
Regarding claim 9, Froese modified by Maier disclose the topology of claim 7 wherein each switch is assigned to one of two sets and packets received on global links are routed to a switch assigned to the other set in the VRG (Froese [0025-0026] discloses switches that are grouped where every switch within a group is connected to every other switch in the same group by one or more local links. The groups may assign or identify as a source or intermediate or destination group of switches. [0162] a Dragonfly routing is hierarchical, distinguishing between local destinations (those in same group as source) and global destinations. Thus, in a dragonfly network, a switch routes to a destination group and then to a switch within that group using two tables rather than to individual destinations using one large table).
The motivation to combine is similar to that of claim 1.
Regarding claim 11, Froese discloses a switch with deadlock prevention in a dragonfly topology (Froese, figs. 8 & 9, [00025] discloses a Dragonfly network topology, the network is subdivided into groups, with each group containing some number of switches and some number of endpoints. A computing component 800 in the network may be used to effectuate deadlock-free multicast routing);
wherein the dragonfly topology comprising a plurality of virtual routing groups (VRGs), each VRG comprising a plurality of switches (Froese [0025] in a fault-free Dragonfly network, every group is connected to every other group in the network by one or more global links and every switch within a group is connected to every other switch in the same group by one or more local links. That is, local links interconnect switches within a group);
each of the switches having terminal links to compute nodes, local links to other switches in the same VRG (Froese [0025], With the Dragonfly network topology, the network is subdivided into groups, with each group containing some number of switches and some number of endpoints. In a fault-free Dragonfly network, every group is connected to every other group in the network by one or more global links and every switch within a group is connected to every other switch in the same group by one or more local links), and
global links to switches in other VRGs (Froese [0025, With the Dragonfly network topology, the network is subdivided into groups, with each group containing some number of switches and some number of endpoints. In a fault-free Dragonfly network, every group is connected to every other group in the network by one or more global links and every switch within a group is connected to every other switch in the same group by one or more local links); and
wherein each switch in each of the VRGs is assigned to a particular set within its VRG (Froese [0025-0026] discloses switches that are grouped where every switch within a group is connected to every other switch in the same group by one or more local links. The groups may assign or identify as a source or intermediate or destination group of switches. [0162] a Dragonfly routing is hierarchical, distinguishing between local destinations (those in same group as source) and global destinations. Thus, in a dragonfly network, a switch routes to a destination group and then to a switch within that group using two tables rather than to individual destinations using one large table); and
the switch comprising: a plurality of ports including a transmit controller and a receive controller (Froese [0025] In the Dragonfly network topology, the network is subdivided into groups, with each group containing some number of switches and some number of endpoints. Each switch is an ASIC with many interconnected ports. The ports of each switch are divided between edge ports, local ports, and global ports, Edge ports are where traffic enters and leaves the network. Each switch can transmit network traffic through a controller and receives traffic through a controller);
a control port comprising a management processor and transmit controller and a receive controller (Froese, fig. 8, [0025] In the Dragonfly network topology, the network is subdivided into groups, with each group containing some number of switches and some number of endpoints. Each switch is an ASIC with many interconnected ports. The ports of each switch are divided between edge ports, local ports, and global ports, Edge ports are where traffic enters and leaves the network. Each switch can transmit network traffic through a controller and receives traffic through a controller. [0196] discloses a computing component 800/controller which receives traffic at an input port (step 806) and transmits traffic through an output port (step 814); and
a switch core configured to: receive a packet on a global link or a terminal link of a source VRG or a destination VRG (Froese [0026] When a packet enters the network at one group (the source group) and leaves the network at a different group the destination group), the packet may be globally routed (routed between its source and destination group) either minimally or non-minimally);
route the packet to a local switch in the same set if the packet was received on a terminal link (Froese [0028] a packet arriving at an edge port might be routed across a local link to another switch in the same group which has some global ports the packet can use); and
route the packet to a local switch in the other set if the packet was received on a global link (Froese [0025] ports of each switch are divided between edge ports, local ports, and global ports, Edge ports are where traffic enters and leaves the network. Packets can be transmitted between different groups of switches by using a combination of local and global links. The packet is transmitted to the edge of a source group using local links. Using global links, the packet is transmitted to the edge of a second group and transmitted to an internal switch within the second group using local links within the second group. Local ports connect to other switches within the same group. Global ports connect to other switches that are in a different group).
Froese did not explicitly disclose wherein each of the local links of each switch in each VRG is assigned to either ingress traffic from terminal links or ingress traffic from global links.
Maier discloses wherein each of its local links (link between EH3 and VSW1; link between EH6,EH1 and VSW2) of each switch in each VRG is assigned to either ingress traffic from terminal (End host EH1 – EH6) links or ingress traffic from global links (Maier, [0070] as illustrated in fig. 8, after grouping the switches in the Virtual Routing group (VR1) into two smaller sets (VSW1 and VSW2), virtual switch VSW1 may be assigned end host EH3, which establishes a local ingress link between VSW1 and a terminal/ end host EH3. Virtual switch VSW2 may be assigned end hosts EH1 and EH6, and similarly establish local ingress links between VSW2 and the respective end hosts (EH1 and EH6). Furthermore, virtual switch VSW3 may be assigned end hosts EH2, EH4, and EH5. Similarly local ingress links between VSW3 are established to the respective end hosts (EH2, EH4 and EH5).
The motivation to combine is similar to that of claim 1.
Regarding claim 13, Froese discloses a VRG, the VRG comprising: a plurality of switches (Froese [0025] in a fault-free Dragonfly network, every group is connected to every other group in the network by one or more global links and every switch within a group is connected to every other switch in the same group by one or more local links. That is, local links interconnect switches within a group);
each of the switches having terminal links to compute nodes, local links to other switches (Froese [0025, With the Dragonfly network topology, the network is subdivided into groups, with each group containing some number of switches and some number of endpoints. In a fault-free Dragonfly network, every group is connected to every other group in the network by one or more global links and every switch within a group is connected to every other switch in the same group by one or more local links. [0181] in the situation of three switches, A, B, and C within a group, where each switch is connected to each other switch by four local links), and
global links to switches in other VRGs (Froese [0025] In a fault-free Dragonfly network, every group is connected to every other group in the network by one or more global links and every switch within a group is connected to every other switch in the same group by one or more local links).
Froese did not explicitly disclose each of the local links of each of the switches comprising a link to a switch assigned for ingress traffic from terminal links or a link to a switch assigned for ingress traffic from global links.
Maier discloses each of the local links (link between EH3 and VSW1; link between EH6,EH1 and VSW2) of each of the switches comprising a link to a switch assigned for ingress traffic from terminal (End host EH1 – EH6) links or a link to a switch assigned for ingress traffic from global links (Maier, [0070] as illustrated in fig. 8, after grouping the switches in the Virtual Routing group (VR1) into two smaller sets (VSW1 and VSW2), virtual switch VSW1 may be assigned end host EH3, which establishes a local ingress link between VSW1 and a terminal/ end host EH3. Virtual switch VSW2 may be assigned end hosts EH1 and EH6, and similarly establish local ingress links between VSW2 and the respective end hosts (EH1 and EH6). Furthermore, virtual switch VSW3 may be assigned end hosts EH2, EH4, and EH5. Similarly local ingress links between VSW3 are established to the respective end hosts (EH2, EH4 and EH5).
The motivation to combine is similar to that of claim 1.
Regarding claim(s) 15-17 the claim(s) is/are rejected with rational similar to that of claim(s) 8-9 and 2 respectively.
Claim(s) 5 and 14 is/are rejected under 35 U.S.C. 103 as being unpatentable over Froese et al. (US 2022/0166705 A1), in view of Maier et al. (US 2016/0021032 A1), further in view of Marripudi et al. (US 2019/0294513 A1).
Regarding claim 5, Froese modified by Maier disclose the topology of claim 1 but did not explicitly disclose wherein the VRG contains an even number of switches and half the switches are assigned to one set and the other half of the switches are assigned to another set.
Marripudi discloses wherein the VRG contains an even number of switches and half the switches are assigned to one set and the other half of the switches are assigned to another set (Marripudi, claim 1, discloses a computing system providing high-availability access to computing resources comprising: a plurality of interfaces; a plurality of groups of switches, each group comprising at least two switches, each switch being: directly connected to a corresponding one of the interfaces via a corresponding host link, and directly connected to at least one switch of another group of switches via one of a plurality of cross-connections
One of ordinary skill would have been motivated to combine the teachings of Froese, Maier, and Marripudi because these teachings are from the same field of endeavor with respect to providing high-availability access to computing resources.
Therefore, before the effective filing date of the invention, it would have been obvious to a person of ordinary skill in the art to incorporate the strategies by Marripudi into the method by Froese and Maier, thereby enabling each of the switches in a network to be configured such that data traffic is distributed to remaining ones of the switches through a plurality of cross-connections between the switches if one of the switches fails, Marripudi, [Abstract].
Regarding claim 14, the claim is rejected with rational similar to that of claim 5.
Claim(s) 10 is/are rejected under 35 U.S.C. 103 as being unpatentable over Froese et al. (US 2022/0166705 A1), in view of Maier et al. (US 2016/0021032 A1), further in view Ronen et al. (US 2022/0407796 A1).
Regarding claim 10, Froese modified by Maier disclose the topology of claim 1 but did not explicitly disclose wherein each switch supports a plurality of virtual lanes on each link.
Ronen discloses wherein each switch supports a plurality of virtual lanes on each link (Ronen [0007] discloses subnetwork each of which includes multiple switches, where the switches are configured to communicate via at least first and second virtual lanes and are arranged in a bipartite topology including an upper tier containing upper-tier switches, which are connected to one or more of the trunk links, and a lower tier containing lower-tier switches, which are connected by local links to the upper-tier switches).
One of ordinary skill would have been motivated to combine the teachings of Froese, Maier and Ronen because these teachings are from the same field of endeavor with respect to partitioning local links in a subnetwork of a packet data network into at least first and second groups.
Therefore, before the effective filing date of the invention, it would have been obvious to a person of ordinary skill in the art to incorporate the strategies by Ronen into the method by Froese and Maier, thereby upon a failure of the local link connecting the first upper-tier switch to the first lower-tier switch, data packets arriving from the network at the first upper-tier switch are rerouted to pass via the corresponding detour route to the first lower-tier switch, Ronen, [Abstract].
Claim(s) 12 is/are rejected under 35 U.S.C. 103 as being unpatentable over Froese et al. (US 2022/0166705 A1), in view of Maier et al. (US 2016/0021032 A1), further in view of Tucker et al. (US 2004/0001487 A1).
Regarding claim 12, Froese modified by Maier disclose the switch of claim 11 but did not explicitly disclose wherein routing the packet to a local switch in the other set and routing the packet to a local switch in the same set includes transmitting the packet on a local link on virtual lane level Vlev0.
Tucker discloses wherein routing the packet to a local switch in the other set and routing the packet to a local switch in the same set includes transmitting the packet on a local link on virtual lane level Vlev0 (Tucker [0012] discloses Data packets convey IBA operations that can include a number of different headers. For example, the Local Route Header (LRH) is always present and it identifies the local source and local destination ports where switches will route the packet and also specifies the Service Level (SL) and Virtual Lane (VL) on which the packet travels).
One of ordinary skill would have been motivated to combine the teachings of Froese, Maier and Tucker because these teachings are from the same field of endeavor with respect to a switch which includes a crossbar that redirects packet based data based on a forwarding table.
Therefore, before the effective filing date of the invention, it would have been obvious to a person of ordinary skill in the art to incorporate the strategies by Tucker into the method by Froese and Maier, thereby a switch includes a crossbar that redirects packet based data based on a forwarding table. That is, at least one port that receives data from a network and selectively transfers that data to the crossbar at different times, Tucker, [Abstract].
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure. The following publications show the state of the art related to the use of Dragonfly network topology in preventing deadlock in a computer network.
Krause (US 2002/0133620 A1)
THIS ACTION IS MADE FINAL. Applicant is reminded of the extension of time policy as set forth in 37 CFR 1.136(a).
A shortened statutory period for reply to this final action is set to expire THREE MONTHS from the mailing date of this action. In the event a first reply is filed within TWO MONTHS of the mailing date of this final action and the advisory action is not mailed until after the end of the THREE-MONTH shortened statutory period, then the shortened statutory period will expire on the date the advisory action is mailed, and any nonprovisional extension fee (37 CFR 1.17(a)) pursuant to 37 CFR 1.136(a) will be calculated from the mailing date of the advisory action. In no event, however, will the statutory period for reply expire later than SIX MONTHS from the mailing date of this final action.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to DIXON F DABIPI whose telephone number is (571)270-3673. The examiner can normally be reached on Monday – Friday from 9:00 am – 5:00 pm.
If attempts to reach the examiner by telephone are unsuccessful, the examiner’s supervisor, Christopher L Parry, can be reached at telephone number 571-272-8328. The fax phone number for the organization where this application or proceeding is assigned is 571-273-8300.
Information regarding the status of an application may be obtained from Patent Center. Status information for published applications may be obtained from Patent Center. Status information for unpublished applications is available through Patent Center to authorized users only. Should you have questions about access to the USPTO patent electronic filing system, contact the Electronic Business Center (EBC) at 866-217-9197 (toll-free).
Examiner interviews are available via a variety of formats. See MPEP § 713.01. To schedule an interview, applicant is encouraged to use the USPTO Automated Interview Request (AIR) Form at https://www.uspto.gov/InterviewPractice.
/D.F.D/ Examiner, Art Unit 2451
/Chris Parry/Supervisory Patent Examiner, Art Unit 2451
Prosecution Insights