`
`In re patent of: Back et al.
`
`§ Petition for Inter Parres Review
`
`§
`
`U.S. Patent No. 6,978,346
`
`§ Attorney Docket No.:
`
`47415.430
`
`Issued: December 20, 2005
`
`§ Customer No.:
`
`§
`
`§
`
`Title: APPARATUS FOR
`
`§ Real Parties in Interest: Dell Inc.,
`
`REDUNDANT INTER-
`
`§ Hewlett-Packard Company, and NetApp,
`
`CONNECTION
`
`BETWEEN MULTIPLE
`
`HOSTS AND RAID
`
`Inc.
`
`§
`
`§
`
`§
`
`Declaration of Dr. M. Ray Mercer
`
`Under 37 C.F.R.
`
`1.68
`
`I, Dr. M. Ray Mercer, do hereby declare:
`
`I.
`
`I am making this declaration at the request of Dell Inc., Hewlett-
`
`Packard Company, and NetApp, Inc. in the matter of the Inter Partes Review of
`
`U.S. Patent No 6,978,346 (“the ‘346 Patent") to Back et al.
`
`2.
`
`I am being compensated for my work in this matter. My
`
`compensation in no way depends upon the outcome of this proceeding.
`
`3.
`
`In the preparation of this declaration, I have studied:
`
`(1)
`
`The ‘346 patent, DHPN-I001;
`
`~1~
`
`Page 1 of1B5
`
`
`
`(2)
`
`The prosecution history of the ‘346 patent, DHPN-1002;
`
`(3)
`
`Peter Weygant, Clustersfor HIgh Availability.‘ A Primer ofHP- UX
`
`Solutions, 1996 (“Weygant”), DHPN-I003;
`
`(4)
`
`Managing MC/Servz'ceGuard, I-lewlett—Packard Company, 1998
`
`(“ServiceGuard"), DHPN-1004;
`
`(5)
`
`Hathom et al., U.S. Pat. No. 5,574,950 (“the ‘950 patent”), DHPN-
`
`1005;
`
`(6)
`
`Surugguchi ct al., International Publication No. W0 99/38067
`
`(“Mylex”), DHPN-1007; and
`
`(7)
`
`American National Standardfor Information Technology — Fibre
`
`Channel Arbitrated Loop (FC—/IL-2), June 28, 1999 (“ANSI”),
`
`DHCP-1008.
`
`40
`
`In forming the opinions expressed below, I have considered:
`
`(1)
`
`The documents listed above,
`
`(2)
`
`The relevant legal standards, including the standard for obviousness
`
`provided in KSR International Co. v. Teleflex, Inc., 550 U.S. 398 (2007) and
`
`any additional authoritative documents as cited in the body of this
`
`declaration, and
`
`-2-
`
`Pagez ef1B5
`
`
`
`(3) My knowledge and experience based upon my work in this area as
`
`described below.
`
`Qualifications and Professional Experience
`
`5.
`
`My qualifications are set forth in my curriculum vitae, a copy of
`
`which is attached as Appendix 1.
`
`6.
`
`I have over 45 years of dual industrial and academic experience in
`
`Electrical Engineering and Computer Engineering.
`
`I received a B.S. in Electrical
`
`Engineering from Texas Tech University in 1968. From 1968 to 1973, I was a
`
`Research/Development Engineer at General Telephone and Electronics Sylvania in
`
`Mountain View, California, and I received an MS. in Electrical Engineering from
`
`Stanford University in 1971. From 1973 to 1977, I was a Member of Technical
`
`Staff at Hewlett-Packard's Santa Clara Division and subsequently at Hewlett-
`
`Packard Laboratories in Palo Alto, California. From 1977 to 1980, I was a
`
`Lecturer in the Division of Mathematics, Statistics, and Computer Science at the
`
`University of Texas at San Antonio, and I received a Ph.D. in Electrical
`
`Engineering from the University of Texas at Austin in 1980. From 1980 to 1933, I
`
`was a Member of Technical Staff at Bell Laboratories in Murray Hill, New Jersey.
`
`'7.
`
`In I983, I was appointed Assistant Professor of Electrical and
`
`Computer Engineering at the University of Texas at Austin.
`
`In 1987, I was
`
`promoted to Associate Professor and in 1991, Professor.
`
`In 1995, I was appointed
`
`-3-
`
`no
`
`:-
`
`Page3of1a5
`
`
`
`Professor of Electrical and Computer Engineering, Leader of the Computer
`
`Engineering Group and Holder of the Computer Engineering Chair at Texas A&M
`
`University in College Station, Texas. My teaching, my research, my technical
`
`publications, and my supervision of graduate students during this period included
`
`the areas of computer clusters, redundant connections, and networking — key issues
`
`in this proceeding.
`
`8.
`
`In September 2005, I retired, and the Regents of the Texas A&M
`
`University System appointed me as Professor Emeritus of Electrical and Computer
`
`Engineering at Texas A&M University.
`
`9.
`
`Since 1984, I have been an independent consultant and provided
`
`private consultation and advice in Electrical and Computer Engineering to
`
`numerous entities including IBM, Inc., Rockwell International, Motorola
`
`Semiconductor, AT&T, Inc., and SigmaTel.
`
`I also have been hired by numerous
`
`law firms to provide them and their clients with expert consultation and expert
`
`testimony — often in the areas of patent infringement litigation related to Electrical
`
`and Computer Engineering.
`
`10.
`
`I was actively involved in numerous professional organizations
`
`including the Institute of Electrical and Electronics Engineers (“IEEE"), and I was
`
`recognized as an IEEE Fellow in 1994.
`
`1 was the Program Chairman for the 1989
`
`International Test Conference, which is an IEEE-sponsored annual conference with
`
`+
`
`Page 4 of 185
`
`
`
`(at that time) more than one thousand attendees and over one hundred presented
`
`papers.
`
`I won the Best Paper Award at the 1982 International Test Conference.
`
`I
`
`also won a Best Paper Award at the 1991 Design Automation Conference, an
`
`annual conference with (at that time) more than ten thousand attendees and five
`
`hundred submitted papers, many of which related to the design of integrated circuit
`
`based systems. The subject of this paper involved trade—ofTs between power
`
`consumption and processing speed in integrated circuits.
`
`1 also won a Best Paper
`
`Award at the 1999 VLSI Test Symposium.
`
`I am the inventor on United States
`
`patents that relate to the design of integrated circuits.
`
`I was selected as a National
`
`Science Foundation Presidential Young Investigator in 1986.
`
`11.
`
`I am familiar with the knowledge and capabilities one of ordinary skill
`
`in the networking and computing cluster arts in the period around 2000.
`
`Specifically, my work with students, undergraduates as well as masters and Ph.D.
`
`candidates, with colleagues in academia, and with engineers practicing in industry
`
`allowed me to become personally familiar with the level of skill of individuals and
`
`the general state of the art. Unless otherwise stated, my testimony below refers to
`
`the knowledge of one of ordinary skill in the networking and computing cluster
`
`arts in the period around 2000 — the period that includes the filing date of the ‘346
`
`patent.
`
`Relevant Legal Standards
`
`-5-
`
`Page5of185
`
`
`
`12.
`
`I have been asked to provide my opinions regarding whether the
`
`claims of the ‘346 patent are anticipated or would have been obvious to a person
`
`having ordinary skill in the art at the time of the alleged invention, in light of the
`
`prior art.
`
`It is my understanding that, to anticipate a claim under 35 U.S.C. § 102,
`
`a reference must teach every element of the claim. Further, it is my understanding
`
`that a claimed invention is unpatentable under 35 U.S.C. § 103 if the differences
`
`between the invention and the prior art are such that the subject matter as a whole
`
`would have been obvious at the time the invention was made to a person having
`
`ordinary skill in the art to which the subject matter pertains.
`
`I also understand that
`
`the obviousness analysis takes into account factual inquiries including the level of
`
`ordinary skill in the art, the scope and content of the prior art, and the differences
`
`between the prior art and the claimed subject matter.
`
`13.
`
`It is my understanding that the Supreme Court has recognized several
`
`rationales for combining references or modifying a reference to show obviousness
`
`of claimed subject matter. Some ofthese rationales include the following:
`
`combining prior art elements according to known methods to yield predictable
`
`results; simple substitution of one known element for another to obtain predictable
`
`results; use of a known technique to improve a similar device (method, or product)
`
`in the same way; applying a known technique to a known device (method, or
`
`product) ready for improvement to yield predictable results; choosing from a finite
`
`-6-
`
`Page6of185
`
`
`
`number of identified, predictable solutions, with a reasonable expectation of
`
`success; and some teaching, suggestion, or motivation in the prior art that would
`
`have led one of ordinary skill to modify the prior art reference or to combine prior
`
`art reference teachings to arrive at the claimed invention.
`
`Bael_cgrountl Of ‘346 patent
`
`14.
`
`The ‘346 Patent relates to a system having “redundant
`
`interconnections between multiple hosts and a RAID.” Fig. 4 of the ‘346 patent is
`
`especially illustrative and is reproduced below for reference:
`
`FIG. 4
`r------I-‘Eh r ------I-Q-hr------I--1r----‘*1--1r---- --J-an r ---- ---I-‘E:
`IIGTOQHJIBIJ
`tl'l3T@PUTElIIKHf(X1|l’|JTERIIPC|8TOCIl’lJ'lERIIP@l'G2IFUlBlI n-Iosreunrraau
`
`
`
`::
`A:
`sage.“
`
`E _'
`I:sr=:i:s.e:e.s|
`
`_..-u-...__.-._
`
`,___________
`
`--n.---u——_¢._——_—————_-pu--u--o-nn
`
`‘346 patent, Fig. 4
`
`15.
`
`The storage system includes two RAID controllers—460 and 461.
`
`Each RAID controller 460, 461 has two Network Interface Controllers (NICS), so
`
`—7—
`
`Page7of185
`
` ......-———..-.—.—
`
`|%.'t§'dli;¥E.a‘H
`
`e
`
`-='r...-.3 mm:
`
`15'"“‘34‘u"'
`
`
`
`RAID controller 460 includes NICs 470 and 471, and RAID controller 46]
`
`includes NICS 480, 481. The system also has two “hub or switch” devices—44O
`
`and 441. Each RAID controller is connected to each “hub or switch” device by
`
`one of its NICS. RAID controller 460, on the left, is connected to “hub or switch”
`
`440 by NIC 470 and to “hub or switch” 441 by NIC 471. Similarly, RAID
`
`controller 461, on the right, is connected to “hub or switch” 441 by NIC 481 and to
`
`“hub or switch” 440 by NIC 480.
`
`16.
`
`The structure described above provides for a “communication passage
`
`between two RAID controllers.” ‘346 Patent, 3:64-65. For instance, a
`
`communication passage exists between the RAID controller 460, on the left, and
`
`the RAID controller 461, on the right, via NIC 471, switch/hub 441, and NIC 481
`
`(at RAID controller 461). ‘346 Patent, 3:66 — 4:2.
`
`In the same way, a
`
`communication passage exists between NIC 481 and NIC 471.
`
`‘346 Patent, 3:64 —
`
`4:12. Also, a communication passage exists between RAID controller 460, on the
`
`left, and RAID controller 461, on the right, via NIC 470, “hub or switch” 440, and
`
`NIC 480. Id.
`
`In the same way, a communication passage exists between NIC 480
`
`and NIC 470. Id.
`
`17.
`
`The ‘346 patent fails to provide any examples regarding the types of
`
`information that maybe exchanged between the NICs nor any examples regarding
`
`how communication paths between the NICS might be used.
`
`-8-
`
`Page 8 M185
`
`
`
`18.
`
`The system attempts to provide a “fault tolerant function.” ‘346
`
`Patent, 3:63-66. A RAID controller “having [an] error occurrence is removed from
`
`the network," then a NIC from other RAID controller “takes over a function" of a
`
`NIC on the RAID controller with the error.
`
`‘346 Patent, 4: 19-25. However, such
`
`limitation is not reflected in every claim of the ‘346 patent.
`
`19.
`
`Claim 1 provides a basic overview of the teachings of the ‘346 patent:
`
`I. An apparatus for a redundant interconnection between
`
`multiple hosts and a RAID, comprising:
`
`a first RAID controlling units and a second RAID
`
`controlling unit for processing a requirement of numerous host
`
`computers, the first RAID controlling unit including a first
`
`network controlling unit and a second network controlling unit,
`
`and the second RAID controlling unit including a third network
`
`controlling unit and a fourth network controlling unit; and
`
`a plurality of connection units for connecting the first
`
`RAID controlling units and the second RAID controlling unit to
`
`the numerous host computers, wherein the first RAID
`
`controlling unit and the second RAID controlling unit directly
`
`exchange information with the numerous host computers
`
`through the plurality of connecting units, and the first network
`
`controlling unit exchanges information with the fourth network
`
`controlling unit, and the second network controlling unit
`
`exchanges information with the third network controlling unit.
`
`Claim Construction
`
`—9-
`
`Page9of1B5
`
`
`
`20.
`
`It is my understanding that in order to properly evaluate the ‘346
`
`patent, the terms of the claims must first be interpreted.
`
`It is my understanding that
`
`the claims are to be given their broadest reasonable interpretation in light of the
`
`specification.
`
`It is my further understanding that claim terms are given their
`
`ordinary and accustomed meaning as would be understood by one of ordinary skill
`
`in the art, unless the inventor, as a lexicographer, has set forth a special meaning
`
`for a term.
`
`21.
`
`In order to construe the claims, I have reviewed the entirety of the
`
`‘346 patent, as well as its prosecution history.
`
`network controlling unit, network interfiace controlling um‘:
`
`22.
`
`These terms appear in claim 1 and in various dependent claims. The
`
`specification of the ‘346 patent does not use the term network controlling unit or
`
`mm-vork interface controlling unit. The terms appear to rely on disclosure in the
`
`specification regarding “network interface controllers" for enablement and
`
`description. The following passage is an example.
`
`Network interface controllers, 410 to 415, contained into the host
`
`computers, 400 to 405, and the network interface controllers 470,
`
`47 l , 480, 481 of the RAID controllers 460, 461 are connected with
`
`one another by two networks through two hubs 440, 441, and
`
`according to a sort of the networks,
`
`the network interface
`
`controller becomes a fibre channel controller, an ATM controller
`
`-10-
`
`mifilmfi
`
`Pane1D of1B5
`
`
`
`and an lnfiniBand controller etc. ‘346 Patent, 3:31-37.
`
`Furthermore,
`
`it appears that the claims use the two terms interchangeably. For
`
`instance, claim 1 uses network controlling unit, while claim 4 (depending from
`
`claim 1) uses the term network interface controlling unit.
`
`23.
`
`It is my opinion that a person of ordinary skill in the art would
`
`understand the broadest reasonable interpretation of network controlling unit and
`
`network interface controlling unit in view of the specification to be any
`
`component allowing a device to communicate over a network (e.g., Fibre Channel,
`
`ATM, or other networks). Furthermore, because of the way the two terms are used
`
`interchangeably within the claims, a person of ordinary skill in the art would
`
`understand that both terms are intended to mean the same thing.
`
`Network inter ace controller
`
`24.
`
`The specification of the ‘346 patent uses the term network interface
`
`controller throughout, but does not seek to define or limit the term. See, e.g., ‘346
`
`Patent, 3:3 I -37. Furthennore, it appears that claim 9 uses network interface
`
`controller interchangeably with network controlling unit. See, e.g., ‘346 Patent,
`
`6:31 and 53 (using first network controlling unit to refer back to first network
`
`interface controller).
`
`25.
`
`It is my opinion that a person of ordinary skill in the art would
`
`-1 l—
`
`DI-IPN—l00
`
`Page 11 ol135
`
`
`
`understand the broadest reasonable interpretation of network interface controller
`
`in view of the specification to refer to any component allowing a device to
`
`communicate over a network (e.g., Fibre Channel, ATM, or other network).
`
`Specifically, with no further direction from the specification or the claims, a person
`
`of ordinary skill in the art would read the term network interface controller to be
`
`the same as network controlling unit and network interface controlling unit
`
`(immediately above).
`
`the second network interflnce controlling unit and the [ourth network
`
`controlling unit are used [or executing a Qnction of the trrst network
`
`interface controlling unit and the third network controlling unit when one of
`
`the tn-st RAID controlling um‘! and the second RAID controlling unit is taulm
`
`26.
`
`A literal interpretation of this element from claim 4 is not supported
`
`by the specification. For instance, there is no described embodiment in which both
`
`the second and fourth network controlling units execute a function of both the first
`
`and third network controlling units when a single RAID controller fails.
`
`Furthermore, a literal reading of this element does not make sense when the
`
`context ofclaim 1 is taken into account. Specifically, the first and second network
`
`controlling units are both on one RAID controller, and the third and fourth network
`
`controlling units are both on another RAID controller, according to claim 1. Thus,
`
`if the first RAID controller is faulty, the second network controlling unit would not
`
`~I2~
`
`Page 12 of185
`
`
`
`be used, and if the second RAID controller is faulty, the fourth network controlling
`
`unit would not be used. with these concerns in mind, a person of ordinary skill in
`
`the art would avoid a literal reading of this element.
`
`27.
`
`Instead, the specification of the ‘346 patent states:
`
`If any one out of two RAID controllers 460, 46] has an occurrence
`
`of an error, the RAID controller having the error occurrence is
`
`removed from the network, and a second network interface
`
`controller of an opposite RAID controller not having the error
`
`occurrence takes over a function of a first network interface
`
`controller of the RAID controller having the error occurrence.
`
`‘346 Patent, 4: 19-24.
`
`28.
`
`It is my opinion that a person of ordinary skill in the art, when
`
`grappling with these difficult issues with the literal wording, would understand the
`
`broadest reasonable interpretation of the above-recited term to be “if either one of
`
`the first RAID controlling unit or second RAID controlling unit has an occurrence
`
`of an error, the apparatus uses a network controlling unit of the RAID controlling
`
`unit not having the error occurrence.” A person of ordinary skill in the art would
`
`favor this interpretation because it is consistent with the specification at column 4,
`
`lines 19-24 of the ‘346 patent.
`
`(32 o[ the or least [[2 connection gorts is [are] coupled no one of the first
`
`network interface controlling unit and the third network controlling unit
`
`-13-
`
`Page 13 of1B5
`
`
`
`29.
`
`In the above-recited feature of claims 5, 6, and 7, X (two orfour) is
`
`the subject, so that X connection ports are coupled as claimed. The term one is the
`
`object of the preposition of the tenn coupled to, so that one ofthe set (where the
`
`set is defined as thefirst network interface controlling unit and the third network
`
`controlling unit) is referred to by coupled to. Therefore, a literal and grammatical
`
`reading of the above-quoted portion of claims 5, 6, and 7 means that X connecting
`
`ports must be coupled to the first network controlling unit or X connecting ports
`
`must be coupled to the third network controlling unit, where either condition would
`
`satisfy the claim limitation. (Also, see my construction of cougled to herein
`
`bLn.v.) However, upon reading the specification at 3:43-47, I believe that the
`
`patentee probably intended to say “a connection port is coupled to the first network
`
`controlling unit, and another connection port is coupled to the third network
`
`controlling unit,” in the case of claims 5 and 6 (e.g., port 423 coupled to NIC 470
`
`and port 422 coupled to NIC 480 of Fig. 4). This is a non-literal reading of the
`
`claim feature because it is not consistent with a grammatically correct reading of
`
`the limitation.
`
`In the case of claim 7, which recites four instead of two, the
`
`patentee probably intended to say “out of a total of four connection ports, some of
`
`those four connection ports are coupled to the first network controlling unit, and
`
`the others of the four connection ports are coupled to the third network controlling
`
`unit." However, I do not think that the patent supports such features, as the ‘346
`
`14
`
`EEIIEIE
`
`Page 14 at 135
`
`
`
`specification refers to the items 420-424 and 430-434 as “ports,” yet there is no
`
`disclosed embodiment where more than one of the ports is shown with multiple
`
`lines to any one of the NICS in Fig. 4.
`
`30.
`
`In the case of claims 5-7, this is evidence that the term coupied to is
`
`broader than “connected to" and, in the context of a hub or switch, coupled to
`
`means that any connection port in a hub or a switch is connected to any other port
`
`in a hub or a switch by virtue of the internal structure of the hub or switch. Such a
`
`reading of coupled to would mean that any one of ports 420-424 is coupled to NIC
`
`470 and NIC 480, and any port 430-434 is coupled to NIC 48] and NIC 471 in Fig.
`
`4 directly or indirectly by virtue of the structure of the switch or hub. Because of
`
`the above-described tension between the literal, grammatical reading of the phrases
`
`and the disclosure in the specification, it is my opinion that a person of ordinary
`
`skill in the art, when grappling with these errors in the literal wording of each
`
`limitation, if motivated to preserve the validity of a claim, would interpret the
`
`broadest reasonable interpretation of [X] ofthe at least [Y] connection ports is
`
`[are] coupled to one of thefirst network interface controlting unit and the third
`
`network controtling unit to include both a scenario where [X] connection ports are
`
`coupled to the same network controlling unit and the scenario where some of the
`
`[X] connection ports are coupled to one network interface controlling unit and
`
`others of the [X] connection ports are coupled to the other network interface
`
`-15-
`
`Page 15 of 185
`
`
`
`controlling unit: “a hub (or switch) that has at least [Y] ports where at least [X] of
`
`the ports are connected directly or indirectly with the first network interface
`
`controlling unit or the third network controlling unit."
`
`the rest o the connection orts bein
`
`rovided as a hub c ui rncnt network
`
`switch equipment, switchz connected with the numerous host computers
`
`31.
`
`In the above~recited feature of claims 5, 6, and 7, connected with
`
`modifies hub equipment, network switch equipment, or switch and does not
`
`modify the connection ports simply as a matter of grammar because connected
`
`with immediately follows hub equipment, network switch equipment, and switch.
`
`The passage in the ‘346 specification at 3:48-50 uses the term “the rest,” but it
`
`does not address hub equipment, network switch equipment, or switch and is,
`
`thus, less illuminating than the grammatical structure of the claim itself.
`
`I note that
`
`the construction I propose below is not inconsistent with the specification in any
`
`event.
`
`It is my opinion that a person of ordinary skill in the art would recognize
`
`that such construction is consistent with Figs. 4, 5, and 6 of the ‘346 patent
`
`showing a hub or switch connected with the host computers. Furthermore, a
`person ofordinary skill in the art would recognize that the term the rest does not
`
`exclude that the other ports, coupled to the network controlling units, are also
`
`provided as part of the hub equipment, network switch equipment, or switch.
`
`as
`
`~16-
`
`Page 16 M185
`
`
`
`32.
`
`The term hub encompasses both hubs and switches because the ‘346
`
`patent defines the term as such.
`
`Herewith, the hubs 440, 441 are provided to connect a system
`
`connected to these hubs by one network
`
`and it can be as a hub or a
`
`switch. Hereinafter, they are named a "hub" altogether.
`
`‘346
`
`Patent, 3: 13-18 (emphasis added).
`
`Thus, in order to comport with the definition in the specification, the term hub
`
`should be construed as “hub or switch" in its broadest reasonable interpretation.
`
`coupled to
`
`33.
`
`This phrase appears only in claims 3, 5, 6, and 7.
`
`It does not appear in
`
`the specification.
`
`34.
`
`The phrase “connected to” appears in claims 2 and 8. As one
`
`example, claim 8 contains the phrase “wherein the first network interface
`
`controlling unit of the first RAID controlling unit being connected to a first
`
`connecting unit.“ (emphasis added)
`
`35.
`
`In addition, "connected to” appears in the specification in numerous
`
`places. Three examples of the use of this phrase in the specificatiorz are cited
`
`below:
`
`Meanwhile, two network interface controllers 470, 47] of the first RAID
`
`controller 460 are respectively connected to two different huh ports 423,
`
`I7
`
`Page 17 of 135
`
`
`
`432, and two network interface controllers 480, 481 of the second RAID
`
`controller 461 are respectively connected to two different hub ports 422,
`
`433. The rest ports 420, 421, 424, 430, 431, 434 of the hubs 440, 441
`
`are connected to the host computers 400 to 405.
`
`‘346 Patent, col. 3, ll.
`
`43-49 (emphasis added).
`
`36.
`
`It is my opinion that a person of ordinary skill in the art would
`
`understand the broadest reasonable interpretation of “coupled to” to be broader
`
`than the phrase “connected to.” For example if entity A is “coupled to” entity B,
`
`then entity A is connected, directly or indirectly, in order to enable the transfer of
`
`signals between entities A and B. See also my explanation of the term [X] ofthe
`
`at least [Y] connection ports is [are] coupled to one oftheflrst network interface
`
`controlling unit and the third network controlling unit, given above.
`
`host computers
`
`37.
`
`This term appears in both independent claims 1 and 9 and appears
`
`many times in the specification of the ‘346 patent, e.g., at 3:32 (describing host‘
`
`computers 400-405 of Figure 4). However, the term is not used in a manner that
`
`defines the term nor narrows the term, nor does the specification even appear to
`
`give an example of operation of the host computers. Claims 1 and 9 use the term
`
`"host computers" (e.g., claim 1-" wherein the first RAID controlling unit and the
`
`second RAID controlling unit directly exchange information with the numerous
`
`host computers", claim 9-" wherein the first network interface controller in the first
`
`-18-
`
`Page 18 02185
`
`
`
`RAID controller supplies data to the host computers") in the context of the host
`
`computers being in communication with the RAID controllers [RAID controlling
`
`units].
`
`38.
`
`An example of a definition from a technical dictionary from the time
`
`is that found in IEEE 100 The Authoritative Dictionary of IEEE standard terms,
`
`7th ed., 2000 (“Host Computer (1): A computer, attached to a network, providing
`
`primarily services such as computation, database access or specific programs of
`
`special programming languages”), indicating that a host computer is a network
`
`computer.
`
`It is my opinion that a person of ordinary skill in the art at the time
`
`would have understood the broadest reasonable interpretation of host computers,
`
`in light of the present specification, to refer to “network connected computers."
`
`RAID controlling um‘!
`
`39.
`
`This phrase appears in claim I and its dependent claims, as well as in
`
`claim 9.
`
`It does not appear in the specification. The term appears to rely on
`
`disclosure in the specification regarding “RAID controller" for enablement and
`
`description. However, the specification of the ‘346 patent does not define nor
`
`narrow “RAID controller.” The following passage is an example:
`
`As shown in FIG. 4, in the inventive host interface system, a
`
`communication circuit is provided in order for an error recovery
`
`between two RAID controllers 460, 461 , and the bandwidth between
`
`-19-
`
`Page 19 cf135
`
`
`
`two groups as the host computers 400 to 405 and two RAID
`
`controllers 460, 461 becomes twice the single connection bandwidth.
`
`Also, in the inventive host interface system, even though one RAID
`
`controller 460 or 461 has an occurrence of a trouble, the bandwidth
`
`becomes twice the single connection bandwidth. ‘346 Patent, Col. 3,
`
`ll.1-9)
`
`40.
`
`It is my opinion that a person of ordinary skill in the art at the time
`
`would have understood the broadest reasonable interpretation ofRAID controlling
`
`unit, in light of the present specification, to refer to “a functional component
`
`including hardware that may be controlled by computer code, the functional
`
`component providing control to implement RAID storage in an array of storage
`
`drives."
`
`RAID controller
`
`41.
`
`This term appears in claim 9. As I mentioned above, it is used in the
`
`specification, though neither defined nor narrowed.
`
`It should also be noted that
`
`RAID controller is used interchangeably with RAID controlling unit in claim 9
`
`(see, e.g., 6: 35—36—“second RAID controller"—and 6: 55-56—“second RAID
`
`controlling unit”). Furthermore. the file history shows at least one place where
`
`RAID controller and RAID controlling unit were used interchangeably by the
`
`applicant. See, e.g., Response to Office Action, Filed August 19, 2004, at the
`
`paragraph spanning pages 8-9 (paragraph uses both terms and makes no distinction
`
`20
`
`Page 20 of 185
`
`
`
`therebetween). With that in mind, it is my opinion that a person of ordinary skill in
`
`the art at the time would have understood the broadest reasonable interpretation of
`
`RAID controller, in light of the present specification, to be the same as RAID
`
`controlling um‘! (immediately above, “a functional component including hardware
`
`that may be controlled by computer code, the functional component providing
`
`control to implement RAID storage in an array of storage drives”).
`
`1
`
`42.
`
`This term appears in the preambles of claims 1 and 9. The term is
`
`also used in claim 9—“a plurality of connection units for connecting the host
`
`computers and the RAID; a first and a second RAID controllers, included in the
`
`RAID.” ‘346 Patent at 6:23-26. RAID is used in the specification to, e.g., refer to
`
`RAID 490 of Fig. 4. There is no one definition of the term that is agreed upon by
`
`everyone. To the contrary, RAID is used in a variety of different ways to refer to
`
`an array of disks and sometime an array of disks plus other components. As one
`
`example, the Abstract of the ‘346 patent defines RAID as “a redundant array of
`
`inexpensive disks," thereby referring only to the disks themselves. However, Fig.
`
`4 of the "346 patent shows RAID 490, which includes RAID controllers 460, 471,
`
`as well as hubs 440, 441. Also, claim 9 recites that the first and second RAID
`
`controllers are “included in the RAID." In other words, even the ‘346 patent is
`
`inconsistent about what a RAID is.
`
`-21-
`
`Page 21 at 185
`
`
`
`43.
`
`Dictionary definitions tend to also be somewhat inconsistent. The
`
`Microsofi Computer Dictionary, 4"‘ ed., 1999, provides the following definition of
`
`RAID that focuses on a method:
`
`RAID \rad\ n. Acronym for redundant array of independent disks
`
`(formerly called redundant array of inexpensive disks). A data
`
`storage method in which data, along with information used for error
`
`correction, such as parity bits or Hamming codes, is distributed among
`
`two or more hard disks in order to improve performance and
`
`reliability. The hard disk array is governed by array management
`
`software and a disk controller, which handles the error correction.
`
`RAID is generally used on network servers. Several defined levels of
`
`RAID offer differing trade-offs among access speed, reliability, and
`
`cost. See also disk controller, error-correction coding, Hamming code,
`
`hard disk, parity bit, server (definition 1).
`
`44.
`
`The cited art, Weygant, provides a definition of RAID that seems to
`
`focus on the disks themselves:
`
`RAID: RAID is an acronym for redundant array of inexpensive disks.
`
`A RAID device consists of a group of disks that can be configured in
`
`many ways, either as a single unit or in various combinations of
`
`striped and mirrored configurations. The types of configuration
`
`available are called RAID levels:
`
`° RAID 0: Disk striping.
`
`- RAID 1: Disk mirroring.
`
`- RAID 0/ I : Sector Interleaved groups of mirrored disks. Also called
`
`-22-
`
`Page 22 of 135
`
`
`
`RAID 1/0 or RAID 10
`
`- RAID 2: Multiple check disks using Hamming code.
`
`- RAID 3: Byte striped, single check disk using parity.
`
`- RAID 4: Block striped, single check disk using parity.
`
`- RAID 5: Block striped, data and parity spread over all disks.
`
`45. With these different definitions and uses in mind, it is my opinion that
`
`a person of ordinary skill in the art at the time would have understood the broadest
`
`reasonable interpretation of RAID, in light of the present specification, to refer to
`
`“at least a redundant array of independent disks."
`
`Challenge #1 - Claims 1-3, 5,and 8 are anticipated under 35 U.S.C. §
`
`l02[b[ over Weygant
`
`46.
`
`It is my opinion that Weygant anticipates claims 1-3, 5, and 8 of the
`
`‘346 patent.
`
`47. Weygant is a publication by I-lewlett—Packard Company, describing
`
`High Availability (HA) server cluster principles in the context of Hewlett-Packard
`
`Company’s UX operating system. Weygant discusses, among other things,
`
`systems having multiple server nodes where elimination of single points of failure
`
`is a goal. See, e.g., Chapter 2 of Weygant generally (discussing avoiding single
`
`points of failure). An example is the system shown in Figs. 2.10 and 2.12, where
`
`each node has redundant LAN interfaces (also referred to as “LAN cards“ in
`
`Weygant), and a given LAN interface can take over for another failed LAN
`
`-23-
`
`Page 23 of 185
`
`
`
`interface at its node. See, e.g., Weygant at p. 147, defi