HEWLETT PACKARD ENTERPRISE DEVELOPMENT LP

Patent Trials and Appeals Board

Jun 24, 2020

14483661 - (D) (P.T.A.B. Jun. 24, 2020)

UNITED STATES PATENT AND TRADEMARK OFFICE
UNITED STATES DEPARTMENT OF COMMERCE
United States Patent and Trademark Office
Address: COMMISSIONER FOR PATENTS
P.O. Box 1450
Alexandria, Virginia 22313-1450
www.uspto.gov
APPLICATION NO. FILING DATE FIRST NAMED INVENTOR ATTORNEY DOCKET NO. CONFIRMATION NO.
14/483,661 09/11/2014 Thomas A. Phelan 90737903 2210
56436 7590 06/24/2020
Hewlett Packard Enterprise
3404 E. Harmony Road
Mail Stop 79
Fort Collins, CO 80528
EXAMINER
KNIGHT, PAUL M
ART UNIT PAPER NUMBER
2139
NOTIFICATION DATE DELIVERY MODE
06/24/2020 ELECTRONIC
Please find below and/or attached an Office communication concerning this application or proceeding.
The time period for reply, if any, is set in the attached communication.
Notice of the Office communication was sent electronically on above-indicated "Notification Date" to the
following e-mail address(es):
chris.mania@hpe.com
hpe.ip.mail@hpe.com
PTOL-90A (Rev. 04/07)
UNITED STATES PATENT AND TRADEMARK OFFICE
BEFORE THE PATENT TRIAL AND APPEAL BOARD
Ex parte THOMAS A. PHELAN, MICHAEL J. MORETTI,
GUNASEELAN LAKSHMINARAYANAN, and
RAMASWAMI KISHORE
Appeal 2019-002346
Application 14/483,661
Technology Center 2100
Before MICHAEL J. STRAUSS, IRVIN E. BRANCH, and
DAVID J. CUTITTA II, Administrative Patent Judges.
STRAUSS, Administrative Patent Judge.
DECISION ON APPEAL1
STATEMENT OF THE CASE
Pursuant to 35 U.S.C. § 134(a), Appellant2 appeals from the
Examiner’s decision to reject claims 1, 3, 5, 7, 9, 10, 12, 14, 16, 18–22, and

1 We refer to the Specification, filed September 11, 2014 (“Spec.”); Final
Office Action, mailed February 22, 2018 (“Final Act.”); Appeal Brief, filed
September 24, 2018 (“Appeal Br.”); Examiner’s Answer, mailed November
30, 2018 (“Ans.”); and Reply Brief, filed January 30, 2019 (“Reply Br.”).
2 We use the word Appellant to refer to “applicant” as defined in 37 C.F.R.
§ 1.42. Appellant identifies the real party in interest as BLUEDATA
SOFTWARE, INC. Appeal Br. 2.
Appeal 2019-002346
Application 14/483,661
2
24–26. See Final Act. 1; Appeal Br. 2. Claims 2, 4, 6, 8, 11, 13, 15, 17, and
23 are canceled. Claims Appendix. We have jurisdiction under
35 U.S.C. § 6(b).
We AFFIRM.
CLAIMED SUBJECT MATTER
The claims are directed to allocating shared memory for a job based
on the quality of service determined for the job. Abstract. Claim 1,
reproduced below with claim element labels added in brackets and disputed
limitations emphasized in italics, is illustrative of the claimed subject matter:
1. A method of providing shared memory in a data processing
cluster environment, the data processing cluster environment
comprising a plurality of virtual machines executing on one or
more host computing systems, the method comprising:
[(i)] identifying a plurality of jobs to be processed by the
plurality of virtual machines, wherein the plurality of jobs
executes using a distributed data processing framework;
[(ii)] determining a quality of service for each job of the
plurality of jobs; and
[(iii)] assigning each of the plurality of jobs to one or more
virtual machines in the plurality of virtual machines based on the
quality of service for each of the plurality of jobs and a portion
size of the shared memory allocated to each of the plurality of
virtual machines,
[(iv)] wherein the plurality of virtual machines is allocated
various sized portions of the shared memory used to cache data
for the plurality of jobs, and
[(v)] wherein the shared memory comprises memory
accessible by the plurality of virtual machines and a cache
service shared by the plurality of virtual machines that caches
data for processing by the plurality of jobs.
Appeal 2019-002346
Application 14/483,661
3
REFERENCES
The prior art relied upon by the Examiner is:
Name Reference Date
Illikkal et al. (“Illikkal”)
Konik et al. (“Konik”)
US 2009/0006755 A1
US 2014/0173614 A1
Jan. 1, 2009
June 19, 2014
REJECTION
Claims 1, 3, 5, 7, 9, 10, 12, 14, 16, 18–22, and 24–26 are rejected
under 35 U.S.C. § 103 as being unpatentable over Illikkal and Konik. Final
Act. 2–14.
STANDARD OF REVIEW
We review the appealed rejection for error based upon the issues
identified by Appellant, and in light of the arguments and evidence produced
thereon. Ex parte Frye, 94 USPQ2d 1072, 1075 (BPAI 2010) (precedential).
OPINION
The Examiner finds the combination of Illikkal and Konik teaches or
suggests the subject matter of claim 1. Final Act. 2–7. The Examiner relies
on Illikkal for teaching the preamble and claim elements (i), (ii), (iv), and
(v). Id. The Examiner relies on the combination of Illikkal and Konik to
teach or suggest claim element (iii). Id. at 6 (“[T]he combination of [Illikkal
and Konik] teaches . . . assigning resources including memory based on
[quality of service] (Illikkal) as well as assigning tasks to [a virtual machine]
based on the [virtual machine]’s resources including memory (Konik).”).
The disputed limitation of claim element (iii) is “assigning each of the
plurality of jobs to one or more virtual machines in the plurality of virtual
machines based on . . . a portion size of the shared memory allocated to each
of the plurality of virtual machines.” Appeal Br. 7–8.
Appeal 2019-002346
Application 14/483,661
4
Konik’s disclosure of “[the] first virtual machine 150 calculates the
estimated times using the respective resources that are currently allocated to
other virtual machines, . . . [and] selects a selected virtual machine with the
smallest estimated time . . . ” is found to teach assigning a job to a virtual
machine based on the virtual machine’s allocated resources. See Final
Act. 5 (citing Konik ¶ 46). The virtual machine’s allocated resources are
found by the Examiner to include memory, because Konik discloses
“allocat[ing] resources (e.g., processor and/or memory) that will allow . . . to
complete the task [] before the expiration time . . . . In an embodiment, the
first virtual machine 150 calculates the amount of resources to allocate by
searching the history log 158 . . . .” Id. (citing ¶ 48) (emphasis omitted).
The Examiner cites Konik’s Figure 3 (id. (reproduced below)), which further
teaches the allocated resources for the virtual machines include memories of
various sizes. Konik Fig. 3, ¶ 38 (“The allocated memory field 318, in each
entry, specifies the amount of the memory 102 that is allocated to the virtual
machine 150 identified by the virtual machine identifier field 312.”).

Appeal 2019-002346
Application 14/483,661
5
Examples of Konik’s Virtual Machines with Allocated Resources
(Konik Fig. 3)

Appellant contends “[s]electing a virtual machine based on the
estimated time to complete a task[, as taught by Konik,] is neither equivalent
nor suggestive to identifying virtual machine(s) for processing jobs based on
a memory size allocated to the virtual machine, [as required by claim 1].”
Appeal Br. 7–8. Appellant argues “claim 1 is not directed at determining or
using processing times for any purpose.” Id. at 7. In particular, Appellant
argues, contrary to claim 1 and according to Konik, “a first virtual
machine[,] allocated a large amount of processing resources [and] a smaller
portion of cache memory[,]” may be selected over “other virtual machines
with a larger portion of cache memory,” because the estimated processing
time for the first virtual machine may be less. Id. at 8. That is, according to
Appellant, Konik’s selection of a virtual machine may not be determined
based exclusively on memory resources but may include additional factors.
The Examiner responds “Konik’s teaching of assigning tasks/jobs [to
a virtual machine] based on estimated time and estimating time based on
allocated memory resources [of the virtual machine] reads on the claimed
assigning tasks/jobs [to a virtual machine] based on allocated memory
resources [of the virtual machine].” Ans. 3 (emphasis omitted). In response
to Appellant’s contention that “claim 1 is not directed at determining or
using processing times for any purpose” (Appeal Br. 7), the Examiner
responds “a claim using ‘comprising’ as the transitional phrase does not
exclude unmentioned items [related to processing time] based on their
absence.” Ans. 7. That is, although claim 1 does not recite processing time
as a factor in assigning jobs, neither does it exclude time as a factor.
Appeal 2019-002346
Application 14/483,661
6
In response to Appellant’s argument that Konik fails to teach the
contested limitation of “assigning . . . based on . . . a portion size of the
shared memory,” because Konik does not teach that a larger portion of cache
memory allocated to a virtual machine necessarily leads to the virtual
machine being selected (See Appeal Br. 8), the Examiner finds Appellant’s
argument is not commensurate in scope with claim 1. See Ans. 7–8. In
particular, the Examiner finds “Appellant is conflating the claimed job
allocation ‘based on’ allocated memory, with a requirement that more jobs
be allocated to a system with more memory in all instances, which is not
claimed.” Id. at 7. The Examiner adds “[t]he claims do not contain
language requiring that allocated memory alone be determinative of job
allocation.” Id. at 8 (emphasis omitted).
Appellant replies “[w]hile the Examiner asserts that the memory may
play a factor in determining the estimated time in Konik, Konik neither
directly nor implicitly indicates that a memory portion size should be used in
selecting the virtual machine.” Reply Br. 2. In particular, Appellant argues
“Konik fails to teach that the quantity of memory would necessarily have
any effect on the estimated completion time for a task. In fact, in many
computing operations, the memory may not be a limitation for the task.” Id.
at 3.
Appellant further contends for the first time in the Reply Brief that
“Konik fails to teach or suggest a requirement [of claim 1] that the virtual
machines are allocated various sized portions of cache memory.” Id.
(emphasis added). Appellant also raises a new contention that “Konik fails
to teach or require that each of the virtual machines are allocated different
quantities of cache memory.” Id. (emphasis added.) In particular, Appellant
Appeal 2019-002346
Application 14/483,661
7
argues “if each of the virtual machines in Konik were allocated the same
amount of memory, a virtual machine may not be selected based on the
portion size of shared memory, as required by claim 1.” Id.
Appellant’s arguments are unpersuasive of reversible Examiner error.
We agree with the Examiner that Konik teaches “assigning tasks/jobs [to a
virtual machine] based on estimated time and estimating time based on
allocated memory resources [of the virtual machine].” Ans. 3; cf. Reply
Br. 2–3 (“In particular, Konik teaches determining an estimated time to
perform the task using [information about] the resources that are allocated to
the first virtual machine, wherein the resources may include processors and
memory.”). Based on these teachings, we agree with the Examiner that
Konik further teaches “assigning tasks/jobs [to a virtual machine] based on
allocated memory resources [of the virtual machine].” Ans. 3. Furthermore,
Konik’s allocated memory resources for virtual machines have various sizes.
Konik Fig. 3, ¶ 38 (disclosing memory allocations of .25, 1.25, .25, and 0 to
respective virtual machines VM A through VM D). The size/amount of
Konik’s allocated memories has an effect on the processing time for some
tasks. Konik ¶ 48 (“[A]llocate resources (e.g., processor and/or memory)
that will allow . . . to complete the task [] before the expiration time . . . .
[C]alculate[] the amount of resources to allocate by searching the history log
158 . . . .”). Therefore, Konik teaches or suggests assigning tasks/jobs [to a
virtual machine] based on the size of the allocated memory resources, which
influences the processing time of a task. Accordingly, we disagree with
Appellant’s contention that “Konik neither directly nor implicitly indicates
that a memory portion size should be used in selecting the virtual machine.”
Reply Br. 2.
Appeal 2019-002346
Application 14/483,661
8
Furthermore, Appellant’s argument that “Konik fails to teach that the
quantity of memory would necessarily have any effect on the estimated
completion time for a task” is unpersuasive. Id. at 3. The argument is not
commensurate in scope with claim 1. In particular, claim 1 recites
“assigning . . . based on . . . a portion size of the shared memory,” and it
does not require the portion size be solely determinative of the assignment.
Similarly unpersuasive is Appellant’s argument that Konik does not teach
that a larger portion of cache memory assigned to a virtual machine
necessarily leads to the virtual machine being selected. See Appeal Br. 8.
Again, the argument is not commensurate in scope with claim 1. We agree
with the Examiner “Appellant is conflating the claimed job allocation ‘based
on’ allocated memory, with a requirement that more jobs be allocated to a
system with more memory in all instances, which is not claimed.” Ans. 7.
In the Reply Brief, Appellant also argues for the first time that Konik
does not teach or suggest “a requirement [by claim 1] that the virtual
machines are allocated various sized portions of cache memory.” Reply
Br. 3. However, Appellant fails to show good cause for these new
arguments, and as such, Appellant’s belated argument is deemed waived as
untimely. 37 C.F.R. § 41.41(b)(2) (2016). See In re Hyatt, 211 F.3d 1367,
1373 (Fed. Cir. 2000) (noting that an argument not first raised in the brief to
the Board is waived on appeal); Ex parte Nakashima, 93 USPQ2d 1834,
1837 (BPAI 2010) (informative) (explaining that arguments and evidence
not timely presented in the principal Brief, will not be considered when filed
in a Reply Brief, absent a showing of good cause explaining why the
argument could not have been presented in the Principal Brief); Ex parte
Borden, 93 USPQ2d 1473, 1477 (BPAI 2010) (informative) (“[p]roperly
Appeal 2019-002346
Application 14/483,661
9
interpreted, the Rules do not require the Board to take up a belated argument
that has not been addressed by the Examiner, absent a showing of good
cause.”).
Nonetheless, Konik teaches various sized portions of the cache
memory allocated to a plurality of virtual machines. Konik Fig. 3, ¶ 38.
The Examiner also relies on Illikkal to teach “wherein the plurality of virtual
machines is allocated various sized portions of the shared memory used to
cache data for the plurality of jobs” (Final Act. 6–7), which is not disputed
by Appellant. Thus, even if timely presented, Appellant’s argument is
unpersuasive.
Appellant’s additional belatedly presented argument that “Konik fails
to teach or require that each of the virtual machines are allocated different
quantities of cache memory” (Reply Br. 3) is not commensurate in scope
with claim 1. In particular, claim 1 recites “wherein the plurality of virtual
machines is allocated various sized portions” and does not require each of
the virtual machines be allocated a different quantity of cache memory.
For the reasons discussed above, Appellant’s arguments are
unpersuasive of reversible Examiner error. Accordingly, we sustain the
rejection of claim 1 under 35 U.S.C. § 103. For the same reasons, we further
sustain the rejections of independent claims 10 and 21 that are argued
together with claim 1. Appeal Br. 8 (“Independent claims 10 and 21 contain
limitations like those discussed above with respect to claim 1.”). Further, we
sustain the rejections of dependent claims 3, 5, 7, 9, 12, 14, 16, 18–20, 22,
and 24–26, because they are not argued separately with particularity. See
Appeal Br. 8.
Appeal 2019-002346
Application 14/483,661
10
CONCLUSION
We affirm the rejection of claims 1, 3, 5, 7, 9, 10, 12, 14, 16, 18–22,
and 24–26 under 35 U.S.C. § 103.
DECISION SUMMARY
Claims
Rejected
35 U.S.C.
§
Reference(s)/Basis Affirmed Reversed
1, 3, 5, 7, 9,
10, 12, 14,
16, 18–22,
24–26
103 Illikkal, Konik 1, 3, 5, 7, 9,
10, 12, 14,
16, 18–22,
24–26

TIME PERIOD FOR RESPONSE
No time period for taking any subsequent action in connection with
this appeal may be extended under 37 C.F.R. § 1.136(a). See 37 C.F.R.
§ 1.136(a)(1)(iv).
AFFIRMED