U.S. patent application number 15/850325 was filed with the patent office on 2019-02-28 for technologies for auto-discovery of fault domains.
The applicant listed for this patent is Intel Corporation. Invention is credited to Anjaneya Reddy Chagam Reddy.
Application Number | 20190068466 15/850325 |
Document ID | / |
Family ID | 65434219 |
Filed Date | 2019-02-28 |
![](/patent/app/20190068466/US20190068466A1-20190228-D00000.png)
![](/patent/app/20190068466/US20190068466A1-20190228-D00001.png)
![](/patent/app/20190068466/US20190068466A1-20190228-D00002.png)
![](/patent/app/20190068466/US20190068466A1-20190228-D00003.png)
![](/patent/app/20190068466/US20190068466A1-20190228-D00004.png)
![](/patent/app/20190068466/US20190068466A1-20190228-D00005.png)
![](/patent/app/20190068466/US20190068466A1-20190228-D00006.png)
![](/patent/app/20190068466/US20190068466A1-20190228-D00007.png)
![](/patent/app/20190068466/US20190068466A1-20190228-D00008.png)
![](/patent/app/20190068466/US20190068466A1-20190228-D00009.png)
![](/patent/app/20190068466/US20190068466A1-20190228-D00010.png)
View All Diagrams
United States Patent
Application |
20190068466 |
Kind Code |
A1 |
Chagam Reddy; Anjaneya
Reddy |
February 28, 2019 |
TECHNOLOGIES FOR AUTO-DISCOVERY OF FAULT DOMAINS
Abstract
A compute device to auto-discover power system fault domains
within a computer network is provided. The compute device includes
a fault domain manager to receive sled data for at least one sled
of a plurality of sleds in the computer network, the sled data
including sled identification data and sled health data, parse the
sled identification data to identify at least one power zone
wherein each power zone includes a subset of the plurality of
sleds, generate a fault domain mapping using the at least one
identified power zone. The compute device also includes a
distributed processing adapter to convert the generated fault
domain mapping into a consumable fault domain mapping that is
consumable by a distributed processing software system, and provide
the consumable fault domain mapping to the distributed processing
software system.
Inventors: |
Chagam Reddy; Anjaneya Reddy;
(Chandler, AZ) |
|
Applicant: |
Name |
City |
State |
Country |
Type |
Intel Corporation |
Santa Clara |
CA |
US |
|
|
Family ID: |
65434219 |
Appl. No.: |
15/850325 |
Filed: |
December 21, 2017 |
Related U.S. Patent Documents
|
|
|
|
|
|
Application
Number |
Filing Date |
Patent Number |
|
|
62584401 |
Nov 10, 2017 |
|
|
|
Current U.S.
Class: |
1/1 |
Current CPC
Class: |
G06F 11/3442 20130101;
H04L 41/5025 20130101; H05K 7/1489 20130101; G06F 2201/885
20130101; H04L 49/40 20130101; H05K 7/1498 20130101; G06F 9/44
20130101; G06F 9/5061 20130101; B25J 15/0014 20130101; G06F 9/4856
20130101; G06F 1/20 20130101; G06F 11/3006 20130101; H04L 41/14
20130101; H04L 43/0876 20130101; G06F 9/505 20130101; G06F 13/4022
20130101; G06Q 30/0283 20130101; G06F 15/7867 20130101; H04L 43/065
20130101; H04L 63/0428 20130101; H05K 7/18 20130101; Y02D 30/00
20180101; G06F 1/183 20130101; G06Q 10/0631 20130101; H04L 41/0816
20130101; H04L 41/044 20130101; G06F 2201/86 20130101; G06F
2200/201 20130101; G06F 11/3409 20130101; H04L 41/0896 20130101;
Y02D 10/00 20180101; G06F 11/3466 20130101; G06F 21/105 20130101;
G06N 3/063 20130101; G06F 15/7807 20130101; G06F 9/5088 20130101;
H04L 41/5019 20130101; H04L 67/1008 20130101; H05K 7/20736
20130101; H04L 43/16 20130101 |
International
Class: |
H04L 12/26 20060101
H04L012/26; G06F 1/30 20060101 G06F001/30; G06F 1/18 20060101
G06F001/18 |
Foreign Application Data
Date |
Code |
Application Number |
Aug 30, 2017 |
IN |
201741030632 |
Claims
1. A compute device to auto-discover power system fault domains
within a computer network, the compute device comprising: one or
more processors; and one or more memory devices having stored
therein a plurality of instructions that, when executed by the one
or more processors, cause the compute device to: receive sled data
for at least one sled of a plurality of sleds in the computer
network, the sled data including sled identification data and sled
health data; parse the sled identification data to identify at
least one power zone wherein each power zone includes a subset of
the plurality of sleds; generate a fault domain mapping using the
at least one identified power zone; convert the generated fault
domain mapping into a consumable fault domain mapping that is
consumable by a distributed processing software system; and provide
the consumable fault domain mapping to the distributed processing
software system.
2. The compute device of claim 1, wherein to receive the sled data
comprises to receive an advertisement generated by the at least one
sled via a link layer discovery protocol (LLDP), wherein LLDP is
configured to identify one or more relationships between one or
more sleds of the plurality of sleds, and wherein the sled health
data includes one or more of a number of sockets, a number of
cores, a number of drives, a latency metric, a reliability metric,
and a memory capacity metric.
3. The compute device of claim 1, wherein the one or more memory
devices have stored therein a plurality of instructions that, when
executed by the one or more processors, further cause the compute
device to identify, within the sled identification data, a first
top-of-rack switch identifier for a first top-of-rack switch that
is communicatively coupled to the at least one sled of the
plurality of sleds.
4. The compute device of claim 3, wherein the one or more memory
devices have stored therein a plurality of instructions that, when
executed by the one or more processors, further cause the compute
device to identify, within the sled identification data, a second
top-of-rack switch identifier for a second top-of-rack switch that
is distinct from the first top-of-rack switch, wherein the
second-top-of-rack switch is communicatively coupled to the at
least one sled.
5. The compute device of claim 4, wherein the one or more memory
devices have stored therein a plurality of instructions that, when
executed by the one or more processors, further cause the compute
device to determine that the first top-of-rack switch and the
second top-of-rack switch are communicatively coupled to a rack
compute device.
6. The compute device of claim 5, wherein the one or more memory
devices have stored therein a plurality of instructions that, when
executed by the one or more processors, further cause the compute
device to determine that the rack compute device is communicatively
coupled to at least one power source device, wherein the at least
one power source device is associated with the at least one power
zone.
7. The compute device of claim 5, wherein the one or more memory
devices have stored therein a plurality of instructions that, when
executed by the one or more processors, further cause the compute
device to determine that the rack compute device is communicatively
coupled to at least one other power source device, wherein the at
least one other power source device is associated with at least one
other power zone.
8. The compute device of claim 1, wherein the computer network
includes a composed node, wherein the composed node includes the at
least one sled, and wherein the one or more memory devices have
stored therein a plurality of instructions that, when executed by
the one or more processors, further cause the compute device to:
determine that the at least one sled corresponds to the at least
one identified power zone; and identify that the composed node
corresponds to the at least one identified power zone within the
fault domain mapping.
9. The compute device of claim 1, wherein the one or more memory
devices have stored therein a plurality of instructions that, when
executed by the one or more processors, further cause the compute
device to identify, within the sled identification data, a
datacenter identifier for a datacenter, wherein the datacenter
includes at least one manager computer that manages at least one
sled of the plurality of sleds, and wherein the manager computer is
communicatively coupled to the at least one sled.
10. The compute device of claim 1, wherein the one or more memory
devices have stored therein a plurality of instructions that, when
executed by the one or more processors, further cause the compute
device to: determine a data format corresponding to the distributed
processing software system; select a plug-in application based on
the data format; and convert the generated fault domain mapping
into a consumable fault domain mapping by executing the selected
plug-in application.
11. The compute device of claim 1, wherein the distributed
processing software system includes at least one of Apache Hadoop,
Apache Cassandra, Ceph, and MongoDB.
12. One or more computer-readable storage media comprising a
plurality of instructions stored thereon that, when executed by a
compute device cause the compute device to: receive sled data for
at least one sled of a plurality of sleds in the computer network,
the sled data including sled identification data and sled health
data; parse the sled identification data to identify at least one
power zone wherein each power zone includes a subset of the
plurality of sleds; generate a fault domain mapping using the at
least one identified power zone; convert the generated fault domain
mapping into a consumable fault domain mapping that is consumable
by a distributed processing software system; and provide the
consumable fault domain mapping to the distributed processing
software system.
13. The one or more computer-readable storage media of claim 12,
wherein the plurality of instructions further cause the compute
device to receive an advertisement generated by the at least one
sled via a link layer discovery protocol (LLDP), wherein LLDP is
configured to identify one or more relationships between one or
more sleds of the plurality of sleds, and wherein the sled health
data includes one or more of a number of sockets, a number of
cores, a number of drives, a latency metric, a reliability metric,
and a memory capacity metric.
14. The one or more computer-readable storage media of claim 12,
further comprising a plurality of instructions stored thereon that,
when executed by the compute device cause the compute device to
identify, within the sled identification data, a first top-of-rack
switch identifier for a first top-of-rack switch that is
communicatively coupled to the at least one sled of the plurality
of sleds.
15. The one or more computer-readable storage media of claim 12,
further comprising a plurality of instructions stored thereon that,
when executed by the compute device cause the compute device to
identify, within the sled identification data, a second top-of-rack
switch identifier for a second top-of-rack switch that is distinct
from the first top-of-rack switch, wherein the second-top-of-rack
switch is communicatively coupled to the at least one sled.
16. The one or more computer-readable storage media of claim 15,
further comprising a plurality of instructions stored thereon that,
when executed by the compute device cause the compute device to
determine that the first top-of-rack switch and the second
top-of-rack switch are communicatively coupled to a rack compute
device.
17. The one or more computer-readable storage media of claim 16,
further comprising a plurality of instructions stored thereon that,
when executed by the compute device cause the compute device to
determine that the rack compute device is communicatively coupled
to at least one power source device, wherein the at least one power
source device is associated with the at least one power zone.
18. The one or more computer-readable storage media of claim 16,
further comprising a plurality of instructions stored thereon that,
when executed by the compute device cause the compute device to
determine that the rack compute device is communicatively coupled
to at least one other power source device, wherein the at least one
other power source device is associated with at least one other
power zone.
19. The one or more computer-readable storage media of claim 12,
wherein the computer network includes a composed node, wherein the
composed node includes the at least one sled, and further
comprising a plurality of instructions stored thereon that, when
executed by the compute device cause the compute device to:
determine that the at least one sled corresponds to the at least
one identified power zone; and identify that the composed node
corresponds to the at least one identified power zone within the
fault domain mapping.
20. The one or more computer-readable storage media of claim 12,
further comprising a plurality of instructions stored thereon that,
when executed by the compute device cause the compute device to
identify, within the sled identification data, a datacenter
identifier for a datacenter, wherein the datacenter includes at
least one manager computer that manages at least one sled of the
plurality of sleds, and wherein the manager computer is
communicatively coupled to the at least one sled.
21. The one or more computer-readable storage media of claim 12,
further comprising a plurality of instructions stored thereon that,
when executed by the compute device cause the compute device to:
determine a data format corresponding to the distributed processing
software system; select a plug-in application based on the data
format; and convert the generated fault domain mapping into a
consumable fault domain mapping by executing the selected plug-in
application.
22. The one or more computer-readable storage media of claim 12,
wherein the distributed processing software system includes at
least one of Apache Hadoop, Apache Cassandra, Ceph, and
MongoDB.
23. A compute device of automatically discovering power system
fault domains within a computer network, the compute device
comprising: circuitry for receiving sled data for at least one sled
of a plurality of sleds in the computer network, the sled data
including sled identification data and sled health data; means for
parsing the sled identification data to identify at least one power
zone wherein each power zone includes a subset of the plurality of
sleds; means for generating a fault domain mapping using the at
least one identified power zone; means for converting the generated
fault domain mapping into a consumable fault domain mapping that is
consumable by a distributed processing software system; and means
for providing the consumable fault domain mapping to the
distributed processing software system.
24. A method of automatically discovering power system fault
domains within a computer network, the method comprising: receiving
sled data for at least one sled of a plurality of sleds in the
computer network, the sled data including sled identification data
and sled health data; parsing the sled identification data to
identify at least one power zone wherein each power zone includes a
subset of the plurality of sleds; generating a fault domain mapping
using the at least one identified power zone; converting the
generated fault domain mapping into a consumable fault domain
mapping that is consumable by a distributed processing software
system; and providing the consumable fault domain mapping to the
distributed processing software system.
25. The method of claim 24, wherein the computer network includes a
composed node, wherein the composed node includes the at least one
sled, and further comprising: determining that the at least one
sled corresponds to the at least one identified power zone; and
identifying that the composed node corresponds to the at least one
identified power zone within the fault domain mapping.
26. The method of claim 24, further comprising: determining a data
format corresponding to the distributed processing software system;
selecting a plug-in application based on the data format; and
converting the generated fault domain mapping into a consumable
fault domain mapping by executing the selected plug-in application.
Description
CROSS-REFERENCE TO RELATED APPLICATIONS
[0001] The present application claims the benefit Indian
Provisional Patent Application No. 201741030632, filed Aug. 30,
2017, and U.S. Provisional Patent Application No. 62/584,401, filed
Nov. 10, 2017.
BACKGROUND
[0002] A cloud computing facility, data center, server farm, or any
similar large-scale computer architecture often includes a large
number of computer devices. These computer devices may be organized
in various ways. For example, based on connectivity or usage, these
computer devices will often be organized into groups by network
type, application type, or the like. Additionally, computer devices
have specific power requirements and are connected to one or more
power source devices. These power source devices may draw power
from various sources and may not all be interconnected. As a
result, groups of power source devices (sometimes referred to as
power zones) may be separate from other groups of power source
devices. In the event of a power outage or other power loss
incident, the impact on one power source device may affect multiple
connected computer devices. Known methods of maintaining an
inventory of connections between computer devices, network devices,
and power source devices include manual inventory of the computer
devices that are connected to each power source device. This manual
inventory may also be entered into a distributed data processing
framework that performs data replication and other data management
services for the computer devices.
BRIEF DESCRIPTION OF THE DRAWINGS
[0003] The concepts described herein are illustrated by way of
example and not by way of limitation in the accompanying figures.
For simplicity and clarity of illustration, elements illustrated in
the figures are not necessarily drawn to scale. Where considered
appropriate, reference labels have been repeated among the figures
to indicate corresponding or analogous elements.
[0004] FIG. 1 is a diagram of a conceptual overview of a data
center in which one or more techniques described herein may be
implemented according to various embodiments;
[0005] FIG. 2 is a diagram of an example embodiment of a logical
configuration of a rack of the data center of FIG. 1;
[0006] FIG. 3 is a diagram of an example embodiment of another data
center in which one or more techniques described herein may be
implemented according to various embodiments;
[0007] FIG. 4 is a diagram of another example embodiment of a data
center in which one or more techniques described herein may be
implemented according to various embodiments;
[0008] FIG. 5 is a diagram of a connectivity scheme representative
of link-layer connectivity that may be established among various
sleds of the data centers of FIGS. 1, 3, and 4;
[0009] FIG. 6 is a diagram of a rack architecture that may be
representative of an architecture of any particular one of the
racks depicted in FIGS. 1-4 according to some embodiments;
[0010] FIG. 7 is a diagram of an example embodiment of a sled that
may be used with the rack architecture of FIG. 6;
[0011] FIG. 8 is a diagram of an example embodiment of a rack
architecture to provide support for sleds featuring expansion
capabilities;
[0012] FIG. 9 is a diagram of an example embodiment of a rack
implemented according to the rack architecture of FIG. 8;
[0013] FIG. 10 is a diagram of an example embodiment of a sled
designed for use in conjunction with the rack of FIG. 9;
[0014] FIG. 11 is a diagram of an example embodiment of a data
center in which one or more techniques described herein may be
implemented according to various embodiments;
[0015] FIG. 12 is a simplified block diagram of at least one
embodiment of a compute device for automatic discovery of fault
domains;
[0016] FIG. 13 is a simplified block diagram of at least one
embodiment of an environment established by the compute device of
FIG. 12;
[0017] FIG. 14 is a simplified flow diagram of at least one
embodiment of a method for automatic discovery of fault domains
that may be executed by a sled shown in FIG. 16;
[0018] FIGS. 15 and 16 are a simplified flow diagram of at least
one embodiment of a method for automatic discovery of fault domains
that may be executed by the compute device of FIGS. 12-13; and
[0019] FIG. 17 is a diagram of a datacenter or computing network
that includes one or more sleds and other compute devices, any one
of which may perform a method for automatic discovery of fault
domains as shown in FIGS. 15 and 16.
DETAILED DESCRIPTION OF THE DRAWINGS
[0020] While the concepts of the present disclosure are susceptible
to various modifications and alternative forms, specific
embodiments thereof have been shown by way of example in the
drawings and will be described herein in detail. It should be
understood, however, that there is no intent to limit the concepts
of the present disclosure to the particular forms disclosed, but on
the contrary, the intention is to cover all modifications,
equivalents, and alternatives consistent with the present
disclosure and the appended claims.
[0021] References in the specification to "one embodiment," "an
embodiment," "an illustrative embodiment," etc., indicate that the
embodiment described may include a particular feature, structure,
or characteristic, but every embodiment may or may not necessarily
include that particular feature, structure, or characteristic.
Moreover, such phrases are not necessarily referring to the same
embodiment. Further, when a particular feature, structure, or
characteristic is described in connection with an embodiment, it is
submitted that it is within the knowledge of one skilled in the art
to effect such feature, structure, or characteristic in connection
with other embodiments whether or not explicitly described.
Additionally, it should be appreciated that items included in a
list in the form of "at least one A, B, and C" can mean (A); (B);
(C); (A and B); (A and C); (B and C); or (A, B, and C). Similarly,
items listed in the form of "at least one of A, B, or C" can mean
(A); (B); (C); (A and B); (A and C); (B and C); or (A, B, and
C).
[0022] The disclosed embodiments may be implemented, in some cases,
in hardware, firmware, software, or any combination thereof. The
disclosed embodiments may also be implemented as instructions
carried by or stored on a transitory or non-transitory
machine-readable (e.g., computer-readable) storage medium, which
may be read and executed by one or more processors. A
machine-readable storage medium may be embodied as any storage
device, mechanism, or other physical structure for storing or
transmitting information in a form readable by a machine (e.g., a
volatile or non-volatile memory, a media disc, or other media
device).
[0023] In the drawings, some structural or method features may be
shown in specific arrangements and/or orderings. However, it should
be appreciated that such specific arrangements and/or orderings may
not be required. Rather, in some embodiments, such features may be
arranged in a different manner and/or order than shown in the
illustrative figures. Additionally, the inclusion of a structural
or method feature in a particular figure is not meant to imply that
such feature is required in all embodiments and, in some
embodiments, may not be included or may be combined with other
features.
[0024] FIG. 1 illustrates a conceptual overview of a data center
100 that may generally be representative of a data center or other
type of computing network in/for which one or more techniques
described herein may be implemented according to various
embodiments. As shown in FIG. 1, data center 100 may generally
contain a plurality of racks, each of which may house computing
equipment comprising a respective set of physical resources. In the
particular non-limiting example depicted in FIG. 1, data center 100
contains four racks 102A to 102D, which house computing equipment
comprising respective sets of physical resources 105A to 105D.
According to this example, a collective set of physical resources
106 of data center 100 includes the various sets of physical
resources 105A to 105D that are distributed among racks 102A to
102D. Physical resources 106 may include resources of multiple
types, such as--for example--processors, co-processors,
accelerators, field-programmable gate arrays (FPGAs), memory, and
storage. The embodiments are not limited to these examples.
[0025] The illustrative data center 100 differs from typical data
centers in many ways. For example, in the illustrative embodiment,
the circuit boards ("sleds") on which components such as CPUs,
memory, and other components are placed are designed for increased
thermal performance In particular, in the illustrative embodiment,
the sleds are shallower than typical boards. In other words, the
sleds are shorter from the front to the back, where cooling fans
are located. This decreases the length of the path that air must to
travel across the components on the board. Further, the components
on the sled are spaced further apart than in typical circuit
boards, and the components are arranged to reduce or eliminate
shadowing (i.e., one component in the air flow path of another
component). In the illustrative embodiment, processing components
such as the processors are located on a top side of a sled while
near memory, such as dual inline memory modules (DIMMs), are
located on a bottom side of the sled. As a result of the enhanced
airflow provided by this design, the components may operate at
higher frequencies and power levels than in typical systems,
thereby increasing performance Furthermore, the sleds are
configured to blindly mate with power and data communication cables
in each rack 102A, 102B, 102C, 102D, enhancing their ability to be
quickly removed, upgraded, reinstalled, and/or replaced. Similarly,
individual components located on the sleds, such as processors,
accelerators, memory, and data storage drives, are configured to be
easily upgraded due to their increased spacing from each other. In
the illustrative embodiment, the components additionally include
hardware attestation features to prove their authenticity.
[0026] Furthermore, in the illustrative embodiment, the data center
100 utilizes a single network architecture ("fabric") that supports
multiple other network architectures including Ethernet and
Omni-Path. The sleds, in the illustrative embodiment, are coupled
to switches via optical fibers, which provide higher bandwidth and
lower latency than typical twisted pair cabling (e.g., Category 5,
Category 5e, Category 6, etc.). Due to the high bandwidth, low
latency interconnections and network architecture, the data center
100 may, in use, pool resources, such as memory, accelerators
(e.g., graphics accelerators, FPGAs, application-specific
integrated circuits (ASICs), etc.), and data storage drives that
are physically disaggregated, and provide them to compute resources
(e.g., processors) on an as needed basis, enabling the compute
resources to access the pooled resources as if they were local. The
illustrative data center 100 additionally receives usage
information for the various resources, predicts resource usage for
different types of workloads based on past resource usage, and
dynamically reallocates the resources based on this
information.
[0027] The racks 102A, 102B, 102C, 102D of the data center 100 may
include physical design features that facilitate the automation of
a variety of types of maintenance tasks. For example, data center
100 may be implemented using racks that are designed to be
robotically-accessed, and to accept and house
robotically-manipulatable resource sleds. Furthermore, in the
illustrative embodiment, the racks 102A, 102B, 102C, 102D include
integrated power sources that receive a greater voltage than is
typical for power sources. The increased voltage enables the power
sources to provide additional power to the components on each sled,
enabling the components to operate at higher than typical
frequencies.
[0028] FIG. 2 illustrates an exemplary logical configuration of a
rack 202 of the data center 100. As shown in FIG. 2, rack 202 may
generally house a plurality of sleds, each of which may comprise a
respective set of physical resources. In the particular
non-limiting example depicted in FIG. 2, rack 202 houses sleds
204-1 to 204-4 comprising respective sets of physical resources
205-1 to 205-4, each of which constitutes a portion of the
collective set of physical resources 206 comprised in rack 202.
With respect to FIG. 1, if rack 202 is representative of--for
example--rack 102A, then physical resources 206 may correspond to
the physical resources 105A comprised in rack 102A. In the context
of this example, physical resources 105A may thus be made up of the
respective sets of physical resources, including physical storage
resources 205-1, physical accelerator resources 205-2, physical
memory resources 205-3, and physical compute resources 205-5
comprised in the sleds 204-1 to 204-4 of rack 202. The embodiments
are not limited to this example. Each sled may contain a pool of
each of the various types of physical resources (e.g., compute,
memory, accelerator, storage). By having robotically accessible and
robotically manipulatable sleds comprising disaggregated resources,
each type of resource can be upgraded independently of each other
and at their own optimized refresh rate.
[0029] FIG. 3 illustrates an example of a data center 300 that may
generally be representative of one in/for which one or more
techniques described herein may be implemented according to various
embodiments. In the particular non-limiting example depicted in
FIG. 3, data center 300 comprises racks 302-1 to 302-32. In various
embodiments, the racks of data center 300 may be arranged in such
fashion as to define and/or accommodate various access pathways.
For example, as shown in FIG. 3, the racks of data center 300 may
be arranged in such fashion as to define and/or accommodate access
pathways 311A, 311B, 311C, and 311D. In some embodiments, the
presence of such access pathways may generally enable automated
maintenance equipment, such as robotic maintenance equipment, to
physically access the computing equipment housed in the various
racks of data center 300 and perform automated maintenance tasks
(e.g., replace a failed sled, upgrade a sled). In various
embodiments, the dimensions of access pathways 311A, 311B, 311C,
and 311D, the dimensions of racks 302-1 to 302-32, and/or one or
more other aspects of the physical layout of data center 300 may be
selected to facilitate such automated operations. The embodiments
are not limited in this context.
[0030] FIG. 4 illustrates an example of a data center 400 that may
generally be representative of one in/for which one or more
techniques described herein may be implemented according to various
embodiments. As shown in FIG. 4, data center 400 may feature an
optical fabric 412. Optical fabric 412 may generally comprise a
combination of optical signaling media (such as optical cabling)
and optical switching infrastructure via which any particular sled
in data center 400 can send signals to (and receive signals from)
each of the other sleds in data center 400. The signaling
connectivity that optical fabric 412 provides to any given sled may
include connectivity both to other sleds in a same rack and sleds
in other racks. In the particular non-limiting example depicted in
FIG. 4, data center 400 includes four racks 402A to 402D. Racks
402A to 402D house respective pairs of sleds 404A-1 and 404A-2,
404B-1 and 404B-2, 404C-1 and 404C-2, and 404D-1 and 404D-2. Thus,
in this example, data center 400 comprises a total of eight sleds.
Via optical fabric 412, each such sled may possess signaling
connectivity with each of the seven other sleds in data center 400.
For example, via optical fabric 412, sled 404A-1 in rack 402A may
possess signaling connectivity with sled 404A-2 in rack 402A, as
well as the six other sleds 404B-1, 404B-2, 404C-1, 404C-2, 404D-1,
and 404D-2 that are distributed among the other racks 402B, 402C,
and 402D of data center 400. The embodiments are not limited to
this example.
[0031] FIG. 5 illustrates an overview of a connectivity scheme 500
that may generally be representative of link-layer connectivity
that may be established in some embodiments among the various sleds
of a data center, such as any of example data centers 100, 300, and
400 of FIGS. 1, 3, and 4. Connectivity scheme 500 may be
implemented using an optical fabric that features a dual-mode
optical switching infrastructure 514. Dual-mode optical switching
infrastructure 514 may generally comprise a switching
infrastructure that is capable of receiving communications
according to multiple link-layer protocols via a same unified set
of optical signaling media, and properly switching such
communications. In various embodiments, dual-mode optical switching
infrastructure 514 may be implemented using one or more dual-mode
optical switches 515. In various embodiments, dual-mode optical
switches 515 may generally comprise high-radix switches. In some
embodiments, dual-mode optical switches 515 may comprise multi-ply
switches, such as four-ply switches. In various embodiments,
dual-mode optical switches 515 may feature integrated silicon
photonics that enable them to switch communications with
significantly reduced latency in comparison to conventional
switching devices. In some embodiments, dual-mode optical switches
515 may constitute leaf switches 530 in a leaf-spine architecture
additionally including one or more dual-mode optical spine switches
520.
[0032] In various embodiments, dual-mode optical switches may be
capable of receiving both Ethernet protocol communications carrying
Internet Protocol (IP packets) and communications according to a
second, high-performance computing (HPC) link-layer protocol (e.g.,
Intel's Omni-Path Architecture's, Infiniband) via optical signaling
media of an optical fabric. As reflected in FIG. 5, with respect to
any particular pair of sleds 504A and 504B possessing optical
signaling connectivity to the optical fabric, connectivity scheme
500 may thus provide support for link-layer connectivity via both
Ethernet links and HPC links. Thus, both Ethernet and HPC
communications can be supported by a single high-bandwidth,
low-latency switch fabric. The embodiments are not limited to this
example.
[0033] FIG. 6 illustrates a general overview of a rack architecture
600 that may be representative of an architecture of any particular
one of the racks depicted in FIGS. 1 to 4 according to some
embodiments. As reflected in FIG. 6, rack architecture 600 may
generally feature a plurality of sled spaces into which sleds may
be inserted, each of which may be robotically-accessible via a rack
access region 601. In the particular non-limiting example depicted
in FIG. 6, rack architecture 600 features five sled spaces 603-1 to
603-5. Sled spaces 603-1 to 603-5 feature respective multi-purpose
connector modules (MPCMs) 616-1 to 616-5.
[0034] FIG. 7 illustrates an example of a sled 704 that may be
representative of a sled of such a type. As shown in FIG. 7, sled
704 may comprise a set of physical resources 705, as well as an
MPCM 716 designed to couple with a counterpart MPCM when sled 704
is inserted into a sled space such as any of sled spaces 603-1 to
603-5 of FIG. 6. Sled 704 may also feature an expansion connector
717. Expansion connector 717 may generally comprise a socket, slot,
or other type of connection element that is capable of accepting
one or more types of expansion modules, such as an expansion sled
718. By coupling with a counterpart connector on expansion sled
718, expansion connector 717 may provide physical resources 705
with access to supplemental computing resources 705B residing on
expansion sled 718. The embodiments are not limited in this
context.
[0035] FIG. 8 illustrates an example of a rack architecture 800
that may be representative of a rack architecture that may be
implemented in order to provide support for sleds featuring
expansion capabilities, such as sled 704 of FIG. 7. In the
particular non-limiting example depicted in FIG. 8, rack
architecture 800 includes seven sled spaces 803-1 to 803-7, which
feature respective MPCMs 816-1 to 816-7. Sled spaces 803-1 to 803-7
include respective primary regions 803-1A to 803-7A and respective
expansion regions 803-1B to 803-7B. With respect to each such sled
space, when the corresponding MPCM is coupled with a counterpart
MPCM of an inserted sled, the primary region may generally
constitute a region of the sled space that physically accommodates
the inserted sled. The expansion region may generally constitute a
region of the sled space that can physically accommodate an
expansion module, such as expansion sled 718 of FIG. 7, in the
event that the inserted sled is configured with such a module.
[0036] FIG. 9 illustrates an example of a rack 902 that may be
representative of a rack implemented according to rack architecture
800 of FIG. 8 according to some embodiments. In the particular
non-limiting example depicted in FIG. 9, rack 902 features seven
sled spaces 903-1 to 903-7, which include respective primary
regions 903-1A to 903-7A and respective expansion regions 903-1B to
903-7B. In various embodiments, temperature control in rack 902 may
be implemented using an air cooling system. For example, as
reflected in FIG. 9, rack 902 may feature a plurality of fans 919
that are generally arranged to provide air cooling within the
various sled spaces 903-1 to 903-7. In some embodiments, the height
of the sled space is greater than the conventional "1U" server
height. In such embodiments, fans 919 may generally comprise
relatively slow, large diameter cooling fans as compared to fans
used in conventional rack configurations. Running larger diameter
cooling fans at lower speeds may increase fan lifetime relative to
smaller diameter cooling fans running at higher speeds while still
providing the same amount of cooling. The sleds are physically
shallower than conventional rack dimensions. Further, components
are arranged on each sled to reduce thermal shadowing (i.e., not
arranged serially in the direction of air flow). As a result, the
wider, shallower sleds allow for an increase in device performance
because the devices can be operated at a higher thermal envelope
(e.g., 250 W) due to improved cooling (i.e., no thermal shadowing,
more space between devices, more room for larger heat sinks,
etc.).
[0037] MPCMs 916-1 to 916-7 may be configured to provide inserted
sleds with access to power sourced by respective power modules
920-1 to 920-7, each of which may draw power from an external power
source 921. In various embodiments, external power source 921 may
deliver alternating current (AC) power to rack 902, and power
modules 920-1 to 920-7 may be configured to convert such AC power
to direct current (DC) power to be sourced to inserted sleds. In
some embodiments, for example, power modules 920-1 to 920-7 may be
configured to convert 277-volt AC power into 12-volt DC power for
provision to inserted sleds via respective MPCMs 916-1 to 916-7.
The embodiments are not limited to this example.
[0038] MPCMs 916-1 to 916-7 may also be arranged to provide
inserted sleds with optical signaling connectivity to a dual-mode
optical switching infrastructure 914, which may be the same as--or
similar to--dual-mode optical switching infrastructure 514 of FIG.
5. In various embodiments, optical connectors contained in MPCMs
916-1 to 916-7 may be designed to couple with counterpart optical
connectors contained in MPCMs of inserted sleds to provide such
sleds with optical signaling connectivity to dual-mode optical
switching infrastructure 914 via respective lengths of optical
cabling 922-1 to 922-7. In some embodiments, each such length of
optical cabling may extend from its corresponding MPCM to an
optical interconnect loom 923 that is external to the sled spaces
of rack 902. In various embodiments, optical interconnect loom 923
may be arranged to pass through a support post or other type of
load-bearing element of rack 902. The embodiments are not limited
in this context. Because inserted sleds connect to an optical
switching infrastructure via MPCMs, the resources typically spent
in manually configuring the rack cabling to accommodate a newly
inserted sled can be saved.
[0039] FIG. 10 illustrates an example of a sled 1004 that may be
representative of a sled designed for use in conjunction with rack
902 of FIG. 9 according to some embodiments. Sled 1004 may feature
an MPCM 1016 that comprises an optical connector 1016A and a power
connector 1016B, and that is designed to couple with a counterpart
MPCM of a sled space in conjunction with insertion of MPCM 1016
into that sled space. Coupling MPCM 1016 with such a counterpart
MPCM may cause power connector 1016 to couple with a power
connector comprised in the counterpart MPCM. This may generally
enable physical resources 1005 of sled 1004 to source power from an
external source, via power connector 1016 and power transmission
media 1024 that conductively couples power connector 1016 to
physical resources 1005.
[0040] Sled 1004 may also include dual-mode optical network
interface circuitry 1026. Dual-mode optical network interface
circuitry 1026 may generally comprise circuitry that is capable of
communicating over optical signaling media according to each of
multiple link-layer protocols supported by dual-mode optical
switching infrastructure 914 of FIG. 9. In some embodiments,
dual-mode optical network interface circuitry 1026 may be capable
both of Ethernet protocol communications and of communications
according to a second, high-performance protocol. In various
embodiments, dual-mode optical network interface circuitry 1026 may
include one or more optical transceiver modules 1027, each of which
may be capable of transmitting and receiving optical signals over
each of one or more optical channels. The embodiments are not
limited in this context.
[0041] Coupling MPCM 1016 with a counterpart MPCM of a sled space
in a given rack may cause optical connector 1016A to couple with an
optical connector comprised in the counterpart MPCM. This may
generally establish optical connectivity between optical cabling of
the sled and dual-mode optical network interface circuitry 1026,
via each of a set of optical channels 1025. Dual-mode optical
network interface circuitry 1026 may communicate with the physical
resources 1005 of sled 1004 via electrical signaling media 1028. In
addition to the dimensions of the sleds and arrangement of
components on the sleds to provide improved cooling and enable
operation at a relatively higher thermal envelope (e.g., 250 W), as
described above with reference to FIG. 9, in some embodiments, a
sled may include one or more additional features to facilitate air
cooling, such as a heat pipe and/or heat sinks arranged to
dissipate heat generated by physical resources 1005. It is worthy
of note that although the example sled 1004 depicted in FIG. 10
does not feature an expansion connector, any given sled that
features the design elements of sled 1004 may also feature an
expansion connector according to some embodiments. The embodiments
are not limited in this context.
[0042] FIG. 11 illustrates an example of a data center 1100 that
may generally be representative of one in/for which one or more
techniques described herein may be implemented according to various
embodiments. As reflected in FIG. 11, a physical infrastructure
management framework 1150A may be implemented to facilitate
management of a physical infrastructure 1100A of data center 1100.
In various embodiments, one function of physical infrastructure
management framework 1150A may be to manage automated maintenance
functions within data center 1100, such as the use of robotic
maintenance equipment to service computing equipment within
physical infrastructure 1100A. In some embodiments, physical
infrastructure 1100A may feature an advanced telemetry system that
performs telemetry reporting that is sufficiently robust to support
remote automated management of physical infrastructure 1100A. In
various embodiments, telemetry information provided by such an
advanced telemetry system may support features such as failure
prediction/prevention capabilities and capacity planning
capabilities. In some embodiments, physical infrastructure
management framework 1150A may also be configured to manage
authentication of physical infrastructure components using hardware
attestation techniques. For example, robots may verify the
authenticity of components before installation by analyzing
information collected from a radio frequency identification (RFID)
tag associated with each component to be installed. The embodiments
are not limited in this context.
[0043] As shown in FIG. 11, the physical infrastructure 1100A of
data center 1100 may comprise an optical fabric 1112, which may
include a dual-mode optical switching infrastructure 1114. Optical
fabric 1112 and dual-mode optical switching infrastructure 1114 may
be the same as--or similar to--optical fabric 412 of FIG. 4 and
dual-mode optical switching infrastructure 514 of FIG. 5,
respectively, and may provide high-bandwidth, low-latency,
multi-protocol connectivity among sleds of data center 1100. As
discussed above, with reference to FIG. 1, in various embodiments,
the availability of such connectivity may make it feasible to
disaggregate and dynamically pool resources such as accelerators,
memory, and storage. In some embodiments, for example, one or more
pooled accelerator sleds 1130 may be included among the physical
infrastructure 1100A of data center 1100, each of which may
comprise a pool of accelerator resources--such as co-processors
and/or FPGAs, for example--that is globally accessible to other
sleds via optical fabric 1112 and dual-mode optical switching
infrastructure 1114.
[0044] In another example, in various embodiments, one or more
pooled storage sleds 1132 may be included among the physical
infrastructure 1100A of data center 1100, each of which may
comprise a pool of storage resources that is available globally
accessible to other sleds via optical fabric 1112 and dual-mode
optical switching infrastructure 1114. In some embodiments, such
pooled storage sleds 1132 may comprise pools of solid-state storage
devices such as solid-state drives (SSDs). In various embodiments,
one or more high-performance processing sleds 1134 may be included
among the physical infrastructure 1100A of data center 1100. In
some embodiments, high-performance processing sleds 1134 may
comprise pools of high-performance processors, as well as cooling
features that enhance air cooling to yield a higher thermal
envelope of up to 250 W or more. In various embodiments, any given
high-performance processing sled 1134 may feature an expansion
connector 1117 that can accept a far memory expansion sled, such
that the far memory that is locally available to that
high-performance processing sled 1134 is disaggregated from the
processors and near memory comprised on that sled. In some
embodiments, such a high-performance processing sled 1134 may be
configured with far memory using an expansion sled that comprises
low-latency SSD storage. The optical infrastructure allows for
compute resources on one sled to utilize remote accelerator/FPGA,
memory, and/or SSD resources that are disaggregated on a sled
located on the same rack or any other rack in the data center. The
remote resources can be located one switch jump away or two-switch
jumps away in the spine-leaf network architecture described above
with reference to FIG. 5. The embodiments are not limited in this
context.
[0045] In various embodiments, one or more layers of abstraction
may be applied to the physical resources of physical infrastructure
1100A in order to define a virtual infrastructure, such as a
software-defined infrastructure 1100B. In some embodiments, virtual
computing resources 1136 of software-defined infrastructure 1100B
may be allocated to support the provision of cloud services 1140.
In various embodiments, particular sets of virtual computing
resources 1136 may be grouped for provision to cloud services 1140
in the form of SDI services 1138. Examples of cloud services 1140
may include--without limitation--software as a service (SaaS)
services 1142, platform as a service (PaaS) services 1144, and
infrastructure as a service (IaaS) services 1146.
[0046] In some embodiments, management of software-defined
infrastructure 1100B may be conducted using a virtual
infrastructure management framework 1150B. In various embodiments,
virtual infrastructure management framework 1150B may be designed
to implement workload fingerprinting techniques and/or
machine-learning techniques in conjunction with managing allocation
of virtual computing resources 1136 and/or SDI services 1138 to
cloud services 1140. In some embodiments, virtual infrastructure
management framework 1150B may use/consult telemetry data in
conjunction with performing such resource allocation. In various
embodiments, an application/service management framework 1150C may
be implemented in order to provide quality of service (QoS)
management capabilities for cloud services 1140. The embodiments
are not limited in this context.
[0047] Referring now to FIG. 12, an illustrative compute device
1200 for automatic discovery of fault domains includes a processor
1220, an input/output (I/O) subsystem 1222, a memory 1224, and a
data storage device 1226. The compute device 1200 may be embodied
as server computer, a rack server, a blade server, a compute node,
and/or a sled in a data center, such as a sled 204 as described
above in connection with FIG. 2, a sled of the physical
infrastructure 1100A as described above in connection with FIG. 11,
or another sled of the data center.
[0048] The processor 1220 may be embodied as any type of processor
capable of performing the functions described herein. For example,
the processor 1220 may be embodied as a single or multi-core
processor(s), digital signal processor, microcontroller, or other
processor or processing/controlling circuit. Similarly, the memory
1224 may be embodied as any type of volatile or non-volatile memory
or data storage capable of performing the functions described
herein. In operation, the memory 1224 may store various data and
software used during operation of the compute device 1200 such
operating systems, applications, programs, libraries, and drivers.
The memory 1224 is communicatively coupled to the processor 1220
via the I/O subsystem 1222, which may be embodied as circuitry
and/or components to facilitate input/output operations with the
processor 1220, the memory 1224, and other components of the
compute device 1200. For example, the I/O subsystem 1222 may be
embodied as, or otherwise include, memory controller hubs,
input/output control hubs, sensor hubs, firmware devices,
communication links (i.e., point-to-point links, bus links, wires,
cables, light guides, printed circuit board traces, etc.) and/or
other components and subsystems to facilitate the input/output
operations. In some embodiments, the I/O subsystem 1222 may form a
portion of a system-on-a-chip (SoC) and be incorporated, along with
the processor 1220, the memory 1224, and other components of the
compute device 1200, on a single integrated circuit chip.
[0049] The data storage device 1226 may be embodied as any type of
device or devices configured for short-term or long-term storage of
data such as, for example, memory devices and circuits, memory
cards, hard disk drives, solid-state drives, non-volatile flash
memory, or other data storage devices. The compute device 1200 may
also include a communications circuitry 1228, which may be embodied
as any communication circuit, device, or collection thereof,
capable of enabling communications between the compute device 1200
and other remote devices over a computer network (not shown). The
communications circuitry 1228 may be configured to use any one or
more communication technology (e.g., wired or wireless
communications) and associated protocols (e.g., Ethernet,
InfiniBand.RTM., Bluetooth.RTM., Wi-Fi.RTM., WiMAX, 3G, 4G LTE,
etc.) to effect such communication.
[0050] The compute device 1200 may further include one or more
peripheral devices 1232. The peripheral devices 1232 may include
any number of additional input/output devices, interface devices,
hardware accelerators, and/or other peripheral devices. For
example, in some embodiments, the peripheral devices 1232 may
include a touch screen, graphics circuitry, a graphical processing
unit (GPU) and/or processor graphics, an audio device, a
microphone, a camera, a keyboard, a mouse, a network interface,
and/or other input/output devices, interface devices, and/or
peripheral devices.
[0051] Referring now to FIG. 13, the compute device 1200 may
establish an environment 1300 during operation. The illustrative
environment 1300 includes a fault domain manager 1302 and a
distributed processing adapter 1304. Each of the components of the
environment 1300 may be embodied as hardware, firmware, software,
or a combination thereof. As such, in some embodiments, one or more
of the components of the environment 1300 may be embodied as
circuitry or a collection of electrical devices (e.g., fault domain
manager 1302 circuitry and distributed processing adapter 1304
circuitry, etc.). It should be appreciated that, in such
embodiments, one or more of the fault domain manager 1302 circuitry
and distributed processing adapter 1304 circuitry may form a
portion of one or more of the compute device 1200, the
communication circuitry 1228, the I/O subsystem 1222, and/or other
components of the compute device 1200.
[0052] Additionally, the illustrative environment 1300 includes
fault domain data 1306 which may be embodied as any data indicative
of rack data, datacenter manager computer data, network
connectivity data, power source device data, power zone data, or
the like. The illustrative environment 1300 further includes sled
data 1308, which may be embodied as any data indicative of sled
identification data, which may further include data regarding
compute devices connected to a particular sled (e.g., a sled 1718
as described in greater detail below with respect to FIG. 17). For
example, sled identification data may include identifiers for power
source devices, rack compute devices, top-of-rack switch devices,
and any other devices directly or indirectly connected to a sled.
Sled identification data may further include data regarding sled
capabilities, manufacturer and device type/class identifiers, or
the like. Sled data may further include sled health data. In the
illustrative embodiment, sled health data may be embodied as any
data indicative of a number of sockets, a number of cores, a number
of drives, a latency metric, a reliability metric, and a memory
capacity metric associated with the sled. Sled health data may also
be embodied as any data indicative of other metrics such as sled
performance data, sled performance history data, or the like.
[0053] In addition, both sled identification data and sled health
data may be embodied as any data indicative or particular qualities
or capabilities of the sled. For example, sled data for a compute
sled may be embodied as any data indicative of a number of sockets,
a number of cores, speed, memory types, memory modes, memory
capacity and memory performance, NIC data or the like for the
compute sled. Similarly, sled data for a storage sled may be
embodied as any data indicative of a number of drives, drive
information (e.g. performance, latency, bandwidth}, capacity,
endurance, reliability (e.g., replication metrics), security, or
the like. Sled data for an accelerator sled may be embodied as any
data indicative of a number of accelerator devices (e.g., ASICs,
FPGAs), accelerator device performance, an accelerator gate count,
identifiers related to bitstreams of data input or output from the
accelerator device, network address data, health data, or the like.
Sled data for a network sled may be embodied as any data indicative
of a number of ports, per port performance, network configuration,
port connectivity, health data, or the like.
[0054] In the illustrative environment 1300, the fault domain
manager 1302, which may be embodied as hardware, firmware,
software, virtualized hardware, emulated architecture, and/or a
combination thereof as discussed above, is configured to receive
sled data for at least one sled in a computer network. For example,
the fault domain manager 1302 may receive sled data for one of the
sleds 1716 that are described in greater detail below with respect
to FIG. 17. As described herein, sled data may include one or more
of sled identification data and sled health data. In the
illustrative embodiment, the fault domain manager 1302 receives
sled data each time a sled boots up. For example, each sled may be
configured to transmit sled data to a connected fault domain
manager 1302 at boot time. In the illustrative embodiment, the sled
employs the link layer discovery protocol (LLDP) to generate sled
data information. As used herein, LLDP refers to a network protocol
that can be used by a device to advertise its identity,
capabilities, and neighbors. When activated, LLDP is used by a
device to send messages (also referred as advertisements) that
include data that may be sent in the form of an Ethernet frame.
Each frame contains one LLDP Data Unit (LLDPDU). Each LLDPDU is a
sequence of type-length-value (TLV) structures. In the illustrative
embodiment, the LLDP is extended to enable a sled to provide sled
data as described herein. Accordingly, the fault domain manager
1302 is configured to receive one or more LLDPUs, some of which
will contain one or more items of sled data as described above.
[0055] The fault domain manager 1302 is also configured to parse
the sled identification data to identify a power zone. A datacenter
may be organized into one or more power zones, each of which may
include a group of power source devices (e.g., main power lines,
unlimited power supply devices, backup generator devices, or the
like). Additionally, each power zone is associated with one or more
sleds (e.g., power zone A 1710 as described below with respect to
FIG. 17). One power zone may be associated with multiple sleds. In
other words, power source devices grouped into one power zone may
be supplying power services to multiple sleds. Accordingly, the
fault domain manager 1302 identifies and stores data regarding the
power zone associated with a sled. In the illustrative embodiment,
the fault domain manager receives sled data for multiple sleds and
parses sled identification data for each sled. The fault domain
manager 1302 is also configured to collate or otherwise group sleds
by power zone identifier. For example, the fault domain manager
1302 is configured to group all sleds that are associated with a
particular power zone. The fault domain manager 1302 is configured
to perform this discovery process for each sled for which sled data
is available.
[0056] Using the collated sled data and power zone identifier data
generated from the parsing, the fault domain manager 1302 is also
configured to generate a fault domain mapping using the identified
power zone. More specifically, the fault domain manager 1302
generates a fault domain mapping that includes the power zone. A
fault domain may describe the structure or organization of the
group of compute devices that are associated with a particular
power zone. The fault domain may include rack devices, switch
devices, power source devices, and sleds. Accordingly, the fault
domain mapping may be embodied as any data indicative of
interconnections between rack devices, switch devices, power source
devices, and sleds. For example, the sled identification data may
be embodied as any data indicative of the top-of-rack switches that
a sled is connected to, as well as the rack device(s) that each of
the identified top-of-rack switches is connected to.
[0057] The fault domain manager 1302 is also configured to store
the generated fault domain mapping in a data structure. For
example, the fault domain manager 1302 may store the fault domain
mapping in a tree structure, with a power zone identifier
represented by a root or parent node with rack devices represented
as child nodes, switches represented as child nodes of the rack
device nodes, and sleds represented as child nodes of the switch
device nodes. As another example, the fault domain manager 1302 may
store the fault domain mapping in a graph database, with each
device stored as a node object and relationship data stored in edge
objects (e.g., top-of-rack switch X connects to sled Y and sled
Z).
[0058] The distributed processing adapter 1304, which may be
embodied as hardware, firmware, software, virtualized hardware,
emulated architecture, and/or a combination thereof, is configured
to convert the generated fault domain mapping into a consumable
fault domain mapping that is consumable by a distributed processing
software system (sometimes also referred to as a "distributed
storage software system"). More specifically, the distributed
processing adapter adapts the fault domain mapping data (e.g., that
is stored in a data structure as described above) and
programmatically converts into a particular format. The format may
be determined based on the target distributed processing software
system.
[0059] As used herein, "distributed processing software system"
refers to any software or software framework used for distributed
storage and processing of large datasets. Frequently, a distributed
processing software system includes a storage component, one that
may be embodied as a distributed file system, for example. Also, a
distributed processing software system includes a processing
component to process the data from the file system. For example, a
programming model and/or schema may be provided that provides
interfaces for object-, block- and file-level storage. Distributed
processing software systems often enable processing of large
datasets by distributing the large dataset into smaller chunks
across multiple processing nodes, delivering packaged processing
code to those nodes, and processing these chunks in parallel. One
example of a distributed processing software system is Apache
Hadoop.RTM. (APACHE and HADOOP are registered trademarks of the
Apache Software Foundation, located at Forest Hill, Md., USA). As
an example, a Hadoop distributed file system may be able to consume
the fault domain mapping data if it is formatted for consumption by
code written in the Java.RTM. programming language (JAVA is a
registered trademark of the Oracle Corporation, located at Redwood
Shores, Redwood City, Calif., USA). Accordingly, the distributed
processing adapter 1304 formats the fault domain mapping data into
a format consumable by a Hadoop architecture. After conversion, the
distributed processing adapter 1304 provides the fault domain
mapping to the distributed processing software system.
[0060] Another example of a distributed processing software system
is Ceph (CEPH is a registered trademark of Red Hat Inc., located at
Raleigh, N.C., USA). Yet another example of a distributed
processing software system is Cassandra (CASSANDRA is a registered
trademark of Apache Software Foundation, located at Forest Hill,
Md., USA). Yet another example of a distributed processing software
system is MongoDB (MONGODB is a registered trademark of MongoDB
Inc., located at Palo Alto, Calif., United States).
[0061] It should be appreciated that each of the fault domain
manager 1302 and the distributed processing adapter 1304 may be
separately embodied as hardware, firmware, software, virtualized
hardware, emulated architecture, and/or a combination thereof. For
example, the distributed processing adapter 1304 may be embodied as
a hardware component, while the fault domain manager 1302 is
embodied as a virtualized hardware component or as some other
combination of hardware, firmware, software, virtualized hardware,
emulated architecture, and/or a combination thereof. Further it
should be appreciated that in some embodiments, a sled 1718 (as
described in greater detail below with respect to FIG. 17) may
establish an environment similar to the environment 1300 described
above.
[0062] Referring now to FIG. 14, in use, a sled 1718 may execute a
method 1400 for automatic discovery of fault domains. More
specifically, FIG. 14 describes the processes a sled 1718 executes
to generate sled data that will later be used by, for example, the
fault domain manager 1302. The method 1400 begins in block 1402, in
which the sled 1718 initiates a sled boot process. In the
illustrative embodiment, the sled 1718 is configured to, for
example, initiate loading of operating system program loading, as
in block 1404.
[0063] In block 1406, the sled 1718 performs a sled data discovery
process. In the illustrative embodiment, sled data discovery is
performed using an LLDP protocol extension. As described above,
LLDP is used to transmit advertisements by a device including data
regarding the device's identity, capabilities, neighbors, and the
like. Accordingly, in block 1408, the sled 1718 discovers its
capabilities (for example, those described above with respect to
sled identification data and sled health data). In block 1410, the
sled 1718 discovers the sled 1718's position (e.g., with respect to
other sleds and other devices). For example, the sled 1718 may be a
member of a group of compute sleds, accelerator sleds, or other
sleds loaded in a single rack. In addition to determining its
neighbors, in block 1412, the sled 1718 discovers the rack
device(s), switch device(s), and power source devices that it is
directly or indirectly connected to. In one embodiment, the sled
1718 queries connected devices with specific queries regarding
rack, switch, and power source devices that are associated with the
sled 1718. In other embodiments, the sled 1718 itself may receive,
for example, LLDP advertisements that bear identification data for
other devices. For example, a rack device may send the sled 1718 an
LLDP advertisement indicating to the sled 1718 that the sled 1718
is connected to that rack device.
[0064] Relatedly, in block 1414, the sled 1718 is configured to
perform discovery protocols (e.g., LLDP) across switch domains. For
example, the sled 1718 may be configured to receive advertisements
from specific devices. Additionally, a compute device may be
configured during installation to transmit data to a specific sled
(or any compute device). Using the example of LLDP, the LLDP
protocol (which may be disabled by default) will be activated on a
specific compute device. As an example, the compute device (e.g., a
rack device) may be configured during installation to transmit
periodic LLDP advertisements to all connected switch devices, which
are, in turn, configured during installation to transmit periodic
LLDP advertisements to all connected sleds. Referring now to FIG.
17, a diagram 1700 illustrates a potential connectivity between
rack devices, switch devices, and sleds. This connectivity may be
advertised to a particular sled 1718 using the methods illustrated
above.
[0065] In block 1416, the sled 1718 transmits the discovered sled
data to a fault domain manager 1302. It should be appreciated that,
in some embodiments, the fault domain manager 1302 may be a
sub-component of the sled 1718 that is executing method 1400. As a
result, the generated sled data will be passed to the fault domain
manager 1302 of the sled 1718. In other embodiments, the fault
domain manager 1302 may be a component of another sled or compute
device, in which case the sled 1718 transmits the generated sled
data to the remote fault domain manager 1302 located on another
compute device.
[0066] Referring now to FIG. 15, in use, the compute device 1200
may execute a method 1500 for automatic discovery of fault domains.
It should be appreciated that, in some embodiments, the operations
of the method 1500 may be performed by one or more components of
the compute device 1200 as shown in FIG. 13, such as a processor
1220. More specifically, the processor 1220 may execute (in
hardware or software) at least one of the fault domain manager 1302
and the distributed processing adapter 1304. The method 1500 may
also be performed by one or more components of a sled 1718 as shown
in FIG. 17.
[0067] The method 1500 begins in block 1502, in which the compute
device 1200 checks for sled boot up. As described above, method
1500 may be performed by a sled 1718 which in turn detects whether
it has been booted up. If method 1500 is performed by another
compute device 1200, the compute device 1200 is configured to check
monitoring applications that monitor sled activity and transmit
alerts to the compute device 1200, as shown in block 1504. In block
1506, the compute device 1200 receives sled boot up confirmation
(e.g., directly from a sled 1718 or from a monitoring application).
In block 1508, the compute device 1200 receives sled data from a
sled 1718. Referring now to FIG. 17, a diagram 1700 illustrates one
potential computing network in which multiple sleds are
interconnected with various other types of devices. Any one of the
devices illustrated in FIG. 17 may represent the compute device
1200 and may perform method 1500 and receive sled data for one or
more of sleds 1718.
[0068] Referring back to FIG. 15, in block 1510, the compute device
1200 receives sled identification data (as described above with
respect to sled data 1308). Similarly, in block 1512, the compute
device 1200 receives sled health data (as described above with
respect to sled data 1308). In block 1514, the compute device 1200
parses sled data to identify at least one power zone corresponding
to the sled 1718. More specifically, the compute device 1200
identifies at least one rack device, switch device, and/or power
source device connected directly or indirectly to the sled 1718. If
the sled data is transmitted, for example, as an LLDP
advertisement, the compute device 1200 is configured to parse the
sled data by reading each LLDPU and extracting one or more
type-length-value structures (TLVs) inside the LLDPU that represent
one or more items of sled data. For example, one TLV may be (2: 9
bits: 1234), where type 2 represents the data type (e.g., Port ID),
length 9 bits represents the length of the value, and 1234
represents the value itself (e.g., a port identifier for a port
associated with a sled 1718).
[0069] The compute device 1200 is also configured to parse specific
types of incoming sled data. In the illustrative embodiment, in
block 1516, the compute device 1200 parses storage sled data, which
may be embodied as any data indicative of a number of drives, drive
information (e.g. performance, latency, bandwidth), capacity,
endurance, reliability (e.g., replication metrics), security, or
the like. In block 1518, the compute device 1200 parses compute
sled data, which may be embodied as any data indicative of a number
of sockets, a number of cores, speed, memory types, memory modes,
memory capacity and memory performance, NIC data or the like. In
block 1520, the compute device 1200 parses accelerator sled data,
which may be embodied as any data indicative of a number of
accelerator devices (e.g., ASICs, FPGAs), accelerator device
performance, an accelerator gate count, identifiers related to
bitstreams of data input or output from the accelerator device,
network address data, health data, or the like.
[0070] In block 1522, the compute device 1200 identifies a rack
device associated with the sled 1718 based on the sled
identification data. In the illustrative embodiment, the compute
device 1200 may determine the rack device from sled data received
directly from the sled 1718. In another embodiment, the compute
device 1200 may determine the rack device from sled data received
from another device connected to the sled 1718 (e.g., a top-of-rack
switch device). In some embodiments, for example, the compute
device 1200 uses an LLDP extension to enable the native LLDP
protocol to include an optional TLV that bears data regarding the
rack device associated with the sled 1718.
[0071] In block 1524, the compute device 1200 identifies a manager
computer associated with the sled 1718 based on sled identification
data. In the illustrative embodiment, a manager computer is any
compute device (e.g., an orchestrator server or resource manager
computer) that manages one or more power zones (or one or more rack
devices in conjunction with other devices). In the illustrative
embodiment, the compute device 1200 may determine the manager
computer from sled data received directly from the sled 1718. In
another embodiment, the compute device 1200 may determine the
manager computer from sled data received from another device
connected to the sled 1718 (e.g., a top-of-rack switch device). In
the illustrative embodiment, for example, the compute device 1200
uses an LLDP extension to enable the native LLDP protocol to
include an optional TLV that bears data regarding the manager
computer associated with the sled 1718.
[0072] The method 1500 continues at block 1526, where the compute
device 1200 determines a switch that is associated with a rack
device for a rack which the sled 1718 is located or otherwise
associated with the sled 1718. In one embodiment, the sled 1718 may
be part of a group of sleds that are located within a rack where
the sleds are connected to computers outside the rack using a
top-of-rack switch device 1716. In block 1528, the compute device
1200 identifies power source device based on the determined
top-of-rack switch device 1716. In block 1530, the compute device
1200 determines whether there are additional sleds for which sled
data is available. If there are more sleds for which sled data is
available, the method returns to block 1508 to receive more sled
data. If there are no more sleds for which sled data is available,
the method advances to block 1532, shown in FIG. 16.
[0073] Referring now to FIG. 17, a diagram 1700 illustrates one
potential computing network in which multiple sleds are
interconnected with various other types of devices. As shown, a
logical root is connected to one or more datacenters 1704. More
specifically, the root 1702 may be a system operator's computer, a
mainframe computer used to manage a large number of compute
devices, or the like. Each datacenter 1704 may also be thought of
as one or more manager computers as described above with respect to
block 1524. A datacenter 1704 is connected to one or more power
zones 1706, 1708, 1710, 1712. As described above, each power zone
represents a collection of power source devices (e.g., main power
lines, unlimited power supply devices, backup generator devices, or
the like) that is in turn connected to one or more rack devices
1714. Each rack device is connected to one or more switches 1716,
represented herein as top-of-rack switches 1716. Each top-of-rack
switch 1716 is connected to one or more sleds 1718 (which may be
placed inside or associated with a rack device 1714). FIG. 17 also
illustrates a fault domain 1722. The fault domain 1722 may be
embodied as any data indicative of a subset of the computing
network. The fault domain 1722 may be defined as the group of
devices that rely on the same power zone 1706 (which may include
various power source devices). This reliance may be represented by
an understanding that, were one or more of the power source devices
in power zone 1706 to fail or experience a fault, the issue would
be likely to affect one or more other devices in the fault domain
1722 (e.g., racks, switches, or sleds) but would leave devices
outside the fault domain 1722 unaffected. Moreover, a composed node
1720 is shown as a combination of one or more sleds 1718, where
each sled may perform specific functions. In the case of a composed
node, sleds 1718 may be selected across fault domains. For example,
one sled in the composition may be a compute sled from one fault
domain, another an accelerator sled from another fault domain, and
so on. As a result, the illustrative embodiment provides a
virtual-to-physical topology that represents the connectivity and,
relatedly, the power zone for a composed node 1720.
[0074] Referring now to FIG. 16, in use, the compute device 1200
continues to execute the method 1500 for automatic discovery of
fault domains. The method 1500 continues at block 1532, in which
the compute device 1200 generates a fault domain mapping based on
the sled data. More specifically, and referring to block 1534, the
compute device 1200 generates the fault domain mapping based on
switch data. For example, switch data for each sled 1718 is
collated by sled and the sleds connected to each switch (e.g., a
top-of-rack switch in a rack) are stored in a data structure (e.g.,
a tree or graph) in association with an identifier for the switch.
In block 1536, the compute device 1200 generates the fault domain
mapping based on power source device data. Power source device data
(or power zone data) for each sled 1718 is collated by sled and an
identifier for a power source device (e.g., an AC power source) is
stored in a data structure (e.g., a tree or graph) in association
with each connected sled. In block 1538, the compute device 1200
generates the fault domain mapping based on rack data. For example,
an identifier for the rack device 1714 that holds the sled is
stored in a data structure (e.g., a tree or graph) in association
with identifiers for the sled. In block 1540, the compute device
1200 generates the fault domain mapping based on manager computer
data. For example, an identifier for the manager computer of a
datacenter 1704 that manages the sled is stored in a data structure
(e.g., a tree or graph) in association with identifiers for the
sled.
[0075] In block 1542, the compute device 1200 collates the power
source device identifiers to determine the group of sleds
associated with the same power zone. In the illustrative
embodiment, each power source device may supply power across rack
domains and across switch domains. Grouping sleds by power zone may
generate a fault domain 1722, as illustrated in FIG. 17. The
compute device proceeds to generate a fault domain for each sled
and complete a fault domain mapping that includes each fault
domain.
[0076] In block 1544, the compute device 1200 may programmatically
convert the fault domain mapping into a consumable fault domain
mapping. More specifically, the consumable fault domain mapping is
configured to be consumed by a distributed data processing software
system, as described above with respect to FIG. 13. In the
illustrative embodiment, as shown in block 1546, the compute device
1200 stores the software performing the conversion in the form of a
plug-in application. When a particular distributed data processing
software system is the target for the consumable fault domain
mapping, the compute device 1200 selects the plug-in application
that corresponds to the targeted distributed data processing
software system and uses that plug-in application to perform the
conversion. For example, the plug-in applications for each
distributed data processing software system may be components of
the distributed processing adapter 1304. Thus, the fault domain
discovery process of the compute device 1200 may be adapted to
multiple data processing software systems.
[0077] Relatedly, in block 1548, the compute device 1200 converts a
fault domain mapping for a composed node. As described above with
respect to FIG. 17 sleds 1718 may be selected across fault domains
in the case of a composed node. Accordingly, the consumable fault
domain mapping reflects the cross-domain sled composition of the
composed node. In block 1550, the compute device 1200 transmits the
converted fault domain mapping to distributed data processing
software. In a related embodiment, as shown in block 1552, the
compute device 1200 may expose the converted fault domain mapping
to distributed data processing software using an API. The
distributed data processing software may use the fault domain
mapping information, for example, to distribute application data to
multiple fault domains or to otherwise improve fault tolerance.
After providing the fault domain mapping to the data processing
software system, the method 1500 loops back to block 1502, shown in
FIG. 15, to continue generating fault domain mappings.
EXAMPLES
[0078] Illustrative examples of the technologies disclosed herein
are provided below. An embodiment of the technologies may include
any one or more, and any combination of, the examples described
below.
[0079] Example 1 includes a compute device to auto-discover power
system fault domains within a computer network, the compute device
comprising: one or more processors; and one or more memory devices
having stored therein a plurality of instructions that, when
executed by the one or more processors, cause the compute device
to: receive sled data for at least one sled of a plurality of sleds
in the computer network, the sled data including sled
identification data and sled health data; parse the sled
identification data to identify at least one power zone wherein
each power zone includes a subset of the plurality of sleds;
generate a fault domain mapping using the at least one identified
power zone; convert the generated fault domain mapping into a
consumable fault domain mapping that is consumable by a distributed
processing software system; and provide the consumable fault domain
mapping to the distributed processing software system.
[0080] Example 2 includes the subject matter of Example 1, and
wherein to receive the sled data comprises to receive an
advertisement generated by the at least one sled via a link layer
discovery protocol (LLDP), wherein LLDP is configured to identify
one or more relationships between one or more sleds of the
plurality of sleds, and wherein the sled health data includes one
or more of a number of sockets, a number of cores, a number of
drives, a latency metric, a reliability metric, and a memory
capacity metric.
[0081] Example 3 includes the subject matter of any of Examples 1
and 2, and wherein the one or more memory devices have stored
therein a plurality of instructions that, when executed by the one
or more processors, further cause the compute device to identify,
within the sled identification data, a first top-of-rack switch
identifier for a first top-of-rack switch that is communicatively
coupled to the at least one sled of the plurality of sleds.
[0082] Example 4 includes the subject matter of any of Examples
1-3, and wherein the one or more memory devices have stored therein
a plurality of instructions that, when executed by the one or more
processors, further cause the compute device to identify, within
the sled identification data, a second top-of-rack switch
identifier for a second top-of-rack switch that is distinct from
the first top-of-rack switch, wherein the second-top-of-rack switch
is communicatively coupled to the at least one sled.
[0083] Example 5 includes the subject matter of any of Examples
1-4, and wherein the one or more memory devices have stored therein
a plurality of instructions that, when executed by the one or more
processors, further cause the compute device to determine that the
first top-of-rack switch and the second top-of-rack switch are
communicatively coupled to a rack compute device.
[0084] Example 6 includes the subject matter of any of Examples
1-5, and wherein the one or more memory devices have stored therein
a plurality of instructions that, when executed by the one or more
processors, further cause the compute device to determine that the
rack compute device is communicatively coupled to at least one
power source device, wherein the at least one power source device
is associated with the at least one power zone.
[0085] Example 7 includes the subject matter of any of Examples
1-6, and wherein the one or more memory devices have stored therein
a plurality of instructions that, when executed by the one or more
processors, further cause the compute device to determine that the
rack compute device is communicatively coupled to at least one
other power source device, wherein the at least one other power
source device is associated with at least one other power zone.
[0086] Example 8 includes the subject matter of any of Examples
1-7, and wherein the computer network includes a composed node,
wherein the composed node includes the at least one sled, and
wherein the one or more memory devices have stored therein a
plurality of instructions that, when executed by the one or more
processors, further cause the compute device to: determine that the
at least one sled corresponds to the at least one identified power
zone; and identify that the composed node corresponds to the at
least one identified power zone within the fault domain
mapping.
[0087] Example 9 includes the subject matter of any of Examples
1-8, and wherein the one or more memory devices have stored therein
a plurality of instructions that, when executed by the one or more
processors, further cause the compute device to identify, within
the sled identification data, a datacenter identifier for a
datacenter, wherein the datacenter includes at least one manager
computer that manages at least one sled of the plurality of sleds,
and wherein the manager computer is communicatively coupled to the
at least one sled.
[0088] Example 10 includes the subject matter of any of Examples
1-9, and wherein the one or more memory devices have stored therein
a plurality of instructions that, when executed by the one or more
processors, further cause the compute device to: determine a data
format corresponding to the distributed processing software system;
select a plug-in application based on the data format; and convert
the generated fault domain mapping into a consumable fault domain
mapping by executing the selected plug-in application.
[0089] Example 11 includes the subject matter of any of Examples
1-10, and wherein the distributed processing software system
includes at least one of Apache Hadoop, Apache Cassandra, Ceph, and
MongoDB.
[0090] Example 12 includes a compute sled to transmit sled data to
a fault domain manager within a computer network, the compute sled
comprising: one or more processors; and one or more memory devices
having stored therein a plurality of instructions that, when
executed by the one or more processors, cause the compute sled to:
initiate a boot process for the compute sled; discover sled data,
wherein the sled data includes sled identification data and sled
health data, wherein to discover the sled identification data
comprises to identify a first top-of-rack switch, wherein the first
top-of-rack switch is communicatively coupled to the compute sled;
generate an advertisement that includes the sled data, wherein the
advertisement is configured to identify at least one relationship
between the compute sled and at least one other compute sled within
the computer network; and transmit the sled data to the fault
domain manager.
[0091] Example 13 includes the subject matter of Example 12,
wherein to initiate the boot process comprises to initiate an
operating system program load process.
[0092] Example 14 includes the subject matter of any of Examples 12
and 13, wherein to discover the sled data includes to discover,
within the sled identification data, a second top-of-rack switch
identifier for a second top-of-rack switch that is distinct from
the first top-of-rack switch, wherein the second-top-of-rack switch
is communicatively coupled to the compute sled.
[0093] Example 15 includes the subject matter of any of Examples
12-14, wherein the first top-of-rack switch and the second
top-of-rack switch are communicatively coupled to a rack compute
device.
[0094] Example 16 includes the subject matter of any of Examples
12-15, wherein the rack compute device is communicatively coupled
to at least one power source device, wherein the at least one power
source device is associated with at least one power zone.
[0095] Example 17 includes the subject matter of any of Examples
12-16, wherein the rack compute device is communicatively coupled
to at least one other power source device, wherein the at least one
other power source device is associated with at least one other
power zone.
[0096] Example 18 includes the subject matter of any of Examples
12-17, wherein to discover the sled data includes to discover,
within the sled identification data, sled identification data
further includes a datacenter identifier for a datacenter, wherein
the datacenter includes at least one manager computer that manages
at least one sled of the plurality of sleds, and wherein the
manager computer is communicatively coupled to the at least one
sled.
[0097] Example 19 includes the subject matter of any of Examples
12-18, wherein the sled health data includes one or more of a
number of sockets, a number of cores, a number of drives, a latency
metric, a reliability metric, and a memory capacity metric.
[0098] Example 20 includes the subject matter of any of Examples
12-19, wherein to generate the advertisement comprises to generate
the advertisement using a link layer discovery protocol (LLDP).
[0099] Example 21 includes a method of automatically discovering
power system fault domains within a computer network, the method
comprising: receiving sled data for at least one sled of a
plurality of sleds in the computer network, the sled data including
sled identification data and sled health data; parsing the sled
identification data to identify at least one power zone wherein
each power zone includes a subset of the plurality of sleds;
generating a fault domain mapping using the at least one identified
power zone; converting the generated fault domain mapping into a
consumable fault domain mapping that is consumable by a distributed
processing software system; and providing the consumable fault
domain mapping to the distributed processing software system.
[0100] Example 22 includes the subject matter of Example 21, and
further comprising receiving sled data by an advertisement
generated by the at least one sled via a link layer discovery
protocol (LLDP), wherein LLDP is configured to identify one or more
relationships between one or more sleds of the plurality of sleds,
and wherein the sled health data includes one or more of a number
of sockets, a number of cores, a number of drives, a latency
metric, a reliability metric, and a memory capacity metric.
[0101] Example 23 includes the subject matter of any of Examples 21
and 22, and further comprising identifying, within the sled
identification data, a first top-of-rack switch identifier for a
first top-of-rack switch that is communicatively coupled to the at
least one sled of the plurality of sleds.
[0102] Example 24 includes the subject matter of any of Examples
21-23, and further comprising identifying, within the sled
identification data, a second top-of-rack switch identifier for a
second top-of-rack switch that is distinct from the first
top-of-rack switch, wherein the second-top-of-rack switch is
communicatively coupled to the at least one sled.
[0103] Example 25 includes the subject matter of any of Examples
21-24, and further comprising determining that the first
top-of-rack switch and the second top-of-rack switch are
communicatively coupled to a rack compute device.
[0104] Example 26 includes the subject matter of any of Examples
21-25, and further comprising determining that the rack compute
device is communicatively coupled to at least one power source
device, wherein the at least one power source device is associated
with the at least one power zone.
[0105] Example 27 includes the subject matter of any of Examples
21-26, and further comprising determining that the rack compute
device is communicatively coupled to at least one other power
source device, wherein the at least one other power source device
is associated with at least one other power zone.
[0106] Example 28 includes the subject matter of any of Examples
21-27, and wherein the computer network includes a composed node,
wherein the composed node includes the at least one sled, and
further comprising: determining that the at least one sled
corresponds to the at least one identified power zone; and
identifying that the composed node corresponds to the at least one
identified power zone within the fault domain mapping.
[0107] Example 29 includes the subject matter of any of Examples
21-28, and further comprising identifying, within the sled
identification data, a datacenter identifier for a datacenter,
wherein the datacenter includes at least one manager computer that
manages at least one sled of the plurality of sleds, and wherein
the manager computer is communicatively coupled to the at least one
sled.
[0108] Example 30 includes the subject matter of any of Examples
21-29, and further comprising: determining a data format
corresponding to the distributed processing software system;
selecting a plug-in application based on the data format; and
converting the generated fault domain mapping into a consumable
fault domain mapping by executing the selected plug-in
application.
[0109] Example 31 includes the subject matter of any of Examples
21-30, and wherein the distributed processing software system
includes at least one of Apache Hadoop, Apache Cassandra, Ceph, and
MongoDB.
[0110] Example 32 includes a method of transmitting sled data to a
fault domain manager within a computer network, the method
comprising: initiating, by a compute sled, a boot process for the
compute sled; discovering, by the compute sled, sled data, wherein
the sled data includes sled identification data and sled health
data, wherein to discover the sled identification data comprises to
identify a first top-of-rack switch, wherein the first top-of-rack
switch is communicatively coupled to the compute sled; generating,
by the compute sled, an advertisement that includes the sled data,
wherein the advertisement is configured to identify at least one
relationship between the compute sled and at least one other
compute sled within the computer network; and transmitting, by the
compute sled, the sled data to the fault domain manager.
[0111] Example 33 includes the subject matter of Example 32, and
wherein initiating the boot process comprises initiating initiate
an operating system program load process.
[0112] Example 34 includes the subject matter of any of Examples 32
and 33, and wherein discovering the sled data includes discovering,
within the sled identification data, a second top-of-rack switch
identifier for a second top-of-rack switch that is distinct from
the first top-of-rack switch, wherein the second-top-of-rack switch
is communicatively coupled to the compute sled.
[0113] Example 35 includes the subject matter of any of Examples
32-34, and wherein the first top-of-rack switch and the second
top-of-rack switch are communicatively coupled to a rack compute
device.
[0114] Example 36 includes the subject matter of any of Examples
32-35, and wherein the rack compute device is communicatively
coupled to at least one power source device, wherein the at least
one power source device is associated with at least one power
zone.
[0115] Example 37 includes the subject matter of any of Examples
32-36, and wherein the rack compute device is communicatively
coupled to at least one other power source device, wherein the at
least one other power source device is associated with at least one
other power zone.
[0116] Example 38 includes the subject matter of any of Examples
32-37, and wherein discovering the sled data includes discovering,
within the sled identification data, sled identification data
further includes a datacenter identifier for a datacenter, wherein
the datacenter includes at least one manager computer that manages
at least one sled of the plurality of sleds, and wherein the
manager computer is communicatively coupled to the at least one
sled.
[0117] Example 39 includes the subject matter of any of Examples
32-38, and wherein the sled health data includes one or more of a
number of sockets, a number of cores, a number of drives, a latency
metric, a reliability metric, and a memory capacity metric.
[0118] Example 40 includes the subject matter of any of Examples
32-39, and wherein generating the advertisement comprises
generating the advertisement using a link layer discovery protocol
(LLDP).
[0119] Example 41 includes a computing device comprising: a
processor; and a memory having stored therein a plurality of
instructions that when executed by the processor cause the
computing device to perform the method of any of Examples
21-40.
[0120] Example 42 includes one or more non-transitory, computer
readable storage media comprising a plurality of instructions
stored thereon that in response to being executed result in a
computing device performing the method of any of Examples
21-40.
[0121] Example 43 includes a computing device comprising means for
performing the method of any of Examples 21-40.
[0122] Example 44 includes a compute device to auto-discover power
system fault domains within a computer network, the compute device
comprising: fault domain manager circuitry to: receive sled data
for at least one sled of a plurality of sleds in the computer
network, the sled data including sled identification data and sled
health data; parse the sled identification data to identify at
least one power zone wherein each power zone includes a subset of
the plurality of sleds; generate a fault domain mapping using the
at least one identified power zone; and distributed processing
adapter circuitry to: convert the generated fault domain mapping
into a consumable fault domain mapping that is consumable by a
distributed processing software system; and provide the consumable
fault domain mapping to the distributed processing software
system.
[0123] Example 45 includes the subject matter of Example 44, and
wherein to receive the sled data comprises to receive an
advertisement generated by the at least one sled via a link layer
discovery protocol (LLDP), wherein LLDP is configured to identify
one or more relationships between one or more sleds of the
plurality of sleds, and wherein the sled health data includes one
or more of a number of sockets, a number of cores, a number of
drives, a latency metric, a reliability metric, and a memory
capacity metric.
[0124] Example 46 includes the subject matter of any of Examples 44
and 45, and wherein the fault domain manager circuitry is further
to identify, within the sled identification data, a first
top-of-rack switch identifier for a first top-of-rack switch that
is communicatively coupled to the at least one sled of the
plurality of sleds.
[0125] Example 47 includes the subject matter of any of Examples
44-46, and wherein the fault domain manager circuitry is further to
identify, within the sled identification data, a second top-of-rack
switch identifier for a second top-of-rack switch that is distinct
from the first top-of-rack switch, wherein the second-top-of-rack
switch is communicatively coupled to the at least one sled.
[0126] Example 48 includes the subject matter of any of Examples
44-47, and wherein the fault domain manager circuitry is further to
determine that the first top-of-rack switch and the second
top-of-rack switch are communicatively coupled to a rack compute
device.
[0127] Example 49 includes the subject matter of any of Examples
44-48, and wherein the fault domain manager circuitry is further to
determine that the rack compute device is communicatively coupled
to at least one power source device, wherein the at least one power
source device is associated with the at least one power zone.
[0128] Example 50 includes the subject matter of any of Examples
44-49, and wherein the fault domain manager circuitry is further to
determine that the rack compute device is communicatively coupled
to at least one other power source device, wherein the at least one
other power source device is associated with at least one other
power zone.
[0129] Example 51 includes the subject matter of any of Examples
44-50, and wherein the computer network includes a composed node,
wherein the composed node includes the at least one sled, and
wherein the fault domain manager circuitry is further to: determine
that the at least one sled corresponds to the at least one
identified power zone; and identify that the composed node
corresponds to the at least one identified power zone within the
fault domain mapping.
[0130] Example 52 includes the subject matter of any of Examples
44-51, and wherein the fault domain manager circuitry is further to
identify, within the sled identification data, a datacenter
identifier for a datacenter, wherein the datacenter includes at
least one manager computer that manages at least one sled of the
plurality of sleds, and wherein the manager computer is
communicatively coupled to the at least one sled.
[0131] Example 53 includes the subject matter of any of Examples
44-52, and wherein the distributed processing adapter circuitry is
further to: determine a data format corresponding to the
distributed processing software system; select a plug-in
application based on the data format; and convert the generated
fault domain mapping into a consumable fault domain mapping by
executing the selected plug-in application.
[0132] Example 54 includes the subject matter of any of Examples
44-53, and wherein the distributed processing software system
includes at least one of Apache Hadoop, Apache Cassandra, Ceph, and
MongoDB.
[0133] Example 55 includes a compute sled to transmit sled data to
a fault domain manager within a computer network, the compute sled
comprising: compute engine circuitry to: initiate a boot process
for the compute sled; discover sled data, wherein the sled data
includes sled identification data and sled health data, wherein to
discover the sled identification data comprises to identify a first
top-of-rack switch, wherein the first top-of-rack switch is
communicatively coupled to the compute sled; generate an
advertisement that includes the sled data, wherein the
advertisement is configured to identify at least one relationship
between the compute sled and at least one other compute sled within
the computer network; and transmit the sled data to the fault
domain manager.
[0134] Example 56 includes the subject matter of Example 55,
wherein to initiate the boot process comprises to initiate an
operating system program load process.
[0135] Example 57 includes the subject matter of any of Examples 55
and 56, wherein to discover the sled data includes to discover,
within the sled identification data, a second top-of-rack switch
identifier for a second top-of-rack switch that is distinct from
the first top-of-rack switch, wherein the second-top-of-rack switch
is communicatively coupled to the compute sled.
[0136] Example 58 includes the subject matter of any of Examples
55-57, wherein the first top-of-rack switch and the second
top-of-rack switch are communicatively coupled to a rack compute
device.
[0137] Example 59 includes the subject matter of any of Examples
55-58, wherein the rack compute device is communicatively coupled
to at least one power source device, wherein the at least one power
source device is associated with at least one power zone.
[0138] Example 60 includes the subject matter of any of Examples
55-59, wherein the rack compute device is communicatively coupled
to at least one other power source device, wherein the at least one
other power source device is associated with at least one other
power zone.
[0139] Example 61 includes the subject matter of any of Examples
55-60, wherein to discover the sled data includes to discover,
within the sled identification data, sled identification data
further includes a datacenter identifier for a datacenter, wherein
the datacenter includes at least one manager computer that manages
at least one sled of the plurality of sleds, and wherein the
manager computer is communicatively coupled to the at least one
sled.
[0140] Example 62 includes the subject matter of any of Examples
55-61, wherein the sled health data includes one or more of a
number of sockets, a number of cores, a number of drives, a latency
metric, a reliability metric, and a memory capacity metric.
[0141] Example 63 includes the subject matter of any of Examples
55-62, wherein to generate the advertisement comprises to generate
the advertisement using a link layer discovery protocol (LLDP).
[0142] Example 64 includes a compute device of automatically
discovering power system fault domains within a computer network,
the compute device comprising: circuitry for receiving sled data
for at least one sled of a plurality of sleds in the computer
network, the sled data including sled identification data and sled
health data; means for parsing the sled identification data to
identify at least one power zone wherein each power zone includes a
subset of the plurality of sleds; means for generating a fault
domain mapping using the at least one identified power zone; means
for converting the generated fault domain mapping into a consumable
fault domain mapping that is consumable by a distributed processing
software system; and means for providing the consumable fault
domain mapping to the distributed processing software system.
[0143] Example 65 includes the subject matter of Example 64, and
further comprising means for receiving sled data by an
advertisement generated by the at least one sled via a link layer
discovery protocol (LLDP), wherein LLDP is configured to identify
one or more relationships between one or more sleds of the
plurality of sleds, and wherein the sled health data includes one
or more of a number of sockets, a number of cores, a number of
drives, a latency metric, a reliability metric, and a memory
capacity metric.
[0144] Example 66 includes the subject matter of any of Examples 64
and 65, and further comprising means for identifying, within the
sled identification data, a first top-of-rack switch identifier for
a first top-of-rack switch that is communicatively coupled to the
at least one sled of the plurality of sleds.
[0145] Example 67 includes the subject matter of any of Examples
64-66, and further comprising means for identifying, within the
sled identification data, a second top-of-rack switch identifier
for a second top-of-rack switch that is distinct from the first
top-of-rack switch, wherein the second-top-of-rack switch is
communicatively coupled to the at least one sled.
[0146] Example 68 includes the subject matter of any of Examples
64-67, and further comprising means for determining that the first
top-of-rack switch and the second top-of-rack switch are
communicatively coupled to a rack compute device.
[0147] Example 69 includes the subject matter of any of Examples
64-68, and further comprising means for determining that the rack
compute device is communicatively coupled to at least one power
source device, wherein the at least one power source device is
associated with the at least one power zone.
[0148] Example 70 includes the subject matter of any of Examples
64-69, and further comprising means for determining that the rack
compute device is communicatively coupled to at least one other
power source device, wherein the at least one other power source
device is associated with at least one other power zone.
[0149] Example 71 includes the subject matter of any of Examples
64-70, and wherein the computer network includes a composed node,
wherein the composed node includes the at least one sled, and
further comprising: means for determining that the at least one
sled corresponds to the at least one identified power zone; and
means for identifying that the composed node corresponds to the at
least one identified power zone within the fault domain
mapping.
[0150] Example 72 includes the subject matter of any of Examples
64-71, and further comprising means for identifying, within the
sled identification data, a datacenter identifier for a datacenter,
wherein the datacenter includes at least one manager computer that
manages at least one sled of the plurality of sleds, and wherein
the manager computer is communicatively coupled to the at least one
sled.
[0151] Example 73 includes the subject matter of any of Examples
64-72, and further comprising: means for determining a data format
corresponding to the distributed processing software system; means
for selecting a plug-in application based on the data format; and
means for converting the generated fault domain mapping into a
consumable fault domain mapping by executing the selected plug-in
application.
[0152] Example 74 includes the subject matter of any of Examples
64-73, and wherein the distributed processing software system
includes at least one of Apache Hadoop, Apache Cassandra, Ceph, and
MongoDB.
[0153] Example 75 includes a compute device of transmitting sled
data to a fault domain manager within a computer network, the
compute device comprising: circuitry for initiating, by a compute
sled, a boot process for the compute sled; means for discovering,
by the compute sled, sled data, wherein the sled data includes sled
identification data and sled health data, wherein to discover the
sled identification data comprises to identify a first top-of-rack
switch, wherein the first top-of-rack switch is communicatively
coupled to the compute sled; means for generating, by the compute
sled, an advertisement that includes the sled data, wherein the
advertisement is configured to identify at least one relationship
between the compute sled and at least one other compute sled within
the computer network; and circuitry for transmitting, by the
compute sled, the sled data to the fault domain manager.
[0154] Example 76 includes the subject matter of Example 75, and
wherein the circuitry for initiating the boot process comprises
circuitry for initiating initiate an operating system program load
process.
[0155] Example 77 includes the subject matter of any of Examples 75
and 76, and wherein the means for discovering the sled data
includes means for discovering, within the sled identification
data, a second top-of-rack switch identifier for a second
top-of-rack switch that is distinct from the first top-of-rack
switch, wherein the second-top-of-rack switch is communicatively
coupled to the compute sled.
[0156] Example 78 includes the subject matter of any of Examples
75-77, and wherein the first top-of-rack switch and the second
top-of-rack switch are communicatively coupled to a rack compute
device.
[0157] Example 79 includes the subject matter of any of Examples
75-78, and wherein the rack compute device is communicatively
coupled to at least one power source device, wherein the at least
one power source device is associated with at least one power
zone.
[0158] Example 80 includes the subject matter of any of Examples
75-79, and wherein the rack compute device is communicatively
coupled to at least one other power source device, wherein the at
least one other power source device is associated with at least one
other power zone.
[0159] Example 81 includes the subject matter of any of Examples
75-80, and wherein the means for discovering the sled data includes
means for discovering, within the sled identification data, sled
identification data further includes a datacenter identifier for a
datacenter, wherein the datacenter includes at least one manager
computer that manages at least one sled of the plurality of sleds,
and wherein the manager computer is communicatively coupled to the
at least one sled.
[0160] Example 82 includes the subject matter of any of Examples
75-81, and wherein the sled health data includes one or more of a
number of sockets, a number of cores, a number of drives, a latency
metric, a reliability metric, and a memory capacity metric.
[0161] Example 83 includes the subject matter of any of Examples
75-82, and wherein the means for generating the advertisement
comprises means for generating the advertisement using a link layer
discovery protocol (LLDP).
* * * * *