U.S. patent application number 15/395679 was filed with the patent office on 2018-01-25 for technologies for variable-extent storage over network fabrics.
The applicant listed for this patent is Steven C. Miller, David Minturn. Invention is credited to Steven C. Miller, David Minturn.
Application Number | 20180024740 15/395679 |
Document ID | / |
Family ID | 60804962 |
Filed Date | 2018-01-25 |
United States Patent
Application |
20180024740 |
Kind Code |
A1 |
Miller; Steven C. ; et
al. |
January 25, 2018 |
TECHNOLOGIES FOR VARIABLE-EXTENT STORAGE OVER NETWORK FABRICS
Abstract
Technologies for variable extent storage include multiple
computing devices in communication over an optical fabric. A
computing device receives a key-value storage request from an
application that is indicative of a key. The computing device
identifies one or more non-volatile storage blocks to store a value
associated with the key and issues a non-volatile memory (NVM)
input/output (I/O) command indicative of the NVM storage blocks to
an NVM subsystem. The key-value storage request may include a read
request or a store request, and the I/O command may include a read
command or a write command. The I/O command may be issued to an NVM
subsystem over the optical fabric. The computing device may be
embodied as a storage sled of a data center, and the application
may be executed by a compute sled of the data center. Other
embodiments are described and claimed.
Inventors: |
Miller; Steven C.;
(Livermore, CA) ; Minturn; David; (Hillsboro,
CA) |
|
Applicant: |
Name |
City |
State |
Country |
Type |
Miller; Steven C.
Minturn; David |
Livermore
Hillsboro |
CA
CA |
US
US |
|
|
Family ID: |
60804962 |
Appl. No.: |
15/395679 |
Filed: |
December 30, 2016 |
Related U.S. Patent Documents
|
|
|
|
|
|
Application
Number |
Filing Date |
Patent Number |
|
|
62365969 |
Jul 22, 2016 |
|
|
|
62376859 |
Aug 18, 2016 |
|
|
|
62427268 |
Nov 29, 2016 |
|
|
|
Current U.S.
Class: |
710/5 |
Current CPC
Class: |
G06F 3/0631 20130101;
G06F 3/0683 20130101; G06F 16/9014 20190101; H04L 9/3263 20130101;
H04Q 2011/0037 20130101; G02B 6/3882 20130101; G02B 6/4292
20130101; G06F 3/064 20130101; G11C 7/1072 20130101; G11C 11/56
20130101; H04L 12/2809 20130101; H04L 67/1097 20130101; H04W 4/023
20130101; H05K 7/20709 20130101; H05K 7/20736 20130101; G06F 3/0653
20130101; G06F 12/1408 20130101; G06F 2212/1024 20130101; H04L
41/147 20130101; H04L 67/34 20130101; H05K 5/0204 20130101; G06F
13/385 20130101; H03M 7/4031 20130101; H04L 43/0894 20130101; H04L
69/04 20130101; H05K 7/1421 20130101; G06F 3/0611 20130101; G06F
2209/5022 20130101; H04Q 2011/0052 20130101; H05K 7/20727 20130101;
Y10S 901/01 20130101; G06F 3/0625 20130101; G06F 9/5016 20130101;
G06F 2212/402 20130101; G06F 13/161 20130101; H04L 9/3247 20130101;
H04L 43/16 20130101; H05K 7/1489 20130101; G06F 3/0616 20130101;
G11C 5/02 20130101; H04L 41/5019 20130101; H04Q 2213/13523
20130101; G06F 3/061 20130101; G06F 3/0665 20130101; G06F 9/5077
20130101; G06F 13/1694 20130101; G06F 2212/152 20130101; H04Q
2213/13527 20130101; H05K 7/1442 20130101; H05K 7/1492 20130101;
G06F 3/0613 20130101; G08C 2200/00 20130101; H04L 43/08 20130101;
H04L 45/52 20130101; H04L 47/765 20130101; H04L 49/00 20130101;
H04L 67/1029 20130101; H05K 7/1491 20130101; G05D 23/2039 20130101;
H03M 7/6023 20130101; H05K 1/0203 20130101; Y02D 10/00 20180101;
G06F 9/5072 20130101; G06F 2209/483 20130101; G06F 2209/5019
20130101; G06F 2212/7207 20130101; G06Q 50/04 20130101; H04L
43/0817 20130101; H05K 13/0486 20130101; H03M 7/40 20130101; H04B
10/25891 20200501; H04L 9/14 20130101; H04L 41/0813 20130101; H04L
49/555 20130101; H04L 67/306 20130101; H04Q 11/00 20130101; G06F
9/30036 20130101; G06F 2212/1041 20130101; G06F 2212/202 20130101;
H05K 1/181 20130101; B25J 15/0014 20130101; G06F 3/0688 20130101;
G06F 2212/401 20130101; H04L 41/12 20130101; H04L 49/15 20130101;
H04L 67/12 20130101; H04Q 1/04 20130101; H04Q 2011/0079 20130101;
G06F 3/0679 20130101; G06Q 10/087 20130101; G06Q 10/20 20130101;
H04L 49/357 20130101; H04L 67/02 20130101; H04Q 1/09 20130101; G06F
12/10 20130101; G06F 15/8061 20130101; G07C 5/008 20130101; H04L
67/1012 20130101; H05K 2201/10159 20130101; Y02P 90/30 20151101;
G06F 2212/1008 20130101; H04L 41/145 20130101; H04L 47/24 20130101;
H05K 7/1422 20130101; G06F 1/183 20130101; G06F 3/0689 20130101;
H04L 67/1014 20130101; H05K 7/20745 20130101; H04L 9/0643 20130101;
H05K 7/1418 20130101; H05K 2201/066 20130101; H04L 47/782 20130101;
H04L 67/10 20130101; H04Q 2011/0086 20130101; G06F 9/3887 20130101;
G06F 9/4881 20130101; H03M 7/3086 20130101; H04L 43/065 20130101;
H04Q 2011/0041 20130101; H05K 7/1485 20130101; G08C 17/02 20130101;
H04L 29/12009 20130101; H04L 41/046 20130101; H04L 41/0896
20130101; H04L 45/02 20130101; H04L 47/805 20130101; H04L 49/25
20130101; H04Q 11/0071 20130101; H05K 7/1447 20130101; G02B 6/3893
20130101; G06F 3/0638 20130101; G06F 9/4401 20130101; G06F 9/5044
20130101; H04L 67/1034 20130101; H04L 67/16 20130101; H05K
2201/10121 20130101; B65G 1/0492 20130101; G06F 3/0655 20130101;
G06F 11/141 20130101; H03M 7/30 20130101; H04L 41/024 20130101;
H04L 47/823 20130101; H04L 67/1008 20130101; H04W 4/80 20180201;
G06F 1/20 20130101; G06F 3/065 20130101; G06Q 10/06314 20130101;
H04B 10/25 20130101; H04Q 11/0003 20130101; H04Q 11/0005 20130101;
H05K 7/1498 20130101; G02B 6/3897 20130101; G05D 23/1921 20130101;
G06F 9/5027 20130101; G06F 13/1668 20130101; H04L 49/35 20130101;
H04L 67/1004 20130101; G06F 3/0659 20130101; G11C 5/06 20130101;
Y04S 10/50 20130101; G06F 3/0647 20130101; G06F 3/067 20130101;
G06F 3/0673 20130101; G06F 13/42 20130101; G06F 2212/1044 20130101;
H03M 7/4056 20130101; H03M 7/4081 20130101; H04L 69/329 20130101;
H04Q 2011/0073 20130101; H05K 7/2039 20130101; G06F 9/505 20130101;
G06F 12/0862 20130101; G06F 13/4068 20130101; G11C 14/0009
20130101; H03M 7/3084 20130101; H04L 41/082 20130101; H05K
2201/10189 20130101; G06F 3/0658 20130101; G06F 12/0893 20130101;
G06F 13/409 20130101; G06F 13/4282 20130101; G06F 15/161 20130101;
G02B 6/4452 20130101; G06F 11/3414 20130101; G06F 12/109 20130101;
G06F 13/4022 20130101; H04L 47/38 20130101; H04L 47/82 20130101;
H04Q 11/0062 20130101; H05K 7/1487 20130101; G06F 3/0619 20130101;
G06F 3/0664 20130101; G06F 8/65 20130101; G06F 9/544 20130101; G06Q
10/06 20130101; H03M 7/6005 20130101; H04L 43/0876 20130101; H04L
49/45 20130101; H05K 7/1461 20130101; H05K 7/20836 20130101 |
International
Class: |
G06F 3/06 20060101
G06F003/06 |
Claims
1. A computing device for data storage, the computing device
comprising: a variable extent storage layer to (i) receive a
key-value storage request from an application, wherein the
key-value storage request is indicative of a key and (ii) identify
one or more non-volatile storage data blocks to store a value
associated with the key; and a block storage layer to (i) issue a
non-volatile memory input/output (I/O) command to a non-volatile
memory subsystem, wherein the I/O command is indicative of the one
or more non-volatile storage data blocks, and (ii) receive a
response from the non-volatile memory subsystem in response to
performance of the non-volatile memory I/O command by the
non-volatile memory subsystem.
2. The computing device of claim 1, wherein to issue the
non-volatile memory I/O command comprises to issue the non-volatile
memory I/O command to a non-volatile memory subsystem of the
computing device.
3. The computing device of claim 1, wherein to issue the
non-volatile memory I/O command comprises to issue the non-volatile
memory I/O command to a non-volatile memory over fabric subsystem
via an optical fabric interface of the computing device.
4. The computing device of claim 1, wherein the block storage
subsystem is further to access the one or more non-volatile storage
data blocks in response to issuance of the non-volatile memory I/O
command.
5. The computing device of claim 4, wherein to access the one or
more non-volatile storage data blocks comprises to access one or
more solid-state storage devices of the computing device that
include the non-volatile storage data blocks.
6. The computing device of claim 1, wherein: the key-value storage
request comprises a store request that is further indicative of the
value associated with the key; and the non-volatile memory I/O
command comprises a non-volatile memory write command that is
further indicative of the value.
7. The computing device of claim 6, further comprising a data
durability layer to add a protection code to the value in response
to receipt of the store request.
8. The computing device of claim 1, wherein: the key-value storage
request comprises a read request; the non-volatile memory I/O
command comprises a non-volatile memory read command; and the
response is indicative of the value associated with the key.
9. The computing device of claim 8, wherein the variable extent
storage layer is further to send the value associated with the key
to the application in response to receipt of the response from the
non-volatile memory subsystem.
10. The computing device of claim 8, further comprising a data
durability layer to verify a protection code associated with the
value in response to receipt of the response from the non-volatile
memory subsystem.
11. The computing device of claim 1, wherein: the computing device
comprises a storage sled of a data center, wherein the storage sled
comprises a processor and a plurality of solid-state storage
devices; and the application comprises a workload executed by a
compute sled of the data center.
12. A method for data storage, the method comprising: receiving, by
a computing device, a key-value storage request from an
application, wherein the key-value storage request is indicative of
a key; identifying, by the computing device, one or more
non-volatile storage data blocks to store a value associated with
the key; issuing, by the computing device, a non-volatile memory
input/output (I/O) command to a non-volatile memory subsystem,
wherein the I/O command is indicative of the one or more
non-volatile storage data blocks; and receiving, by the computing
device, a response from the non-volatile memory subsystem in
response to performance of the non-volatile memory I/O command by
the non-volatile memory subsystem.
13. The method of claim 12, wherein issuing the non-volatile memory
I/O command comprises issuing the non-volatile memory I/O command
to a non-volatile memory subsystem of the computing device.
14. The method of claim 12, wherein issuing the non-volatile memory
I/O command comprises issuing the non-volatile memory I/O command
to a non-volatile memory over fabric subsystem via an optical
fabric interface of the computing device.
15. The method of claim 12, further comprising accessing, by the
computing device, the one or more non-volatile storage data blocks
in response to issuing the non-volatile memory I/O command.
16. The method of claim 12, wherein: receiving the key-value
storage request comprises receiving a store request, wherein the
store request is further indicative of the value associated with
the key; and issuing the non-volatile memory I/O command comprises
issuing a non-volatile memory write command to the non-volatile
memory subsystem, wherein the non-volatile memory write command is
further indicative of the value.
17. The method of claim 16, further comprising adding, by the
computing device, a protection code to the value in response to
receiving the store request.
18. The method of claim 12, wherein: receiving the key-value
storage request comprises receiving a read request; issuing the
non-volatile memory I/O command comprises issuing a non-volatile
memory read command to the non-volatile memory subsystem; and
receiving the response from the non-volatile memory subsystem
further comprises receiving a response that is indicative of the
value associated with the key.
19. One or more computer-readable storage media comprising a
plurality of instructions that in response to being executed cause
a computing device to: receive a key-value storage request from an
application, wherein the key-value storage request is indicative of
a key; identify one or more non-volatile storage data blocks to
store a value associated with the key; issue a non-volatile memory
input/output (I/O) command to a non-volatile memory subsystem,
wherein the I/O command is indicative of the one or more
non-volatile storage data blocks; and receive a response from the
non-volatile memory subsystem in response to performance of the
non-volatile memory I/O command by the non-volatile memory
subsystem.
20. The one or more computer-readable storage media of claim 19,
wherein to issue the non-volatile memory I/O command comprises to
issue the non-volatile memory I/O command to a non-volatile memory
subsystem of the computing device.
21. The one or more computer-readable storage media of claim 19,
wherein to issue the non-volatile memory I/O command comprises to
issue the non-volatile memory I/O command to a non-volatile memory
over fabric subsystem via an optical fabric interface of the
computing device.
22. The one or more computer-readable storage media of claim 19,
further comprising a plurality of instructions that in response to
being executed cause the computing device to access the one or more
non-volatile storage data blocks in response to issuing the
non-volatile memory I/O command.
23. The one or more computer-readable storage media of claim 19,
wherein: to receive the key-value storage request comprises to
receive a store request, wherein the store request is further
indicative of the value associated with the key; and to issue the
non-volatile memory I/O command comprises to issue a non-volatile
memory write command to the non-volatile memory subsystem, wherein
the non-volatile memory write command is further indicative of the
value.
24. The one or more computer-readable storage media of claim 23,
further comprising a plurality of instructions that in response to
being executed cause the computing device to add a protection code
to the value in response to receiving the store request.
25. The one or more computer-readable storage media of claim 19,
wherein: to receive the key-value storage request comprises to
receive a read request; to issue the non-volatile memory I/O
command comprises to issue a non-volatile memory read command to
the non-volatile memory subsystem; and to receive the response from
the non-volatile memory subsystem further comprises to receive a
response that is indicative of the value associated with the key.
Description
CROSS-REFERENCE TO RELATED APPLICATIONS
[0001] The present application claims the benefit of U.S.
Provisional Patent Application No. 62/365,969, filed Jul. 22, 2016,
U.S. Provisional Patent Application No. 62/376,859, filed Aug. 18,
2016, and U.S. Provisional Patent Application No. 62/427,268, filed
Nov. 29, 2016.
BACKGROUND
[0002] In a typical cloud-based computing environment (e.g., a data
center), multiple compute nodes may execute workloads (e.g.,
processes, applications, services, etc.) on behalf of customers.
During execution of workloads, the compute nodes may generate or
access stable data that is to be stored long-term in durable
storage. Durable storage may be provided using local storage
devices of the compute nodes, or using durable storage provided by
one or more remote compute nodes.
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 system for variable-extent data storage;
[0016] FIG. 13 is a top perspective view of an example embodiment
of a storage sled of FIG. 12;
[0017] FIG. 14 is a bottom perspective view of an example
embodiment of a storage sled of FIG. 12;
[0018] FIG. 15 is a simplified block diagram of at least one
embodiment of an environment that may be established by a storage
sled of FIG. 12;
[0019] FIG. 16 is a simplified flow diagram of at least one
embodiment of a method for storing variable-extent data that may be
executed by a storage sled of FIGS. 12-15; and
[0020] FIG. 17 is a simplified flow diagram of at least one
embodiment of a method for reading variable-extent data that may be
executed by a storage sled of FIGS. 12-15.
DETAILED DESCRIPTION OF THE DRAWINGS
[0021] 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.
[0022] 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).
[0023] 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).
[0024] 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.
[0025] 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.
[0026] 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.
[0027] 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, 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.
[0028] 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.
[0029] 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.
[0030] 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.
[0031] 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.
[0032] 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.
[0033] 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.
[0034] 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.
[0035] 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.
[0036] 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.
[0037] 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.).
[0038] 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.
[0039] 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.
[0040] 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.
[0041] 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.
[0042] 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.
[0043] 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.
[0044] 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.
[0045] 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.
[0046] 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.
[0047] 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.
[0048] Referring now to FIG. 12, in an illustrative embodiment, a
system 1200 for variable-extent storage includes a storage sled
204-1 in communication with multiple other sleds 204 (e.g., one or
more compute sleds 204-4 and memory sleds 204-3 as shown) over an
optical fabric 1202. The system 1200 may be implemented in
accordance with the data centers 100, 300, 400, 1100 described
above with reference to FIGS. 1, 3, 4, and 11. In use, as described
further below, the storage sled 204-1 may receive key-value storage
requests from applications executed by other entities of the system
1200 (e.g., by one or more compute sleds 204-4). The key-value
storage requests include requests to store a particular value
associated with a key and requests to read the value associated
with a key. In response to receiving a key-value storage request,
the storage sled 204-1 identifies one or more storage blocks for
the value (e.g., newly allocated blocks or existing blocks) and
then issues a non-volatile memory (NVM) I/O command to an NVM
subsystem to perform the requested operation. The storage blocks
may be stored at one or more SSDs 1228 of the storage sled 204-1 or
may be stored at SSDs 1228 of other storage sleds 204-1 also
connected to the optical fabric 1202. The system 1200 may also
create and store a protection code or other protection data (e.g.,
an erasure code, RAID, LRC) to help ensure data integrity. Thus,
the system 1200 may provide applications with a simple,
variable-extent interface to manage stable data stored by the
system 1200. Additionally, by storing the data in storage blocks
spread among multiple SSDs 1228, the system 1200 may allow data
transfers to fully utilize the large amounts of bandwidth available
over the optical fabric 1202. Also, by performing the
variable-extent storage operations using processor resources of the
storage sleds 204-1, the system 1200 may reduce usage of processor
resources of the compute sleds 204-4 or other compute nodes.
Reducing compute node processor usage may make more compute
capacity available to customers of the data center, improve power
efficiency, or otherwise improve data center operations.
[0049] As shown in FIG. 12, the storage sled 204-1 illustratively
includes a processor 1220, an input/output subsystem 1222, a memory
1224, a communication subsystem 1226, and multiple solid state
drives (SSDs) 1228. Of course, the storage sled 204-1 may include
other or additional components, such as those commonly found in
rack-mounted server (e.g., various input/output devices), in other
embodiments. Additionally, in some embodiments, one or more of the
illustrative components may be incorporated in, or otherwise form a
portion of, another component. For example, the memory 1224, or
portions thereof, may be incorporated in the processor 1220 in some
embodiments.
[0050] The processor 1220 may be embodied as any type of processor
capable of performing the functions described herein. 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 storage sled 204-1 such as 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 storage sled
204-1. For example, the I/O subsystem 1222 may be embodied as, or
otherwise include, memory controller hubs, input/output control
hubs, platform controller hubs, integrated control circuitry,
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 storage sled 204-1, on a single integrated
circuit chip.
[0051] The communication subsystem 1228 may be configured to use
any one or more communication technology (e.g., wired or wireless
communications) and associated protocols (e.g., Ethernet,
Bluetooth.RTM., Wi-Fi.RTM., WiMAX, etc.) to effect such
communication. In particular, the communication subsystem 1228 may
include one or more optical transceiver modules, silicon photonics
devices, or other components used to communicate with other devices
over the optical fabric 1202.
[0052] Each of the SSDs 1228 may be embodied as any type of
solid-state, non-volatile storage device or devices configured for
short-term or long-term storage of data such as, for example,
memory devices and circuits, memory cards, solid-state drives, or
other data storage devices. As shown, the illustrative storage sled
204-1 includes eight SSDs 1228-1 to 1228-8. In other embodiments,
each storage sled 204-1 may include a different number of SSDs
1228, and in some embodiments the SSDs 1228 may be hot-pluggable,
replaceable, or otherwise configurable.
[0053] As shown, each storage sled 204-1 may also include one or
more peripheral devices 1230. The peripheral devices 1230 may
include any number of additional input/output devices, interface
devices, sensors, and/or other peripheral devices. For example, in
some embodiments, the peripheral devices 1230 may include a
display, touch screen, graphics circuitry, keyboard, mouse, speaker
system, microphone, network interface, and/or other input/output
devices, interface devices, and/or peripheral devices.
[0054] Referring now to FIG. 13, a top perspective view of an
illustrative storage sled 204-1 is shown. As illustrated, the
storage sled 204-1 includes a top side 1302. The storage sled 204-1
includes two processors 1220 and a communications subsystem 1226
positioned on the top side 1302. The storage sled 204-1 further
includes a storage cage 1304 positioned at one end of the storage
sled 204-1 that includes the physical storage resources 205-1. The
illustrative storage sled 204-1 includes sixteen SSDs 1228 mounted
to slots in the storage cage 1304. As shown, the storage cage 1304
extends above and below the top side 1302 of the storage sled
204-1.
[0055] Referring now to FIG. 14, a bottom perspective view of the
illustrative storage sled 204-1 is shown. As illustrated, the
storage sled 204-1 also includes a bottom side 1402. The storage
sled 204-1 includes memory 1224 positioned within slots on the
bottom side 1402. In some examples, the memory 1224 may include
multiple DIMMs. For these examples, each DIMM may include volatile
and/or non-volatile types of memory. FIG. 14 also illustrates the
storage cage 1304 positioned at the end of the storage sled 204-1
that includes the SSDs 1228. As shown, the storage cage 1304
extends above and below the bottom side 1402 of the storage sled
204-1.
[0056] Referring now to FIG. 15, in an illustrative embodiment, the
storage sled 204-1 establishes an environment 1500 during
operation. The illustrative environment 1500 includes a variable
extent storage layer 1502, a data durability layer 1504, and a
block storage layer 1506. The various components of the environment
1500 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 1500 may be embodied as circuitry
or collection of electrical devices (e.g., variable extent storage
circuitry 1502, data durability circuitry 1504, and/or block
storage circuitry 1506). It should be appreciated that, in such
embodiments, one or more of the variable extent storage circuitry
1502, the data durability circuitry 1504, and/or the block storage
circuitry 1506 may form a portion of the processor 1220, the I/O
subsystem 122, the SSDs 1228, and/or other components of the
storage sled 204-1. Additionally, in some embodiments, one or more
of the illustrative components may form a portion of another
component and/or one or more of the illustrative components may be
independent of one another.
[0057] The variable extent storage layer 1502 is configured to
receive a key-value storage request from an application, data
services layer, or other higher-level client. The key-value storage
request is indicative of a key. The variable extent storage layer
1502 is further configured to identify one or more non-volatile
storage data blocks to store a value associated with the key. The
key-value storage request may be embodied as a store request that
is further indicative of the value associated with the key or as a
read request. The variable extent storage layer 1502 may be further
configured to send the value associated with the key to the
application in response to a read request.
[0058] The data durability layer 1504 may be configured to add a
protection code to the value in response to receiving a store
request. The data durability layer 1504 may be configured to verify
a protection code associated with the value in response to a read
request.
[0059] The block storage layer 1506 is configured to issue a
non-volatile memory (NVM) I/O command to an NVM subsystem. The I/O
command is indicative of the one or more non-volatile storage data
blocks for the value associated with the key. The block storage
layer 1506 may be configured to issue the NVM I/O command to an NVM
subsystem of the storage sled 204-1 or to issue the NVM I/O command
to an NVM over fabric subsystem via an optical fabric 1202
interface of the storage sled 204-1. The block storage layer 1506
may be further configured to access the one or more non-volatile
storage data blocks in response to issuing the NVM I/O command. The
block storage layer 1506 is further configured to receive a
response from the NVM subsystem in response to the NVM I/O command
being performed by the NVM subsystem. In some embodiments, those
functions may be performed by one or more sub-components, such as a
local NVM subsystem layer 1508 and/or an NVM over fabric layer
1510.
[0060] Referring now to FIG. 16, in use, the storage sled 204-1 may
execute a method 1600 for storing variable-extent data. It should
be appreciated that, in some embodiments, the method 1600 may be
embodied as various instructions stored on a computer-readable
media, which may be executed by the processor 1220, the I/O
subsystem 1222, and/or other components of the storage sled 204-1
to cause the storage sled 204-1 to perform the method 1600. The
computer-readable media may be embodied as any type of media
capable of being read by the storage sled 204-1 including, but not
limited to, the memory 1224, an SSD 1228, firmware devices, and/or
other media. Additionally or alternatively, it should be
appreciated that, in some embodiments, the operations of the method
1600 may be performed by one or more components of the environment
1500 of the storage sled 204-1 as shown in FIG. 15.
[0061] The method 1600 begins in block 1602, in which the storage
sled 204-1 receives a store request from an application. The store
request identifies a key and an associated value to store for the
key. The key may be embodied as an identifier, a string, a
filename, or any other data that may be used to uniquely identify
the associated value. Similarly, the value may be embodied as any
string, stream, binary blob, or other data that is to be stored.
The value may have variable extent--that is, the value may have a
variable length and is not required to include any particular
length, block size, page size, or other amount of data. As
described above, the storage sled 204-1 receives the store request
from an application. The application may be embodied as any
application, thread, virtual machine, or other workload executed by
the system 1200. In particular, the application may be embodied as
a workload executed by a compute sled 204-4, an accelerator sled
204-2, and/or other sled 204 of the system 1200. In some
embodiments, the application may include cloud-based client
applications (e.g., web applications, database applications, etc.),
middleware, libraries, system services, data services, or other
higher-level clients (e.g., active data services, file interfaces,
block interfaces, or other storage interfaces).
[0062] In block 1604, the storage sled 204-1 identifies one or more
storage blocks to store the value associated with the supplied key.
Each of the storage blocks may be embodied as any fixed-sized
storage unit of an SSD 1228. For example, each storage block may be
a logical block that is identified by a logical block address (LBA)
of an SSD 1228. The storage sled 204-1 may use any appropriate
algorithm to allocate or otherwise manage storage blocks for each
key. In particular, the storage sled 204-1 may allocate new storage
blocks to store the value, identify existing storage blocks
associated with the value to be overwritten, or otherwise identify
the storage blocks. The storage blocks may be striped or otherwise
spread across multiple SSDs 1228 of the storage sled 204-1. In some
embodiments, as described further below, the storage blocks may be
stored by one or more SSDs 1228 included in a different storage
sled 204-1 that is accessible via the optical fabric 1202.
[0063] In block 1606, in some embodiments, the storage sled 204-1
may add a protection code to the value. The protection code may be
embodied as any checksum, hash, error correcting code, or other
code that may be used to verify the integrity of the value and/or
correct bit errors that may occur in the value. The protection code
may be appended to the end of the value or stored in a separate
location. Additionally, in some embodiments the protection code may
be added by a different entity of the system 1200. For example, the
protection code may be added by a non-volatile memory (NVM)
subsystem, as described below, or the protection code may be added
by the application. If added by the application, the protection
code may be included in the value and thus transparent to the
storage sled 204-1.
[0064] In block 1608, the storage sled 204-1 issues one or more
write commands to an NVM subsystem to store the value in the
identified NVM storage blocks. Issuing the write command may cause
the NVM subsystem to perform one or more direct memory access
operations, remote direct memory access operations, fabric data
transfers, or other operations to read the value from the
application (e.g., from the memory of a compute sled 204-4 and/or
memory sled 204-3). In some embodiments, in block 1610 the storage
sled 204-1 may issue the write command(s) to a local NVM subsystem
of the storage sled 204-1, such as an NVM Express (NVMe) subsystem.
The local NVM subsystem may receive the write commands over a local
interconnect provided by the I/O subsystem 1222 such as PCI Express
and perform the write operation as described below. In some
embodiments, in block 1612 the storage sled 204-1 may issue the
write command(s) to an NVM-over-fabric subsystem such as an NVM
Express over Fabrics (NVMf) subsystem. The storage sled 204-1 may
issue the write commands to an NVMf subsystem established by the
storage sled 204-1 and/or to an NVMf subsystem established by a
different storage sled 204-1 via the optical fabric 1202. In some
embodiments, in block 1614, the NVM subsystem may add a protection
code to the value, as described above.
[0065] In some embodiments, in block 1616, the storage sled 204-1
may store the value in one or more storage blocks contained by
local storage devices of the storage sled 204-1 (e.g., the SSDs
1228). As described above, a local NVM subsystem (such as an NVMe
subsystem and/or an NVMf subsystem) of the storage sled 204-1 may
write the value into one or more storage blocks of the SSDs 1228 in
response to receiving the write command(s).
[0066] In block 1618, the storage sled 204-1 receives a response
from the NVM subsystem. For example, the storage sled 204-1 may
receive a completion from an NVMe subsystem and/or a response
capsule from an NVMf subsystem. The response may indicate whether
the write command completed successfully. The storage sled 204-1
may also provide a response to the application to indicate that the
store request was completed successfully or that an error occurred.
After performing the store request, the method 1600 loops back to
block 1602 to process additional store requests.
[0067] Referring now to FIG. 17, in use, the storage sled 204-1 may
execute a method 1700 for reading variable-extent data. It should
be appreciated that, in some embodiments, the method 1700 may be
embodied as various instructions stored on a computer-readable
media, which may be executed by the processor 1220, the I/O
subsystem 1222, and/or other components of the storage sled 204-1
to cause the storage sled 204-1 to perform the method 1700. The
computer-readable media may be embodied as any type of media
capable of being read by the storage sled 204-1 including, but not
limited to, the memory 1224, an SSD 1228, firmware devices, and/or
other media. Additionally or alternatively, it should be
appreciated that, in some embodiments, the operations of the method
1700 may be performed by one or more components of the environment
1500 of the storage sled 204-1 as shown in FIG. 15.
[0068] The method 1700 begins in block 1702, in which the storage
sled 204-1 receives a read request from an application. The read
request identifies a key, which, as described above, may be
embodied as an identifier, a string, a filename, or any other data
that may be used to uniquely identify an associated value. As
described above, the storage sled 204-1 receives the read request
from an application, which may be embodied as any application,
thread, virtual machine, or other workload executed by the system
1200. In particular, the application may be embodied as a workload
executed by a compute sled 204-4, an accelerator sled 204-2, and/or
other sled 204 of the system 1200. As described above, the
application may include cloud-based client applications (e.g., web
applications, database applications, etc.), middleware, libraries,
and/or system services (e.g., active data services, filesystems, or
other storage interfaces).
[0069] In block 1704, the storage sled 204-1 identifies one or more
storage blocks to store the value associated with the supplied key.
Each of the storage blocks may be embodied as any fixed-sized
storage unit of an SSD 1228. For example, each storage block may be
a logical block that is identified by a logical block address (LBA)
of an SSD 1228. The storage sled 204-1 may use any appropriate
algorithm to locate or otherwise manage storage blocks for each
key. In particular, the storage sled 204-1 may identify existing
storage blocks associated with the key that store the value to be
read, identify that no such value exists, or perform other
retrieval operations. As described above, the storage blocks may be
striped or otherwise spread across multiple SSDs 1228 of the
storage sled 204-1. In some embodiments, as described further
below, the storage blocks may be stored by one or more SSDs 1228
included in a different storage sled 204-1 that is accessible via
the optical fabric 1202.
[0070] In block 1706, the storage sled 204-1 issues one or more
read commands to an NVM subsystem to read the value in the
identified NVM storage blocks. In some embodiments, in block 1708
the storage sled 204-1 may issue the read command(s) to a local NVM
subsystem of the storage sled 204-1, such as an NVM Express (NVMe)
subsystem. The local NVM subsystem may receive the read commands
over a local interconnect provided by the I/O subsystem 1222 such
as PCI Express and perform the read operation as described below.
In some embodiments, in block 1710 the storage sled 204-1 may issue
the read command(s) to an NVM-over-fabric subsystem such as an NVM
Express over Fabrics (NVMf) subsystem. The storage sled 204-1 may
issue the read commands to an NVMf subsystem established by the
storage sled 204-1 and/or to an NVMf subsystem established by a
different storage sled 204-1 via the optical fabric 1202. In some
embodiments, in block 1712, the NVM subsystem may verify a
protection code associated with the value. The protection code may
be embodied as any checksum, hash, error correcting code, or other
code that may be used to verify the integrity of the value and/or
correct bit errors that may occur in the value. As described above,
the protection code may have earlier been added by the NVM
subsystem, the storage sled 204-1, the application, or other entity
of the system 1200.
[0071] In some embodiments, in block 1714, the storage sled 204-1
may read the value stored in one or more storage blocks contained
by local storage devices of the storage sled 204-1 (e.g., the SSDs
1228). As described above, a local NVM subsystem (such as an NVMe
subsystem and/or an NVMf subsystem) of the storage sled 204-1 may
read the value from one or more storage blocks of the SSDs 1228 in
response to receiving the read command(s).
[0072] In block 1716, the storage sled 204-1 receives a response
from the NVM subsystem. For example, the storage sled 204-1 may
receive a completion from an NVMe subsystem and/or a response
capsule from an NVMf subsystem. The response may indicate whether
the read command completed successfully, and may include the value
that was read and/or a reference to the value. The storage-sled
204-1 may receive the value associated with the key via one or more
direct memory access operations, remote direct memory access
operations, fabric data transfers, or other operations. In some
embodiments, in block 1718, the storage sled 204-1 may verify a
protection code associated with the value.
[0073] In block 1720, the storage sled 204-1 sends the value read
from the storage blocks to the application. For example, the
storage sled 204-1 may send the value data over the optical
interconnect 1202 using any remote direct memory access operations,
fabric data transfers, or other data transfer operations. In some
embodiments, the storage sled 204-1 may also send status
information that indicates whether the read was performed
successfully and/or other status information to the application.
After performing the read request, the method 1700 loops back to
block 1702 to process additional read requests.
EXAMPLES
[0074] 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.
[0075] Example 1 includes a computing device for data storage, the
computing device comprising: a variable extent storage layer to (i)
receive a key-value storage request from an application, wherein
the key-value storage request is indicative of a key and (ii)
identify one or more non-volatile storage data blocks to store a
value associated with the key; and a block storage layer to (i)
issue a non-volatile memory input/output (I/O) command to a
non-volatile memory subsystem, wherein the I/O command is
indicative of the one or more non-volatile storage data blocks, and
(ii) receive a response from the non-volatile memory subsystem in
response to performance of the non-volatile memory I/O command by
the non-volatile memory subsystem.
[0076] Example 2 includes the subject matter of Example 1, and
wherein to issue the non-volatile memory I/O command comprises to
issue the non-volatile memory I/O command to a non-volatile memory
subsystem of the computing device.
[0077] Example 3 includes the subject matter of any of Examples 1
and 2, and wherein to issue the non-volatile memory I/O command
comprises to issue the non-volatile memory I/O command to a
non-volatile memory over fabric subsystem via an optical fabric
interface of the computing device.
[0078] Example 4 includes the subject matter of any of Examples
1-3, and wherein the block storage subsystem is further to access
the one or more non-volatile storage data blocks in response to
issuance of the non-volatile memory I/O command.
[0079] Example 5 includes the subject matter of any of Examples
1-4, and wherein to access the one or more non-volatile storage
data blocks comprises to access one or more solid-state storage
devices of the computing device that include the non-volatile
storage data blocks.
[0080] Example 6 includes the subject matter of any of Examples
1-5, and wherein: the key-value storage request comprises a store
request that is further indicative of the value associated with the
key; and the non-volatile memory I/O command comprises a
non-volatile memory write command that is further indicative of the
value.
[0081] Example 7 includes the subject matter of any of Examples
1-6, and further comprising a data durability layer to add a
protection code to the value in response to receipt of the store
request.
[0082] Example 8 includes the subject matter of any of Examples
1-7, and wherein: the key-value storage request comprises a read
request; the non-volatile memory I/O command comprises a
non-volatile memory read command; and the response is indicative of
the value associated with the key.
[0083] Example 9 includes the subject matter of any of Examples
1-8, and wherein the variable extent storage layer is further to
send the value associated with the key to the application in
response to receipt of the response from the non-volatile memory
subsystem.
[0084] Example 10 includes the subject matter of any of Examples
1-9, and further comprising a data durability layer to verify a
protection code associated with the value in response to receipt of
the response from the non-volatile memory subsystem.
[0085] Example 11 includes the subject matter of any of Examples
1-10, and wherein: the computing device comprises a storage sled of
a data center, wherein the storage sled comprises a processor and a
plurality of solid-state storage devices; and the application
comprises a workload executed by a compute sled of the data
center.
[0086] Example 12 includes a method for data storage, the method
comprising: receiving, by a computing device, a key-value storage
request from an application, wherein the key-value storage request
is indicative of a key; identifying, by the computing device, one
or more non-volatile storage data blocks to store a value
associated with the key; issuing, by the computing device, a
non-volatile memory input/output (I/O) command to a non-volatile
memory subsystem, wherein the I/O command is indicative of the one
or more non-volatile storage data blocks; and receiving, by the
computing device, a response from the non-volatile memory subsystem
in response to performance of the non-volatile memory I/O command
by the non-volatile memory subsystem.
[0087] Example 13 includes the subject matter of claim 12, and
wherein issuing the non-volatile memory I/O command comprises
issuing the non-volatile memory I/O command to a non-volatile
memory subsystem of the computing device.
[0088] Example 14 includes the subject matter of any of claims 12
and 13, and wherein issuing the non-volatile memory I/O command
comprises issuing the non-volatile memory I/O command to a
non-volatile memory over fabric subsystem via an optical fabric
interface of the computing device.
[0089] Example 15 includes the subject matter of any of claims
12-14, and further comprising accessing, by the computing device,
the one or more non-volatile storage data blocks in response to
issuing the non-volatile memory I/O command.
[0090] Example 16 includes the subject matter of any of claims
12-15, and wherein accessing the one or more non-volatile storage
data blocks comprises accessing one or more solid-state storage
devices of the computing device that include the non-volatile
storage data blocks.
[0091] Example 17 includes the subject matter of any of claims
12-16, and wherein: receiving the key-value storage request
comprises receiving a store request, wherein the store request is
further indicative of the value associated with the key; and
issuing the non-volatile memory I/O command comprises issuing a
non-volatile memory write command to the non-volatile memory
subsystem, wherein the non-volatile memory write command is further
indicative of the value.
[0092] Example 18 includes the subject matter of any of claims
12-17, and further comprising adding, by the computing device, a
protection code to the value in response to receiving the store
request.
[0093] Example 19 includes the subject matter of any of claims
12-18, and wherein: receiving the key-value storage request
comprises receiving a read request; issuing the non-volatile memory
I/O command comprises issuing a non-volatile memory read command to
the non-volatile memory subsystem; and receiving the response from
the non-volatile memory subsystem further comprises receiving a
response that is indicative of the value associated with the
key.
[0094] Example 20 includes the subject matter of any of claims
12-19, and further comprising sending, by the computing device, the
value associated with the key to the application in response to
receiving the response from the non-volatile memory subsystem.
[0095] Example 21 includes the subject matter of any of claims
12-20, and further comprising verifying, by the computing device, a
protection code associated with the value in response to receiving
the response from the non-volatile memory subsystem.
[0096] Example 22 includes the subject matter of any of claims
12-21, and wherein: the computing device comprises a storage sled
of a data center, wherein the storage sled comprises a processor
and a plurality of solid-state storage devices; and the application
comprises a workload executed by a compute sled of the data
center.
[0097] Example 23 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
12-22.
[0098] Example 24 includes one or more machine 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 12-22.
[0099] Example 25 includes a computing device comprising means for
performing the method of any of Examples 12-22.
[0100] Example 26 includes a computing device for data storage, the
computing device comprising: means for receiving a key-value
storage request from an application, wherein the key-value storage
request is indicative of a key; means for identifying one or more
non-volatile storage data blocks to store a value associated with
the key; means for issuing a non-volatile memory input/output (I/O)
command to a non-volatile memory subsystem, wherein the I/O command
is indicative of the one or more non-volatile storage data blocks;
and means for receiving a response from the non-volatile memory
subsystem in response to performance of the non-volatile memory I/O
command by the non-volatile memory subsystem.
[0101] Example 27 includes the subject matter of claims 26, and
wherein the means for issuing the non-volatile memory I/O command
comprises means for issuing the non-volatile memory I/O command to
a non-volatile memory subsystem of the computing device.
[0102] Example 28 includes the subject matter of any of claims 26
and 27, and wherein the means for issuing the non-volatile memory
I/O command comprises means for issuing the non-volatile memory I/O
command to a non-volatile memory over fabric subsystem via an
optical fabric interface of the computing device.
[0103] Example 29 includes the subject matter of any of claims
26-28, and further comprising means for accessing the one or more
non-volatile storage data blocks in response to issuing the
non-volatile memory I/O command.
[0104] Example 30 includes the subject matter of any of claims
26-29, and wherein the means for accessing the one or more
non-volatile storage data blocks comprises means for accessing one
or more solid-state storage devices of the computing device that
include the non-volatile storage data blocks.
[0105] Example 31 includes the subject matter of any of claims
26-30, and wherein: the means for receiving the key-value storage
request comprises means for receiving a store request, wherein the
store request is further indicative of the value associated with
the key; and the means for issuing the non-volatile memory I/O
command comprises means for issuing a non-volatile memory write
command to the non-volatile memory subsystem, wherein the
non-volatile memory write command is further indicative of the
value.
[0106] Example 32 includes the subject matter of any of claims
26-31, and further comprising means for adding a protection code to
the value in response to receiving the store request.
[0107] Example 33 includes the subject matter of any of claims
26-32, and wherein: the means for receiving the key-value storage
request comprises means for receiving a read request; the means for
issuing the non-volatile memory I/O command comprises means for
issuing a non-volatile memory read command to the non-volatile
memory subsystem; and the means for receiving the response from the
non-volatile memory subsystem further comprises means for receiving
a response that is indicative of the value associated with the
key.
[0108] Example 34 includes the subject matter of any of claims
26-33, and further comprising means for sending the value
associated with the key to the application in response to receiving
the response from the non-volatile memory subsystem.
[0109] Example 35 includes the subject matter of any of claims
26-34, and further comprising means for verifying a protection code
associated with the value in response to receiving the response
from the non-volatile memory subsystem.
[0110] Example 36 includes the subject matter of any of claims
26-35, and wherein: the computing device comprises a storage sled
of a data center, wherein the storage sled comprises a processor
and a plurality of solid-state storage devices; and the application
comprises a workload executed by a compute sled of the data
center.
* * * * *