公开(公告)号：US12271372B2

公开(公告)日：2025-04-08

申请号：US18633209

申请日：2024-04-11

Applicant: Oracle International Corporation

Inventor： Ajit Mylavarapu ,  Vasudha Krishnaswamy ,  Sukhada Pendse ,  Solmaz Kolahi ,  Ankita Kumar ,  Garret F. Swart ,  Tirthankar Lahiri ,  Juan R Loaiza

IPC: G06F16/23 ,  G06F16/28

Abstract: One or more engine instances are executed on each host to form an engine cluster. A plurality of control instances are executed on a first set of hosts to form a control cluster and comprise a control instance leader and one or more control instance followers. In response to a first host indicating a failure of a neighbor host, a pair-wise focused investigation is initiated to check peer-to-peer connections between the first host and the neighbor host. In response to one or more additional hosts indicating failures of neighbor hosts while the pair-wise focused investigation is being performed, a wide investigation is performed to check connections between the control cluster and the plurality of hosts. One or more hosts are added to an eviction list and an eviction protocol is performed to evict the one or more hosts from the engine cluster using the eviction list.

公开(公告)号：US20250086176A1

公开(公告)日：2025-03-13

申请号：US18638931

申请日：2024-04-18

Applicant: Oracle International Corporation

Inventor： Lawrence Lim ,  Laleh Aghababaie Beni ,  Garret F. Swart

IPC: G06F16/2453 ,  G06F11/34 ,  G06F16/2452

Abstract: In a computer, each of many statement plan trees respectively represents a distinct database statement in a database workload. Each statement plan tree contains a distinct set of tree nodes. A first statement plan tree contains a first subtree and represents a first statement. A second statement plan tree contains a second subtree, and a third statement plan tree contains a third subtree. By agglomeration, a first cluster subplan is generated that represents the first subtree of the first statement plan tree and the second subtree of the second statement plan tree. By subsequent agglomeration, a second cluster subplan is generated that represents the third subtree of the third statement plan tree and the first cluster subplan. Execution of the first database statement uses the second cluster subplan for acceleration. Agglomeration may be decided based on novel net benefit estimation, novel inter-cluster distance, and a novel and tunable compilation cost.

公开(公告)号：US11550771B2

公开(公告)日：2023-01-10

申请号：US17070277

申请日：2020-10-14

Applicant: Oracle International Corporation

Inventor： Jesse Kamp ,  Allison L. Holloway ,  Meichun Hsu ,  Hideaki Kimura ,  Boris Klots ,  Vasudha Krishnaswamy ,  Kartik Kulkarni ,  Teck Hua Lee ,  Yunrui Li ,  Aurosish Mishra ,  Ajit Mylavarapu ,  Sukhada Pendse ,  Garret F. Swart ,  Shasank K. Chavan ,  Tirthankar Lahiri ,  Juan R. Loaiza

IPC: G06F16/22 ,  G06F16/27 ,  G06F16/21 ,  G06F16/174 ,  G06F16/18 ,  G06F16/23 ,  G06F16/11

Abstract: A shared-nothing database system is provided in which parallelism and workload balancing are increased by assigning the rows of each table to “slices”, and storing multiple copies (“duplicas”) of each slice across the persistent storage of multiple nodes of the shared-nothing database system. When the data for a table is distributed among the nodes of a shared-nothing system in this manner, requests to read data from a particular row of the table may be handled by any node that stores a duplica of the slice to which the row is assigned. For each slice, a single duplica of the slice is designated as the “primary duplica”. All DML operations (e.g. inserts, deletes, updates, etc.) that target a particular row of the table are performed by the node that has the primary duplica of the slice to which the particular row is assigned. The changes made by the DML operations are then propagated from the primary duplica to the other duplicas (“secondary duplicas”) of the same slice.

公开(公告)号：US11514029B2

公开(公告)日：2022-11-29

申请号：US17136568

申请日：2020-12-29

Applicant: Oracle International Corporation

Inventor： Vasudha Krishnaswamy ,  Sukhada Pendse ,  Solmaz Kolahi ,  Ankita Kumar ,  Ajit Mylavarapu ,  Garret F. Swart ,  Tirthankar Lahiri ,  Juan R. Loaiza

IPC: G06F16/23 ,  G06F16/27 ,  G06F16/21

Abstract: A shared-nothing database system is provided in which parallelism and workload balancing are increased by assigning the rows of each table to “slices”, and storing multiple copies (“duplicas”) of each slice across the persistent storage of multiple nodes of the shared-nothing database system. When the data for a table is distributed among the nodes of a shared-nothing system in this manner, requests to read data from a particular row of the table may be handled by any node that stores a duplica of the slice to which the row is assigned. For each slice, a single duplica of the slice is designated as the “primary duplica”. All DML operations (e.g. inserts, deletes, updates, etc.) that target a particular row of the table are performed by the node that has the primary duplica of the slice to which the particular row is assigned. The changes made by the DML operations are then propagated from the primary duplica to the other duplicas (“secondary duplicas”) of the same slice.

公开(公告)号：US20210390075A1

公开(公告)日：2021-12-16

申请号：US17176856

申请日：2021-02-16

Applicant: Oracle International Corporation

Inventor： Tinggang Wang ,  Shuo Yang ,  Hideaki Kimura ,  Garret F. Swart ,  Spyros Blanas

IPC: G06F15/173 ,  G06F16/2453

Abstract: Systems and methods for reducing latency of probing operations of remotely located linear hash tables are described herein. In an embodiment, a system receives a request to perform a probing operation on a remotely located linear hash table based on a key value. Prior to performing the probing operation, the system dynamically predicts a number of slots for a single read of the linear hash table to minimize total cost for an average probing operation. The system determines a hash value based on the key value and determines a slot of the linear hash table to which the hash value corresponds. After predicting the number of slots, the system issues an RDMA request to perform a read of the predicted number of slots from the linear hash table starting at the slot to which the hash value corresponds.

公开(公告)号：US20200057731A1

公开(公告)日：2020-02-20

申请号：US16542222

申请日：2019-08-15

Applicant: Oracle International Corporation

Inventor： Hideaki Kimura ,  Garret F. Swart ,  Spyros Blanas

IPC: G06F12/1081 ,  G06F16/23

Abstract: Techniques are described for offloading remote direct memory operations (RDMOs) to “execution candidates”. The execution candidates may be any hardware capable of performing the offloaded operation. Thus, the execution candidates may be network interface controllers, specialized co-processors, FPGAs, etc. The execution candidates may be on a machine that is remote from the processor that is offloading the operation, or may be on the same machine as the processor that is offloading the operation. Details for certain specific RDMOs, which are particularly useful in online transaction processing (OLTP) and hybrid transactional/analytical (HTAP) workloads, are provided.

公开(公告)号：US20200042489A1

公开(公告)日：2020-02-06

申请号：US16055978

申请日：2018-08-06

Applicant: Oracle International Corporation

Inventor： Tirthankar Lahiri ,  Juan R. Loaiza ,  Garret F. Swart ,  Jesse Kamp ,  Avneesh Pant ,  Hideaki Kimura

IPC: G06F15/167 ,  G06F15/173 ,  G06F9/54 ,  G06F9/455

Abstract: Techniques are provided to allow more sophisticated operations to be performed remotely by machines that are not fully functional. Operations that can be performed reliably by a machine that has experienced a hardware and/or software error are referred to herein as Remote Direct Memory Operations or “RDMOs”. Unlike RDMAs, which typically involve trivially simple operations such as the retrieval of a single value from the memory of a remote machine, RDMOs may be arbitrarily complex. The techniques described herein can help applications run without interruption when there are software faults or glitches on a remote system with which they interact.

公开(公告)号：US10346315B2

公开(公告)日：2019-07-09

申请号：US15606327

申请日：2017-05-26

Applicant: Oracle International Corporation

Inventor： Siddharth Teotia ,  Krishna Kunchithapadam ,  Tirthankar Lahiri ,  Jesse Kamp ,  Michael J. Gleeson ,  Juan R. Loaiza ,  Garret F. Swart ,  Neil J. S. MacNaughton ,  Kam Shergill

IPC: G06F16/22 ,  G06F16/901 ,  G06F12/1018 ,  G06F16/2453

Abstract: A hashing scheme includes a cache-friendly, latchless, non-blocking dynamically resizable hash index with constant-time lookup operations that is also amenable to fast lookups via remote memory access. Specifically, the hashing scheme provides each of the following features: latchless reads, fine grained lightweight locks for writers, non-blocking dynamic resizability, cache-friendly access, constant-time lookup operations, amenable to remote memory access via RDMA protocol through one sided read operations, as well as non-RDMA access.

公开(公告)号：US20160098364A1

公开(公告)日：2016-04-07

申请号：US14964805

申请日：2015-12-10

Applicant: Oracle International Corporation

Inventor： Kathirgamar Aingaran ,  Garret F. Swart

IPC: G06F13/10 ,  G06F13/40 ,  G06F13/362

CPC classification number: G06F9/30065 ,  G06F9/381 ,  G06F9/3851 ,  G06F9/3867 ,  G06F9/546 ,  G06F12/0804 ,  G06F12/082 ,  G06F12/12 ,  G06F12/1408 ,  G06F12/1475 ,  G06F13/102 ,  G06F13/362 ,  G06F13/4068 ,  G06F15/17331 ,  G06F15/7889 ,  G06F17/30324 ,  G06F17/30442 ,  G06F17/30483 ,  G06F17/30495 ,  G06F17/30498 ,  G06F17/30501 ,  G06F17/30519 ,  G06F17/30578 ,  G06F17/30595 ,  G06F17/30867 ,  G06F21/6209 ,  H04L69/14 ,  Y02D10/14 ,  Y02D10/151 ,  Y02D10/45

Abstract: A method and apparatus for reconfiguring hardware structures to pipeline the execution of multiple special purpose hardware implemented functions, without saving intermediate results to memory, is provided. Pipelining functions in a program is typically performed by a first function saving its results (the “intermediate results”) to memory, and a second function subsequently accessing the memory to use the intermediate results as input. Saving and accessing intermediate results stored in memory incurs a heavy performance penalty, requires more power, consumes more memory bandwidth, and increases the memory footprint. Due to the ability to redirect the input and output of the hardware structures, intermediate results are passed directly from one special purpose hardware implemented function to another without storing the intermediate results in memory. Consequently, a program that utilizes the method or apparatus, reduces power consumption, consumes less memory bandwidth, and reduces the program's memory footprint.

Abstract translation: 提供了一种用于重新配置硬件结构以管理多个专用硬件实现的功能的执行而不将中间结果保存到存储器的方法和装置。 程序中的流水线功能通常由将其结果（“中间结果”）保存到存储器的第一功能执行，而第二功能随后访问存储器以将中间结果用作输入。 保存和访问存储在内存中的中间结果会导致严重的性能损失，需要更多的电力，消耗更多的内存带宽，并增加内存占用。 由于能够重定向硬件结构的输入和输出，中间结果直接从一个专用硬件实现的功能传递到另一个而不将中间结果存储在存储器中。 因此，利用该方法或装置的程序降低功耗，消耗较少的存储器带宽，并减少程序的存储器占用。

公开(公告)号：US09158810B2

公开(公告)日：2015-10-13

申请号：US13778307

申请日：2013-02-27

Applicant: Oracle International Corporation

Inventor： Kathirgamar Aingaran ,  William H. Bridge, Jr. ,  Garret F. Swart ,  Sumti Jairath ,  John G. Johnson

IPC: G06F3/00 ,  G06F9/44 ,  G06F9/46 ,  G06F13/00 ,  G06F17/30 ,  G06F9/54 ,  G06F9/38 ,  G06F12/08 ,  G06F12/12 ,  G06F15/173 ,  G06F12/14

CPC classification number: G06F9/30065 ,  G06F9/381 ,  G06F9/3851 ,  G06F9/3867 ,  G06F9/546 ,  G06F12/0804 ,  G06F12/082 ,  G06F12/12 ,  G06F12/1408 ,  G06F12/1475 ,  G06F13/102 ,  G06F13/362 ,  G06F13/4068 ,  G06F15/17331 ,  G06F15/7889 ,  G06F17/30324 ,  G06F17/30442 ,  G06F17/30483 ,  G06F17/30495 ,  G06F17/30498 ,  G06F17/30501 ,  G06F17/30519 ,  G06F17/30578 ,  G06F17/30595 ,  G06F17/30867 ,  G06F21/6209 ,  H04L69/14 ,  Y02D10/14 ,  Y02D10/151 ,  Y02D10/45

Abstract: A method and apparatus for sending and receiving messages between nodes on a compute cluster is provided. Communication between nodes on a compute cluster, which do not share physical memory, is performed by passing messages over an I/O subsystem. Typically, each node includes a synchronization mechanism, a thread ready to receive connections, and other threads to process and reassemble messages. Frequently, a separate queue is maintained in memory for each node on the I/O subsystem sending messages to the receiving node. Such overhead increases latency and limits message throughput. Due to a specialized coprocessor running on each node, messages on an I/O subsystem are sent, received, authenticated, synchronized, and reassembled at a faster rate and with lower latency. Additionally, the memory structure used may reduce memory consumption by storing messages from multiple sources in the same memory structure, eliminating the need for per-source queues.

Abstract translation: 提供了一种用于在计算集群上的节点之间发送和接收消息的方法和装置。 通过在I / O子系统上传递消息来执行不共享物理内存的计算集群上的节点之间的通信。 通常，每个节点包括同步机制，准备好接收连接的线程以及处理和重新组合消息的其他线程。 通常，I / O子系统中的每个节点向存储器中维护单独的队列，向接收节点发送消息。 这种开销增加了延迟并限制了消息吞吐量。 由于在每个节点上运行的专用协处理器，I / O子系统上的消息以更快的速率和更低的延迟被发送，接收，认证，同步和重新组装。 此外，所使用的存储器结构可以通过在相同存储器结构中存储来自多个源的消息来减少存储器消耗，从而消除对每个源队列的需要。