CN112395141A - Data page management method and device, electronic equipment and storage medium - Google Patents
Data page management method and device, electronic equipment and storage medium Download PDFInfo
- Publication number
- CN112395141A CN112395141A CN202011337844.7A CN202011337844A CN112395141A CN 112395141 A CN112395141 A CN 112395141A CN 202011337844 A CN202011337844 A CN 202011337844A CN 112395141 A CN112395141 A CN 112395141A
- Authority
- CN
- China
- Prior art keywords
- data page
- array
- page information
- active node
- determined
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F11/00—Error detection; Error correction; Monitoring
- G06F11/07—Responding to the occurrence of a fault, e.g. fault tolerance
- G06F11/16—Error detection or correction of the data by redundancy in hardware
- G06F11/20—Error detection or correction of the data by redundancy in hardware using active fault-masking, e.g. by switching out faulty elements or by switching in spare elements
- G06F11/202—Error detection or correction of the data by redundancy in hardware using active fault-masking, e.g. by switching out faulty elements or by switching in spare elements where processing functionality is redundant
- G06F11/2035—Error detection or correction of the data by redundancy in hardware using active fault-masking, e.g. by switching out faulty elements or by switching in spare elements where processing functionality is redundant without idle spare hardware
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F11/00—Error detection; Error correction; Monitoring
- G06F11/07—Responding to the occurrence of a fault, e.g. fault tolerance
- G06F11/16—Error detection or correction of the data by redundancy in hardware
- G06F11/20—Error detection or correction of the data by redundancy in hardware using active fault-masking, e.g. by switching out faulty elements or by switching in spare elements
- G06F11/202—Error detection or correction of the data by redundancy in hardware using active fault-masking, e.g. by switching out faulty elements or by switching in spare elements where processing functionality is redundant
- G06F11/2023—Failover techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/21—Design, administration or maintenance of databases
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/27—Replication, distribution or synchronisation of data between databases or within a distributed database system; Distributed database system architectures therefor
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2201/00—Indexing scheme relating to error detection, to error correction, and to monitoring
- G06F2201/80—Database-specific techniques
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Databases & Information Systems (AREA)
- Quality & Reliability (AREA)
- Data Mining & Analysis (AREA)
- Computing Systems (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention discloses a data page management method and device, electronic equipment and a storage medium. Applied to an active node in a shared storage database cluster, the method comprising: writing first local data page information which cannot be determined to be valid according to the external global array and the external local array in the current active node into a first array to be determined until first arrays to be determined of all active nodes are obtained; according to the first array to be determined of other active nodes, determining a data page which is modified in the first array to be determined in the current active node and has the latest data page sequence number greater than or equal to the log sequence number of the data page in the disk of the shared storage database cluster as a target local data page of the current active node; the destination local data page of each active node is accessed in response to an instance program of the shared storage database cluster. The embodiment of the invention reduces a large amount of invalid IOs in the process of determining whether the data page in the active node cache is latest, and improves the fault processing efficiency.
Description
Technical Field
The embodiment of the invention relates to the technical field of data management in the technical field of computers, in particular to a data page management method and device, electronic equipment and a storage medium.
Background
In a shared storage database cluster environment, the same data page may be distributed in caches of different database instance nodes, and it is not guaranteed that the data page contents in each node cache are completely the same, the latest data is only stored in some node caches, and a history version of the data page is stored in other node caches. The shared storage database cluster environment uses Global Buffer Server (GBS) and Local Buffer Server (LBS) to complete access control to the data pages. REDO logs are an important means in database management systems to handle system failure recovery. The Log Sequence Number (LSN) is an incremental value maintained inside the dbms to identify the REDO Log records, and each LSN value represents a set of a series of data modification operations inside the dbms; the modify data operation generates the REDO log while recording the LSN value in the data page header.
In a shared storage database cluster environment, global latch information is managed according to data page number fragments, and each node maintains part of global latch information; when the node failure occurs, the remaining active nodes perform failure processing, and data pages in the REDO log recovery cache of the failed node need to be redone. Before REDO of the REDO log of the failed node, it is necessary to determine whether the data PAGEs in the cache of the remaining active nodes are the latest, in the prior art, all the data PAGEs in the cache are compared with the data in the DISK, if the data PAGE LSN (DISK _ LSN) read out from the DISK is less than or equal to the data PAGE LSN (PAGE _ LSN) in the cache, it indicates that the data PAGE in the cache is valid, otherwise, it is invalid, and it needs to be discarded. However, the method of directly reading the data page comparison LSN in the disk may generate a large number of invalid IOs, which reduces the failure processing efficiency.
Disclosure of Invention
The invention provides a data page management method, a data page management device, electronic equipment and a storage medium, so that a large number of invalid IOs are reduced, and the fault processing efficiency is improved.
In a first aspect, an embodiment of the present invention provides a data page management method, which is applied to an active node in a shared storage database cluster, and the method includes:
writing first local data page information which cannot be determined to be valid according to an external global array and an external local array in a current active node into a first array to be determined, wherein the external global array is global data page information of other active nodes, and the external local array is local data page information of other active nodes until first arrays to be determined of all active nodes are obtained;
according to the first array to be determined of other active nodes, determining a data page which is modified in the first array to be determined in the current active node and has the latest data page sequence number greater than or equal to the log sequence number of the data page in the disk of the shared storage database cluster as a target local data page of the current active node until the target local data pages of all the active nodes are obtained;
the destination local data page of each active node is accessed in response to an instance program of the shared storage database cluster.
Further, before writing the first local data page information that cannot be determined to be valid according to the external global array and the external local array in the current active node into the first array to be determined, the method further includes:
searching corresponding global data page information in the external global array according to the first local data page information in the memory of the current active node;
determining the validity of first local data page information in the memory of the current active node according to the corresponding global data page information in the external global array and the blocking mode corresponding to each active node;
and if the first local data page information in the memory of the current active node is valid, taking the first local data page information in the memory of the current active node as a target local data page of the current active node.
Further, the determining the validity of the first local data page information in the memory of the current active node according to the blocking mode corresponding to the global data page information corresponding to each active node in the external global array includes:
if the external global array does not have corresponding global data page information, the validity of the first local data page information in the memory of the active node cannot be determined;
or, if the corresponding data page information exists in the external global array and each node does not have the corresponding blocking mode, the validity of the first local data page information in the memory of the current active node cannot be determined.
Further, after the failing to determine the validity of the first local data page information in the memory of the current active node, the method further includes:
searching corresponding local data page information in the external local array according to the first local data page information in the memory of the current active node;
determining the validity of the first local data page information in the memory of the current active node according to the local data page information corresponding to the external local array and the blocking mode corresponding to each active node;
and if the first local data page information in the memory of the current active node is valid, taking the first local data page information in the memory of the current active node as a target local data page of the current active node.
Further, the first to-be-determined array of other active nodes includes:
if the first local data page information of the current active node cannot determine the validity according to the external global data group and the external local array, sending the first array to be determined to the other active nodes;
and each active node receives the respective first array to be determined of the other nodes to form the first array to be determined of the other active nodes.
Further, before determining, according to the first to-be-determined array of the other active nodes, that the data page in the first to-be-determined array of the current active node that is modified and has the latest data page sequence number greater than or equal to the data page log sequence number in the disk of the shared storage database cluster is used as the destination local data page of the current active node, the method further includes:
correspondingly selecting data page information corresponding to the latest log serial number of the latest log serial number which is larger than the latest log serial number of the first local data page information in the current active node from the first array to be determined of the other active nodes;
and if not, correspondingly selecting the data page information corresponding to the active node with the minimum node number in the other active nodes, wherein the latest log serial number is equal to the latest log serial number of the first local data page information in the current active node, from the first array to be determined of the other active nodes.
Further, the data page information corresponding to the latest log sequence number, of which the latest log sequence number is greater than that of the first local data page information in the current active node, is correspondingly selected from the first to-be-determined arrays of the other active nodes; if not, after correspondingly selecting the data page information corresponding to the active node with the minimum node number in the other active nodes, of which the latest log sequence number is equal to the latest log sequence number of the first local data page information in the current active node, from the first array to be determined of the other active nodes, the method further includes:
if the node number of the last modified data page in the corresponding data page information is equal to a preset value, directly discarding the first local data page information in the first array to be determined;
and if the node number of the last modified data page in the correspondingly selected data page information is not equal to a preset value, reading the log serial number of the corresponding data page from the disk.
In a second aspect, an embodiment of the present invention further provides a data page management apparatus, where the apparatus includes:
the to-be-determined writing module is used for writing first local data page information which cannot be determined to be valid according to an external global array and an external local array in a current active node into a first to-be-determined array, wherein the external global array is global data page information of other active nodes, and the external local array is local data page information of other active nodes until the first to-be-determined arrays of all the active nodes are obtained;
the destination determining module is used for determining a data page which is modified in the first array to be determined in the current active node and has the latest data page sequence number greater than or equal to the data page log sequence number in the disk of the shared storage database cluster as a destination local data page of the current active node according to the first array to be determined of other active nodes until the destination local data pages of all the active nodes are obtained;
and the effective access module is used for responding the access of the example program of the shared storage database cluster to the target local data page of each active node.
In a third aspect, an embodiment of the present invention further provides an electronic device, where the electronic device includes:
one or more processors;
a storage device for storing one or more programs,
when executed by the one or more processors, cause the one or more processors to implement any of the data page management methods.
In a fourth aspect, the present invention further provides a computer-readable storage medium, on which a computer program is stored, which when executed by a processor implements any of the data page management methods.
Writing effective first local data page information which cannot be determined according to an external global array and an external local array in a current active node into a first array to be determined, wherein the external global array is global data page information of other active nodes, and the external local array is local data page information of other active nodes until the first array to be determined of all the active nodes is obtained; according to the first array to be determined of other active nodes, determining a data page which is modified in the first array to be determined in the current active node and has the latest data page sequence number greater than or equal to the log sequence number of the data page in the disk of the shared storage database cluster as a target local data page of the current active node until the target local data pages of all the active nodes are obtained; the target local data PAGE of each active node responds to the access of the example program of the shared storage database cluster, the problem that in the process of determining whether the data PAGE in the cache of the remaining active nodes is the latest, the log serial number of the data PAGE comparison data PAGE is directly read from a DISK, a large number of invalid IOs are generated, and the fault processing efficiency is reduced is solved.
Drawings
FIG. 1 is a flowchart of a data page management method according to a first embodiment of the present invention;
FIG. 2 is a flowchart of a data page management method according to a second embodiment of the present invention;
FIG. 3 is a flowchart of a data page management method according to a third embodiment of the present invention;
FIG. 4 is a schematic structural diagram of a data page management apparatus according to a fourth embodiment of the present invention;
fig. 5 is a schematic structural diagram of an electronic device in a fifth embodiment of the present invention.
Detailed Description
The present invention will be described in further detail with reference to the accompanying drawings and examples. It is to be understood that the specific embodiments described herein are merely illustrative of the invention and are not limiting of the invention. It should be further noted that, for the convenience of description, only some of the structures related to the present invention are shown in the drawings, not all of the structures.
Example one
Fig. 1 is a flowchart of a data page management method according to an embodiment of the present invention, where this embodiment is applicable to a situation where data pages in remaining active nodes need to be managed when a node in a shared storage database cluster fails, and the method may be executed by a data page management apparatus, where the apparatus may be implemented in a software/hardware manner, and may specifically inherit in an electronic device with storage and computation capabilities to perform data page management.
As shown in fig. 1, a data page management method is provided, which is applied to an active node in a shared storage database cluster, and specifically includes the following steps:
step S110, writing first local data page information which cannot be determined to be valid in the current active node according to an external global array and an external local array into a first array to be determined, wherein the external global array is global data page information of other active nodes, and the external local array is local data page information of other active nodes until the first array to be determined of all the active nodes is obtained;
in the embodiment of the invention, the active node can be understood as a non-fault node in the cluster environment of the shared storage database during fault processing. The currently active node may be understood as any of the non-failed nodes in the shared storage database cluster environment when failing. The external global array may be understood as an array formed by collecting global data page information of other active nodes by the current active node, and is cached in the memory of the current active node. The external local array may be understood as an array formed by collecting local data page information of other active nodes by the current active node, and cached in the memory of the current active node. The first local data page information may be understood as any data page information cached in the memory of the currently active node. The first array to be determined may be understood as an array formed by data page information of which validity cannot be determined in the memory of the current active node, wherein the first array to be determined is cached in the memory of the current node in a new memory structure.
In the embodiment of the present invention, the local data page information may be understood as local control information of a data page cached in the active node. Wherein the local control information of the data page includes: data page address, data page log information, etc. The global data page information may be understood as global control information of the data page cached in the active node. Wherein the global control information of the data page comprises: basic information, blocking information, latest data distribution information, etc. of the data page. The basic information and the latest data distribution information of the data page may be:
TS _ ID data page belonged table space number;
FILE _ ID data page belonging FILE number;
PAGE NO data PAGE number;
the FRESH _ EP modifies the node number of the data page at last;
ACCESS _ MAP has an array of node numbers of the most recent data page;
FRESH LSN value of the most recent data page.
The blocking information of the data page may be:
EP _ NO owns the authorized instance node number;
MODE lock MODE.
In the embodiment of the invention, in the shared storage database cluster environment, in the process of determining whether the data page in the cache of the non-fault node is the latest, the current active node needs to collect the global data page information and the local data page information of other active nodes to respectively form an external global array and an external local array, so as to assist the current active node in judging the validity of the data page information in the memory. And determining the validity of the current active node according to the external global array and the external local array, namely determining whether the data page information stored in the current active node is up-to-date according to the external global array and the external local array. If the data page information stored in the current active node is determined to be valid according to the external global array and the external local array, the data page information stored in the current active node is reserved in the memory of the current active node; and if the validity of the data page information cannot be determined according to the external global array and the external local array, writing the data page information in the current active node into the first array to be determined from the memory of the current active node. And storing the data page information in the memory of the current active node before the data page information is not written into the first array to be determined.
In the embodiment of the invention, after the current active node collects the global data information and the local data page information of other active nodes to respectively form the external global array and the external local array, the corresponding hash cache structures can be respectively constructed to obtain the hash value lists, so that the global data page information and the local data page information of the data pages in the external global array and the external local array can be conveniently searched.
Step S120, according to the first array to be determined of other active nodes, determining a data page which is modified in the first array to be determined in the current active node and has the latest data page sequence number more than or equal to the data page log sequence number in the disk of the shared storage database cluster as a target local data page of the current active node until the target local data pages of all the active nodes are obtained;
in the embodiment of the present invention, the first to-be-determined array of the other active nodes may be understood as an array formed by the first to-be-determined arrays of each active node except the current active node. The first to-be-determined arrays of other active nodes comprise the first to-be-determined arrays of all active nodes except the current active node in the shared storage database cluster. The latest data page sequence number can be understood as the LSN value of the latest data page in the FRESH _ LSN in the data page information when any data page in the first array to be determined of the current active node is judged to be valid. The log serial number of the data page in the disk of the shared storage database cluster can be understood as the log serial number in the data page information read in the disk according to the data page information when the validity of any data page in the first array to be determined of the current active node is judged. The destination local data page may be understood as a data page that is valid in the currently active node.
In the embodiment of the invention, according to the comparison of the same data page information in the first array to be determined of other active nodes and the first array to be determined of the current active node, whether the data page in the first array to be determined of the current active node is modified or not is determined. If the data page in the first array to be determined in the current active node is modified, the validity of the data page in the first array to be determined in the current active node needs to be determined according to the log sequence number of the data page in the disk of the shared storage database cluster and the latest log sequence number of the data page in the first array to be determined in the current active node. And if the latest log sequence of the data page in the first array to be determined in the current active node is smaller than the log sequence number of the data page in the disk of the shared storage database cluster, the data page information in the first array to be determined in the current active node is invalid, and the data page information in the first array to be determined in the current active node is discarded.
Step S130, the destination local data page of each active node responds to the instance program access of the shared storage database cluster.
In the embodiment of the present invention, the access of the instance program may be understood as all operations that can be performed after each active node in the shared storage database cluster confirms the latest data page in the memory, and is not limited to the data access in which the instance program calls the data information of the shared storage database cluster. The destination local data page of each active node may be understood as a valid data page in each active node in the shared storage database cluster, that is, all valid data pages in the current shared storage database cluster.
In the embodiment of the invention, after all the active nodes in the shared storage database cluster confirm the validity of the data pages in the memory and discard the invalid data pages in the active nodes, the data pages cached in the memory of the active nodes in the shared storage database cluster are all valid data pages, namely, target local data pages. And when an instance program performs data access or performs operation on other effective data pages, sending a corresponding operation request, and performing corresponding response on the target local data page of each active node in the shared storage database cluster according to the request.
Further, before writing the first local data page information that cannot be determined to be valid according to the external global array and the external local array in the current active node into the first array to be determined, the method further includes:
searching corresponding global data page information in the external global array according to first local data page information in the memory of the active node;
determining the validity of first local data page information in the memory of the active node according to the corresponding global data page information in the external global array and the blocking mode corresponding to each active node;
and if the first local data page information in the memory of the current active node is valid, taking the first local data page information in the memory of the current active node as a target local data page of the current active node.
In the embodiment of the invention, the blocking mode can be understood as a blocking mode of data page information in the memory of the current active node. The blocking mode can be divided into three types, namely an NA mode, an S mode and an X mode. The NA module can be understood that the current active node has no modification authority on the data page in the memory; the S mode can be understood that the current active node has a read right to a data page in the memory, a plurality of nodes can have the S right at the same time, and any node cannot modify the data page; the X mode can be understood as that only the current active node can modify the data page information in the memory, and other nodes cannot access and modify the data page.
In the embodiment of the invention, according to the first local data page information in the memory of the active node, the global data page information corresponding to the first local data page information is searched in the collected external global array; and determining the validity of the first local data page information according to the corresponding authority of the global data page information in the external global array and the corresponding locking mode of the first local data page information in each active node. If the blocking mode of the current active node for the first local data page information is the S mode or the X mode, the first local data page information in the memory of the current active node is valid, that is, the first local data page information is not modified after being shared or only the current active node can be modified, and the first local data page information in the memory of the current active node is latest. If the current active node is in the NA mode, the current active node has no modification authority for the first local data page information, and the validity of the first local data page information in the current active node needs to be judged according to the blocking mode corresponding to the first local data page information in other active nodes in the external global array. And if the blocking mode of any one of the other active nodes in the external global array on the first local data page information is the S blocking mode, the first local data page information in the memory of the current active node is valid. If the first local data page information in the memory of the current active node is valid, the first local data page information in the memory of the current active node is used as a target local data page of the current active node, that is, the first local data page information in the memory of the current active node is kept in the memory of the current active node as valid data page information.
Further, the determining the validity of the first local data page information in the memory of the current active node according to the blocking mode corresponding to the global data page information corresponding to each active node in the external global array includes:
if the external global array does not have corresponding global data page information, the information validity of a first local data page in the memory of the active node cannot be determined;
or, if the corresponding data page information exists in the external global array and each node does not have the corresponding blocking mode, it cannot be determined that the information of the first local data page in the memory of the current active node is valid.
In the embodiment of the invention, if the corresponding global data page control information is not found in the external global array according to the first local data page information in the memory of the current active node, the validity of the first local data page information in the memory of the current active node cannot be determined only according to the blocking mode of the current active node.
In the embodiment of the invention, if the corresponding global data page control information is found in the external global array according to the first local data page information in the memory of the current active node, but the locking mode of the current active node is an NA mode, and the locking mode of any one of other active nodes is not an S locking mode, the validity of the first local data page information in the memory of the current active node cannot be judged.
Further, after it cannot be determined that the information of the first local data page in the memory of the current active node is valid, the method further includes:
searching corresponding local data page information in the external local array according to the first local data page information in the memory of the current active node;
determining the validity of the first local data page information in the memory of the current active node according to the local data page information corresponding to the external local array and the blocking mode corresponding to each active node;
and if the first local data page information in the memory of the current active node is valid, taking the first local data page information in the memory of the current active node as a target local data page of the current active node.
In the embodiment of the present invention, if the validity of the first local data page information in the memory of the current active node cannot be determined by searching the global data page information in the external global array according to the first local data page information in the memory of the current active node, the local data page information is searched in the external local array according to the first local data page information in the memory of the current active node. And searching the latest data page log serial number in the data page information pointed by the data page address in the local data page information in the external local data group according to the searched first local data page information in the memory of the current active node, and judging the validity of the first local data page information in the memory of the current active node. If the latest data page log serial number in the data page information pointed by the data page address in the local data page information is equal to the data page log serial number in the first local data page information in the current active node memory and the active node corresponding to the data page address in the local data page information is in an S mode or an X mode relative to the first local data page information blocking mode, the first local data page information in the current active node memory is valid. If the corresponding local data page information is not found in the external local array according to the first local data page information in the memory of the current active node, the validity of the first local data page information in the memory of the current active node cannot be determined.
Writing effective first local data page information which cannot be determined according to an external global array and an external local array in a current active node into a first array to be determined, wherein the external global array is global data page information of other active nodes, and the external local array is local data page information of other active nodes until the first array to be determined of all the active nodes is obtained; according to the first array to be determined of other active nodes, determining a data page which is modified in the first array to be determined in the current active node and has the latest data page sequence number greater than or equal to the log sequence number of the data page in the disk of the shared storage database cluster as a target local data page of the current active node until the target local data pages of all the active nodes are obtained; the target local data PAGE of each active node responds to the access of the example program of the shared storage database cluster, the problem that in the process of determining whether the data PAGE in the cache of the remaining active nodes is the latest, the log serial number of the data PAGE comparison data PAGE is directly read from a DISK, a large number of invalid IOs are generated, and the fault processing efficiency is reduced is solved.
Example two
Fig. 2 is a flowchart of a data page management method according to a second embodiment of the present invention. The technical scheme of the embodiment is further refined on the basis of the technical scheme, and specifically mainly comprises the following steps:
step S210, writing first local data page information which cannot be determined to be valid in the current active node according to an external global array and an external local array into a first array to be determined, wherein the external global array is global data page information of other active nodes, and the external local array is local data page information of other active nodes until the first array to be determined of all the active nodes is obtained;
in the embodiment of the invention, when the validity of the first local data page information in the current active node cannot be determined according to the external global array and the external local array, the first local data page information is written into the first array to be determined. And writing the first local data page information into the first array to be determined, wherein the first local data page information needs to be written into the first array to be determined in a new memory structure form. The new memory structure RECV _ CTL comprises: the table space number TS _ ID of the data PAGE, the FILE number FILE _ ID of the data PAGE, the data PAGE number PAGE _ NO, the node number FRESH _ EP of the last modified data PAGE, the LSN value FRESH _ LSN of the latest data PAGE and the like.
Step S220, if the first local data page information of the current active node can not determine validity according to the external global data group and the external local array, sending the first array to be determined to the other active nodes; and each active node receives the respective first array to be determined of the other nodes to form the first array to be determined of the other active nodes.
In the embodiment of the present invention, if the validity of the first local data page information in the current active node cannot be determined according to the external global array and the external local array, before the first array to be determined is sent to other active nodes, each node needs to traverse the first array to be determined of itself, and confirm the validity of the first local data page information in the memory of the current active node to other active nodes. And if the first local data page information in the memory of the current active node is determined to be valid to any active node of other active nodes, the first local data page information is removed from the first array to be determined of the current active node and is stored in the memory of the current active node as a target local data page of the current active node.
In the embodiment of the invention, if the validity of the first local data page information in the current active node cannot be determined according to the external global array and the external local array, the first array to be determined of the current active node is sent to other active nodes. The current active node receives the first array to be determined respectively sent by other active nodes to form the first array to be determined of other active nodes. The first to-be-determined arrays of the other active nodes comprise first to-be-determined arrays corresponding to the other active nodes.
Step S230, according to the first array to be determined of other active nodes, determining a data page which is modified in the first array to be determined in the current active node and has the latest data page sequence number more than or equal to the data page log sequence number in the disk of the shared storage database cluster as a target local data page of the current active node until the target local data pages of all the active nodes are obtained;
in step S240, the destination local data page of each active node responds to the instance program access of the shared storage database cluster.
Writing effective first local data page information which cannot be determined according to an external global array and an external local array in a current active node into a first array to be determined, wherein the external global array is global data page information of other active nodes, and the external local array is second local data page information of other active nodes until the first array to be determined of all the active nodes is obtained; according to the first array to be determined of other active nodes, determining a data page which is modified in the first array to be determined in the current active node and has the latest data page sequence number greater than or equal to the log sequence number of the data page in the disk of the shared storage database cluster as a target local data page of the current active node until the target local data pages of all the active nodes are obtained; the target local data PAGE of each active node responds to the access of the example program of the shared storage database cluster, the problem that in the process of determining whether the data PAGE in the cache of the remaining active nodes is the latest, the log serial number of the data PAGE comparison data PAGE is directly read from a DISK, a large number of invalid IOs are generated, and the fault processing efficiency is reduced is solved.
EXAMPLE III
Fig. 3 is a flowchart of a data page management method according to a second embodiment of the present invention. The technical scheme of the embodiment is further refined on the basis of the technical scheme, and specifically mainly comprises the following steps:
step S310, writing first local data page information which cannot be determined to be valid in the current active node according to an external global array and an external local array into a first array to be determined, wherein the external global array is global data page information of other active nodes, and the external local array is local data page information of other active nodes until the first array to be determined of all the active nodes is obtained;
step S320, correspondingly selecting data page information corresponding to the latest log serial number of the latest log serial number which is larger than the latest log serial number of the first local data page information in the current active node from the first array to be determined of the other active nodes; and if not, correspondingly selecting the data page information corresponding to the active node with the minimum node number in the other active nodes, wherein the latest log serial number is equal to the latest log serial number of the first local data page information in the current active node, from the first array to be determined of the other active nodes.
In the embodiment of the invention, if the first array to be determined of other active nodes has the data page information corresponding to the first local data page information in the current active node, the data page information of which the latest log serial number is greater than the log serial number of the first local data page information in the current active node is selected from the first array to be determined of other active nodes. And if the data page information which meets the conditions does not exist, selecting the data page information of which the latest log serial number of the data page information in the first array to be determined of other active nodes is equal to the log serial number of the first local data page information in the current active node, and selecting the data page information in the node with the minimum node number.
Further, the data page information corresponding to the latest log sequence number, of which the latest log sequence number is greater than that of the first local data page information in the current active node, is correspondingly selected from the first to-be-determined arrays of the other active nodes; if not, after correspondingly selecting the data page information corresponding to the active node with the minimum node number in the other active nodes, of which the latest log sequence number is equal to the latest log sequence number of the first local data page information in the current active node, from the first array to be determined of the other active nodes, the method further includes:
if the node number of the last modified data page in the corresponding data page information is equal to a preset value, directly discarding the first local data page information in the first array to be determined;
and if the node number of the last modified data page in the correspondingly selected data page information is not equal to a preset value, reading the log serial number of the corresponding data page from the disk.
In the embodiment of the present invention, the preset value may be understood as a node number corresponding to a case where information of a first local data page in a first array to be determined in a current active node is not modified.
In the embodiment of the invention, the node number of the last modified data page in the corresponding data page information selected from the first array to be determined of other active nodes is equal to the node number corresponding to the unmodified first local data page information in the first array to be determined in the current active node, which indicates that the first local data page information in the first array to be determined in the current active node is not updated and is not the latest data page information, and the corresponding data page information does not need to be read from a magnetic disk for comparison, and the first local data page information in the first array to be determined in the current active node is directly discarded.
In the embodiment of the invention, the node number of the last modified data page in the corresponding data page information selected from the first array to be determined of other active nodes is not equal, and the node number corresponding to the unmodified first local data page information in the first array to be determined in the current active node indicates that the modified first local data page information in the first array to be determined in the current active node cannot judge whether the first local data page information in the first array to be determined in the current active node is the latest data page information, the corresponding data page information needs to be read from a disk for comparison, and the size of the latest data page sequence number of the first local data page information in the first array to be determined in the current active node is compared with the data page log sequence number read from the disk. Step S330, according to the first array to be determined of other active nodes, determining a data page which is modified in the first array to be determined in the current active node and has the latest data page sequence number more than or equal to the data page log sequence number in the disk of the shared storage database cluster as a target local data page of the current active node until the target local data pages of all the active nodes are obtained;
step S340, the destination local data page of each active node responds to the access of the instance program of the shared storage database cluster.
Writing effective first local data page information which cannot be determined according to an external global array and an external local array in a current active node into a first array to be determined, wherein the external global array is global data page information of other active nodes, and the external local array is second local data page information of other active nodes until the first array to be determined of all the active nodes is obtained; according to the first array to be determined of other active nodes, determining a data page which is modified in the first array to be determined in the current active node and has the latest data page sequence number greater than or equal to the log sequence number of the data page in the disk of the shared storage database cluster as a target local data page of the current active node until the target local data pages of all the active nodes are obtained; the target local data PAGE of each active node responds to the access of the example program of the shared storage database cluster, the problem that in the process of determining whether the data PAGE in the cache of the remaining active nodes is the latest, the log serial number of the data PAGE comparison data PAGE is directly read from a DISK, a large number of invalid IOs are generated, and the fault processing efficiency is reduced is solved.
Example four
Fig. 4 is a schematic structural diagram of a data page management apparatus according to a fourth embodiment of the present invention. The device includes: a pending write module 410, a destination determination module 420, and a valid access module 430.
A to-be-determined writing module 410, configured to write, into a first to-be-determined array, first local data page information that cannot be determined to be valid according to an external global array and an external local array in a current active node, where the external global array is global data page information of other active nodes, and the external local array is local data page information of other active nodes, until first to-be-determined arrays of all active nodes are obtained;
a destination determining module 420, configured to determine, according to the first to-be-determined arrays of other active nodes, a data page that is modified in the first to-be-determined array in the current active node and has a latest data page sequence number greater than or equal to a data page log sequence number in a disk of the shared storage database cluster, as a destination local data page of the current active node, until destination local data pages of all active nodes are obtained;
an efficient access module 430 for responding to an instance program access of the shared-storage database cluster to a destination local data page of each active node.
Further, the to-be-determined writing module 410 is further specifically configured to:
searching corresponding global data page information in the external global array according to the first local data page information in the memory of the current active node;
determining the validity of first local data page information in the memory of the current active node according to the corresponding global data page information in the external global array and the blocking mode corresponding to each active node;
and if the first local data page information in the memory of the current active node is valid, taking the first local data page information in the memory of the current active node as a target local data page of the current active node.
Further, the to-be-determined writing module 410 is further specifically configured to:
if the external global array does not store the corresponding global data page information, the validity of the first local data page information in the memory of the active node cannot be determined;
or, if the corresponding data page information exists in the external global array and each node does not have the corresponding blocking mode, the validity of the first local data page information in the memory of the current active node cannot be determined.
Further, the to-be-determined writing module 410 is further specifically configured to:
searching corresponding local data page information in the external local array according to the first local data page information in the memory of the current active node;
determining the validity of the first local data page information in the memory of the current active node according to the local data page information corresponding to the external local array and the blocking mode corresponding to each active node;
and if the first local data page information in the memory of the current active node is valid, taking the first local data page information in the memory of the current active node as a target local data page of the current active node.
Further, the purpose determining module 420 is further configured to:
if the first local data page information of the current active node cannot determine the validity according to the external global data group and the external local array, sending the first array to be determined to the other active nodes;
and each active node receives the respective first array to be determined of the other nodes to form the first array to be determined of the other active nodes.
Further, the purpose determining module 420 is further configured to:
correspondingly selecting data page information corresponding to the latest log serial number of the latest log serial number which is larger than the latest log serial number of the first local data page information in the current active node from the first array to be determined of the other active nodes;
and if not, correspondingly selecting the data page information corresponding to the active node with the minimum node number in the other active nodes, wherein the latest log serial number is equal to the latest log serial number of the first local data page information in the current active node, from the first array to be determined of the other active nodes.
Further, the purpose determining module 420 is further configured to:
if the node number of the last modified data page in the corresponding data page information is equal to a preset value, directly discarding the first local data page information in the first array to be determined;
and if the node number of the last modified data page in the correspondingly selected data page information is not equal to a preset value, reading the log serial number of the corresponding data page from the disk.
The data page management device provided by the embodiment of the invention can execute the data page management method provided by any embodiment of the invention, and has corresponding functional modules and beneficial effects of the execution method.
EXAMPLE five
Fig. 5 is a schematic structural diagram of an electronic device according to a fifth embodiment of the present invention. FIG. 5 illustrates a block diagram of an exemplary electronic device 12 suitable for use in implementing embodiments of the present invention. The electronic device 12 shown in fig. 5 is only an example and should not bring any limitation to the function and the scope of use of the embodiment of the present invention.
As shown in FIG. 5, electronic device 12 is embodied in the form of a general purpose computing device. The components of electronic device 12 may include, but are not limited to: one or more processors or processing units 16, a system memory 28, and a bus 18 that couples various system components including the system memory 28 and the processing unit 16.
The system memory 28 may include computer system readable media in the form of volatile memory, such as Random Access Memory (RAM)30 and/or cache memory 32. The electronic device 12 may further include other removable/non-removable, volatile/nonvolatile computer system storage media. By way of example only, storage system 34 may be used to read from and write to non-removable, nonvolatile magnetic media (not shown in FIG. 5, and commonly referred to as a "hard drive"). Although not shown in FIG. 5, a magnetic disk drive for reading from and writing to a removable, nonvolatile magnetic disk (e.g., a "floppy disk") and an optical disk drive for reading from or writing to a removable, nonvolatile optical disk (e.g., a CD-ROM, DVD-ROM, or other optical media) may be provided. In these cases, each drive may be connected to bus 18 by one or more data media interfaces. Memory 28 may include at least one program product having a set (e.g., at least one) of program modules that are configured to carry out the functions of embodiments of the invention.
A program/utility 40 having a set (at least one) of program modules 42 may be stored, for example, in memory 28, such program modules 42 including, but not limited to, an operating system, one or more application programs, other program modules, and program data, each of which examples or some combination thereof may comprise an implementation of a network environment. Program modules 42 generally carry out the functions and/or methodologies of the described embodiments of the invention.
The processing unit 16 executes various functional applications and data processing by executing programs stored in the system memory 28, for example, implementing a data page management method provided by an embodiment of the present invention, the method including:
writing first local data page information which cannot be determined to be valid according to an external global array and an external local array in a current active node into a first array to be determined, wherein the external global array is global data page information of other active nodes, and the external local array is local data page information of other active nodes until first arrays to be determined of all active nodes are obtained;
according to the first array to be determined of other active nodes, determining a data page which is modified in the first array to be determined in the current active node and has the latest data page sequence number greater than or equal to the log sequence number of the data page in the disk of the shared storage database cluster as a target local data page of the current active node until the target local data pages of all the active nodes are obtained;
the destination local data page of each active node is accessed in response to an instance program of the shared storage database cluster.
EXAMPLE six
An embodiment of the present invention further provides a storage medium including computer executable instructions, where the computer executable instructions are used to execute a data page management method when executed by a computer processor, and are applied to a shared storage database cluster, where the method includes:
writing first local data page information which cannot be determined to be valid according to an external global array and an external local array in a current active node into a first array to be determined, wherein the external global array is global data page information of other active nodes, and the external local array is local data page information of other active nodes until first arrays to be determined of all active nodes are obtained;
according to the first array to be determined of other active nodes, determining a data page which is modified in the first array to be determined in the current active node and has the latest data page sequence number greater than or equal to the log sequence number of the data page in the disk of the shared storage database cluster as a target local data page of the current active node until the target local data pages of all the active nodes are obtained;
the destination local data page of each active node is accessed in response to an instance program of the shared storage database cluster.
Computer storage media for embodiments of the invention may employ any combination of one or more computer-readable media. The computer readable medium may be a computer readable signal medium or a computer readable storage medium. A computer readable storage medium may be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the foregoing. More specific examples (a non-exhaustive list) of the computer readable storage medium would include the following: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the context of this document, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device.
A computer readable signal medium may include a propagated data signal with computer readable program code embodied therein, for example, in baseband or as part of a carrier wave. Such a propagated data signal may take many forms, including, but not limited to, electro-magnetic, optical, or any suitable combination thereof. A computer readable signal medium may also be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device.
Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.
Computer program code for carrying out operations for aspects of the present invention may be written in any combination of one or more programming languages, including an object oriented programming language such as Java, Smalltalk, C + + or the like and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or the connection may be made to an external computer (for example, through the Internet using an Internet service provider).
It is to be noted that the foregoing is only illustrative of the preferred embodiments of the present invention and the technical principles employed. It will be understood by those skilled in the art that the present invention is not limited to the particular embodiments described herein, but is capable of various obvious changes, rearrangements and substitutions as will now become apparent to those skilled in the art without departing from the scope of the invention. Therefore, although the present invention has been described in greater detail by the above embodiments, the present invention is not limited to the above embodiments, and may include other equivalent embodiments without departing from the spirit of the present invention, and the scope of the present invention is determined by the scope of the appended claims.
Claims (10)
1. A data page management method is applied to an active node in a shared storage database cluster, and comprises the following steps:
writing first local data page information which cannot be determined to be valid according to an external global array and an external local array in a current active node into a first array to be determined, wherein the external global array is global data page information of other active nodes, and the external local array is local data page information of other active nodes until first arrays to be determined of all active nodes are obtained;
according to the first array to be determined of other active nodes, determining a data page which is modified in the first array to be determined in the current active node and has the latest data page sequence number greater than or equal to the log sequence number of the data page in the disk of the shared storage database cluster as a target local data page of the current active node until the target local data pages of all the active nodes are obtained;
the destination local data page of each active node is accessed in response to an instance program of the shared storage database cluster.
2. The method of claim 1, wherein before writing the first local data page information that cannot be determined to be valid in the currently active node according to the external global array and the external local array into the first array to be determined, the method further comprises:
searching corresponding global data page information in the external global array according to the first local data page information in the memory of the current active node;
determining the validity of first local data page information in the memory of the current active node according to the corresponding global data page information in the external global array and the blocking mode corresponding to each active node;
and if the first local data page information in the memory of the current active node is valid, taking the first local data page information in the memory of the current active node as a target local data page of the current active node.
3. The method according to claim 2, wherein the determining the validity of the first local data page information in the memory of the current active node according to the blocking mode corresponding to the global data page information corresponding to each active node in the external global array comprises:
if the external global array does not store the corresponding global data page information, the validity of the first local data page information in the memory of the active node cannot be determined;
or, if the corresponding data page information exists in the external global array and each node does not have the corresponding blocking mode, the validity of the first local data page information in the memory of the current active node cannot be determined.
4. The method of claim 3, wherein after failing to determine the validity of the first local data page information in the current active node memory, further comprising:
searching corresponding local data page information in the external local array according to the first local data page information in the memory of the current active node;
determining the validity of the first local data page information in the memory of the current active node according to the local data page information corresponding to the external local array and the blocking mode corresponding to each active node;
and if the first local data page information in the memory of the current active node is valid, taking the first local data page information in the memory of the current active node as a target local data page of the current active node.
5. The method of claim 1, wherein the first pending array of other active nodes comprises:
if the first local data page information of the current active node cannot determine the validity according to the external global data group and the external local array, sending the first array to be determined to the other active nodes;
and each active node receives the respective first array to be determined of the other nodes to form the first array to be determined of the other active nodes.
6. The method of claim 1, wherein determining, according to the first to-be-determined array of other active nodes, that a data page in the first to-be-determined array of the current active node that is modified and has a latest data page sequence number greater than or equal to a data page log sequence number in a disk of the shared storage database cluster is a destination local data page of the current active node, further comprises:
correspondingly selecting data page information corresponding to the latest log serial number of the latest log serial number which is larger than the latest log serial number of the first local data page information in the current active node from the first array to be determined of the other active nodes;
and if not, correspondingly selecting the data page information corresponding to the active node with the minimum node number in the other active nodes, wherein the latest log serial number is equal to the latest log serial number of the first local data page information in the current active node, from the first array to be determined of the other active nodes.
7. The method according to claim 6, wherein the data page information corresponding to the latest log sequence number that is greater than the latest log sequence number of the first local data page information in the current active node is correspondingly selected from the first to-be-determined array of the other active nodes; if not, after correspondingly selecting the data page information corresponding to the active node with the minimum node number in the other active nodes, of which the latest log sequence number is equal to the latest log sequence number of the first local data page information in the current active node, from the first array to be determined of the other active nodes, the method further includes:
if the node number of the last modified data page in the corresponding data page information is equal to a preset value, directly discarding the first local data page information in the first array to be determined;
and if the node number of the last modified data page in the correspondingly selected data page information is not equal to a preset value, reading the log serial number of the corresponding data page from the disk.
8. A data page management apparatus, comprising:
the to-be-determined writing module is used for writing first local data page information which cannot be determined to be valid according to an external global array and an external local array in a current active node into a first to-be-determined array, wherein the external global array is global data page information of other active nodes, and the external local array is local data page information of other active nodes until the first to-be-determined arrays of all the active nodes are obtained;
the destination determining module is used for determining a data page which is modified in the first array to be determined in the current active node and has the latest data page sequence number greater than or equal to the data page log sequence number in the disk of the shared storage database cluster as a destination local data page of the current active node according to the first array to be determined of other active nodes until the destination local data pages of all the active nodes are obtained;
and the effective access module is used for responding the access of the example program of the shared storage database cluster to the target local data page of each active node.
9. An electronic device, characterized in that the electronic device comprises:
one or more processors;
a storage device for storing one or more programs,
when executed by the one or more processors, cause the one or more processors to implement a data page management method as recited in any of claims 1-7.
10. A computer-readable storage medium, on which a computer program is stored which, when being executed by a processor, carries out the data page management method according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011337844.7A CN112395141B (en) | 2020-11-25 | 2020-11-25 | Data page management method and device, electronic equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011337844.7A CN112395141B (en) | 2020-11-25 | 2020-11-25 | Data page management method and device, electronic equipment and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112395141A true CN112395141A (en) | 2021-02-23 |
| CN112395141B CN112395141B (en) | 2023-07-21 |
Family
ID=74607210
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011337844.7A Active CN112395141B (en) | 2020-11-25 | 2020-11-25 | Data page management method and device, electronic equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112395141B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113420012A (en) * | 2021-07-14 | 2021-09-21 | 上海达梦数据库有限公司 | Database node management method and device, database node and storage medium |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7822727B1 (en) * | 2004-07-02 | 2010-10-26 | Borland Software Corporation | System and methodology for performing read-only transactions in a shared cache |
| US20140279907A1 (en) * | 2013-03-14 | 2014-09-18 | International Business Machines Corporation | Reducing Reading Of Database Logs By Persisting Long-Running Transaction Data |
| CN111444147A (en) * | 2020-03-30 | 2020-07-24 | 上海达梦数据库有限公司 | Data page creating method and device, terminal equipment and storage medium |
| CN111930558A (en) * | 2019-05-13 | 2020-11-13 | 华为技术有限公司 | Fault repair method of database system, database system and computing equipment |
-
2020
- 2020-11-25 CN CN202011337844.7A patent/CN112395141B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7822727B1 (en) * | 2004-07-02 | 2010-10-26 | Borland Software Corporation | System and methodology for performing read-only transactions in a shared cache |
| US20140279907A1 (en) * | 2013-03-14 | 2014-09-18 | International Business Machines Corporation | Reducing Reading Of Database Logs By Persisting Long-Running Transaction Data |
| CN111930558A (en) * | 2019-05-13 | 2020-11-13 | 华为技术有限公司 | Fault repair method of database system, database system and computing equipment |
| CA3137745A1 (en) * | 2019-05-13 | 2020-11-19 | Chuanting WANG | Fault repair method for database system, database system, and computing device |
| CN111444147A (en) * | 2020-03-30 | 2020-07-24 | 上海达梦数据库有限公司 | Data page creating method and device, terminal equipment and storage medium |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113420012A (en) * | 2021-07-14 | 2021-09-21 | 上海达梦数据库有限公司 | Database node management method and device, database node and storage medium |
| CN113420012B (en) * | 2021-07-14 | 2024-04-09 | 上海达梦数据库有限公司 | Database node management method and device, database node and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112395141B (en) | 2023-07-21 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US8429134B2 (en) | Distributed database recovery | |
| CN108664359B (en) | Database recovery method, device, equipment and storage medium | |
| US8332367B2 (en) | Parallel data redundancy removal | |
| US20180060318A1 (en) | Coordinated hash table indexes to facilitate reducing database reconfiguration time | |
| US8996611B2 (en) | Parallel serialization of request processing | |
| US8745012B2 (en) | Log-structured store for streaming data | |
| CN111078147B (en) | Processing method, device and equipment for cache data and storage medium | |
| CN109710190B (en) | Data storage method, device, equipment and storage medium | |
| US9858160B2 (en) | Restoring distributed shared memory data consistency within a recovery process from a cluster node failure | |
| US9898414B2 (en) | Memory corruption detection support for distributed shared memory applications | |
| US6807615B1 (en) | Apparatus and method for providing a cyclic buffer using logical blocks | |
| US7962615B1 (en) | Multi-system deadlock reduction | |
| CN111444147B (en) | Data page creation method and device, terminal equipment and storage medium | |
| CN109471851B (en) | Data processing method, device, server and storage medium | |
| CN103559231A (en) | File system quota managing method, device and system | |
| US8782375B2 (en) | Hash-based managing of storage identifiers | |
| CN110647318A (en) | Method, device, equipment and medium for creating instance of stateful application | |
| CN106528322B (en) | Method and apparatus for detecting non-documented corruption of data | |
| CN112395141B (en) | Data page management method and device, electronic equipment and storage medium | |
| CN111930684A (en) | Small file processing method, device and equipment based on HDFS (Hadoop distributed File System) and storage medium | |
| CN111290881A (en) | Data recovery method, device, equipment and storage medium | |
| US20140156908A1 (en) | Stale pointer detection with overlapping versioned memory | |
| CN112783683A (en) | Data processing method, device, equipment and storage medium | |
| JP2006079485A (en) | Method for information collection for fault analysis in electronic computer | |
| CN112818204A (en) | Service processing method, device, equipment and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |