CN116471213B - Link tracking method, link tracking system and medium - Google Patents
Link tracking method, link tracking system and medium Download PDFInfo
- Publication number
- CN116471213B CN116471213B CN202310678676.5A CN202310678676A CN116471213B CN 116471213 B CN116471213 B CN 116471213B CN 202310678676 A CN202310678676 A CN 202310678676A CN 116471213 B CN116471213 B CN 116471213B
- Authority
- CN
- China
- Prior art keywords
- data
- call
- engine
- calling
- abnormal
- 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.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 60
- 239000012634 fragment Substances 0.000 claims abstract description 187
- 230000002159 abnormal effect Effects 0.000 claims abstract description 108
- 238000012545 processing Methods 0.000 claims abstract description 76
- 238000005070 sampling Methods 0.000 claims abstract description 56
- 230000008569 process Effects 0.000 claims description 14
- 230000003993 interaction Effects 0.000 claims description 6
- 238000013507 mapping Methods 0.000 claims description 2
- 230000006870 function Effects 0.000 description 9
- 238000003491 array Methods 0.000 description 8
- 230000004888 barrier function Effects 0.000 description 4
- 238000004891 communication Methods 0.000 description 4
- 238000001514 detection method Methods 0.000 description 4
- 238000010586 diagram Methods 0.000 description 4
- 230000000903 blocking effect Effects 0.000 description 3
- 238000012986 modification Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 238000000354 decomposition reaction Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 230000004044 response Effects 0.000 description 2
- 238000006467 substitution reaction Methods 0.000 description 2
- 238000012795 verification Methods 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 1
- 230000002547 anomalous effect Effects 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000012163 sequencing technique Methods 0.000 description 1
- 208000019116 sleep disease Diseases 0.000 description 1
- 230000001360 synchronised effect Effects 0.000 description 1
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L43/00—Arrangements for monitoring or testing data switching networks
- H04L43/10—Active monitoring, e.g. heartbeat, ping or trace-route
-
- 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
- G06F11/0703—Error or fault processing not based on redundancy, i.e. by taking additional measures to deal with the error or fault not making use of redundancy in operation, in hardware, or in data representation
- G06F11/0766—Error or fault reporting or storing
- G06F11/0787—Storage of error reports, e.g. persistent data storage, storage using memory protection
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L43/00—Arrangements for monitoring or testing data switching networks
- H04L43/02—Capturing of monitoring data
- H04L43/022—Capturing of monitoring data by sampling
- H04L43/024—Capturing of monitoring data by sampling by adaptive sampling
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/01—Protocols
- H04L67/1396—Protocols specially adapted for monitoring users' activity
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/50—Network services
- H04L67/535—Tracking the activity of the user
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/50—Network services
- H04L67/56—Provisioning of proxy services
- H04L67/566—Grouping or aggregating service requests, e.g. for unified processing
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/50—Network services
- H04L67/56—Provisioning of proxy services
- H04L67/568—Storing data temporarily at an intermediate stage, e.g. caching
- H04L67/5682—Policies or rules for updating, deleting or replacing the stored data
Landscapes
- Engineering & Computer Science (AREA)
- Signal Processing (AREA)
- Computer Networks & Wireless Communication (AREA)
- Theoretical Computer Science (AREA)
- General Engineering & Computer Science (AREA)
- Computer Hardware Design (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Quality & Reliability (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Cardiology (AREA)
- Debugging And Monitoring (AREA)
Abstract
The invention relates to the technical field of computers, in particular to a link tracking method, a link tracking system and a medium, and aims to solve the problem that abnormal link data are difficult to collect in the existing link tracking method. For this purpose, the invention obtains service log data by controlling the preposed data engine and obtains abnormal call fragments based on the service log data; controlling a preposed data engine to acquire the number of abnormal calling fragments and judging whether the number of the calling fragments meets the preset number condition; selectively controlling the pre-data engine to acquire random call fragments based on the service log data based on the judgment result; based on the sampling calling segment, controlling a front-end data engine and a back-end processing engine to acquire first calling chain data; the control back-end processing engine performs a corresponding link trace operation based on the first call chain data. The setting can avoid that the link data acquired during sampling is too random, and the use experience of a user is improved.
Description
Technical Field
The invention relates to the technical field of computers, and particularly provides a link tracking method, a link tracking system and a medium.
Background
A distributed link tracking system is a system used to collect data within the scope of a request, i.e. when a user sends a request on a page, all the processing of this request is recorded, such as how many services are being experienced, on which machines time consuming and anomalous situations for each service, etc.
In the process of collecting link data, the more data is collected by the distributed link tracking system, the more cost is consumed, so in order to keep the performance loss of the link tracking system at a low level, it is common practice to sample the link data. The current common sampling mode mainly comprises fixed proportion sampling and reservoir sampling, wherein the fixed proportion sampling is a sampling method for setting a certain sampling rate during sampling; reservoir sampling is a method of sampling with event complexity O (N) based on a fixed sampling scale. However, the link data collected by the sampling strategy is too random, so that abnormal link data which is concerned by operation and maintenance personnel is difficult to collect, thereby being unfavorable for fault detection and influencing the use experience of users.
Accordingly, there is a need in the art for a new link tracking method to address the above-described problems.
Disclosure of Invention
The invention aims to solve the technical problems that the existing link tracking method is difficult to collect abnormal link data, so that the fault detection is not facilitated.
To achieve the above object, in a first aspect, the present invention provides a link tracking method, which is applied to a link tracking system, the link tracking system including a front-end data engine and a back-end processing engine, and information interaction between the front-end data engine and the back-end processing engine, the method comprising the steps of:
controlling the preposed data engine to acquire service log data and acquiring an abnormal call fragment based on the service log data;
controlling the preposed data engine to acquire the number of the abnormal calling fragments and judging whether the number of the abnormal calling fragments meets the preset number condition;
selectively controlling the pre-data engine to acquire a random call fragment based on the service log data based on a judgment result;
based on a sampling calling segment, controlling the preposed data engine and the back-end processing engine to acquire first calling chain data, wherein the sampling calling segment is the abnormal calling segment or the abnormal calling segment and the random calling segment;
And controlling the back-end processing engine to execute corresponding link tracking operation based on the first call link data.
In an optional solution of the above link tracking method, the step of "controlling the preamble engine to acquire service log data" includes:
and controlling the preposed data engine to read the service log data and caching the read service log data into a preset List < Map < String >, list < String > > data structure space.
In an optional technical solution of the above link tracking method, the service log data includes a plurality of groups of calling fragments, the calling fragments include tag data information, and the step of controlling the preamble engine to obtain an abnormal calling fragment based on the service log data includes:
judging whether the calling fragment is an abnormal calling fragment or not based on the tag data information;
and when the calling fragment is an abnormal calling fragment, temporarily storing the calling fragment to acquire the abnormal calling fragment.
In an optional technical solution of the above link tracking method, the step of "determining whether the calling segment is an abnormal calling segment based on the tag data information" includes:
judging whether the tag data information contains error=1 and/or http.status_code |=200;
When the tag data information contains error=1 and/or http.status_code |=200, determining that the calling fragment containing the tag data information is an abnormal calling fragment.
In an optional technical solution of the above link tracking method, the step of "selectively controlling the preamble engine to obtain the random call fragment based on the service log data" includes:
and when the number of the abnormal call fragments does not meet the preset number condition, controlling the preposed data engine to acquire random call fragments based on the non-abnormal call fragments.
In an optional technical solution of the above link tracking method, the step of controlling the pre-data engine and the back-end processing engine to obtain the first call chain data based on the sample call fragment includes:
controlling the preposed data engine to report the acquired sampling calling fragment to the back-end processing engine;
the back-end processing engine receives the sampling calling segment and sends a notification for acquiring first calling chain data to the preposed data engine based on the sampling calling segment;
The preposed data engine receives the notification of acquiring the first call chain data, acquires the first call chain data based on the notification of acquiring the first call chain data and reports the first call chain data to the back-end processing engine.
In an optional solution of the above link tracking method, the step of "controlling the back-end processing engine to perform a corresponding link tracking operation based on the first call link data" includes:
based on a merging and sorting algorithm, controlling the back-end processing engine to process the first call chain data so as to obtain second call chain data;
and controlling the back-end processing engine to calculate based on the second call chain data so as to realize link tracking.
In a second aspect, the present invention also provides a link tracking system comprising a pre-data engine and a back-end processing engine, information interaction between the pre-data engine and the back-end processing engine, the pre-data engine configured to perform a first operation in a multithreaded parallel manner, wherein the first operation comprises:
acquiring service log data and acquiring an abnormal call fragment based on the service log data;
Acquiring the number of the abnormal call fragments and judging whether the number of the abnormal call fragments meets the preset number condition;
based on the judging result, selectively acquiring a random call segment based on the service log data;
acquiring first call chain data based on a sampling call fragment and a notification of acquiring the first call chain data, and reporting the first call chain data to the back-end processing engine, wherein the sampling call fragment is the exception call fragment or the exception call fragment and the random call fragment;
the back-end processing engine is configured to: and sending the notice of acquiring the first call chain data to the prepositive data engine based on the sampling call fragment, receiving the first call chain data and executing a link tracking operation based on the first call chain data.
In an alternative solution of the above link tracking system, the preamble engine is configured to perform the first operation in the multithreaded parallel manner based on at least one of semaphore.acquisition (), keyword volatile, and thread.
In a third aspect, the present invention also provides a readable storage medium having stored therein a plurality of program codes adapted to be loaded and executed by a processor to perform the link tracking method of any of the above.
As can be appreciated by those skilled in the art, in the technical solution of the present invention, service log data is obtained by controlling a pre-data engine and an exception call fragment is obtained based on the service log data; controlling a preposed data engine to acquire the number of abnormal calling fragments and judging whether the number of the calling fragments meets the preset number condition; selectively controlling the pre-data engine to acquire random call fragments based on the service log data based on the judgment result; based on the sampling calling segment, controlling a preposed data engine and a back-end processing engine to acquire first calling chain data, wherein the sampling calling segment is an abnormal calling segment or an abnormal calling segment and a random calling segment; the control back-end processing engine performs a corresponding link trace operation based on the first call chain data. The setting can avoid the link data that gathers when the sampling too random, also can maintain the performance loss of link tracking system at lower level simultaneously, has promoted user's use experience.
Further, the service log data includes an exception calling segment and a non-exception calling segment, and selectively controlling the preamble engine to obtain the random calling segment based on the service log data based on the determination result includes: when the number of the abnormal calling fragments does not meet the preset number condition, controlling the preposed data engine to acquire random calling fragments based on the non-abnormal calling fragments. The setting can collect abnormal call fragments, can ensure that the preset sampling quantity condition is met, improves the positioning efficiency of the link tracking method, and further improves the use experience of users.
Drawings
The present disclosure will become more readily understood with reference to the accompanying drawings. As will be readily appreciated by those skilled in the art: the drawings are for illustrative purposes only and are not intended to limit the scope of the present invention. Moreover, like numerals in the figures are used to designate like parts, wherein:
FIG. 1 is a schematic diagram of the overall architecture of a micro service invocation system involved in a practical application scenario according to the present invention;
FIG. 2 is a flow chart illustrating the main steps of a link tracking method according to one embodiment of the present invention;
FIG. 3 is a flowchart illustrating the main steps of controlling a pre-data engine to retrieve exception call segments based on service log data, according to one embodiment of the present invention;
FIG. 4 is a flowchart illustrating the main steps for controlling a front-end data engine and a back-end processing engine to obtain first call chain data based on a sample call fragment, according to one embodiment of the present invention;
fig. 5 is a detailed step flow diagram of a link tracking method according to another embodiment of the present invention.
Detailed Description
Some embodiments of the invention are described below with reference to the accompanying drawings. It should be understood by those skilled in the art that these embodiments are merely for explaining the technical principles of the present invention, and are not intended to limit the scope of the present invention.
In the description of the present invention, a "module," "processor" may include hardware, software, or a combination of both. A module may comprise hardware circuitry, various suitable sensors, communication ports, memory, or software components, such as program code, or a combination of software and hardware. The processor may be a central processor, a microprocessor, an image processor, a digital signal processor, or any other suitable processor. The processor has data and/or signal processing functions. The processor may be implemented in software, hardware, or a combination of both. Non-transitory computer readable storage media include any suitable medium that can store program code, such as magnetic disks, hard disks, optical disks, flash memory, read-only memory, random access memory, and the like. The term "at least one A or B" or "at least one of A and B" has a meaning similar to "A and/or B" and may include A alone, B alone or A and B. The singular forms "a", "an" and "the" include plural referents.
As described in the background section, the present invention provides a link tracking method, which aims at the problem that the existing link tracking method is difficult to collect abnormal link data, thereby being unfavorable for checking faults.
The link tracking method can be applied to a link tracking system, so that the link tracking system can track the link of the micro-service calling system. The micro service invocation system is a system composed of a plurality of nodes, and different data processing programs are configured on different nodes so as to realize specific data computing functions.
Referring to fig. 1, fig. 1 is a schematic diagram of the overall structure of a micro service invocation system according to the present invention, which is involved in a practical application scenario. As shown in fig. 1, in some embodiments, the micro service invocation system may include four nodes, node 1, node 2, node 3, and node 4, respectively; a service A is configured in the node 1, and the service A is used for realizing the function of verifying whether a client really operates and verifying the secret; a service B is configured in the node 2, and the service B is used for realizing the payment function; a service C is configured in the node 3 and is used for realizing the function of wind control checking and checking; the node 4 is configured with a service D for implementing a function of account balance inquiry and deduction. When a client initiates a payment request, calling a service A to receive the request, thereby verifying whether the user really operates and verifies the secret based on the service A; and when the verification of the service A is passed, calling the service B to pay, calling the service C to carry out risk checking and verification by the service B, and calling the service D to carry out account balance inquiry and deduction at the same time.
The sample data for analysis becomes a call chain (trace), the link ID (trace) is a digital identifier set according to the request order, and the trace is the same value in the same request link; because the calling service a, the calling service B, the calling service C, and the calling service D are all calling links under the request of the payment request initiated by the client, the calling service a, the calling service B, the calling service C, and the calling service D are all identical traceids, such as traceid1001. The calling fragment (span) records information that can reflect the calling process, such as the operation name, the starting time, etc. of a cross-service call, and one calling chain may include a plurality of calling fragments. The span ID is a digital identifier set according to a span service call, and the calling service a, the calling service B, the calling service C, and the calling service D described above belong to the same calling link, but are different span service calls, so that the calling service a, the calling service B, the calling service C, and the calling service D respectively have different spans, and may be, for example, span 2001, span 2002, span 2003, and span 2004, respectively.
Those skilled in the art will appreciate that the overall architecture shown in fig. 1 does not constitute a limitation of the micro service invocation system, and in actual practice, the micro service invocation system may include more or fewer components than shown, or may combine certain components, or may have a different arrangement of components. For example, in practical application, the micro-service calling system may include more or fewer nodes, different nodes may set different data computing functions, and different calling modes may be generated when a request initiated by a client is received; meanwhile, the value of the track and the value of the span can be selected according to actual conditions, and the like.
Next, a link tracking method according to an embodiment of the present invention will be described in detail with reference to the accompanying drawings.
Referring to fig. 2, fig. 2 is a schematic flow chart of main steps of a link tracking method according to an embodiment of the present invention, where the link tracking method may be performed by a link tracking system, or may be performed by a server or a server cluster in communication with the link tracking system, and is not limited herein. As shown in fig. 2, the link tracking method of the present invention is applied to a link tracking system, the link tracking system includes a front-end data engine and a back-end processing engine, and the information interaction between the front-end data engine and the back-end processing engine includes the following steps:
step S101: and controlling the prepositive data engine to acquire service log data and acquiring an abnormal call fragment based on the service log data.
Specifically, the control pre-data engine obtains an abnormal call segment within a preset time window based on the service log data.
In some embodiments, obtaining service log data includes: based on the Reactor mode, service log character stream data is acquired using streaming. Specifically, the Reactor mode (i.e., reactor mode) is one implementation of event-driven architecture (event-driven architecture) that is capable of handling scenarios where multiple clients concurrently request services from a server. The Reactor mode mainly comprises two core parts, namely a Reactor and a processing resource pool, wherein the Reactor is responsible for monitoring and distributing events, and the event type comprises a connection event and a read-write event; the processing resource pool is responsible for processing events. I.e., the Reactor mode will decouple the service of concurrent request and distribute to the corresponding event handler for processing.
In some embodiments, controlling the preamble engine to obtain service log data comprises: and controlling the preposed data engine to read the service log data and caching the read service log data into a preset List < Map < String >, list < String > > data structure space. Specifically, list represents a List, list represents a generic type, and List represents storing a certain type of data. Map is an object mapping keys to values, and a value corresponding to a key can be found in Map by using an anonymous object; in Map < String >, list < String >, the bond is String, and the value is List < String >.
For example, the key of Map may be set to track, and the value of Map may be set to each set of service log data, i.e., related information of each calling fragment. The Map setting manner described above is merely illustrative, and may be selected according to actual needs in practical applications.
Referring to fig. 3, fig. 3 is a flowchart illustrating main steps of controlling a preamble engine to acquire an exception call fragment based on service log data according to an embodiment of the present invention. As shown in fig. 3, in some embodiments, the service log data includes multiple sets of calling fragments, the calling fragments include tag data information, and controlling the pre-data engine to obtain an exception calling fragment based on the service log data includes the steps of:
Step S1011: and judging whether the calling fragment is an abnormal calling fragment or not based on tag data information.
Step S1012: and when the calling fragment is the abnormal calling fragment, temporarily storing the calling fragment to acquire the abnormal calling fragment.
Specifically, the service log data includes a plurality of lines of data, each line of data being a calling segment. When the link tracking is carried out, operators pay more attention to the calling fragments with errors or slow response and other anomalies, so that the fault detection of the micro-service calling system can be facilitated. Therefore, it is necessary to determine whether or not the calling fragment is an abnormal calling fragment based on tag (flag bit) data information of the calling fragment, and temporarily store the calling fragment determined as the abnormal calling fragment to acquire the abnormal calling fragment.
In some embodiments, determining whether the calling fragment is an abnormal calling fragment based on tag data information includes the steps of:
step S10111: judging whether the tag data information contains error=1 and/or http.
Step S10112: when the tag data information contains error=1 and/or http.status_code |=200, the calling fragment containing the tag data information is determined to be an abnormal calling fragment.
Specifically, when error=1 and/or http.status_code |=200 are included in the tag data information, the request fails, and therefore the call fragment including the tag data information is referred to as an abnormal call fragment.
Step S102: and controlling the preposed data engine to acquire the number of the abnormal call fragments and judging whether the number of the abnormal call fragments meets the preset number condition.
Specifically, the preset number of conditions is the lowest condition that the data of the abnormal call segments need to meet, that is, if the number of the abnormal call segments does not meet the preset number of conditions, the number of the call segments to be sampled is too small, and the number of samples in the preset time window needs to be further increased.
Step S103: based on the judgment result, the preamble engine is selectively controlled to acquire the random call fragment based on the service log data.
Specifically, when the judgment result is that the number of the abnormal calling fragments does not meet the preset number condition, controlling the prepositive data engine to further acquire random calling fragments based on the service log data; otherwise, when the judgment result is that the number of the abnormal call fragments meets the preset number condition, the preposed data engine is not controlled to further acquire the random call fragments based on the service log data. Such an arrangement can avoid too few samples in the link trace, thereby reducing failure detection efficiency; meanwhile, the generation of larger sampling cost in the link tracking is avoided, and the balance of cost and income is realized.
Step S104: and controlling the front-end data engine and the back-end processing engine to acquire first call chain data based on the sampling call fragment, wherein the sampling call fragment is an abnormal call fragment or an abnormal call fragment and a random call fragment.
Specifically, when the number of the abnormal calling fragments meets the preset number condition, the random calling fragments do not need to be further acquired, and the sampling calling fragments are the abnormal calling fragments; when the number of the abnormal calling fragments does not meet the preset number condition and the random calling fragments need to be further acquired, the sampling calling fragments are the abnormal calling fragments and the random calling fragments.
Step S105: the control back-end processing engine performs a corresponding link trace operation based on the first call chain data.
Based on the steps S101 to S105, the invention obtains service log data by controlling the preposed data engine and obtains an abnormal call fragment based on the service log data; controlling a preposed data engine to acquire the number of abnormal calling fragments and judging whether the number of the calling fragments meets the preset number condition; selectively controlling the pre-data engine to acquire random call fragments based on the service log data based on the judgment result; based on the sampling calling segment, controlling a preposed data engine and a back-end processing engine to acquire first calling chain data, wherein the sampling calling segment is an abnormal calling segment or an abnormal calling segment and a random calling segment; the control back-end processing engine performs a corresponding link trace operation based on the first call chain data. The setting can avoid the link data that gathers when the sampling too random, also can maintain the performance loss of link tracking system at lower level simultaneously, has promoted user's use experience.
Next, step S103 to step S105 will be further described.
In some embodiments, the service log data includes an exception calling segment and a non-exception calling segment, and selectively controlling the preamble engine to obtain the random calling segment based on the service log data based on the determination result includes the steps of:
step S1031: when the number of the abnormal calling fragments does not meet the preset number condition, controlling the preposed data engine to acquire random calling fragments based on the non-abnormal calling fragments.
Specifically, the preset number condition may be a preset sampling rate to be reached by a ratio of the number of abnormal call segments to the number of service log data in a preset time window, and when the number of abnormal call segments does not meet the preset number condition, the front data engine is controlled to obtain random call segments based on non-abnormal call segments in the preset window.
For example, the number of service log data in the preset time window may be 20000 rows, and the preset sampling rate may be 40%, that is, the preset number condition is that the number of abnormal call fragments needs to reach 8000 rows. If the number of the abnormal call fragments is 5000 lines, the condition that the number of the abnormal call fragments does not reach the preset number is indicated, and the preposed data engine needs to be controlled to extract 3000 lines of random call fragments from the rest 15000 lines of service log data in the non-abnormal call fragments within a preset time window; if the number of the abnormal call fragments is 8500 lines, the abnormal call fragments are indicated to reach the preset number condition, so that the front data engine is not required to be controlled to acquire the random call fragments. The above values of the number of service log data in the preset time window, the preset sampling rate, the number of abnormal call segments, etc. are only illustrative, and may be selected according to actual needs in practical applications.
Referring to fig. 4, fig. 4 is a flowchart illustrating the main steps of controlling a front-end data engine and a back-end processing engine to obtain first call chain data based on a sample call fragment according to an embodiment of the present invention. As shown in fig. 4, in some embodiments, controlling the front-end data engine and the back-end processing engine to obtain the first call chain data based on the sample call fragment comprises the steps of:
step S1041: and controlling the pre-data engine to report the acquired sampling calling fragments to the back-end processing engine.
Step S1042: the back-end processing engine receives the sample call fragment and sends a notification to the front-end data engine to obtain the first call chain data based on the sample call fragment.
Step S1043: the front-end data engine receives a notification of acquiring the first call chain data, acquires the first call chain data based on the notification of acquiring the first call chain data and reports the first call chain data to the back-end processing engine.
In some embodiments, the pre-data engine obtaining the first call chain data based on the notification of obtaining the first call chain data comprises the steps of:
step S10431: and controlling the pre-data engine to acquire corresponding call chain data based on the sampling call fragments.
Step S10432: and after the acquisition of the corresponding call chain data is completed, controlling the preposed data engine to sort the corresponding call chain data so as to generate first call chain data.
Specifically, when the sampling calling segment is an abnormal calling segment, acquiring the corresponding calling chain data is to acquire the calling chain data corresponding to the abnormal calling segment; when the sampling calling segment is an abnormal calling segment and a random calling segment, acquiring the corresponding calling chain data is to acquire the calling chain data corresponding to the abnormal calling segment and acquire the calling chain data corresponding to the random calling segment. The corresponding call chain data comprises a plurality of groups of call fragments, the sorting of the corresponding call chain data means sorting the plurality of groups of call fragments in the corresponding call chain data in time, and the corresponding call chain data with the sorting completed is called first call chain data.
In some embodiments, controlling the back-end processing engine to perform the respective link trace operations based on the first call chain data includes the steps of:
step S1051: and controlling the back-end processing engine to process the first call chain data based on the merging and sorting algorithm so as to obtain second call chain data.
Step S1052: and controlling the back-end processing engine to calculate based on the second call chain data so as to realize link tracking.
In particular, the data files are sequential in time, but the files are interspersed with several data within the nodes, and in order to deal with this out-of-order nature of the data across the nodes, an ordering process needs to be performed. The Merge Sort (Merge Sort) algorithm is an effective Sort algorithm based on Merge operation, which sorts by divide-and-conquer method, and therefore is divided into two steps, decomposition and merging. The decomposition means that the array is divided into two arrays, each array is further divided into two arrays, and the element prime array is regarded as an ordered array until each array is an element finally; the merging means that the divided ordered arrays are ordered, the ordered arrays are merged with the arrays divided together after being ordered into ordered arrays, and the ordering is completed at the moment until the arrays are merged into the original arrays.
Referring to fig. 5, fig. 5 is a detailed step flow diagram of a link tracking method according to another embodiment of the present invention, where the link tracking method may be performed by a link tracking system, or may be performed by a server or a server cluster in communication with the link tracking system, and is not limited herein. As shown in fig. 5, the link tracking method of the present invention is applied to a link tracking system, the link tracking system includes a front-end data engine and a back-end processing engine, and information interaction between the front-end data engine and the back-end processing engine, the method includes the following steps:
Step S201: the prepositive data engine reads the service log data and caches the read service log data to a preset List < Map < String >, list < String > > data structure space.
Specifically, the pre-data engine obtains a log data at each service, where the log data includes a plurality of lines of data, and each line of data (i.e., a calling segment) includes at least the following information: traceid, spanid, host, serviceName, startTime, duration and tags, where the track is a link ID, the span is a cross-service ID, the host is a machine identifier, which may be, for example, IP or a machine name, the serviceName is a called service name, startTime is a start time of the call, duration is a call time consuming time, and tags are tag data information in the link information, and there are multiple tag data information in the call fragment.
For example, the number of services may be 4, which are respectively service a, service B, service C, and service D; the number of the preposed data engines can be 2, namely a first preposed data engine and a second preposed data engine respectively, so that the preposed data engine can read and cache the service log data for the first preposed data engine, and the second preposed data engine can read and cache the service log data for the service A and the service B, and the second preposed data engine can read and cache the service C and the service D. The key of Map may be set to track, and the value of Map may be set to service log data of each row, that is, related information of each calling segment, where such setting can facilitate pulling of the first calling chain data by the subsequent back-end processing engine. The above-mentioned setting of the number of services, the setting of the number of the preamble engines, the setting mode based on reading and caching of service log data by the preamble engines, and the setting mode of maps are merely illustrative, and may be selected according to actual needs in practical applications.
Step S202: based on the cached service log data, the pre-data engine screens the abnormal call fragments within a preset time window.
Specifically, each service log data includes a plurality of lines of log data, one line of log data is a group of calling fragments, and the pre-data engine screens abnormal calling fragments within a preset time window based on tags in each group of calling fragments, that is, when the tags contain error=1 or http.
Step S203: the preposed data engine judges whether the data of the abnormal call fragments meet the preset quantity condition.
Specifically, the preset number of conditions may be a preset sampling rate to be reached by a ratio of the number of abnormal call segments to the number of service log data in a preset time window.
Step S204: when the data of the abnormal calling fragments do not meet the preset number of conditions, the prepositive data engine acquires the random calling fragments based on the cached service log data.
Specifically, the service log data includes an exception calling segment and a non-exception calling segment, and when the number of exception calling segments does not satisfy a preset number of conditions, the pre-data engine acquires a random calling segment based on the non-exception calling segment within a preset time window.
Step S205: the preposed data engine reports the abnormal calling fragments and the random calling fragments to the back-end processing engine.
Specifically, the number of the prepositive data engines may be one or more, and when the number of the prepositive data engines is multiple, the situation that the same calling segment is acquired by different prepositive data engines may occur, so that the situation that the same calling segment is an abnormal calling segment in one prepositive data engine and is a non-abnormal calling segment in another prepositive data engine may occur, and communication between different prepositive data engines is impossible. Therefore, the front-end data engine is required to report the selected abnormal calling fragments and the extracted random calling fragments to the back-end processing engine, and then the back-end processing engine performs unified processing.
Step S206: the back-end processing engine receives the exception calling segment and the random calling segment reported by the front-end data engine, and sends a notification of acquiring first call chain data of the exception calling segment and the random calling segment to the front-end data engine.
Step S207: the front-end data engine receives a notification sent by the back-end processing engine, acquires the abnormal call fragments and call chain data corresponding to the random call fragments based on the notification, sorts a plurality of groups of call fragments in the corresponding call chain data to generate first call chain data, and reports the first call chain data to the back-end processing engine.
Specifically, because there may be a case of cross-service invocation of data of the same request link, there may be an execution time interval that may span the duration of two time windows, i.e., the start time of the last invocation fragment is in the last time window and the start time of the next invocation fragment is in the next time window. Therefore, the first call chain data reporting operation needs to be executed after the threads for processing data in the pre-data engine process currentBatch Number +1 threads. Meanwhile, the number of the front-end data engines can be multiple, and the number of the back-end processing engines is only one, so that partial sequencing work is put down to the front-end data engines in order to reduce the processing pressure of the back-end processing engines.
Step S208: the back-end processing engine receives the first call chain data reported by the front-end data engine, performs a merging and sorting method on the first call chain data to generate second call chain data, and calculates based on the second call chain data to achieve link tracking.
It should be noted that, although the foregoing embodiments describe the steps in a specific order, it will be understood by those skilled in the art that, in order to achieve the effects of the present invention, the steps are not necessarily performed in such an order, and may be performed simultaneously (in parallel) or in other orders, and these variations are within the scope of the present invention. Meanwhile, all the above embodiments may be combined to form an optional embodiment of the present invention, and will not be described in detail herein.
The present invention also provides a link tracking system comprising a pre-data engine and a back-end processing engine, information interaction between the pre-data engine and the back-end processing engine, the pre-data engine configured to perform a first operation in a multithreaded parallel manner, wherein the first operation comprises:
acquiring service log data and acquiring an abnormal call fragment based on the service log data;
acquiring the number of the abnormal call fragments and judging whether the number of the abnormal call fragments meets the preset number condition;
based on the judgment result, selectively acquiring a random call segment based on the service log data;
acquiring first call chain data based on the sampling call fragment and the notification of the first call chain data, and reporting the first call chain data to a back-end processing engine, wherein the sampling call fragment is an abnormal call fragment or an abnormal call fragment and a random call fragment;
the back-end processing engine is configured to: the method includes sending a notification to a front data engine to obtain first call chain data based on the sampling call fragment, receiving the first call chain data, and performing a link tracking operation based on the first call chain data.
In some embodiments, the pre-data engine is configured to perform the first operation in a multithreaded parallel manner based on at least one of semaphore.acquisition (), key volatile, and thread () when the multithreading is blocked.
In particular semaphore is a thread semaphore that functions to control the number of threads accessing a particular resource by coordinating the individual threads to ensure proper use of the resource. When semaphore is initialized, the initial token quantity is assigned to the state of the synchronous queue, and the state value represents the current remained token quantity; semaphore.acquire () is a current thread that tries to get a token out of the synchronization queue, and the process of getting a token, that is, using atomic operations to modify the state of the synchronization queue, gets a token, and then modifies it to state=state-1; if the calculated state is less than 0, the token number is insufficient, a Node is created to join in a blocking queue, and the current thread is suspended; if the calculated state > =0, it represents that the token acquisition is successful.
The key word volatile mainly has the function of thread visibility, namely when one thread modifies a shared variable, the other thread can read the modified value; another effect is sequential consistency, i.e., disabling instruction reordering. When the visibility of the thread is realized, if the variable of the volatile is declared to be written, the data of the cache line where the variable is positioned is written back to the system memory; meanwhile, in order to ensure that the caches of all the processors are consistent, a cache consistency protocol is also realized, so that when the processor finds that the memory address corresponding to the cache line of the processor is modified, the cache line is set to be in an invalid state, and when the processor carries out modification operation on the variable, the variable is read into the processor cache again from the system memory. When order consistency is achieved, reordering is forbidden by a memory barrier instruction, namely a memory barrier is inserted in front of each volatile write operation, and a memory load barrier is inserted in back of each volatile write operation; one LoadLoad, loadStore barrier is inserted after each volt read operation.
Thread () is used to halt execution of the current thread and will inform the thread scheduler to put the current thread in wait state for a specified period of time. When the wait time is over, the thread state is changed back to Runneable and the CPU waits for the rescheduling execution. One process calls thread () to enter a waiting state when running, and after sleeping, the process does not directly return to the running state, but enters a ready queue, and can not enter the running state again until the other process gives up a time slice. Thus, by using thread () the current process can be put into a blocking state from the running state, thereby giving other processes the opportunity to continue executing tasks.
Illustratively, the pre-data engine may perform the first operation in a parallel manner by thread a, thread B, and thread C, where thread a is used to obtain service log data, i.e., to read and cache service log data; the thread B is used for acquiring the abnormal calling fragments and acquiring the random calling fragments when the number of the abnormal calling fragments does not meet the preset number condition; the thread C is used for acquiring the first call chain data based on the exception call fragment or the exception call fragment and the random call fragment. When the thread A reads the service log data, the service log data needs to be put into a next cache area for caching, and if the cache area is not consumed by the thread C, the thread A is blocked; and/or if the next byte [ ] data that needs to be processed by thread B is not downloaded by thread a while thread B is processing the data, thread B will be blocked; and/or thread C can pull data after 3 batches of data of the last time window, the current time window and the next time window are prepared when the thread C pulls the data, and if the thread B does not process the data of the next time window, the thread C is blocked.
When the multithreading is blocked, the problem can be solved by synchronizing one or more of the thread A and the thread B, the thread B and the thread C and the thread A and the thread C. The synchronization thread A and the thread B are as follows: 10 slots are set, each slot is allocated with a semaphore (thread semaphore) to synchronously serve the thread A and the thread B, and after the thread A generates data, the thread semaphore of the corresponding slot is added with 1, so that before the thread B consumes the data, whether a token can be acquired or not needs to be judged based on semaphore.acquisition (). Synchronizing thread B with thread C is: efficient response is achieved based on the key word volatile and thread. Sleep (0, 2), and when thread C finds that thread B has not yet generated data for the next time window, thread C enters a wait state. Synchronization of thread a and thread C is also based on the key word volatile and thread.
The above-described multithreading mode setting of the preamble engine when executing the first operation, the multithreading mode setting in which the multithreading is blocked, the mode setting for solving the multithreading blocking based on at least one of semaphore.acquisition (), the keyword volatile, and the thread.
Further, the invention also provides a computer readable storage medium. In one computer-readable storage medium embodiment according to the present invention, the computer-readable storage medium may be configured to store a program for performing the link tracking method of the above-described method embodiment, which may be loaded and executed by a processor to implement the above-described link tracking method. For convenience of explanation, only those portions of the embodiments of the present invention that are relevant to the embodiments of the present invention are shown, and specific technical details are not disclosed, please refer to the method portions of the embodiments of the present invention. The computer readable storage medium may be a storage device including various electronic devices, and optionally, the computer readable storage medium in the embodiments of the present invention is a non-transitory computer readable storage medium.
Further, it should be understood that, since the respective modules are merely set to illustrate the functional units of the apparatus of the present invention, the physical devices corresponding to the modules may be the processor itself, or a part of software in the processor, a part of hardware, or a part of a combination of software and hardware. Accordingly, the number of individual modules in the figures is merely illustrative.
Those skilled in the art will appreciate that the various modules in the apparatus may be adaptively split or combined. Such splitting or combining of specific modules does not cause the technical solution to deviate from the principle of the present invention, and therefore, the technical solution after splitting or combining falls within the protection scope of the present invention.
Thus far, the technical solution of the present invention has been described in connection with the preferred embodiments shown in the drawings, but it is easily understood by those skilled in the art that the scope of protection of the present invention is not limited to these specific embodiments. Equivalent modifications and substitutions for related technical features may be made by those skilled in the art without departing from the principles of the present invention, and such modifications and substitutions will fall within the scope of the present invention.
Claims (8)
1. A link tracking method applied to a link tracking system, the link tracking system including a preamble engine and a back-end processing engine, the preamble engine and the back-end processing engine interacting information, the method comprising the steps of:
controlling the preposed data engine to acquire service log data and acquiring an abnormal call fragment based on the service log data;
controlling the preposed data engine to acquire the number of the abnormal calling fragments and judging whether the number of the abnormal calling fragments meets the preset number condition;
selectively controlling the pre-data engine to acquire a random call fragment based on the service log data based on a judgment result;
Based on a sampling calling segment, controlling the preposed data engine and the back-end processing engine to acquire first calling chain data, wherein the sampling calling segment is the abnormal calling segment or the abnormal calling segment and the random calling segment;
controlling the back-end processing engine to execute corresponding link tracking operation based on the first call link data;
judging whether the tag data information contains error=1 and/or http.status_code |=200; when the flag bit tag data information contains error=1 and/or http.status_code |=200, judging that a calling fragment containing the flag bit tag data information is an abnormal calling fragment;
when the number of the abnormal call fragments does not meet the preset number condition, controlling the preposed data engine to acquire the random call fragments based on the service log data, wherein the sampling call fragments are the abnormal call fragments and the random call fragments;
and when the number of the abnormal call fragments meets the preset number condition, the sampling call fragments are the abnormal call fragments.
2. The link tracking method of claim 1, wherein the step of controlling the preamble engine to acquire service log data comprises:
And controlling the preposed data engine to read the service log data and caching the read service log data into a preset List < Map < String >, wherein the List is a List, the List < > is a storage of the data, and the Map is an object for mapping keys to values.
3. The link tracking method according to claim 1, wherein the service log data includes an exception call fragment and a non-exception call fragment, and the step of selectively controlling the preamble engine to acquire a random call fragment based on the service log data based on the judgment result includes:
and when the number of the abnormal call fragments does not meet the preset number condition, controlling the preposed data engine to acquire random call fragments based on the non-abnormal call fragments.
4. The link tracking method of claim 1, wherein the step of controlling the pre-data engine and the back-end processing engine to obtain the first call chain data based on the sample call fragment comprises:
controlling the preposed data engine to report the acquired sampling calling fragment to the back-end processing engine;
The back-end processing engine receives the sampling calling segment and sends a notification for acquiring first calling chain data to the preposed data engine based on the sampling calling segment;
the preposed data engine receives the notification of acquiring the first call chain data, acquires the first call chain data based on the notification of acquiring the first call chain data and reports the first call chain data to the back-end processing engine.
5. The link tracking method of claim 1, wherein the step of controlling the back-end processing engine to perform a corresponding link tracking operation based on the first call chain data comprises:
based on a merging and sorting algorithm, controlling the back-end processing engine to process the first call chain data so as to obtain second call chain data;
and controlling the back-end processing engine to calculate based on the second call chain data so as to realize link tracking.
6. A link tracking system comprising a pre-data engine and a back-end processing engine, the pre-data engine and the back-end processing engine in information interaction, the pre-data engine configured to perform a first operation in a multithreaded parallel manner, wherein the first operation comprises:
Acquiring service log data and acquiring an abnormal call fragment based on the service log data;
acquiring the number of the abnormal call fragments and judging whether the number of the abnormal call fragments meets the preset number condition;
based on the judging result, selectively acquiring a random call segment based on the service log data;
acquiring first call chain data based on a sampling call fragment and a notification of acquiring the first call chain data, and reporting the first call chain data to the back-end processing engine, wherein the sampling call fragment is the exception call fragment or the exception call fragment and the random call fragment;
the back-end processing engine is configured to: sending the notice of acquiring the first call chain data to the preposed data engine based on the sampling call fragment, receiving the first call chain data and executing a link tracking operation based on the first call chain data;
judging whether the tag data information contains error=1 and/or http.status_code |=200; when the flag bit tag data information contains error=1 and/or http.status_code |=200, judging that a calling fragment containing the flag bit tag data information is an abnormal calling fragment;
When the number of the abnormal call fragments does not meet the preset number condition, controlling the preposed data engine to acquire a random call fragment based on the service log data, wherein the sampling call fragment is the abnormal call fragment and the random call fragment;
and when the number of the abnormal call fragments meets the preset number condition, the sampling call fragments are the abnormal call fragments.
7. The link tracking system of claim 6, wherein the preamble engine is configured to perform the first operation in the multithreaded parallel manner based on at least one of semaphore.acquisition (), key volatile, and thread.
8. A readable storage medium having stored therein a plurality of program codes, wherein the program codes are adapted to be loaded and executed by a processor to perform the link tracking method of any one of claims 1 to 5.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202310678676.5A CN116471213B (en) | 2023-06-09 | 2023-06-09 | Link tracking method, link tracking system and medium |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202310678676.5A CN116471213B (en) | 2023-06-09 | 2023-06-09 | Link tracking method, link tracking system and medium |
Publications (2)
Publication Number | Publication Date |
---|---|
CN116471213A CN116471213A (en) | 2023-07-21 |
CN116471213B true CN116471213B (en) | 2023-09-15 |
Family
ID=87175683
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202310678676.5A Active CN116471213B (en) | 2023-06-09 | 2023-06-09 | Link tracking method, link tracking system and medium |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN116471213B (en) |
Citations (16)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2017071134A1 (en) * | 2015-10-28 | 2017-05-04 | 北京汇商融通信息技术有限公司 | Distributed tracking system |
CN108462750A (en) * | 2018-03-22 | 2018-08-28 | 平安好房(上海)电子商务有限公司 | Distribution calls method for tracing, operation system, monitoring system and storage medium |
CN111478806A (en) * | 2020-04-02 | 2020-07-31 | 聚好看科技股份有限公司 | Link tracking sampling method and system |
CN112181931A (en) * | 2020-10-20 | 2021-01-05 | 上海依图网络科技有限公司 | Big data system link tracking method and electronic equipment |
CN112486786A (en) * | 2020-11-12 | 2021-03-12 | 贝壳技术有限公司 | Calling link tracking method and device |
CN112860507A (en) * | 2021-01-13 | 2021-05-28 | 时时同云科技(成都)有限责任公司 | Method and device for controlling sampling rate of distributed link tracking system |
CN113516174A (en) * | 2021-06-03 | 2021-10-19 | 清华大学 | Call chain abnormality detection method, computer device, and readable storage medium |
CN114024837A (en) * | 2022-01-06 | 2022-02-08 | 杭州大乘智能科技有限公司 | Fault root cause positioning method of micro-service system |
US11250069B1 (en) * | 2020-10-16 | 2022-02-15 | Splunk Inc. | Related content identification for different types of machine-generated data |
CN114185708A (en) * | 2021-12-15 | 2022-03-15 | 中国农业银行股份有限公司 | Data analysis method and device based on distributed link tracking and electronic equipment |
US11388211B1 (en) * | 2020-10-16 | 2022-07-12 | Splunk Inc. | Filter generation for real-time data stream |
CN114816915A (en) * | 2022-04-21 | 2022-07-29 | 阿里巴巴(中国)有限公司 | Link tracking method and device |
CN115422036A (en) * | 2022-07-29 | 2022-12-02 | 重庆长安汽车股份有限公司 | Vehicle-end SOA service call chain tracking method based on OpenTelemetry |
CN115687406A (en) * | 2022-11-07 | 2023-02-03 | 北京优特捷信息技术有限公司 | Sampling method, device and equipment of call chain data and storage medium |
CN115883343A (en) * | 2022-12-07 | 2023-03-31 | 天翼云科技有限公司 | Micro-service link tracking method and system |
CN116028469A (en) * | 2023-01-04 | 2023-04-28 | 北京夏石科技有限责任公司 | Data security link tracking method and device |
Family Cites Families (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US11785115B2 (en) * | 2021-09-27 | 2023-10-10 | International Business Machines Corporation | Request tracing |
-
2023
- 2023-06-09 CN CN202310678676.5A patent/CN116471213B/en active Active
Patent Citations (16)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2017071134A1 (en) * | 2015-10-28 | 2017-05-04 | 北京汇商融通信息技术有限公司 | Distributed tracking system |
CN108462750A (en) * | 2018-03-22 | 2018-08-28 | 平安好房(上海)电子商务有限公司 | Distribution calls method for tracing, operation system, monitoring system and storage medium |
CN111478806A (en) * | 2020-04-02 | 2020-07-31 | 聚好看科技股份有限公司 | Link tracking sampling method and system |
US11250069B1 (en) * | 2020-10-16 | 2022-02-15 | Splunk Inc. | Related content identification for different types of machine-generated data |
US11388211B1 (en) * | 2020-10-16 | 2022-07-12 | Splunk Inc. | Filter generation for real-time data stream |
CN112181931A (en) * | 2020-10-20 | 2021-01-05 | 上海依图网络科技有限公司 | Big data system link tracking method and electronic equipment |
CN112486786A (en) * | 2020-11-12 | 2021-03-12 | 贝壳技术有限公司 | Calling link tracking method and device |
CN112860507A (en) * | 2021-01-13 | 2021-05-28 | 时时同云科技(成都)有限责任公司 | Method and device for controlling sampling rate of distributed link tracking system |
CN113516174A (en) * | 2021-06-03 | 2021-10-19 | 清华大学 | Call chain abnormality detection method, computer device, and readable storage medium |
CN114185708A (en) * | 2021-12-15 | 2022-03-15 | 中国农业银行股份有限公司 | Data analysis method and device based on distributed link tracking and electronic equipment |
CN114024837A (en) * | 2022-01-06 | 2022-02-08 | 杭州大乘智能科技有限公司 | Fault root cause positioning method of micro-service system |
CN114816915A (en) * | 2022-04-21 | 2022-07-29 | 阿里巴巴(中国)有限公司 | Link tracking method and device |
CN115422036A (en) * | 2022-07-29 | 2022-12-02 | 重庆长安汽车股份有限公司 | Vehicle-end SOA service call chain tracking method based on OpenTelemetry |
CN115687406A (en) * | 2022-11-07 | 2023-02-03 | 北京优特捷信息技术有限公司 | Sampling method, device and equipment of call chain data and storage medium |
CN115883343A (en) * | 2022-12-07 | 2023-03-31 | 天翼云科技有限公司 | Micro-service link tracking method and system |
CN116028469A (en) * | 2023-01-04 | 2023-04-28 | 北京夏石科技有限责任公司 | Data security link tracking method and device |
Non-Patent Citations (1)
Title |
---|
事件驱动的微服务调用链路数据动态采集方法;李鹏等;《计算机应用》;第42卷(第11期);第3493-3499页 * |
Also Published As
Publication number | Publication date |
---|---|
CN116471213A (en) | 2023-07-21 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US7698602B2 (en) | Systems, methods and computer products for trace capability per work unit | |
US9389936B2 (en) | Monitoring the responsiveness of a user interface | |
US9495199B2 (en) | Management of bottlenecks in database systems | |
US8028201B2 (en) | Leveled logging data automation for virtual tape server applications | |
CN110895487B (en) | Distributed task scheduling system | |
US9652307B1 (en) | Event system for a distributed fabric | |
CN112148221B (en) | Method, device, equipment and storage medium for inspecting redundant array of inexpensive disks | |
CN110750592A (en) | Data synchronization method, device and terminal equipment | |
US20090100196A1 (en) | Generic shared memory barrier | |
US11526413B2 (en) | Distributed tracing of huge spans for application and dependent application performance monitoring | |
CN111580939B (en) | Method and device for processing transactions in hierarchical and asynchronous mode | |
CN110895483A (en) | Task recovery method and device | |
US9176783B2 (en) | Idle transitions sampling with execution context | |
Liu et al. | Optimizing shuffle in wide-area data analytics | |
CN110764962B (en) | Log processing method and device | |
CN110895486B (en) | Distributed task scheduling system | |
JP5545761B2 (en) | Failure analysis support system, failure analysis support method, and failure analysis support program | |
CN116471213B (en) | Link tracking method, link tracking system and medium | |
CN113746883B (en) | Link tracking method and system | |
CN110895485A (en) | Task scheduling system | |
CN113849317B (en) | Memory pool resource using method and related device | |
CN109257256A (en) | Apparatus monitoring method, device, computer equipment and storage medium | |
CN112818204B (en) | Service processing method, device, equipment and storage medium | |
CN111290942A (en) | Pressure testing method, device and computer readable medium | |
CN112559445B (en) | Data writing method and device |
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 |