JP2656474B2 - Data processing system and method - Google Patents

Description

Description: BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to a data processing system and method, and more particularly to processing data obtained during a logging operation for investigating a formation through a borehole. But not limited thereto.

BACKGROUND OF THE INVENTION Drilling logging is an important step in discovering and developing underground resources of hydrocarbons and other valuable raw materials. Typically, after drilling a hole, an elongated logging device or sonde can be lowered to the bottom of the hole and power and signals can be transmitted between the surface equipment and the sonde via an armored table containing electrical conductors. So that The sonde is then lifted up along the borehole by winding up the cable and sensors in the sonde are used to measure electrical, acoustic and / or nuclear parameters of the formation through which the borehole has been passed. . The measurements are sent upwards via a cable and recorded on a surface device. Analyzing and decoding these measurements at the location of the borehole during the logging operation or at a later location can provide information regarding the presence and productivity of hydrocarbons and other feedstocks.

Due to the shortage of hydrocarbon resources, there is a pressing need to develop resources that are increasingly difficult to extract commercially.
Accordingly, logging instruments used to survey such resources are becoming increasingly complex and sophisticated, and now a computer is installed on ground equipment at the location of the wellbore to monitor and control the operation of the sonde. It is common to collect and analyze the measurements obtained by the sonde. Such computers typically encode timing and other control signals and send them to a sonde to initiate a measurement cycle, receive signals from the sonde and decode them to provide data regarding measurement and sonde operation. Take out, analyze the data to monitor the sound of the sonde and generate a control signal to send to the sound, optimize the sound of the sound based on the conditions of the borehole and the formation, monitor the depth of the sound in the well, Processing the data to obtain the required measurements, processing the measurements to derive values for the formation parameters, and forming a real-time representation of the selected operating parameters, measurements and formation parameters of the sound. Perform various functions. Such a large number of various functions imposes a considerable burden on the computer system. Implementing a computer system to perform all necessary tasks quickly and accurately enough to obtain an acceptable logging rate involves:
It turns out to be very difficult and time consuming.

The need for data collection and control described above is also found in other environments, such as avionics and aerospace.

Problems to be Solved by the Invention What is particularly problematic here is that the computer must perform a data processing function that is essentially independent of the processing time and duration, and is affected by the processing time and duration. That is, the processing control function to be performed must also be performed. Thus, for example, processing the data obtained from a sonde by Fourier transform is a time-independent task, and the same result as the converted output is always obtained from the same set of data values regardless of the processing time and duration. Can be In contrast, collecting data from sondes
Based on time, the actual value found by examining the last of a series of received data items (which affects the next control signal to be sent to the sonde) is determined by the It is based on the speed at which it is sent and the speed at which a series of data items from the sonde are examined. Changes in the processing speed of the equipment being raised and lowered along the wellbore will affect the results. Furthermore, the rate at which the drilling hole is signaled upwards is typically based primarily on the characteristics of the sound, and therefore the time of receipt of each data item at the surface cannot be controlled by the surface computing device. Similarly, the characteristics of the sonde require that commands be sent down the borehole at a speed sufficient to ensure optimal operation. In order to quickly change the sound of the sonde in response to changing conditions, ensure that timeless operations do not interfere with the time-based functions that occur in time with it, so as to avoid data loss and defects. There must be. Similarly, it is important to ensure that time-based functions do not cause errors in time-independent processing. These characteristics must be ensured regardless of a hardware system change (for example, a change in the clock speed of the processor) or a software system change (for example, the addition of a program module).

Techniques such as interrupt processing are known to coordinate the execution of multiple functions. However, these techniques must be applied very carefully to ensure sufficient operating speed and to avoid contention in using processor resources such as random access memory. This is especially true in modern logging operations with boreholes, where advanced measurement techniques generate large amounts of data using sondes, which require precise control as well. In addition, the search demand to complete the logging work as quickly as possible increases the cost. Therefore, to provide a reliable, efficient and effective data processing system operating in such an environment,
Very difficult and, of course, costly.

The problem is exacerbated when multiple tasks are to be performed simultaneously by operating one processor in a time-sharing manner or operating multiple processors in parallel.

Various means are known for subdividing the functions performed by a computer and for coordinating the operation of a multiprocessor system. For example, Information Processing 77, International Federation of Information Processing Society (Information Processing 77, International
Federation of Information Processing Societies)
(1977) G. Kern (G.
Kahn and DBMac Quee
n) “Parallel processing coroutines and networks (Cor
The paper entitled "Outines and Networks of Parallel Process" discloses a system that performs multiple processes that can be run simultaneously and communicate with each other via "channels". These channels act as first-in, first-out buffers that carry information in only one direction from the process and generate data to the process requesting the data. A process requesting a data item has access to the channel connecting it to the process that generates the sequence of that item, and receives the next item in the sequence stored in the channel. Such a system is an example of a so-called data flow architecture.

Another form of data flow system is the 1976 Proceedings of the 1976 International Conference on Parallel Processing (Proceedi
ngs of the International Conference on parallel Pr
Ocessing, pp. 100-105, by DP Misunas, "Performance analysis of a data-flow process.
ssor) and a part-time job, McGraw-Hill (By
te, McGraw-Hill) Volume 10, Issue 5 (May 1985)
It is described in a paper by WGPaseman entitled "Applying data flow in the real world" published on pages 01-214. Such systems communicate between processes by means of fixed size data packets, and the process is not performed until all the data items required to perform its function are completely obtained. When all the necessary data items have been obtained, the execution of the process is started, at which time no control is required as to whether or not the process is to be executed. A similar data flow system is disclosed in U.S. Pat. No. 4,197,589 to Cornish et al.
No. 4,229,790 to Lliland et al.

SUMMARY OF THE INVENTION It is an object of the present invention to provide a data processing system and method for easily performing time-independent and time-based operations together.

It is another object of the present invention to provide such a system and method that facilitates processing data with multiple concurrent processes.

It is yet another object of the present invention to provide a system and method for processing data using multiple data processors.

According to one aspect of the present invention, there is provided a method of processing data obtained from a sensor, including sensor data used to control the sensor and indicating the physical environment of the sensor, wherein only the flow of the sensor data is provided. In the sensor data storage device for receiving and storing the sensor data, the sensor data is written as a sequential data item stream, the sensor data is evaluated, and the data is obtained from the sensor according to the result of the evaluation and within a predetermined time period. If not,
A time limit control comprising ending the operation, comprising: (a) reading the most recently received sensor data item of interest from a sensor data storage device; and (b) retrieving the sensor data item of interest. Determining a first reference value using: (c) storing the first reference value in a first reference value storage device that receives and stores only the first reference value stream; Writing in flow form, and (d) steps (a)-(c) for different sensor data
A second process for processing the sensor data, wherein a first process consisting of sub-processes is sequentially performed, wherein (a) a sensor data item of interest is sequentially read from the sensor data storage device. (B) determining a second reference value using the sensor data item of interest; (c) in a second reference value storage device for receiving and storing only the second reference value stream; Writing a second reference value in the form of a sequential stream of data items; and (d) performing steps (a)-(c) for another sensor data.
Are sequentially repeated to achieve a second process including sub-processes. The first and second processes are simultaneous processes, and the first and second processes are performed simultaneously.
The data processing method is provided in which the percentage of achievement of the processing does not change the reference value determined in the second or first processing, respectively.

According to another aspect of the invention, there is provided a system for processing a sequence of sequential data items that includes a sensor data used for sensor data and that indicates a physical environment of the sensor, the sequential data item comprising: First acquiring means for acquiring the first data means; first storing means for receiving and storing data items only from the first data stream; sensor data And a time limit sensor control according to the result of the evaluation, and a second process for sequentially processing the sensor data. Processing means that are not readable, coupled to the processing means for receiving data items processed in connection with the first processing and receiving data items related to other processing Second storage means, which is not capable of receiving the data items processed in connection with the second processing, and receiving the data items related to other processing. A system comprising a third storage means, which is impossible.

Embodiments Further objects and features of the present invention will become apparent from the following detailed description with reference to the accompanying drawings.

The data processing system and method according to the present invention are not limited to a particular type of data processing. However, these are time-independent functions that operate on data obtained from the measurement work to derive further information,
It can be used effectively for simultaneous execution of processes where both time-based functions, such as real-time control of the measuring device, must be performed. One example involving both of these types of functions is the operation of a logging instrument with a wellbore shown schematically in FIG.

Referring to FIG. 1, an elongated logging device or sonde
The 10 is suspended from a sheathed multi-conductor cable 12 at a borehole 14 that penetrates a formation 16. The sonde 10 has a pulley 20 and a depth gauge with a winch forming part of the ground surface device 24.
The cable 12 is moved up and down the borehole 14 by loosening the cable 12 through 22 and hoisting the cable (while actually performing the logging measurement). The depth gauge 22 is
The displacement of the cable 12 through the borehole and thus the borehole 14
Measure the depth of the sonde 10 at.

Instrument 10 typically includes one or more transducers for measuring parameters of formation 16 by electrical, acoustic or nuclear techniques. These transducers generate electrical signals related to the required parameters, which signals are suitably conditioned by processing and interface circuitry within the sonde 10 and are routed upwards via cable 123 to the surface equipment 24. Apparatus 24 includes a data processor 26, which typically receives, decodes, amplifies, and outputs these signals to a chart and / or magnetic tape recorder for a depth signal generated by depth gauge 22. Record as a function. In addition, device 24 processes the data represented by these signals and generates an indication of the required formation parameters (which are also recorded). By further processing these and other signals from the sound 10, the surface device 24 can monitor the operation of the sound 10 and, for example,
A signal for synchronizing the operation of the circuit components and changing the gain of the amplifier is generated, and the sound
Can be sent down to control.

The details of the structure and operation of the sonde 10 and the device that communicates signals between the sonde 10 and the ground surface device 24 do not form a part of the present invention and will be apparent to those skilled in the art and need to be described here. It is thought that there is no. Similarly, sonde 10
The specific algorithms for processing the data received from the system to derive the values of the formation parameters or to derive the control signals to be sent to the sonde 10 also do not form part of the present invention and will not be described.

Data processor 26 performs two different types of processing. The first type is essentially independent of the time at which it is performed. Therefore, when deriving the value of the required information parameter from the data received from the probe 10, the same result must always be obtained regardless of when the derivation is performed.

The second type of processing is time based. Thus, sensing that a data item being sent up the borehole by the sonde 10 appears on the cable 12 and ensuring that this data is captured and recorded, the processor 26 must
In a timely manner. Similarly, the generation of command signals sent down the borehole to the sound 10 must be at a rate sufficient to operate the sound 10 properly and to respond to changing conditions. .

These two types of processing tend to compete with each other.
Accurate derivation of parameter values requires a significant amount of processing time, causing delays and inaccuracies in the generation of command signals, and / or failing to detect and record data sent upholes. May be. Similarly, receiving data and generating command signals may interfere with the evaluation of the received data by altering the data values such that further calculations are required. In addition, even when the program is functioning properly, when transitioning to another type of computer system that operates at a different speed, or after changing, for example, to add one or more new program modules, It cannot continue to function properly. A system and method for operating a data processor that can easily and effectively be programmed to perform such tasks and alleviate these problems is described with reference to FIGS.

In these figures, data processing is shown for convenience as being performed by a number of central processing units (CPUs) operating in parallel. Each CPU performs only one task exclusively in all processing operations. However, the present invention is also applicable to the case where one or more CPUs are provided and their resources are commonly used among a number of different processes, each corresponding to a task executed by a dedicated CPU. It should be understood that they are equally applicable. The term simultaneous process will hereinafter refer to two or more processes performed by any of these configurations. Such a process is itself very complex and involves hundreds of instructions. If there are two or more CPUs, these may be distribution processing units connected by relatively low bandwidth data links, or they may be relatively high bandwidth links (eg, sharing the same main memory) ) May be connected.

Similarly, storage of data before and after processing by the CPU is shown as being divided among a number of separate storage devices for clarity. However, it is also possible to use one large storage device and divide its capacity appropriately for various data storage requirements. Techniques for sharing processors and memory leases in this manner are known and will not be described in detail here.

For example, FIGS. 2 and 3 relate to a configuration for calculating the root of the following quadratic equation (ie, the value of x such that y = 0).

According to the rule of y = ax ² + bx + c, the above expression is as follows.

Here, a, b and c are inputs as coefficients. CP
U, the number of their inputs and outputs, and the configuration and connections of the storage devices associated therewith are indicated where appropriate. Obviously, those details will vary depending on the particular application for which the processor is being installed.

Referring to FIG. 2, the data processor 30 comprises three
It is shown as having CPUs 32-36. Each CPU
Receives a data item at one or more inputs, performs processing, and then supplies the data item to one or more outputs.
For this purpose, the CPU includes a well-known arithmetic logic circuit, a register, and an instruction decode circuit. In addition, each CPU
Assume that it has its own memory for storing a program of instructions that control its operation and for storing data processed according to these instructions.
Obviously, these CPUs can share a common memory resource for these purposes.

Data processed by the processor 30 (coefficients a, b
And the values of c) are received via input lines 40, 42 and 44, which are connected to inputs 46, 48 and 50 of a data store 52 including storage devices 54 to 64. Each single input 66, 68 and 70 of storage devices 54, 56 and 58 is connected to inputs 46, 48 and 50 for receiving input data to processor 30.
Connected to. Each single input 7 of the other storage devices 60 to 64
2, 74 and 76 are CPUs 32-36 as described below.
Is used to store data obtained by the processing according to. For clarity of illustration, the input lines to the storage devices 54 to 64 are shown with dotted lines to help distinguish them from other connections.

The data storage devices 54 to 64 may incorporate, for example, a semiconductor random access memory, a magnetic disk memory, or a combination of both. As described below, the data storage device may not be able to write a new data value to a location where data has already been written. Therefore, a memory that can only perform a single write operation at a given location can be incorporated. One example of such a memory is a laser disk storage device,
In this case, a permanent pattern of microscopic pits is formed on the surface of a metal disk or a metallized plastic disk, and data is stored using a laser beam so as to be read later. Such storage devices are, for example, Op Op, located in Redondo Beach, California, USA
timem of Sunnyvale, California and Optical Disk Man
Available from ufacturing Co., a division of Alcatel Thomson. Laser disk storage has the advantage that very large amounts of data can be stored in a relatively small physical space.

Each storage device 54-64 is configured to receive data at its respective input 66-76 and to store this data as successive data item streams. Additional data items are added at the end of this flow to the trace of the data items already received. The length of the stream of data items can in principle be extended without limit, but it is clear that the finite physical storage capacity of the storage device places a limit on the amount of data that can be stored at one time. However, each new data stream is treated as extending the length of the stream.

The term data stream is used herein to indicate a particular information entity to be accessed regardless of other items. Therefore, depending on the application, the data item is
For example, a single binary digit (1 bit), an 8-bit byte, a 16-bit or 32-bit word, a multi-byte value representing a value in integer or decimal format, a sequence of bytes encoding a sequence of alphabetic characters, or ,
The whole array of such values. The data item itself is a value that serves as a pointer to the location of another data item in the storage device.

As data items are added to a stream in storage, unique index values are combined based on their position in the stream. The index value of each data item is
1 more than the index value of the immediately preceding item in the same flow
Only big. In the simple case of FIG. 1, where each stream has its own dedicated storage device, this index value is simply the number of data items previously received by the storage device (where the first item is (Assuming index value 0). In these situations, no special action is required to assign a data item its index value. Further, if the physical storage location in the storage device starts at address 0, the index value of the data item directly corresponds to the address of that location in the storage device. The storage device need only maintain an indication of the next free storage location where the next received data item should be written.

Rather than dedicating individual storage devices to each stream of data, multiple streams of data can be stored on the same storage device. One possible solution is to treat the storage device as partitioning it into a number of segments,
Assigning each segment to one stream. In such a case, it is also necessary to maintain a record of the storage location containing the first data item of the stream for each stream. Thus, the storage location of another data item in the same stream can be identified by adding the index value of that item to the address of the storage location containing the first item. Alternatively, data items from different streams can be mixed. In this case, a table of storage locations associated with each stream can be maintained, or a linked list can be used, where each stored data item contains the location of the next data item in the same stream. Are combined. These techniques for managing shared memory are known.

The storage devices 54 to 64 may incorporate a memory capable of writing new data over existing data. If data items that are no longer needed can be identified and their locations can be reused, new data items can continue to be added to the stream indefinitely, but at any time the amount of items in the storage device will be Obviously, the capacity is never exceeded. One way in which such reuse can be performed is to limit the selection of data items to retrieve from the storage device to those data items received after the most recently retrieved data item. Thus, assuming that a numerically increasing index value is specified for a data item received by the storage device,
The index value of the item to be searched cannot be reduced. A position including a data item having an index value smaller than the index value of the last item retrieved from the storage device is a reusable position. Techniques for managing finite memory resources to achieve this result are known, for example, the so-called "garbage collection".

Even if the new data item thus physically re-uses the storage location of the earlier, currently undesired data item, the new item is combined with its own unique index value and the previous The index value of the replaced item is not reused. Also, existing data items are not changed. Replacing the value of one data item with another writes a new data item with its own unique index value and uses this new data item instead of the superseded item before it It is done by doing.

If the storage location is reused, it is necessary to maintain a record of the index value of the earliest data item still stored and the address of its physical location. The difference between this index value and the unique index value of the other data item can be added to the address of the earliest item to derive the address of the other item.

If the storage device 52 incorporates a one-time write memory such as the laser disk device, such reuse is impossible, and therefore, there are no restrictions on the index value of the data item to be searched. There is no need to apply, and the index value for the search for the data item can be arbitrarily increased or decreased. Although the storage device 52 is eventually saturated, its very large storage capacity allows a significant period of effective operation before a storage medium must be replaced or expanded.

Each storage device 54-64 has one or more outputs, and
54 and 56 have three outputs 78, 80, 82 and 84, 86, respectively.
The device 58 has one output 90, the device 60 has two outputs 92 and 94, and the devices 62 and 64 have one output 96 and 98, respectively. Each such output is configured to search for any data item in the flow stored in the associated storage by referring to the index value of the required item. Also, if a data item with an index value for which no data item has been received is requested, the storage device will wait until a data item with that index value is received and then return that data item upon request. It is composed of When the storage location is reused, the same method for identifying the storage location for data retrieval is used as the method for storing the data item, and the range of index values in which the data can be retrieved is as described above. Be restricted.

Each of the storage devices 54, 56 and 60 is shown in FIG. 2 as having a plurality of separate outputs, also separated from the inputs, for clarity of illustration. However, it should be understood that, for example, in a magnetic disk storage device, the input and output functions can be performed by appropriately controlling a single read / write head. Similarly, when using semiconductor memories, these functions are performed by addressing the circuits in a known manner.

The data items received by data processor 30 via input lines 40-44 are stored in storage devices 54-44, respectively.
Stored at 58. All these data items (coefficients a, b
And c) are those used by the CPU 32, so that its three inputs 100-104 are connected to the outputs 82, 84 and 90 of the storage devices 54, 56 and 58, respectively. By means of a dotted control line 106 extending from the CPU 32 to the output 82, the CPU 32 specifies the index value of the data item (value of the coefficient A) retrieved from the storage device 54 and sent to the CPU by the output 82. be able to. Output 84
And 90 through similar control lines 108 and 110.
2 can specify required data items (corresponding values of coefficients b and c) retrieved from the storage devices 56 and 58.
CPU 32 is shown as generating a single stream of data items (the value of the intermediate result, known as radicals), which is provided to storage device 60 via input 72.

By the output 92 of the storage device 60, the CPU 34
, And data items (corresponding values of coefficients a and b) from storage devices 54 and 56, which are used to control the control lines 114 and 116. Originally provided by outputs 80 and 88. The CPU 34 supplies the data items obtained by the process in which it executes to the storage device 62 via the input 74. These data items are the values of one root of the quadratic equation for the corresponding values of the coefficients a, b and c. CPU36
Similarly, the data items specified via control lines 118, 120 and 122 are output from storage devices 54, 56 and 60 to outputs 78 and 86.
And 97, and provides the resulting data item to storage 64 via input 76. These data items are the values of the other root of the quadratic equation for these coefficient values.

Finally, the data items in storage devices 62 and 64 are provided to outputs 124 and 126 of data processor 30 by outputs 96 and 98 based on the index values specified via control lines 128 and 130.

The identification of the stream from which the data stream is to be retrieved may or may not be explicitly specified, depending on the configuration of the storage device and the format of the index values. Thus, in the arrangement of FIG. 2, the required flow is uniquely identified by the physical selection of the appropriate control lines 106-122, 128 or 130. If memory is shared between the various streams, the identification of the streams can be encoded into index values, giving each stream its own separate set of index values. Alternatively, the index value may be similar for each stream, and the identification of the stream may be given as a parameter with the index value when the data item is requested.

The processes performed by each of CPUs 32 through 36 are summarized in FIG. CPU34
And 36 are similar.

Referring to FIG. 3, the index value of the data item to be supplied to the CPU 32 must be initialized when the process is first started. This is represented by step 132. Next, in step 134, the CPU 32 requests a data item of the coefficient a from the storage device 54 based on the current index value. In step 136, the CPU
32 checks if the data item has been received.
If not, until the data item is received,
The process repeats via step 136. When a data item is received, the process continues to step 138, where a data item corresponding to coefficient b is requested from storage 56, and step 140 is repeated as necessary until the data item is received. This sequence of request and repetition is performed a third time in steps 142 and 144, and the data item corresponding to coefficient c is obtained from storage device 58.

When the data items of all three coefficients are obtained, the CPU 32
Goes to step 146, where the corresponding value of radical R is calculated based on the following equation.

This value is provided to the storage device 60 as a data item in step 148, where the storage device
Receive index values corresponding to the retrieved data items at 4, 138 and 142.

The CPU 32 continues to step 150 where the storage devices 54-58
The index value to be specified in retrieving the data item from is incremented, and then step 134 is entered again,
Repeat the sequence for the next set of coefficients a, b and c.

The operation of CPUs 34 and 36 is very similar, but the data items required in step 142 are obtained from storage device 60. In the case of the CPU 34, the calculation performed in step 146 is based on the following equation.

The result is supplied to the storage device 62 as a data item in step 148. In the case of the CPU 36, the calculation performed in step 146 is based on the following equation.

The result is supplied to the storage device 64 in step 148 as a data item.

As shown in FIG. 2, each process executed by any of the CPUs 32 to 36 supplies a data item to a dedicated storage device for storing the data item from that process. Although each process shown in FIG. 2 has only one output, of course, one process can generate more than one output, in which case each output will have its own output. It will have a dedicated storage device. Each process receives data items from one or more storage devices 54-60,
One storage device may supply data items to more than one process. Thus, the only means of communicating between the processes is through storage devices 54-60. This feature has a significant effect. All data exchanges with the process are buffered in storage by the stream of data items. Thus, synchronization between processes is inherently provided by the flow, and no explicit configuration for this need be provided in the process itself. A process can add a data item to the stream and does not have to wait for another process to read it. Each process can request a data item as needed, and the arrival of the data item does not force the process using that item to run. Since the index value is not re-assigned to a new data item and the data item is never changed, the process can always use the data item within the constraints imposed by the finite storage capacity. Within this same control, a process can request any data item in the stream and is not limited to receiving the items in a predetermined sequence. Of course,
There is no risk that the process receives the data items in the wrong order.

Also, in the embodiment shown in FIG. 2, the only means of connecting the inputs and outputs of all data processors 30 and the processes executed by CPUs 32 through 36 is the storage in storage 52 (ie, storage 54). , 56, 58, 62 and 64). This is desirable but not important.

The process functions shown in FIGS. 2 and 3 are purely timeless. In particular, storage devices 54 to 64
The value obtained when searching for a data item from is independent of the occurrence time of the searched item. When a function irrespective of time is performed, another search function as shown in FIGS. 4 and 5 is involved.

FIG. 4 shows a storage device 150, which comprises further circuitry enabling the retrieval of the most recently received data item in the stream stored therein, in which case the The index value of an item is not specified by the CPU or process that needs the item. The control line 152 from the CPU is connected to a register 154, which stores the index value of the most recently received data item via the connection 156 from the storage device 150 as each data item is received via the input line 158. Be updated. Register 154 then outputs the output of storage device 150.
Connected to 160. So the request for the data item is line 1
When received via 52, this is output to register 1 along with the index value of the most recently received item, i.e., the value currently held in register 154.
Sent to 60. The data item received is output line 16
Supplied via 2.

FIG. 5 shows a storage device 164 which has further circuitry that can attempt to retrieve a data item. In this case, a predetermined limit is imposed on the waiting time of the storage device when there is no data item having the specified index value. The control line 166
It is connected directly to the output 168 of the storage device 164 to indicate the index value of the data item to be searched, and is also connected to the trigger input T of the monostable circuit 170. Output line 172
Supplies the retrieved data item and is connected to the clear input of the monostable circuit 170. The set output of the monostable circuit 170 is connected to a time-out signal line 174 and an output 168. When a data item is requested via control line 166, the request is sent to storage 164, and at the same time, monostable circuit 170 is triggered to enter its pseudo-stable state for a predetermined period of time. If the requested data item is in storage 164 or received before the predetermined time has elapsed, it is provided via output line 172 and the monostable circuit 170 is output before the end of the pseudo-stable time is reached. Clear
However, if the requested data item is not available before the expiration of the predetermined time, the monostable 170 times out and generates a signal on the time-out line 174. This signal indicates to the requesting CPU or process that a time-out has occurred and cancels any outstanding requests at output 168 of storage device 164. If desired, the monostable circuit may have a variable pseudo settling time determined based on the value specified on control line 166 by the CPU issuing the request when the data item is requested. The design of a circuit that performs such functions will be apparent to those skilled in the art.

A second data processor according to the present invention will be described with reference to FIG. This processor uses the search operation described with respect to FIGS. 4 and 5 to control the speed of a sensor moving along a trajectory (eg, a logging sonde that can lift a borehole upwards) and the sensor. Perform time-based functions in the form of data collection from This sensor emits a data item once every two seconds, at a rate of
The signal is transmitted every 1/10 second. The processor checks whether data items continue to arrive from the sensor and terminates operation of the sensor if the data is interrupted for a time that exceeds a preset limit.

Referring to FIG. 6, a data item from a sensor is received via a line 176 by a processor generally indicated by the reference numeral 175 and provided to a data storage 178 of a data storage 180. A data item representing the speed of the sensor is received on line 182 and is stored in another data storage 1
Supplied to 84. This storage device has an output 186 configured to perform the function of reading the latest one as described with reference to FIG. This output provides the CPU 188 with the latest data item representing the speed of the sensor.
The CPU also receives the data items from output 190 of storage device 178 and stores the resulting data items in storage device 178.
Supply to 2. Another output 194 from storage 178 having a timeout function as described with reference to FIG. 5 provides sensor data items to a second CPU 196, the output of which is connected to storage 198. Each output 200 and 202 of the storage devices 192 and 198 is connected to a third CPU 204, which supplies data items to the storage device 206. The fourth and last CPU 208 receives the data items of the sensor via its output 210 from the storage device 178 and supplies the data items to the storage device 212. The storage devices 206 and 212 provide outputs 214 and 216 and output lines 218 from the data processor 175 with the data items as output signals.
And 220.

The operation of the CPU 188 is shown in the flowchart of FIG. When the operation of the processor 175 is started, the index value of the data item to be retrieved from the storage devices 178 and 184 is initialized at step 222. Then C
PU188 enters a loop that begins with step 224, where:
The storage 178 requests a sensor data item. Since the sensor only supplies data items once every two seconds,
There is no first data item at the position corresponding to the index value specified by CPU 188 when issuing the request. Thus, when the CPU 188 proceeds to step 226 to determine whether a data item has been received from the storage device 178, the result is initially negative. Therefore, the CPU 188 proceeds to step 226
And continue operation until a data item is received. When a data item is received, the CPU 188 proceeds to step 226 and requests the latest speed data item from the storage device 184. Since the speed data item is received ten times per second, there is already a data item in storage 184 when the first request is made. Therefore, the latest value is always obtained and the request is fulfilled immediately. CPU 188 proceeds to step 230
Then, it is determined whether the speed of the sensor needs to be adjusted. This determination can be made based on an appropriate algorithm, which does not form part of the present invention and will not be described here. If no change is needed, CPU 188 returns to repeat the loop starting at step 224 via step 232, where the index value used to request the data item from storage 178 is incremented. If a change is required, an appropriate command is sent to the storage device 192 in step 234,
The CPU proceeds to step 232 as described above.

The operation of the CPU 196 is shown in the flowchart of FIG. When processor 175 begins operation, the index value is initialized at step 236. The process then proceeds to step 238, where a data item is requested from storage 178 at the specified time limit. Step 2 in Fig. 7
Just as CPU 188 searched for the data item at 24,
There is an interval before a data item is available if needed. With this interval, the CPU 196 performs two decision steps 24
Pass through 0 and 242. In the first of these steps, CPU1
96 checks whether a data value has been received. If so, the CPU 196 proceeds to step 244, increases the index value for retrieval from the storage device 178, and then returns to step 238.

If the result of step 240 is negative, CPU 196 proceeds to step 242 and checks whether a time-out signal is received from output 194 of storage device 178. If no such signal is present, the time limit for interruption of data from the sensor has been exceeded and therefore the CPU 1
96 repeats decision steps 240 and 242. However, if the CPU 196 does not receive the time-out signal,
Proceeding to 246, a command to end the operation of the sensor is supplied to the storage device 198.

As shown in FIG. 9, the CPU 204 first executes step 24
Request data items from both storage devices 192 and 198 at 8 and 250. Next, at step 252, it is checked whether any items have been received from the storage device 192. If so, in step 254,
Sends the received data item to the storage device 206, and proceeds to step 2
At 56, the request for the data item from the storage device 192 is resumed, and the process returns to step 252. If not,
Proceeding to step 258, the receipt of a data item from the storage device 198 is checked. If there is no data item, the check loop is repeated by returning to step 252. Otherwise, step through the received data items
At 260, the data item is sent to the storage device 206. At step 262, the request for the data item from the storage device 198 is resumed, and the process returns to step 252. The effect of the process performed by CPU 204 is to cause the commands generated by CPUs 188 and 196 to be merged and transmitted to storage 206 in the order in which they were generated, and to be provided via line 218 as the output of processor 175. is there. This process is only one example of a time-based process, as the exact sequence of commands appearing in the storage device 206 changes with the conditions experienced by the sensor (eg, borehole conditions) and the resulting effects.

Another way to merge two sets of commands in a time-based way
One approach is to send two inputs to the storage device and add each sequence of commands to the flow in the storage device via each input.

CPU 208 simply retrieves the sensor data items from storage device 178 and performs appropriate processing on these data items to form the desired information, which is then stored in storage device 212.
Output to This processing can take various forms such as a combination with an arithmetic device or other data. The details of such processing are not related to the present invention, and need not be described in detail.

As with the processor 30 of FIG. 2, all data communication between processes executed by the CPU is accomplished by a stream of data items held in storage, each data item being unique in its stream. Are combined.

When a separate CPU is used for each process, this configuration has the following effects. That is, time-independent operation (eg, processing of sensor data by CPU 208) and time-based operation (eg, monitoring of sensor speed by CPU 188) can be performed separately without causing any adverse effects that may occur between processes. In the process. This makes it easy to design, write, and process efficient, effective, and reliable programs. Further, the particular details of the hardware for running the program need not be considered. Similarly, the possibility of subsequent changes to the hardware, the use of different hardware,
Or for changes to the program that executes the process,
No special configuration is required.

Therefore, the processing of data by the CPU 208 depends on the complexity and speed of the operation of the CPU 208, but at an appropriate speed without the risk that the sensor data items waiting for processing will be lost or overwritten by the execution of another process. You can proceed. These data items are made available in the storage device 178 and output by the CPUs 188 and 196.
Regardless of whether it has already been searched through 90 and 194, C
Retrieved via output 210 when requested by PU 208. Similarly, the output data obtained by such a process is output line 218 without risk of data loss prior to extraction.
CPU 208 at a speed independent of the speed at which data is extracted through
Can be caused by:

The time-based process executed by CPU 188 is
It can be implemented to monitor and control the speed of the sensor at a speed that is considered desirable, and in response, a data item can be extracted from storage 178 via output 190. This process functions regardless of the execution of the data processing function in the CPU 208, and there is no possibility that this processing will cause delay or timing problems. Therefore, there is no need to consider timing conflicts when programming the process.

Even when a process is executed in a state where a single CPU is shared between a large number of processes, there is no risk that the data required for the process regardless of time will be degraded by the execution of the time-based process. Delays may occur for time-based processes, but by partitioning the processes such that communication between processes occurs only through the flow of data items, analysis of the behavior of such processors, The identification and reconciliation of potential conflicts is facilitated. Further, it is believed that this architecture provides an effective structure for implementing techniques that can account for timing constraints and avoid timing conflicts.

Further, the present invention helps system designs that can be initially implemented on a single CPU and that can be migrated to a multiple CPU system without significant changes.

It is not necessary to split time-based and time-independent functions between the various processes, but this is generally considered a good idea, reducing timing conflicts and the difficulty of subsequent changes. Help.

All communication between the processor 175 and its outside world preferably occurs through a further stream of data items, as shown in FIG. However, if desired, data may be exchanged directly with other devices in one or more processes. Such exchanges are typically time-based, ie, the result depends, for example, on execution speed.

Processors 30 and 175 of FIGS. 2 and 6 have individual connections for communicating data items between each CPU and storage. Alternatively, such connections can be multiplexed, as shown in FIG. Referring to FIG. 10, the storage unit 270 includes six storage devices 272 to 28.
2 each of which has a respective input 284 to 294
And each has a single output 296-306. Each of these inputs and outputs is connected to an input / output circuit 308 and to each control line 310-320 associated with each output 296-306. The three CPUs 322 to 326 are connected to the input / output circuit 308 by respective control lines 328 to 332 and two-way data lines 334 to 338. An input line 340, an output line 342 and its associated control line 344 are also connected to the input / output circuit 308.

In operation, CPUs 322-326 control lines 328-33.
Data items are obtained from the storage devices 272 to 282 by sending a signal to the input / output circuit 308 via 2. These signals identify the storage device from which the data item was requested and the index value for the requested item. The input / output circuit 308 provides a request, including the index value, to the storage device thus identified via the appropriate control lines 310-320. The requested data item is stored in the input / output circuit via the respective output 296-306 by the storage device.
808 back to the appropriate data line 3
Via 34 to 338, send to the CPU that issued the request. The data items generated by CPUs 320-326 are stored in storage device 272.
Input / output circuit 308 via each one of the data lines 334-338, with signals on corresponding control lines 334-332 identifying which of the data items should receive the data item.
Supplied to The input / output circuit 308 sends the data item to the storage device thus identified by supplying the data item to an appropriate one of the inputs 284-294.

Similarly, input / output circuit 308 provides input data received via input line 340 to appropriate ones of storage devices 272-282, and also outputs data to output line 344 based on requests sent via control line 344. Supply items.

As shown in FIG. 10, each storage device 272-282 need only have one output 296-306, no matter how many CPUs have requested data items from one storage device. . The input / output circuit 308 provides, for each storage device 272-282, the length of the flow of data items in that storage device and the most recently retrieved data for each CPU requesting a data item from that storage device. It is configured to maintain a record with the index value of the item. If the storage unit 270 shares memory among multiple streams of data items as described above, the input / output circuit 308
Maintains a record of the physical location of the data items that make up each stream. Similarly, when using a read / write memory, the input / output circuitry controls the re-use of the storage device when a data item contained in the storage location becomes undesired for further processing. I do. Performing these functions using known techniques for managing memory resources
It will be readily apparent to one skilled in the art.

The input / output circuit comprises, in one possible embodiment, two blocks of random access memory and two registers. One register is used to exchange control and status information between the input / output circuits and the CPU, and the other register is used to transfer data items and index values. The first block of the random access memory is organized as a set of tables, each table having 62 pairs of 16-bit inputs and two 32 bits.
It has a bit input and is used to hold details of up to 62 pending requests for data items from one storage device. One of the 32-bit inputs is used to store the index value of the most recently added data item to the stream of data items in the storage device. Another 32-bit input stores the physical address of the storage location containing the data item. The first in each pair of 16-bit inputs
The input includes an offset from the index value of the most recently added data item to the index value of the data item requested by the CPU. The second input of the pair identifies the CPU or process requesting the data item. A one megabyte random access memory configured in this manner serves to generate up to 62 outputs for each of the 4096 storage devices.

The second block of the random access memory is organized as 1024 groups of four inputs each, and is used as a first-in first-out buffer for data items retrieved in response to requests from the CPU or process. The first input of each group is a 16-bit value that identifies the CPU or process making the request. The second input is a 12-bit value that identifies the storage or stream for which the value was requested. The third input is used to store the data item itself, in this case a 32 bit length. The fourth input is a 4-bit status value. In this configuration, the buffer requires 8 kilobytes of random access memory. The storage itself is 4096
Each stream can be implemented to store up to 512 data items, each 32 bits in length, requiring another 8 megabytes of random access memory.

The CPU performs the write operation by placing the data item to be stored in the data transfer register of the input / output circuit and placing the identification of the destination stream in the control and status register with a code indicating that a write operation is required. be able to. The input / output circuit retrieves the value of the data transfer register and attaches it to the stream of storage data items identified in the control and identification registers. The pending request table for the stream is then updated by increasing the index value of the most recently added data item and the entry for the physical location of the item. Further, the offset entry for the requested data item in each of the 62 pairs of entries in this same table is reduced. If the offset goes to zero and the paired process identifier is non-zero, the data item just added has the index value of the requested data item. In this case, the data item, process identifier and flow identification are added to the retrieved data item's buffer and the process identifier in the pending request table is set to zero to indicate that the request has been satisfied.

The CPU or process requests a data item from the input / output circuit by putting the index value of the requested item into the data transfer register along with the identification of the flow, including the item and its own identification, in the control and status registers. I do. The unused entry pairs in the pending request table for the identified stream are updated with the item's offset from the index value of the item most recently added to that stream, and the identity of the process making the request. The next data item to be retrieved in the buffer is placed in the data transfer register, and the process and flow identifiers at the relevant input of the buffer are placed in the control and status registers. The process thus identified can retrieve the data item from the input / output circuit. If one or more CPUs are shared by a process, the process that added the request to the outstanding requests table is suspended, as described below, and the process identified in the control and status registers is restarted.

Note that in this configuration, a pending request for a data item can be canceled by setting the process identification entry in the pending request table to zero.

Apart from using special hardware, the data processor according to the invention can also be implemented by appropriately programming a general purpose computer to perform the storage and processing functions described above. FIG. 11 to FIG. 15 are flowcharts showing, by way of example, how to perform the various reading and writing functions described above.

In these figures, it is assumed that there are basic memory management and process execution operations such as writing and reading to memory, garbage collection, suspending and re-executing process execution. These actions are:
For example, Interlist-D from Xerox Corporation of Pasadena, California, USA
Programming environment (Interlisp-D programming envir
onment), which is described in the Interlist Reference Manual, published in October 1983 by Xerox Corporation.
terlisp Reference Manual).

Each function is described in the form of a subroutine that can be called by the process that needs to perform it. When such a call occurs, control is temporarily transferred to a subroutine by the calling process. Thus, if the subroutine includes a step that suspends execution until reactivated by another event, execution of the calling process is also suspended.

FIG. 11 shows a procedure for reading a data item from a flow for a specified index value in response to a request from a process. The procedure starts at 350 and first,
It is checked in step 352 whether a data stream is obtained for the requested index value. This can be done, for example, by comparing the index value to the current length of the stream. If the data item is present, the procedure proceeds directly to step 354, where the data item is obtained from memory and provided to the requesting process, after which the procedure returns to the calling process at step 356. If the requested data item is not available (ie, the data item for that index value has not yet been received), the procedure proceeds to step 358. In this step, the identity and index value of the requesting process are added to a table associated with the stream of data items to hold details of the request pending for the stream. This table consists essentially of groups of memory locations previously reserved for this purpose, for example in the form of an array, in the pending request table described above for the input / output circuit of FIG. It is similar. The procedure then proceeds to step 360, where execution of the procedure is suspended until a data item is added to the flow (e.g., using the Interlist-D process suspend operation described above). Once the data item has been added, execution of the procedure is resumed, as described below. Thereafter, the procedure proceeds to step 354 as described above.
Proceed to.

The procedure for writing data items to the flow is shown in FIG. Referring to FIG. 12, this procedure is entered at step 362, beginning at step 364, where the data stream is stored in memory. This is performed in Interlist-D by the CONS operation. In the next step 366,
A counter indicating the length of the stream of data items is incremented by one, and then at step 368 the table of pending requests for that stream is checked for requests for an index value equal to the new stream length. If there is no such request, the procedure proceeds directly to step 370, where the earliest data item read from the stream is identified, and then proceeds to step 372, where all the items having the earliest index value are identified. Data items are deleted. This step can be performed in Interlist-D by the RPLACD operation. These two garbage collection stages release the reuse of memory locations occupied by unwanted data items, making them suitable when limited read / write memory is used. It will be appreciated that these can be omitted if a one time write memory is used. After step 372, the procedure returns to the calling process at 374.

If one or more pending requests are found in step 363, the procedure proceeds to step 376 where the input for each found request is examined. If this includes a reference to a timer function, the timer function is canceled, as described below with respect to FIG. Similarly, if this involves the identification of another flow that has a pending request, the pending request for that flow is removed, as described below with respect to FIG. The entry for each request found in step 368 is then removed from the table. Then, proceeding to step 378, one or more processes that requested the data item at that index value are restarted (this is done in the WAKE.PROCESS operation in Interlist-D). Thereafter, the procedure comprises steps 370 and 372
Get out of garbage collection at step 37
Continue to 4.

Referring to FIG. 13, in step 380, the procedure for executing the reading function including time-out is started. Step 38
At 2, a check is made as to whether a data item has already been obtained for the requested index value. If so, in step 384 the data item is obtained from memory and sent to the requesting process, for which the procedure returns to step 386. Otherwise, the index value and the identity of the requesting process are added at step 388 to the pending request table for that flow. In this regard, the procedure corresponds to step 35 of the normal reading means shown in FIG.
Same as 0 to 358. However, in this case, the timer function is also set during the required time before the time-out signal is generated. The identification is added to the pending request table,
Another table is combined with the timer to determine the time interval that must elapse before generating a timeout signal;
The identity of the process making the request and the identity of the flow from which the data item was requested are indicated. In step 390, a timer is started, and in step 392, the procedure is suspended. Thereafter, when the procedure is restarted, it is checked at step 394 whether the operation has been restarted by the timer generating a signal indicating that a particular time interval has elapsed. If so, step
The request added to the pending request table at 388 is removed at step 395, a time-out signal is generated at step 396, and the procedure returns to the calling process at step 398. Otherwise, resumption must be performed by receiving the data item of the requested index value, in which case the procedure proceeds to step 384, where the data item is obtained and supplied as described above.

FIG. 14 is a flowchart showing the execution of a read including an arbitration function that obtains data items from multiple streams and combines them based on a predetermined arbitration algorithm.
This corresponds to, for example, the data processor 175 shown in FIG.
, Which merges the flow of data items in storage devices 192 and 198.

Referring to FIG. 14, the procedure is entered at step 400, which is initiated at step 402, where an attempt is made to obtain a data item from each of the streams identified by the requesting process. In step 404, it is checked whether a data item has been found. If so, the procedure proceeds to check 406, where one data item is selected based on the predetermined arbitration function. This feature can, for example, select data items from one stream in preference to those from another stream.
In this procedure, the selected data item is provided to the calling process at step 408, to which control is transferred at 410. If no data item is available at step 402, the procedure proceeds to step 412, where the index value and the identity of each calling process are added to the pending table of each associated flow. In addition, the entries in each table include an identification of each other flow for which the request is pending. Thereafter, the procedure suspends operation at step 414 until the requested data item is obtained and the procedure is restarted as described above. The procedure then returns to step 402 to obtain the resulting data item and continues to step 406 as described above.

FIG. 15 shows a procedure for reading the latest value received via the flow. The procedure is entered at step 416 and a check is made at step 418 whether the length of the stream is zero. If not, step
At 420, a data item is obtained for an index value equal to the length of the stream, which is sent to the calling process, and control is returned at step 422. Otherwise, control is returned at step 426 after an indication at step 424 that the data item is not available.

Other reading functions can be provided. One idea is to read the next data item following the most recently obtained data item via the same output. This simply requires that the storage of the index value at the time the last data item was supplied be maintained at the output to the storage device. Another concept is a move command that specifies the index value where the output should be set without the data item being read. This is useful in preparing to use the next item read operation.

A set of data items having adjacent index values in the same stream of data items may be requested by defining the index value of the first item in the set and the number of required items. Yes, but no data items are supplied until all the items in the set have been obtained. Data items can be requested from a number of different streams. However, in this case, the actual index value for each flow is related to a common reference index value in a certain relationship (this is
Different for each flow). This facilitates, for example, the retrieval of corresponding data items generated simultaneously from different sensors.

The data processor of the present invention has fewer CPUs than processes
In particular, when implemented on a single CPU, a supervisor or schedule program is required to coordinate the allocation of CPU resources among the various processes. Such a schedule program merely maintains a first list of processes that can be run immediately and a second list of processes that are pending waiting for data items. Each process is assigned a certain priority rating, which allows
The schedule program can determine which processes in the first list are to be executed in preference to other processes in the list. When a process requests a data item, it requests it by calling the read procedure as described above. If a data item is available, it is supplied immediately and execution of the process continues. Otherwise, the read procedure suspends its own execution, and thus suspends the calling process. When a process is suspended, it will be moved from the first list to the second list. Similarly, when the process is resumed by the procedure for writing the requested data item, the process is returned to the first list. As the executing process transitions to the second list, the schedule program scans the first list and identifies the next process to execute based on the priority rating. Two or more
If CPUs are used, each CPU executes the process and upon its completion begins to execute the highest priority process waiting in the first list of processes.

The data processing method and system according to the present invention have been described in detail above. Although a specific embodiment of the present invention has been described, the present invention is not limited thereto. Also, the present invention has been described with respect to processing data items that occur sequentially, ie, serially. Obviously, with appropriate buffering techniques, data items received in parallel can easily be converted to serial ones. Also, the sequence need not necessarily be a time-based sequence. Although all processes have been shown as receiving data items from at least one stream, they do not receive data items, but only generate data items and provide, for example, time and date information and waveform indications. You can think of such a process. Thus, it will be apparent to one skilled in the art that various modifications may be made to the present invention within the spirit and scope of the appended claims.

[Brief description of the drawings]

FIG. 1 is a schematic diagram showing a logging operation using a wellbore which can conveniently use the present invention, FIG. 2 is a block diagram showing a first embodiment of a data processor according to the present invention, FIG. 3 is FIG. FIG. 4 is a flowchart illustrating the operation of a central processing unit forming a part of the data processor of FIG. 1, FIG. 4 is a block diagram of a storage device used to carry out the present invention, and FIG. FIG. 6 is a block diagram showing a second embodiment of the data processor according to the present invention; FIGS. 7 to 9 are central processing units forming a part of the data processor of FIG. 6; FIG. 10 is a block diagram showing another implementation of the data processor shown in FIGS. 2 and 6, and FIGS. 11 to 15 are general-purpose computers. It is a flowchart illustrating a procedure useful in the practice of the data processor of the present invention by programming the. 10 Logging instrument or sonde 12 Armored multi-conductor cable 14 Drilling hole 16 Geologic formation 20 Pulley 22 Depth gauge 24 Surface equipment 26 Data processor 30 Data processor 32-36 CPU 40, 42, 44 Input line 52 Data storage unit 54-64 Storage device

 ────────────────────────────────────────────────── ─── Continued on the front page (72) Inventor David Earl Barstow, Connecticut, United States 06897 Wilton Heather Lane 64 (56) References JP-A-58-223840 (JP, A) JP-A-55-989 (JP, A) U.S. Pat. No. 6,111,764 (JP, U) U.S. Pat. No. 5,641,341 (JP, U) U.S. Pat. No. 4,153,332 (US, A) U.S. Pat.

Claims (18)

(57) [Claims] 1. A method of processing data obtained from a sensor, including a sensor data used to control the sensor and indicating a physical environment of the sensor, the method comprising: receiving and storing only the sensor data stream. The sensor data is written in the sensor data storage device (178) as a sequential data item flow, the sensor data is evaluated, and data is not obtained from the sensor according to the result of the evaluation and within a predetermined time period. A time limit control comprising ending the operation.
(196) reading the most recently received sensor data item of interest from the sensor data storage device (178); and (b) using the sensor data of interest to generate a first reference value. Determining; (c) writing the first reference value in the form of a sequential data item flow into a first reference value storage device (198) that receives and stores only the first reference value flow; And (d) performing steps (a) to (c) for another sensor data.
A second process (188) for achieving a first process consisting of each sub-step, and sequentially processing the sensor data.
(A) sequentially reading the sensor data items of interest from the sensor data storage device (178); (b) determining a second reference value using the sensor data items of interest; (c) Writing the second reference value in the form of a sequential data item flow into a second reference value storage device (192) for receiving and storing only the second reference value flow; and (d) Steps (a) to (c) for the sensor data of
Are sequentially repeated to achieve a second process including sub-processes. The first and second processes (188, 196) are simultaneous processes, and the percentage of achievement of the first and second processes is, respectively, A data processing method that does not change the reference value determined in the second or first processing. 2. The method according to claim 1, wherein the data is borehole logging data obtained from sensors in a sound (10) installed in the borehole (14). 3. The method according to claim 1, wherein said first and second processes are performed by a single microprocessor. 4. The method according to claim 1, wherein said first processing is performed by a first microprocessor, and said second processing is performed by a second microprocessor. 5. The method according to claim 1, wherein each storage device is a separate storage device for receiving data items only from a corresponding stream. 6. The method according to claim 1, wherein the first processing (196) sequentially reads out all sensor data items written in the sensor data storage device. 7. The second process (188) includes determining a sonde command as a second reference value, and defining the sonde command as a second reference value only for receiving and storing the sonde command. A method according to any one of the preceding claims, comprising a sub-step of writing to a storage device (192) and sending the command to affect sonde operation. 8. The step of writing sensor data comprises writing a data item at every t time, and wherein the first process (196) comprises the steps of: 7. The method of claim 1, further comprising terminating data acquisition if not written to 178). 9. The terminating step includes the step of: terminating a terminating control reference value.
9. A method according to claim 8, comprising the substep of writing to a storage device (198) operable to receive and store only the termination control reference value and sending the termination control reference value as a command to the sonde. 10. The method according to claim 1, wherein none of the read steps change data items contained in each of the storage devices.
10. The method according to any one of claims 1 to 9. 11. A speed storage device (184) operable to receive data indicative of the speed of the sonde from the transducer and to receive and store only this flow of speed data.
3. The method of claim 2 including the step of writing in the form of a stream of sequential data items. 12. The second process (188) sequentially reads out a speed data item of interest from the speed storage device (184) and uses the sensor data item and the speed data item to read the second speed data item. The method of claim 11, comprising determining a reference value and writing a second reference value to a modified speed storage device (192) if the speed data item is not within an acceptable speed range. 13. The storage device of claim 1, wherein each of the writing steps includes a substep of sequentially identifying the storage location in storage using a unique index value. 13. The method according to any one of claims 12 to 12. 14. A system for processing a sequential flow of data items including a sensor data used for the sensor data and indicating a physical environment of the sensor, the system comprising: First acquisition means (176), first storage means (178) coupled to said first acquisition means, for receiving and storing data items only from a first data stream, sensor data Processing means (18) for simultaneously achieving a first process consisting of the evaluation of the data and a time limit sensor control according to the result of the evaluation, and a second process of performing the sequential processing of the sensor data
8, 196), and it is possible to read a data item from the first storage means (178) and to write a new data item into the first data flow. 188, 196), coupled to the processing means (188, 196), it is not possible to receive data items processed in relation to the first processing and to receive data items relating to other processing The second
Receiving the data item related to the second process and receiving the data item related to another process, which is coupled to the storage unit (198) and the processing unit (188, 198). A system comprising a third storage means (192) that is impossible. 15. The system according to claim 14, wherein the sensor is carried in a sound (10) installed through a borehole. 16. The processing means (188, 196) includes two microprocessors, one microprocessor (196) accomplishing the first processing, and the other microprocessor (188) 16. The system according to claim 14, wherein the system performs a second process. 17. The processing means (188, 196) includes a time-out circuit for writing a command to the storage means (198) if the data item is not received by the first storage means (178) within a certain period. 17. The system according to claim 14,15 or 16. 18. A means for obtaining a second data stream of sequential data items related to the speed of said sensor.
16. The system of claim 15, comprising 4).