CN109561105A - A kind of high-performance message capturing transmission platform based on message Zero-copy mode - Google Patents
A kind of high-performance message capturing transmission platform based on message Zero-copy mode Download PDFInfo
- Publication number
- CN109561105A CN109561105A CN201811635089.3A CN201811635089A CN109561105A CN 109561105 A CN109561105 A CN 109561105A CN 201811635089 A CN201811635089 A CN 201811635089A CN 109561105 A CN109561105 A CN 109561105A
- Authority
- CN
- China
- Prior art keywords
- message
- queue
- user space
- skbuf
- interface
- 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.)
- Withdrawn
Links
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L63/00—Network architectures or network communication protocols for network security
- H04L63/14—Network architectures or network communication protocols for network security for detecting or protecting against malicious traffic
- H04L63/1408—Network architectures or network communication protocols for network security for detecting or protecting against malicious traffic by monitoring network traffic
- H04L63/1425—Traffic logging, e.g. anomaly detection
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L63/00—Network architectures or network communication protocols for network security
- H04L63/14—Network architectures or network communication protocols for network security for detecting or protecting against malicious traffic
- H04L63/1441—Countermeasures against malicious traffic
Landscapes
- Engineering & Computer Science (AREA)
- Computer Security & Cryptography (AREA)
- Computer Hardware Design (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Data Exchanges In Wide-Area Networks (AREA)
Abstract
The invention discloses a kind of, and the high-performance message capturing based on message Zero-copy mode sends platform, it includes trawl performance module, kernel Message processing stack module and User space interface dynamic library module, trawl performance module make the data flow of specified network interface card be directed toward kernel Message processing stack;Kernel Message processing stack transmits network data message by the way of queue between kernel state, User space;The interface dynamic base of User space is realized the capture of message using unified interface, is sent.The present invention can operate on a variety of software and hardware platforms, multiple hardwares platform, a variety of linux release versions, Multiple Type network interface card, good compatibility.The present invention can different flow, without error packet loss require under, message is provided and is analyzed and processed to upper layer application, stability is good.After the buffering that the present invention can make message data reach trawl performance, subsequent data message process no longer needs to copy, high-efficient, carries out network flow using identification, protocal analysis suitable for network safety filed.
Description
Technical field
The present invention relates to technical field of network security more particularly to a kind of high-performance messages based on message Zero-copy mode
Capture sends platform.
Background technique
It in network safety filed, needs under real-time or subsequent mode, network flow is carried out using identification, agreement point
Analysis.The premise of flow analysis is that the message capturing of a stabilization, high-performance, compatible a variety of software and hardwares is needed to send platform.Tradition
Message capturing be to develop to catch message and send platform using libpcap, but the message capturing mode of libpcap is: working as message
When reaching network interface card, network interface card is sent it in the buffering ring of trawl performance by dma mode, and is generated when completing DMA transmission
One hardware interrupts.The message received is packaged into sk_buff structure by interrupt handling routine, is then passed to by netif_rx
Network protocol stack is further processed.After kernel network protocol stack and Socket layers of processing, consumer process passes through system tune
Message is read from kernel spacing with read or recvfrom.Since kernel has buffered most I/O operations, kernel buffer empty
User's space and physical equipment are divided to a certain extent, the design for being conducive to application layer program is realized.But kernel buffers
The use in area but increases the overheads such as data copy, interruption and CPU participation, to influence the performance of message capturing.
Summary of the invention
The purpose of the present invention is increase overheads in kernel buffers in sending for existing message capturing, influence message
The problem of acquisition performance, invents a kind of high-performance message capturing transmission platform based on message Zero-copy mode.
A kind of high-performance message capturing transmission platform based on message Zero-copy mode, including
User space interface dynamic library module includes
Message capturing interface, message realizing interface, application skbuf interface, message transmission interface, initialization/cancellation interface, log
Debugging statistics interface;
Kernel Message processing stack module includes
Thread is sent, is responsible for taking out the message with transmission network interface card information, and message is sent to network interface card;
Thread is filled, monitoring skbuf queue is responsible for, as can be just applied for skbuf with skbuf less than 50% in queue and be put into
Into skbuf queue, skbuf queue is used to User space process, big for splicing IP fragmentation message or User space process simulation
Flow fills message data when sending message;
Thread is discharged, is responsible for taking message skbuf in release queue, release is returned in skbuf caching;
Detect thread, that is responsible for each process of detection catches packet queue, think if being more than certain time without operation in queue into
Cheng Yichang closes the queue;
Queue is captured, by being created when User space process initialization platform courses structure example, is interrupted for receiving trawl performance;Hair
Send queue for receiving the message that User space process will occur, message pointer is converted to physical address in interface internal, sends
Thread takes message from transmit queue, after changing into linear address, is sent to specified transmission network interface card;
Skbuf queue, for storing the skbuf of filling thread filling, the address skbuf is physical address, and User space process is logical
Cross interface takes skbuf to use from skbuf queue, and interface internal switchs to User space address;
Queue, the message that will need to discharge after processing for receiving User space process are discharged, interface internal switchs to message address
Physical address, release thread take message to be discharged into skbuf caching from release queue;
Skbuf caching is also used for filling out when User space process sends message for copying stored messages after network interface card packet interrupting
Fill the message of construction;
Platform courses structure example creates when calling initialization interface by User space process, stores kernel state and User space will
The global variable of access, is used for control module function, and the interface of User space uses the information and kernel report in control structure example
Text processing stack mutual message data, control information;
Statistical information creates when calling initialization interface by User space process, User space process and kernel Message processing stack it
Between transmit statistical information;
Trawl performance module, for controlling specified network card data flow direction.
It is of the invention it is preferred in, all interfaces are all internal in the User space interface dynamic library module realizes user
The address conversion of state and kernel state includes queue address conversion and system in data message physical address translations, platform courses example
Count the physical address translations of information.
It is of the invention it is preferred in, network interface card work is arranged in load network card equipment init processing in the trawl performance module
Make in PROMISC mode, to kernel Message processing stack Module registers network card equipment information, when message reaches, application skbuf is simultaneously
Message is copied, message pointer is switched into physical address by linear address using _ _ pa (* pPacketSkbuf), then by message
Address is delivered in capture queue, and application process gets message pointer by interface, and linear address is switched to use by interface internal
The address of family state space, User space process can carry out subsequent message analysis processing.
The present invention is by the maximum value of/proc/iomem file acquisition to current physical address, and by current process space
The memory size used is set as no limitation, while using mmap by entire physical memory according to the maximum physical address got
It is mapped to consumer process space.The initial address of mapping is start, then user mode codes can pass through formula: physical address+
Start=virtual address, User space process can access all objects by accessing the virtual address.
User space process sets initiation parameter in the present invention, and parameter includes: flow, catches message network interface card, sends message
The information such as network interface card.Initialization interface establishes User space process respective items catalogue at/proc, and parameter letter is created under catalogue
Breath.After kernel Message processing stack reads User space process parameter, distribution platform control structure example, kernel Message processing stack will be put down
Corresponding User space process is write under the item catalogue of/proc in the address of platform control structure example, User space process by read its/
Control structure instance pointer under the item catalogue of proc is switched to the virtual address of User space, and subsequent calls platform is various to be connect
It when mouth, is passed to using the control structure pointer as parameter, can be achieved with the various operations such as capture, transmission, statistics.
After User space process obtains the pointer of control structure example, User space process use control structure instance pointer as
The capture of parameter calling platform, transmission interface, so that it may receive message from kernel Message processing stack and send kernel processes for message
Stack.The mode of the above-mentioned memory sharing of queue in control structure, one end is in kernel state, and the other end is in User space, any end
Enqueue or dequeue are only carried out, while concurrently being synchronized in kernel state using spin lock, uses mutex in User space
Concurrently synchronized.
The beneficial effects of the present invention are:
Present invention can apply to multiple hardwares platform, the 2U rack server including HP DL series;IBM M4, M5, X5, X6 system
The rack server of column;The blade server of IBM Blade-HS22* series;The blade server of ATCA standard.
The present invention can carry out message capturing on a plurality of types of network interface cards, message is sent: Intel GE network interface card, Intel
10GE network interface card, Broadcom GE network interface card, Broadcom 10GE network interface card.
The present invention supports the use pattern of a variety of network interface cards: 1 10GE network interface card message capturing and 4 GE network interface card messages are sent;
1 10GE network interface card message capturing and 1 10GE network interface card message are sent;1-8 GE network interface card message capturing and 1-8 GE network interface card message
It sends.
This platform may operate in a variety of linux release versions: SUSE Linux Enterprise 12, Centos-7
X86_64 and Red Hat Enterprise Linux 6.
The installation tool of unloading that the present invention provides wizard-like on the server by stage+module can be on that server
Realize that the message capturing of big flow, message are sent.
The present invention can different flow, without error packet loss require under, message is provided and is analyzed and processed to upper layer application, prop up
Range of flow is held up to 1Gbps-10Gbps, identifies field especially suitable for flow malicious act.
Detailed description of the invention
Fig. 1 is structural block diagram of the invention;
Fig. 2 is module design figure of the invention;
Fig. 3 is message capturing flow diagram of the invention;
Fig. 4 is message transmission process schematic diagram of the invention;
Fig. 5 is message repeating process schematic diagram of the invention.
Specific embodiment
Following will be combined with the drawings in the embodiments of the present invention, and technical solution in the embodiment of the present invention carries out clear, complete
Site preparation description, it is clear that described embodiments are only a part of the embodiments of the present invention, instead of all the embodiments.
As shown in Figure 1, a kind of high-performance message capturing based on message Zero-copy mode sends platform, by User space
Interface dynamic base, kernel Message processing stack and trawl performance composition.
As shown in Fig. 2, the present invention can be divided into lower module when carrying out modularized design:
User space interface dynamic library module is sent comprising message capturing interface, message realizing interface, application skbuf interface, message
Interface, initialization/cancellation interface, log debugging statistics interface.It should be noted that owning in User space interface dynamic library module
The all internal address conversion for realizing User space and kernel state of interface, include data message physical address translations, platform courses
The physical address translations of queue address conversion and statistical information in example.
Kernel Message processing stack module includes
Send thread, filling thread, release thread, detection thread, capture queue, transmit queue, skbuf queue, release queue,
Skbuf caching, platform courses structure example, statistical information;
Wherein, it sends thread to be responsible for taking out the message with network interface card information is sent, sends message to and send network interface card;Filling line
Journey is responsible for monitoring skbuf queue, as can be just applied for skbuf with skbuf less than 50% in queue and be put into skbuf team
In column, skbuf queue is used to User space process, is sent for splicing IP fragmentation message or User space process simulation big flow
Message data is filled when message;Thread is discharged, is responsible for taking message skbuf in release queue, release is returned to skbuf caching
In;Thread is detected, that is responsible for each process of detection catches packet queue, thinks process if being more than certain time without operation in queue
It is abnormal, close the queue;Queue is captured by creating when User space process initialization platform courses structure example, for receiving network interface card
Driving is interrupted;For transmit queue for receiving the message that User space process will occur, message pointer is converted to object in interface internal
Address is managed, thread is sent from transmit queue and takes message, after changing into linear address, is sent to specified transmission network interface card;Skbuf queue is used
In the skbuf of storage filling thread filling, the address skbuf is physical address, and User space process passes through interface from skbuf queue
In take skbuf to use, interface internal switchs to User space address;Release queue will need to release after processing for receiving User space process
Message address is switched to physical address by the message put, interface internal, and release thread takes message to be discharged into skbuf from release queue
Caching;Skbuf caching is also used for filling out when User space process sends message for copying stored messages after network interface card packet interrupting
Fill the message of construction;Platform courses structure example creates when calling initialization interface by User space process, stores kernel state and use
The global variable that family state will access is used for control module function, and the interface of User space uses the information in control structure example,
With kernel Message processing stack mutual message data, control information;Statistical information is created when calling initialization interface by User space process
It builds, transmits statistical information between User space process and kernel Message processing stack;
Trawl performance module, for controlling specified network card data flow direction;Trawl performance module is in load network card equipment init processing
In, setting network interface card works in PROMISC mode, to kernel Message processing stack Module registers network card equipment information, when message reaches
When, application skbuf simultaneously copies message, and message pointer is switched to physics by linear address using _ _ pa (* pPacketSkbuf)
Then message address is delivered in capture queue by address, application process gets message pointer by interface, and interface internal will
Linear address switchs to the address of user's state space, and User space process can carry out subsequent message analysis processing.
As shown in figure 3, the present invention is when carrying out message capturing, network interface card initializes first, and the reception of service is interrupted for network interface card
Ring distributes skbuf, and interrupt handling routine obtains the received message of network interface card and puts message into process capture queue;Process is from catching
It obtains queue and obtains message, after being disposed, process discharges message buffering to release queue, and release thread takes out from release queue
The message buffering given back, release thread discharge the buffering given back into the space system skbuf, and last interrupt handling routine is network interface card
Distribute the caching for receiving next message.
As shown in figure 4, the present invention, when carrying out message transmission, filling thread is distributed from the space system skbuf and cached, will delay
It deposits and is supplemented in caching team;Application process is taken out from buffer queue to be cached and puts the skbuf message that data are written into transmit queue;
It sends thread and takes out message to be sent from transmit queue, message to be sent is then submitted to network interface card, network interface card sends the EM end of message
Give back packet buffer to the space system skbuf afterwards.
As shown in figure 5, the present invention, when carrying out message forwarding, network interface card initialization procedure is that network interface card receives ring distribution caching,
Interrupt handling routine obtains the received message of network interface card, message is then put into process capture queue, process is from capture queue
It obtains message and judges message status, put it to if without forwarding and give back queue;It gives back thread and is taken out from queue is given back
Message buffering is given back, thread is given back by the buffering given back and puts the space system skbuf into;Interrupt handling routine is network interface card distribution later
For receiving the caching of next message, process judges received message at this time, will if message needs to forward
It is put into transmit queue, otherwise abandons.It sends thread and is submitted to network interface card from transmit queue taking-up message to be sent, network interface card sends report
Packet buffer is given back to the space system skbuf after text.
More than, it is merely preferred embodiments of the present invention, but scope of protection of the present invention is not limited thereto, it is any
Those familiar with the art in the technical scope disclosed by the present invention, according to the technique and scheme of the present invention and its invents
Design is subject to equivalent substitution or change, should be covered by the protection scope of the present invention.
Claims (3)
1. a kind of high-performance message capturing based on message Zero-copy mode sends platform, characterized in that including User space interface
Dynamic library module includes message capturing interface, message realizing interface, application skbuf interface, message transmission interface, initialization/note
Pin joint mouth, log debugging statistics interface;
Kernel Message processing stack module is responsible for taking out the message for having and sending network interface card information, and message is sent out comprising sending thread
It send to network interface card;
Thread is filled, monitoring skbuf queue is responsible for, as can be just applied for skbuf with skbuf less than 50% in queue and be put into
Into skbuf queue, skbuf queue is used to User space process, big for splicing IP fragmentation message or User space process simulation
Flow fills message data when sending message;
Thread is discharged, is responsible for taking message skbuf in release queue, release is returned in skbuf caching;
Detect thread, that is responsible for each process of detection catches packet queue, think if being more than certain time without operation in queue into
Cheng Yichang closes the queue;
Queue is captured, by being created when User space process initialization platform courses structure example, is interrupted for receiving trawl performance;Hair
Send queue for receiving the message that User space process will occur, message pointer is converted to physical address in interface internal, sends
Thread takes message from transmit queue, after changing into linear address, is sent to specified transmission network interface card;
Skbuf queue, for storing the skbuf of filling thread filling, the address skbuf is physical address, and User space process is logical
Cross interface takes skbuf to use from skbuf queue, and interface internal switchs to User space address;
Queue, the message that will need to discharge after processing for receiving User space process are discharged, interface internal switchs to message address
Physical address, release thread take message to be discharged into skbuf caching from release queue;
Skbuf caching is also used for filling out when User space process sends message for copying stored messages after network interface card packet interrupting
Fill the message of construction;
Platform courses structure example creates when calling initialization interface by User space process, stores kernel state and User space will
The global variable of access, is used for control module function, and the interface of User space uses the information and kernel report in control structure example
Text processing stack mutual message data, control information;
Statistical information creates when calling initialization interface by User space process, User space process and kernel Message processing stack it
Between transmit statistical information;
Trawl performance module, for controlling specified network card data flow direction.
2. a kind of high-performance message capturing based on message Zero-copy mode according to claim 1 sends platform, special
Sign is that all interfaces all inside realizes User space in the User space interface dynamic library module and the address of kernel state turns
It changes, turns comprising the physical address of queue address conversion and statistical information in data message physical address translations, platform courses example
It changes.
3. a kind of high-performance message capturing based on message Zero-copy mode according to claim 1 sends platform, special
Sign is, in load network card equipment init processing, setting network interface card works in PROMISC mode the trawl performance module, to
Kernel Message processing stack Module registers network card equipment information applies for skbuf and copies message, use _ _ pa when message reaches
Message pointer is switched to physical address by linear address by (* pPacketSkbuf), and message address is then delivered to capture team
In column, application process gets message pointer by interface, and linear address is switched to the address of user's state space by interface internal, uses
Family state process can carry out subsequent message analysis processing.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811635089.3A CN109561105A (en) | 2018-12-29 | 2018-12-29 | A kind of high-performance message capturing transmission platform based on message Zero-copy mode |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811635089.3A CN109561105A (en) | 2018-12-29 | 2018-12-29 | A kind of high-performance message capturing transmission platform based on message Zero-copy mode |
Publications (1)
Publication Number | Publication Date |
---|---|
CN109561105A true CN109561105A (en) | 2019-04-02 |
Family
ID=65871917
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201811635089.3A Withdrawn CN109561105A (en) | 2018-12-29 | 2018-12-29 | A kind of high-performance message capturing transmission platform based on message Zero-copy mode |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109561105A (en) |
Cited By (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111277509A (en) * | 2020-01-13 | 2020-06-12 | 奇安信科技集团股份有限公司 | Flow guiding method and device for IPS engine |
CN112131019A (en) * | 2020-09-17 | 2020-12-25 | 国网宁夏电力有限公司营销服务中心(国网宁夏电力有限公司计量中心) | Method for rapidly communicating processes of microkernel operating system |
CN112532585A (en) * | 2020-11-02 | 2021-03-19 | 杭州迪普科技股份有限公司 | Method, device and medium for inter-process message transmission |
CN113596171A (en) * | 2021-08-04 | 2021-11-02 | 杭州朗和科技有限公司 | Cloud computing data interaction method and system, electronic equipment and storage medium |
CN114070805A (en) * | 2020-07-27 | 2022-02-18 | 武汉神州数码云科网络技术有限公司 | Method for realizing message receiving and transmitting of switch management network port |
CN114124680A (en) * | 2021-09-24 | 2022-03-01 | 绿盟科技集团股份有限公司 | File access control alarm log management method and device |
CN115033407A (en) * | 2022-08-09 | 2022-09-09 | 微栈科技(浙江)有限公司 | System and method for collecting and identifying flow suitable for cloud computing |
CN115225430A (en) * | 2022-07-18 | 2022-10-21 | 中安云科科技发展(山东)有限公司 | High-performance IPsec VPN CPU load balancing method |
-
2018
- 2018-12-29 CN CN201811635089.3A patent/CN109561105A/en not_active Withdrawn
Cited By (12)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111277509A (en) * | 2020-01-13 | 2020-06-12 | 奇安信科技集团股份有限公司 | Flow guiding method and device for IPS engine |
CN111277509B (en) * | 2020-01-13 | 2023-12-05 | 奇安信科技集团股份有限公司 | Flow guiding method and device for IPS engine |
CN114070805A (en) * | 2020-07-27 | 2022-02-18 | 武汉神州数码云科网络技术有限公司 | Method for realizing message receiving and transmitting of switch management network port |
CN112131019A (en) * | 2020-09-17 | 2020-12-25 | 国网宁夏电力有限公司营销服务中心(国网宁夏电力有限公司计量中心) | Method for rapidly communicating processes of microkernel operating system |
CN112532585A (en) * | 2020-11-02 | 2021-03-19 | 杭州迪普科技股份有限公司 | Method, device and medium for inter-process message transmission |
CN113596171A (en) * | 2021-08-04 | 2021-11-02 | 杭州朗和科技有限公司 | Cloud computing data interaction method and system, electronic equipment and storage medium |
CN113596171B (en) * | 2021-08-04 | 2024-02-20 | 杭州网易数之帆科技有限公司 | Cloud computing data interaction method, system, electronic equipment and storage medium |
CN114124680A (en) * | 2021-09-24 | 2022-03-01 | 绿盟科技集团股份有限公司 | File access control alarm log management method and device |
CN114124680B (en) * | 2021-09-24 | 2023-11-17 | 绿盟科技集团股份有限公司 | File access control alarm log management method and device |
CN115225430A (en) * | 2022-07-18 | 2022-10-21 | 中安云科科技发展(山东)有限公司 | High-performance IPsec VPN CPU load balancing method |
CN115033407A (en) * | 2022-08-09 | 2022-09-09 | 微栈科技(浙江)有限公司 | System and method for collecting and identifying flow suitable for cloud computing |
CN115033407B (en) * | 2022-08-09 | 2022-11-04 | 微栈科技(浙江)有限公司 | System and method for collecting and identifying flow suitable for cloud computing |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109561105A (en) | A kind of high-performance message capturing transmission platform based on message Zero-copy mode | |
Li et al. | Socksdirect: Datacenter sockets can be fast and compatible | |
US8543729B2 (en) | Virtualised receive side scaling | |
CN102402487B (en) | Zero copy message reception method and system | |
US20180375782A1 (en) | Data buffering | |
US8537832B2 (en) | Exception detection and thread rescheduling in a multi-core, multi-thread network processor | |
KR101502808B1 (en) | A method and system for improved multi-cell support on a single modem board | |
US8505013B2 (en) | Reducing data read latency in a network communications processor architecture | |
EP2506147B1 (en) | Epoll optimisations | |
KR101636308B1 (en) | Core abstraction layer for telecommunication network applications | |
CN104506379A (en) | Method and system for capturing network data | |
Garzarella et al. | Virtual device passthrough for high speed VM networking | |
CA2432386A1 (en) | Method and apparatus for transferring interrupts from a peripheral device to a host computer system | |
CN101150488A (en) | A receiving method for zero copy network packet | |
CN101540720A (en) | Zero-copy method for supporting link aggregation of multi-type network cards | |
US11875198B2 (en) | Synchronization object issue detection using object type queues and associated monitor threads in a storage system | |
GB2349717A (en) | Low latency network | |
US20070198720A1 (en) | Method and apparatus for a interfacing device drivers to a single multi-function adapter | |
Zhang et al. | Workload adaptive shared memory management for high performance network i/o in virtualized cloud | |
US9304706B2 (en) | Efficient complex network traffic management in a non-uniform memory system | |
US7853713B2 (en) | Communication interface device and communication method | |
GB2436627A (en) | Message handling using a wrapper | |
Jung et al. | Gpu-ether: Gpu-native packet i/o for gpu applications on commodity ethernet | |
Inoue et al. | Low-latency and high bandwidth TCP/IP protocol processing through an integrated HW/SW approach | |
US20070230347A1 (en) | Communication interface device and communication method |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
CB02 | Change of applicant information |
Address after: 210012 Jiangsu Province Yuhuatai District Software Avenue 168, 3 buildings, 5 floors Applicant after: Bozhi Safety Technology Co.,Ltd. Address before: 210012 Jiangsu Province Yuhuatai District Software Avenue 168, 3 buildings, 5 floors Applicant before: JIANGSU BOZHI SOFTWARE TECHNOLOGY Co.,Ltd. |
|
CB02 | Change of applicant information | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
WW01 | Invention patent application withdrawn after publication |
Application publication date: 20190402 |
|
WW01 | Invention patent application withdrawn after publication |