CN108664361A - The nontransparent channel restorative procedures of PCIE and device - Google Patents
The nontransparent channel restorative procedures of PCIE and device Download PDFInfo
- Publication number
- CN108664361A CN108664361A CN201710188633.3A CN201710188633A CN108664361A CN 108664361 A CN108664361 A CN 108664361A CN 201710188633 A CN201710188633 A CN 201710188633A CN 108664361 A CN108664361 A CN 108664361A
- Authority
- CN
- China
- Prior art keywords
- channel
- controller
- mark
- connection
- reset
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F11/00—Error detection; Error correction; Monitoring
- G06F11/07—Responding to the occurrence of a fault, e.g. fault tolerance
- G06F11/16—Error detection or correction of the data by redundancy in hardware
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Quality & Reliability (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Data Exchanges In Wide-Area Networks (AREA)
Abstract
A kind of nontransparent channel restorative procedures of PCIE of the application offer and device, method include：When detecting that repairing mark is set, delay duration is determined according to slot position where this controller；After the delay duration, reset command is sent to local terminal NTB, so that local terminal NTB carries out reset operation to the ports NT；Whether sense channel is connected to；If will be connected to, count is incremented, judge that connection counts whether reach the first default value；If reaching, determine that routing restoration is connected to, mark will be repaired and reset；If not up to, executing the process whether sense channel is connected to；Otherwise connection is counted and is reset, executed when detecting that repairing mark is set, delay duration process is determined according to slot position where this controller.The time of the repair action of two controllers is staggered by the application by certain delay.And avoid causing to judge by accident because channel signal shakes by repeated detection, it once detects the obstructed channel that just re-executes and repairs, to ensure channel connected sets.
Description
Technical field
This application involves technical field of memory more particularly to a kind of nontransparent channel restorative procedures of PCIE and device.
Background technology
The storage device with dual controller is applied more and more extensive at present, another after a controller breaks down
A controller can take over business, to ensure the continuity of business, to make storage system have higher reliability.Usual two
It is connected by NTB (Non Transparent Bridge, non-transparent bridge) between controller, and by negotiating successfully between NTB
The channel NT (Non Transparent, nontransparent) communicated, due to the complexity and storage device building ring of NTB functions
The influence of the factors such as noise, electrical Interference in border, it is possible that the situation that the channels NT are obstructed.It is happened at if the channels NT are obstructed
Under storage device single-point fault situations, it can be made by non-faulting controller take over business, the mode for restarting failed controller
NT routing restorations are connected to, and are happened under storage device two point fault condition if the channels NT are obstructed, even if restarting a control
Device restores traffic handing capacity, but since another controller is still in malfunction, the channels NT can not repair, if restarted again another
One controller can then lead to the data cached loss on another controller, therefore, be happened at storage for the channels NT are obstructed and set
Under standby two point fault condition, NT routing restorations can not be made to be connected to.
Invention content
In view of this, a kind of nontransparent channel restorative procedures of PCIE of the application offer and device, to solve in storage device
Under two point fault condition, can not make NT routing restorations be connected to the problem of.
According to the embodiment of the present application in a first aspect, providing a kind of nontransparent channel restorative procedures of PCIE, the method is answered
For any controller of storage device, the storage device includes at least two controllers, leads between described two controllers
The nontransparent channels PCIE are crossed to be communicated, the method includes：
When detecting that repairing mark is set, delay duration is determined according to slot position where this controller；
After the delay duration determined, reset command is sent to local terminal non-transparent bridge NTB, so that the local terminal
NTB carries out reset operation to itself port NT；
Detect whether the channel is connected to；
If so, will be connected to, count is incremented, and judge whether the connection counting reaches the first default value；If reaching,
It determines the routing restoration connection, the reparation is identified and is reset；If not up to, continuing to execute whether the detection channel connects
Logical process；
Otherwise, the connection is counted and is reset, and executed when detecting that repairing mark is set, according to this controller institute
The process of delay duration is determined in slot position.
According to the second aspect of the embodiment of the present application, a kind of nontransparent channel prosthetic devices of PCIE are provided, described device is answered
For any controller of storage device, the storage device includes at least two controllers, leads between described two controllers
It crosses the nontransparent channels PCIE to be communicated, described device includes：
Delay unit is determined, for when detecting that repairing mark is set, determining and prolonging according to slot position where this controller
Shi Shichang；
NT port reset units, for after the delay duration determined, sending and resetting to local terminal non-transparent bridge NTB
Order, so that the local terminal NTB carries out reset operation to itself port NT；
Connected unit is detected, for detecting whether the channel is connected to；
Count and judging unit, for when the determination result is yes, will connection count is incremented, and judge the connection counting
Whether first default value is reached；
It determines and repairs unit, for when judging result is to reach, determining the routing restoration connection, the reparation being marked
Know and resets；
Repetition detection unit, for when judging result is not up to, continuing to execute what whether the detection channel was connected to
Process；
It counts and resets unit, for when the judgment result is No, the connection is counted and is reset, and execute to work as and detect and repair
When multiple mark is set, the process of delay duration is determined according to slot position where this controller.
Using the embodiment of the present application, when any controller in storage device detects that reparation mark is set, just into
Enter channel and repair flow, can determine delay duration according to slot position where this controller first, and when the delay by determining
After length, reset command is sent to local terminal NTB, so that local terminal NTB carries out reset operation to itself port NT, then sense channel again
Whether it is connected to, if so, will be connected to, count is incremented, and judge whether connection counting reaches the first default value, if reaching, really
Fixed routing restoration connection will be repaired mark and be reset, if not up to, continuing to execute the process whether sense channel is connected to；Otherwise,
Connection is counted and is reset, and is executed when detecting that repairing mark is set, according to when slot position determines delay where this controller
Long process.Based on above-mentioned realization method, controller is when entering channel reparation flow, by just being sent after certain delay
Reset command avoids two controllers simultaneously so as to achieve the purpose that the time point by the repair action of two controllers is staggered
Reset that be detected simultaneously by channel behind NT ports again obstructed and the case where repairing repeatedly occur.In addition, controller passes through multiplicating
Sense channel is connected to determine the mode of channel recovered connection, can cause the feelings judged by accident to avoid because channel signal shakes
Condition, and during repeated detection, as long as once detecting that channel is obstructed, counting will be connected to and reset, and restarted
The flow that channel is repaired is executed, to ensure the reliability of channel connection.
Description of the drawings
Fig. 1 is that scene graph is repaired in a kind of nontransparent channels PCIE of the application shown according to an exemplary embodiment；
Fig. 2 is a kind of embodiment of the nontransparent channel restorative procedures of PCIE of the application shown according to an exemplary embodiment
Flow chart；
Fig. 3 is a kind of hardware configuration of any controller of storage device of the application shown according to an exemplary embodiment
Figure；
Fig. 4 is a kind of embodiment of the nontransparent channel prosthetic devices of PCIE of the application shown according to an exemplary embodiment
Structure chart.
Specific implementation mode
Example embodiments are described in detail here, and the example is illustrated in the accompanying drawings.Following description is related to
When attached drawing, unless otherwise indicated, the same numbers in different drawings indicate the same or similar elements.Following exemplary embodiment
Described in embodiment do not represent all embodiments consistent with the application.On the contrary, they be only with it is such as appended
The example of consistent device and method of some aspects be described in detail in claims, the application.
It is the purpose only merely for description specific embodiment in term used in this application, is not intended to be limiting the application.
It is also intended to including majority in the application and "an" of singulative used in the attached claims, " described " and "the"
Form, unless context clearly shows that other meanings.It is also understood that term "and/or" used herein refers to and wraps
Containing one or more associated list items purposes, any or all may be combined.
It will be appreciated that though various information, but this may be described using term first, second, third, etc. in the application
A little information should not necessarily be limited by these terms.These terms are only used for same type of information being distinguished from each other out.For example, not departing from
In the case of the application range, the first information can also be referred to as the second information, and similarly, the second information can also be referred to as
One information.Depending on context, word as used in this " if " can be construed to " ... when " or " when ...
When " or " in response to determination ".
Fig. 1 is that scene graph is repaired in a kind of nontransparent channels PCIE of the application shown according to an exemplary embodiment, in Fig. 1
Storage device include controller 1 and controller 2, storage device can by HA (High Available, high availability) function
To realize service switching and the load balancing between two controllers.Include CPU (Central in each controller
Processing Unit, central processing unit), caching, main bridge (Host Bridge) and NTB, wherein NTB is PCIE
(one kind in (Peripheral Component Interconnect Express, peripheral component interconnection) bridge,
PCIE scan bus stages, NTB itself will be shown as the PCIE buses of a PCIE device and hiding another controller thereafter
Domain addresses space, to realize the isolation of two controller PCIE address spaces.In addition, two controllers pass through it is nontransparent between NTB
The functions such as data cached real-time mirror image, data forwarding may be implemented in channel, which is that one kind in PCIE channel is logical
Road has the characteristics that transmission speed is fast, protocol overhead is small.
It will be appreciated by persons skilled in the art that two controllers that storage device shown in above-mentioned Fig. 1 includes are only
Unrestricted for exemplary illustration, the storage device in the application may include multiple controllers, between each two controller
It is communicated by the nontransparent channels PCIE, when multiple controllers break down, between each two controller
The obstructed situation in the nontransparent channels PCIE can utilize the nontransparent channels PCIE in the application to repair flow and realize reparation.For
Description is convenient, and the case where including below two controllers with storage device is described in detail.
Fig. 2 is a kind of embodiment of the nontransparent channel restorative procedures of PCIE of the application shown according to an exemplary embodiment
Flow chart, the nontransparent channel restorative procedures of the PCIE can be applied to any controller of storage device, described in above-mentioned Fig. 1,
Communication port of the nontransparent channels the PCIE between two controllers is realized by the NTB in two controllers.In the embodiment of the present application
In, when the operating system collapse on two controllers passes through the kdump of operating system when causing storage device that two point failure occurs
The dump function of service loads a small kernel in the controller on one section of default memory that can be, and the basis for running controller is driven
It moves (for example, serial port drive, network port driving etc.), then controller is automatically performed repairing for the nontransparent channels PCIE using the small kernel
It is multiple, i.e., the automatic reparation in the nontransparent channels PCIE is realized by running the repair procedure in the nontransparent channels PCIE on small kernel.
As shown in Fig. 2, the nontransparent channel restorative procedures of the PCIE include the following steps：
It should be noted that the nontransparent channel reparation flows of the PCIE can be real by any controller in storage device
It is existing, as long as that is, any controller detects that local reparation mark is set, that is, starts the nontransparent channels PCIE and repair flow, under
Flow is repaired using any controller in storage device as executive agent, to the nontransparent channels PCIE and is described in detail in face：
Step 201：When detecting that repairing mark is set, delay duration is determined according to slot position where this controller.
Before executing step 201, controller in preset period of time, can obtain the connectivity deposit of local terminal NTB
Device value, if the connectivity register value and the second default value are inconsistent, it is determined that the nontransparent channel abnormals of PCIE are marked repairing
Know set to continue to execute in preset period of time if the connectivity register value is consistent with the second default value, obtains this
Hold the process of the connectivity register value of NTB.
Wherein, the CPU in controller can check local terminal NTB's by pre-set property heartbeat timer performance period
Connectivity register, when in channel, corresponding link is normal, the connectivity register value on NTB is a pre-set fixation
Numerical value, i.e. the second default value, if the corresponding link in channel is abnormal, which can be revised as it by NTB
Its numerical value.In addition, repairing mark for indicating whether the nontransparent channels PCIE between two controllers need to repair, mark is repaired
Under SM set mode, expression needs to repair, and under cleared condition, expression need not repair.Therefore, local terminal is got in controller
When the connectivity register value and inconsistent the second default value of NTB, it may be determined that the channel abnormal, and set mark is repaired
Position.
In one embodiment, in order to which the time point that two controllers are executed to repair action is staggered, in case two controllers are simultaneously
It resets that be detected simultaneously by channel behind NT ports again obstructed and the case where repairing repeatedly occur, is detecting that repairing mark is set
Afterwards, delay duration can be determined according to slot position where this controller.Wherein, the nontransparent channel reparation flows of the PCIE can be advance
A delay duration is respectively set for the slot position where two controllers, and two delay durations differ, to two controllers
By different delay times, then start to execute channel repair action, it is ensured that the repair action of two controllers is one in front and one in back
Execution.For example, the corresponding delay duration in 1 place slot position of controller could be provided as 5 seconds, 2 place slot position of controller is corresponding
Delay duration could be provided as 8 seconds.
Step 202：After the delay duration determined, reset command is sent to local terminal NTB, so that NTB pairs of local terminal
Itself port NT carries out reset operation.
In one embodiment, reset command can be sent to by the CPU in controller after the delay duration determined
Local terminal NTB, local terminal NTB are based on the reset command, can remove error register first, and disable the ports NT of itself, pass through
After certain delay, then the ports NT of itself are enabled, link is then re-initiated to the NTB of opposite terminal controller by the ports NT
Negotiate, to realize the reparation in nontransparent channel.Wherein, NTB progress NT port resets operation belongs to hardware operation, needs certain
Time makes hardware reach stable state, therefore behind the ports disabling NT, needs to enable the ports NT again by certain delay.
It should be noted that local terminal NTB while carrying out resetting operation, can also reset some and resource is relevant posts
Storage ensures that the ports NT can obtain enough resources and complete link negotiation in order to discharge limited resource in NTB chips.
Step 203：Detect whether the channel is connected to, if it is not, 204 are thened follow the steps, if so, thening follow the steps 205.
In one embodiment, it after process NT port resets operation, if local terminal NTB link negotiations success, can incite somebody to action
Local connectivity register value is set to the second default value, therefore the CPU in controller can obtain the connectivity of local terminal NTB
Register value, and it is whether consistent compared with the second default value, if unanimously, it is determined that the channel is connected to, if inconsistent, it is determined that
The channel is still obstructed.
It should be noted that in order to enhance the reliability of routing restoration connection, controller can also be by posting connectivity
Storage coordinates to determine whether the channel is connected to link width, rate register, is judging connectivity register value and second
While whether default value is consistent, it is also necessary to detect link width on local terminal NTB and whether rate register value is normal.
Step 204：The connection is counted and is reset, and executes the process of step 201.
In one embodiment, after being operated by NT port resets, in order to avoid causing to miss because channel signal shakes
Sentence, whether controller can be connected to repeated detection channel, if there is one-time detection is obstructed to channel, then be counted connection clear
Zero, and restart to execute the flow that channel is repaired, to ensure the reliability of channel connection.
Controller is restarted or the obstruction of shutdown process it should be noted that repairing flow in order to avoid channel, is ensured
The reparation flow does not influence normal system action, during controller repairs flow in entire channel, as long as one receive restart or
Person's shutdown command can will repair mark and reset.To, when controller will connection count reset and then it is secondary return to step
After 201, detects that reparation mark is cleared, exit channel and repair flow.
Step 205：By the connection, count is incremented, and judges whether connection counting reaches the first default value, if so,
It executes step 206 and otherwise continues to execute step 203.
In one embodiment, controller will be connected to after count is incremented, judge whether connection counting reaches the first present count
Value, if reached, thens follow the steps 206, if not up to, continuing to execute the process whether channel is connected to that detects, until
Connection, which counts, reaches the first default value, then exits channel and repair flow.Wherein, which is to need to repeat to examine
The number of survey can be configured according to practical experience, for example, the first default value can be arranged 3 times.
In another embodiment, if connection count be not up to the first default value, controller can be delayed preset duration it
Afterwards, then the process of step 203 is executed, further hardware to be made to reach stable state.
Step 206：It determines that the routing restoration is connected to, mark will be repaired and reset.
By above-described embodiment it is found that when any controller in storage device detect reparation mark be set when, just into
Enter channel and repair flow, can determine delay duration according to slot position where this controller first, and when the delay by determining
After length, reset command is sent to local terminal NTB, so that local terminal NTB carries out reset operation to itself port NT, then sense channel again
Whether it is connected to, if so, will be connected to, count is incremented, and judge whether connection counting reaches the first default value, if reaching, really
Fixed routing restoration connection will be repaired mark and be reset, if not up to, continuing to execute the process whether sense channel is connected to；Otherwise,
Connection is counted and is reset, and is executed when detecting that repairing mark is set, according to when slot position determines delay where this controller
Long process.Based on above-mentioned realization method, controller is when entering channel reparation flow, by just being sent after certain delay
Reset command, to achieve the purpose that the time point by the repair action of two controllers is staggered, avoid two controllers while answer
It is obstructed and the case where repairing repeatedly occur that channel is detected simultaneously by behind the NT ports of position again.In addition, controller is examined by being repeated several times
Channel connection is surveyed to determine the mode of channel recovered connection, the feelings judged by accident can be caused to avoid because channel signal shakes
Condition, and during repeated detection, as long as once detecting that channel is obstructed, counting will be connected to and reset, and restarted
The flow that channel is repaired is executed, to ensure the reliability of channel connection.
Corresponding with the nontransparent embodiments of channel restorative procedure of aforementioned PCIE, it is nontransparent logical that present invention also provides PCIE
The embodiment of road prosthetic device.
The embodiment of the nontransparent channel prosthetic devices of the application PCIE can be applied on any controller of storage device.
Device embodiment can also be realized by software realization by way of hardware or software and hardware combining.It is implemented in software
For, as the device on a logical meaning, being will be corresponding in nonvolatile memory by the processor of equipment where it
Computer program instructions read in memory what operation was formed.For hardware view, as shown in figure 3, for the application according to
A kind of hardware structure diagram of any controller of storage device shown in one exemplary embodiment, in addition to processor shown in Fig. 3,
Except memory, network interface and nonvolatile memory, the reality of equipment in embodiment where device generally according to the equipment
Border function can also include other hardware, be repeated no more to this.
Fig. 4 is a kind of embodiment of the nontransparent channel prosthetic devices of PCIE of the application shown according to an exemplary embodiment
Structure chart, the nontransparent channel prosthetic devices of the PCIE can be applied to any controller of storage device, as shown in figure 4, should
The nontransparent channel prosthetic devices of PCIE include：Determine delay unit 41, NT port resets unit 42, detection connected unit 43, meter
Number and judging unit 44 determine and repair unit 45, repetition detection unit 46, count clearing unit 47.
Delay unit 41 is determined, for when detecting that repairing mark is set, being determined according to slot position where this controller
Delay duration；
NT port resets unit 42, for after the delay duration determined, reset command to be sent to local terminal NTB,
So that the local terminal NTB carries out reset operation to itself port NT；
Connected unit 43 is detected, for detecting whether the channel is connected to；
Count and judging unit 44, for when the determination result is yes, will connection count is incremented, and judge that the connection is counted
Whether number reaches the first default value；
It determines and repairs unit 45, for when judging result is to reach, the routing restoration connection being determined, by the reparation
Mark is reset；
Repetition detection unit 46, for when judging result is not up to, continuing to execute whether the detection channel is connected to
Process；
Clearing unit 47 is counted, is detected for when the judgment result is No, the connection being counted and is reset, and executed to work as
When reparation mark is set, the process of delay duration is determined according to slot position where this controller.
In an optional realization method, described device further includes (being not shown in Fig. 4)：
Repair mark set unit, for the determining delay unit 41 when detect repair mark be set when, root
According to before slot position determines delay duration where this controller, in preset period of time, the connectivity register of local terminal NTB is obtained
Value；If the connectivity register value and the second default value are inconsistent, it is determined that the channel abnormal identifies the reparation
Set.
In an optional realization method, described device further includes (being not shown in Fig. 4)：
It repairs mark and resets unit, for restarting or when shutdown command receiving, by reparations mark clearing.
In an optional realization method, described device further includes (being not shown in Fig. 4)：
Delay unit the preset duration that is delayed and then is held if counting not up to the first default value for the connection
Row detects the process whether channel is connected to.
The function of each unit and the realization process of effect specifically refer to and correspond to step in the above method in above-mentioned apparatus
Realization process, details are not described herein.
For device embodiments, since it corresponds essentially to embodiment of the method, so related place is referring to method reality
Apply the part explanation of example.The apparatus embodiments described above are merely exemplary, wherein described be used as separating component
The unit of explanation may or may not be physically separated, and the component shown as unit can be or can also
It is not physical unit, you can be located at a place, or may be distributed over multiple network units.It can be according to actual
It needs that some or all of module therein is selected to realize the purpose of application scheme.Those of ordinary skill in the art are not paying
In the case of going out creative work, you can to understand and implement.
The foregoing is merely the preferred embodiments of the application, not limiting the application, all essences in the application
With within principle, any modification, equivalent substitution, improvement and etc. done should be included within the scope of the application protection god.
Claims (8)
1. a kind of nontransparent channel restorative procedures of PCIE, which is characterized in that the method is applied to any control of storage device
Device, the storage device include at least two controllers, are led to by the nontransparent channels PCIE between described two controllers
Letter, the method includes：
When detecting that repairing mark is set, delay duration is determined according to slot position where this controller；
After the delay duration determined, reset command is sent to local terminal non-transparent bridge NTB, so that NTB pairs of the local terminal
Itself port NT carries out reset operation；
Detect whether the channel is connected to；
If so, will be connected to, count is incremented, and judge whether the connection counting reaches the first default value；If reaching, it is determined that
The routing restoration connection, the reparation is identified and is reset；If not up to, continuing to execute what whether the detection channel was connected to
Process；
Otherwise, the connection is counted and is reset, and executed when detecting that repairing mark is set, according to slot where this controller
Position determines the process of delay duration.
2. according to the method described in claim 1, it is characterized in that, when detect repair mark be set when, according to this control
Before slot position determines delay duration where device, the method further includes：
In preset period of time, the connectivity register value of local terminal NTB is obtained；
If the connectivity register value and the second default value are inconsistent, it is determined that the channel abnormal marks the reparation
Know set.
3. according to the method described in claim 1, it is characterized in that, the method further includes：
Restart receiving or when shutdown command, the reparation is identified and is reset.
4. according to the method described in claim 1, it is characterized in that, the method further includes：
If the connection, which counts, is not up to the first default value, the preset duration that is delayed and then the execution detection channel are
The process of no connection.
5. a kind of nontransparent channel prosthetic devices of PCIE, which is characterized in that described device is applied to any control of storage device
Device, the storage device include at least two controllers, are led to by the nontransparent channels PCIE between described two controllers
Letter, described device include：
Delay unit is determined, when being delayed for when detecting that repairing mark is set, being determined according to slot position where this controller
It is long；
NT port reset units, for after the delay duration determined, being sent to local terminal non-transparent bridge NTB and resetting life
It enables, so that the local terminal NTB carries out reset operation to itself port NT；
Connected unit is detected, for detecting whether the channel is connected to；
Count and judging unit, for when the determination result is yes, will connection count is incremented, and whether judge the connection counting
Reach the first default value；
It determines and repairs unit, for when judging result is to reach, determining the routing restoration connection, the reparation being identified clear
Zero；
Repetition detection unit, for when judging result is not up to, continuing to execute the process whether channel is connected to that detects；
Clearing unit is counted, reparation mark is detected for when the judgment result is No, the connection being counted and is reset, and executed to work as
When knowledge is set, the process of delay duration is determined according to slot position where this controller.
6. device according to claim 5, which is characterized in that described device further includes：
Repair mark set unit, for the determining delay unit when detect repair mark be set when, according to this control
Before slot position determines delay duration where device processed, in preset period of time, the connectivity register value of local terminal NTB is obtained；If
The connectivity register value and the second default value are inconsistent, it is determined that the reparation is identified set by the channel abnormal.
7. device according to claim 5, which is characterized in that described device further includes：
It repairs mark and resets unit, for restarting or when shutdown command receiving, by reparations mark clearing.
8. device according to claim 5, which is characterized in that described device further includes：
Delay unit the preset duration that is delayed and then executes inspection if counting not up to the first default value for the connection
Survey the process whether channel is connected to.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710188633.3A CN108664361B (en) | 2017-03-27 | 2017-03-27 | PCIE non-transparent channel repairing method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710188633.3A CN108664361B (en) | 2017-03-27 | 2017-03-27 | PCIE non-transparent channel repairing method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN108664361A true CN108664361A (en) | 2018-10-16 |
| CN108664361B CN108664361B (en) | 2021-07-16 |
Family
ID=63786163
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710188633.3A Active CN108664361B (en) | 2017-03-27 | 2017-03-27 | PCIE non-transparent channel repairing method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108664361B (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115658375A (en) * | 2022-12-27 | 2023-01-31 | 苏州浪潮智能科技有限公司 | Device repairing method, repairing system and device, electronic device and storage medium |
| CN115756941A (en) * | 2023-01-09 | 2023-03-07 | 苏州浪潮智能科技有限公司 | Automatic repair method and device for equipment, electronic equipment and storage medium |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102629225A (en) * | 2011-12-31 | 2012-08-08 | 成都市华为赛门铁克科技有限公司 | Dual-controller disk array, storage system and data storage path switching method |
| CN103019870A (en) * | 2012-12-14 | 2013-04-03 | 大唐移动通信设备有限公司 | Method and communication equipment for processing reset signal |
| CN103577284A (en) * | 2013-10-09 | 2014-02-12 | 创新科存储技术（深圳）有限公司 | Abnormity detecting and recovering method for non-transparent bridge chip |
| CN104102559A (en) * | 2014-07-16 | 2014-10-15 | 浪潮电子信息产业股份有限公司 | Redundant heartbeat link and opposite-end restarting link based double-controller storage system |
-
2017
- 2017-03-27 CN CN201710188633.3A patent/CN108664361B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102629225A (en) * | 2011-12-31 | 2012-08-08 | 成都市华为赛门铁克科技有限公司 | Dual-controller disk array, storage system and data storage path switching method |
| CN103019870A (en) * | 2012-12-14 | 2013-04-03 | 大唐移动通信设备有限公司 | Method and communication equipment for processing reset signal |
| CN103577284A (en) * | 2013-10-09 | 2014-02-12 | 创新科存储技术（深圳）有限公司 | Abnormity detecting and recovering method for non-transparent bridge chip |
| CN104102559A (en) * | 2014-07-16 | 2014-10-15 | 浪潮电子信息产业股份有限公司 | Redundant heartbeat link and opposite-end restarting link based double-controller storage system |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115658375A (en) * | 2022-12-27 | 2023-01-31 | 苏州浪潮智能科技有限公司 | Device repairing method, repairing system and device, electronic device and storage medium |
| CN115658375B (en) * | 2022-12-27 | 2023-08-15 | 苏州浪潮智能科技有限公司 | Equipment repairing method, repairing system and device, electronic equipment and storage medium |
| WO2024139840A1 (en) * | 2022-12-27 | 2024-07-04 | 苏州元脑智能科技有限公司 | Device repair method, system and apparatus, and electronic device and non-volatile storage medium |
| CN115756941A (en) * | 2023-01-09 | 2023-03-07 | 苏州浪潮智能科技有限公司 | Automatic repair method and device for equipment, electronic equipment and storage medium |
| WO2024148876A1 (en) * | 2023-01-09 | 2024-07-18 | 苏州元脑智能科技有限公司 | Automatic repair method and apparatus for device, and electronic device and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN108664361B (en) | 2021-07-16 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US7010639B2 (en) | Inter integrated circuit bus router for preventing communication to an unauthorized port | |
| US7240130B2 (en) | Method of transmitting data through an 12C router | |
| CN104536855B (en) | Fault detection method and device | |
| US7082488B2 (en) | System and method for presence detect and reset of a device coupled to an inter-integrated circuit router | |
| JP6741947B2 (en) | Information processing device, diagnostic control device, and communication device | |
| US20160134467A1 (en) | Method and apparatus for switching between master device and backup device | |
| CN103618618B (en) | Line card fault recovery method and related device based on distributed PCIE system | |
| CN106326160A (en) | Processing system and processing method | |
| CN106598790A (en) | Server hardware failure detection method, apparatus of server, and server | |
| US7630304B2 (en) | Method of overflow recovery of I2C packets on an I2C router | |
| CN106502814B (en) | Method and device for recording error information of PCIE (peripheral component interface express) equipment | |
| CN106789306A (en) | Restoration methods and system are collected in communication equipment software fault detect | |
| CN105426275A (en) | Disaster recovery method and apparatus in dual-activation cluster system | |
| US7398345B2 (en) | Inter-integrated circuit bus router for providing increased security | |
| CN104283718B (en) | The network equipment and the hardware fault diagnosis method for the network equipment | |
| CN108664361A (en) | The nontransparent channel restorative procedures of PCIE and device | |
| CN109120522A (en) | A kind of multipath state monitoring method and device | |
| CN104734904B (en) | The automatic test approach and system of bypass equipment | |
| CN109889411A (en) | A kind of method and device of data transmission | |
| CN109271096B (en) | NVME storage expansion system | |
| CN106406963B (en) | Initialization method and device of Linux system | |
| CN102495815B (en) | Processing method for I/O (input/output) data access interrupt, system and equipment | |
| CN106506265A (en) | Detection fpga chip hangs dead method and device | |
| CN114880266B (en) | Fault processing method and device, computer equipment and storage medium | |
| CN107526652A (en) | A kind of method of data synchronization and storage device |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |