CN105357271B - A kind of information processing method and corresponding intrument - Google Patents

A kind of information processing method and corresponding intrument Download PDF

Info

Publication number
CN105357271B
CN105357271B CN201510642169.1A CN201510642169A CN105357271B CN 105357271 B CN105357271 B CN 105357271B CN 201510642169 A CN201510642169 A CN 201510642169A CN 105357271 B CN105357271 B CN 105357271B
Authority
CN
China
Prior art keywords
request
memory node
mark
response results
server
Prior art date
Application number
CN201510642169.1A
Other languages
Chinese (zh)
Other versions
CN105357271A (en
Inventor
冯永刚
Original Assignee
华为技术有限公司
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by 华为技术有限公司 filed Critical 华为技术有限公司
Priority to CN201510642169.1A priority Critical patent/CN105357271B/en
Publication of CN105357271A publication Critical patent/CN105357271A/en
Application granted granted Critical
Publication of CN105357271B publication Critical patent/CN105357271B/en

Links

Abstract

The invention discloses a kind of information processing method and corresponding intrument, for solving the problems, such as in the prior art because of node based on service request return response result is retransmitted caused by business processing total time-consuming it is too long.The described method includes: memory node receives the first request that server is sent, the first request includes the first request mark, and the first request mark is for characterizing the first requested content of request;Memory node obtains the first request mark from the first request, and judges the first request mark whether is preserved in local cache, wherein the local cache of memory node preserves the included request mark of the received request of memory node;If the local cache of memory node preserves the first request mark, memory node will be received in advance of the first request, first response results of the second response results of the second request comprising the first request mark as the first request;Memory node returns to the first response results to server.

Description

A kind of information processing method and corresponding intrument

Technical field

The present invention relates to field of computer technology, in particular to a kind of information processing method and corresponding intrument.

Background technique

In the prior art, server is when sending service request to node, it will usually overtime duration be arranged, if node is not The response results of service request can be returned in overtime duration, then server can retransmit service request to node, ring server It should new received service request and return response result.

But the service request that node response is retransmitted, it is meant that response of the node based on received service request before Journey will be rejected, and cause the waste of system resource and business processing total time-consuming too long.

Summary of the invention

The embodiment of the present invention provides a kind of information processing method and corresponding intrument, for solving in the prior art because of node base In retransmitting the too long problem of business processing total time-consuming caused by service request return response result.

In a first aspect, the embodiment of the present invention provides a kind of information processing method, comprising:

Memory node receives the first request that server is sent, and first request deposits the memory node for requesting The data of storage are operated, and first request includes the first request mark, and the first request mark is for characterizing described the The one requested content of request;

The memory node obtains the first request mark from first request, and judge in local cache whether Preserve the first request mark, wherein it is received that the local cache of the memory node preserves the memory node Request included request mark;

If the local cache of the memory node preserves the first request mark, the memory node will be in institute Received before stating the first request, the second response results of the second request comprising the first request mark are as described first First response results of request;

The memory node returns to first response results to the server.

With reference to first aspect, in the first possible implementation of the first aspect, this is judged in the memory node Ground caching in whether preserve it is described first request mark before, further includes:

The memory node determines that first request includes retransmitting mark, and the re-transmission mark is for showing described first Request is retransmission request.

With reference to first aspect or the first possible implementation of first aspect, second in first aspect are possible In implementation, the second of mark is requested comprising described first by received before first request in the memory node Before the first response results of second response results of request as first request, further includes:

The memory node orients second response results in local cache.

The possible implementation of with reference to first aspect the first, in the third possible implementation of first aspect In, before the first request that the memory node receives that server is sent, further includes:

The memory node receives second request that the server is sent;

The memory node determines second request just to pass request;

The first request mark that second request is included by the memory node is stored in local cache;

Memory node response second request, executes the requested data manipulation of second request;

The memory node generates second response after having executed the requested data manipulation of second request As a result, and second response results are stored in the local cache of the memory node.

The third possible implementation with reference to first aspect, in the 4th kind of possible implementation of first aspect In, the memory node determines second request just to pass request, comprising:

The memory node determines that second request does not include that the re-transmission identifies;Or

The memory node determines that second request includes just passing mark, and the mark that just passes is for showing described second Request is requested just to pass.

The 4th kind of possible implementation of the third possible implementation or first aspect with reference to first aspect, In 5th kind of possible implementation of first aspect, second request is written first in the memory node for requesting Data;

Memory node response second request, executes the requested data manipulation of second request, comprising:

The target in the memory node is written in first data that second request includes by the memory node Storage location;

The memory node generates described second after having executed the requested data manipulation of second request Response results, comprising:

The memory node, which generates, is written the successful message of the first data, and second response results are said write The successful message of first data.

Second aspect, the embodiment of the present invention provide a kind of information processing method, comprising:

Server sent to memory node fail to receive in the setting duration after the second request described second request the When two response results, Xiang Suoshu memory node sends the first request, wherein first request saves the storage for requesting The data of point storage are operated, and first request is identified comprising the first request with second request, and described first asks Ask mark for characterizing the requested content of first request;

The server receives the first response results of first request that the memory node returns, wherein described First response results are the memory node after determining the retransmission request that first request is second request, will be described Second response results are formed as first response results.

In conjunction with second aspect, in the first possible implementation of the second aspect, the server is to the storage Node sends first request, comprising:

The server sends first request comprising retransmitting mark to the memory node, and the re-transmission mark is used In determining the memory node, first request is retransmission request.

In conjunction with the first possible implementation of second aspect, in second of possible implementation of second aspect In, before the server sends first request to the memory node, further includes:

The server is sent to the memory node does not include second request for retransmitting mark, to show Stating the second request is just to pass request;Or

The server sends second request comprising just passing mark to the memory node, and the mark that just passes is used In determining the memory node, second request is requested just to pass;

Wherein, first request of second request for making the memory node include by second request is marked Knowledge is stored in local cache.

The third aspect, the embodiment of the present invention provide a kind of information processing unit, comprising:

Receiving module, for receiving the first request of server transmission, first request is for requesting to the information The data of processing unit storage are operated, and first request includes the first request mark, and the first request mark is used for Characterize the requested content of first request;

Judgment module, for from it is described first request in obtain it is described first request mark, and judge be in local cache It is no to preserve the first request mark, wherein local cache is preserved the received request of the information processing unit and wrapped The request mark contained;

Respond module, for local cache preserve it is described first request mark when, will it is described first request before First response of second response results of received the second request comprising the first request mark as first request As a result;

Sending module, for returning to first response results to the server.

In conjunction with the third aspect, in the first possible implementation of the third aspect, the judgment module is specifically used for: Determine that first request includes retransmitting mark, the re-transmission mark is retransmission request for showing first request;True Fixed first request includes the first request mark being obtained from first request, and sentence after the re-transmission identifies Whether the first request mark is preserved in disconnected local cache.

In conjunction with the possible implementation of the first of the third aspect or the third aspect, second in the third aspect is possible In implementation, the respond module is specifically used for: when local cache preserves the first request mark, in local cache In orient second response results, and using second response results as first response results.

In conjunction with the first possible implementation of the third aspect, in the third possible implementation of the third aspect In, the receiving module is also used to: receiving second request that the server is sent;

The judgment module is also used to: determining second request just to pass request;

The respond module is also used to: the first request mark for including by second request is stored in local cache In;Second request is responded, the requested data manipulation of second request is executed;And executing second request institute After the data manipulation of request, second response results are generated, and second response results are stored in local cache.

In conjunction with the third possible implementation of the third aspect, in the 4th kind of possible implementation of the third aspect In, the judgment module is specifically used for:

Determine that second request does not include that the re-transmission identifies;Or

Determine that second request includes just passing mark, the mark that just passes is for showing that second request is asked for just biography It asks.

In conjunction with the third possible implementation of the third aspect or the 4th kind of possible implementation of the third aspect, In 5th kind of possible implementation of the third aspect, second request is written in the information processing unit for requesting First data;

The respond module is specifically used for: the information processing is written in first data that second request includes Target storage position in device;And the write-in successful message of the first data is generated, and the message is stored in local In caching, second response results are the message.

Fourth aspect, a kind of server of the embodiment of the present invention, comprising:

Sending module, for asking sending to fail to receive described second in the setting duration after the second request to memory node When the second response results asked, Xiang Suoshu memory node sends the first request, wherein first request is for requesting to described The data of memory node storage are operated, and first request is identified comprising the first request with second request, described First request mark is for characterizing the requested content of first request;

Receiving module, for receiving the first response results of first request that the memory node returns, wherein institute Stating the first response results is the memory node after determining the retransmission request that first request is second request, by institute The second response results are stated to be formed as first response results.

In conjunction with fourth aspect, in the first possible implementation of the fourth aspect, the sending module is specifically used for:

First request comprising retransmitting mark is sent to the memory node, the re-transmission mark is for making described deposit Storage node determines that first request is retransmission request.

In conjunction with the first possible implementation of fourth aspect, in second of possible implementation of fourth aspect In, the sending module is specifically used for:

Before sending first request to the memory node, Xiang Suoshu memory node, which is sent, does not include the re-transmission Second request of mark just passes request to show second request;Or

Second request comprising just passing mark is sent to the memory node, the mark that just passes is for making described deposit Storage node determines second request just to pass request;

Wherein, first request of second request for making the memory node include by second request is marked Knowledge is stored in local cache.

The one or more technical solutions provided in the embodiment of the present invention, have at least the following technical effects or advantages:

In the embodiment of the present invention, memory node judges whether is preserved in local cache when receiving the first request Whether the first request mark of one request judges to have been received before and requests the second of same content to ask with the first request with this It asks, if memory node is not necessarily to execute the requested content of the first request comprising the first request mark in local cache, but Directly using the second response results of received second request before as the first response results of the first request, it is sent to service Device.The first requested content of request is executed since memory node can not separately expend the time, is directly returned and the to server The response results of identical second request of the one requested content of request, had not only been able to satisfy the request of server, but also can reduce clothes It is engaged in the time and business time-consuming that device waits.

Detailed description of the invention

To describe the technical solutions in the embodiments of the present invention more clearly, make required in being described below to embodiment Attached drawing is briefly introduced, it should be apparent that, drawings in the following description are only some embodiments of the invention, for this For the those of ordinary skill in field, without any creative labor, it can also be obtained according to these attached drawings His attached drawing.

Fig. 1 is the schematic diagram of the system in the embodiment of the present invention;

Fig. 2 is the flow diagram of information processing method in the embodiment of the present invention;

Fig. 3 is another flow diagram of information processing method in the embodiment of the present invention;

Fig. 4 is the another flow diagram of information processing method in the embodiment of the present invention;

Fig. 5 is the structural schematic block diagram of information processing unit 300 in the embodiment of the present invention;

Fig. 6 is the structural schematic block diagram of server 400 in the embodiment of the present invention;

Fig. 7 is the structural schematic block diagram of memory node 500 in the embodiment of the present invention;

Fig. 8 is the structural schematic block diagram of server 600 in the embodiment of the present invention.

Specific embodiment

The technical solution that embodiment provides to facilitate the understanding of the present invention, first introduces related art below.

Overtime (timeout) mechanism is widely used in computer and the communications field, a kind of implementation of timeout mechanism Are as follows: the first equipment to the second equipment send request (such as: read request of data, be written request of data, data processing request, etc. Deng) when, just start retransmission counter, if receiving the response results of the second equipment return before the timer expires, cancels Restart timer.If not receiving the response results of request before the timer expires, the first equipment can be to the second equipment Request is retransmitted, and the first equipment will no longer receive the response results of the request (also known as are as follows: just pass request) sent before, but Receive the response results for the request (also known as are as follows: retransmission request) retransmitted.

But in actual conditions, the second equipment is likely to be received the first biography request of the first equipment transmission, and has executed and asked Requested task is sought, since the process time-consuming of task execution is too long, is failed in overtime duration to the first equipment returning response As a result, alternatively, although the second equipment obtains response results in overtime duration, since the second equipment sends letter to the first equipment The failure of the link of breath or obstruction cause response results to fail to be sent to the first equipment in overtime duration.

After retransmitting request due to the first equipment, the response results of first biography request before will no longer be connect by the first equipment It receives, so, the second equipment will be rejected based on the first response process for passing request, not only waste corresponding transfer resource and the The processing capacity of two equipment, the first equipment will also wait the second equipment to be based on retransmission request return response result again, it is time-consuming compared with It is long.

Moreover, because the second equipment is likely to occur task blocking or performance decline, the time sheet of response results is obtained Body be more than re-transmission timer overtime duration, or, because the second equipment to the first equipment transmission information link obstruction, needle To retransmission request, the second equipment still will can not send again retransmission request in overtime duration return response result, the first equipment, And the second equipment always can not in overtime duration return response result, not only resulting in task is unable to complete, and will also occupy a large amount of Transfer resource, reduce the efficiency of communication system.

In view of the above-mentioned problems, the embodiment of the present invention provides a kind of information processing method and corresponding intrument, below by attached drawing And specific embodiment is described in detail technical solution of the present invention, it should be understood that in the embodiment of the present invention and embodiment Specific features are the detailed description to technical solution of the present invention, rather than the restriction to technical solution of the present invention, are not being conflicted In the case where, the technical characteristic in the embodiment of the present invention and embodiment can be combined with each other.

Fig. 1 is can be using the schematic diagram of the distributed system of information processing method provided in an embodiment of the present invention, wherein visitor Family end (Client) is used to receive user demand (such as write request and read request);Server (Server), which is responsible for dispatch user, asks It asks;And node is responsible for executing the requested task of user, in the embodiment of the present invention, node can be storage for storing data Node, or other nodes in calculate node or communication system/computer system for handling processor active task, The embodiment of the present invention not limits.

It should be noted that information processing method provided by the embodiment of the present invention is not limited to be applied to shown in FIG. 1 point Cloth system also can be applied to non-distributed systems, or the local area systems only comprising a small number of nodes, the embodiment of the present invention pair This is not limited.

Fig. 2 is the schematic diagram interacted between server and node in the embodiment of the present invention, and interactive process includes the following steps:

Step 101: server fails to receive the second request in the setting duration to after the second request of memory node transmission The second response results when, to memory node send first request, wherein first request for request to memory node storage Data are operated, and the first request is identified comprising the first request with the second request, and the first request mark is asked for characterizing first Seek requested content;

Step 102: memory node receives the first request that server is sent;Continue to execute step 103;

Step 103: memory node obtains the first request mark from the first request, and judges whether save in local cache There is the first request mark;If comprising thening follow the steps 104;

Step 104: memory node by it is received in advance of the first request include the of the second request that the first request identifies First response results of two response results as the first request;Continue to execute step 105;

Step 105: memory node returns to the first response results to server;

Step 106: server receives the first response results that memory node returns.

Specifically, server starts re-transmission timer, such as after sending the second request to memory node in step 101 Fruit fails the second response results for receiving the second request before the timer expires, and server sends the second request to memory node Retransmission request, that is, first request.

Wherein, the first/bis- request can be write data requests, or read data request can also be execution operation The request of task.Corresponding, the response results of write data requests are write-in success message or write-in failed message, read data request Response results can by the data read of request or the advertisement message that can not read of data, execute the sound of processor active task request Answering result can be operation result.

In the embodiment of the present invention, the corresponding request mark of each request is requested for characterizing request (message) Content, it is identical as retransmission request (that is, first requests) requested content due to just passing request (that is, second request), First request is identical as the request mark that the second request includes, and is the first request mark.

In step 102, memory node receives the first request, and continues to execute step 103, obtains the from the first request One request mark, and judge the first request mark whether is preserved in local cache, if in local cache including the first request Mark then can be confirmed that the first request is retransmission request.

Wherein, the mode that memory node obtains the first request mark in the first request can be with are as follows: first, memory node is first First request is saved in memory, the first request mark is then obtained from memory;Second, since data are serial transmissions , and the first request mark can be stored in the head (or position close to head) of the first request (message), memory node can In the case where the first request not yet receives completely, to obtain the first request mark in the first request.Optionally, rear In a kind of situation, if memory node searches the first request mark in local cache, memory node stopping continues to the One request, directly execution step 104 to save transfer resource, and reduce Server latency.

In the embodiment of the present invention, the included request mark of received request is preserved in the local cache of memory node Know, since request mark is for characterizing request (message) requested content, asked if preserving first in local cache Mark is sought, then receiving before showing memory node has the request comprising the first request mark, which is requested with first Content it is identical.

In step 104, since the first request is identified comprising the first request with the second request, the requested content phase of the two Together, therefore memory node is identical as the second response results for the second request for the first response results of the first request, deposits Storing up node can be using the second response results as the first response results, and continues to execute step 105, and the first response results are sent To server.

In the embodiment of the present invention, memory node judges whether is preserved in local cache when receiving the first request Whether the first request mark of one request judges to have been received before and requests the second of same content to ask with the first request with this It asks, if memory node is not necessarily to execute the requested content of the first request comprising the first request mark in local cache, but Directly using the second response results of received second request before as the first response results of the first request, it is sent to service Device.

The first requested content of request is executed since memory node can not separately expend the time, is directly returned to server The response results of the second request identical with the first requested content of request, had not only been able to satisfy the request of server, but also can subtract The time and business that few server waits are time-consuming.

Optionally, in the embodiment of the present invention, in step 103: memory node obtains the first request mark from the first request, Further include following steps referring to Fig. 3 and before judging whether to preserve the first request mark in local cache:

Step 107: memory node determines that the first request includes retransmitting mark.

Specifically, server adds re-transmission mark in the retransmission request of transmission, it is heavy comprising this for characterizing to retransmit mark The request for passing mark is retransmission request.Memory node first checks for whether the first request includes weight when receiving the first request Mark is passed, if comprising showing that the first request is the retransmission request that server is sent, memory node executes step 103, at this First request mark of the first request of retrieval in ground caching, to determine whether to have received in advance of the first request comprising the first request The request of mark.

It, can be with if memory node checks after received first request in the first request of discovery comprising retransmitting mark For the first request of confirmation just to pass request, memory node needs to respond the first request, executes the first requested task of request, obtains First response results, and the first response results are returned into server.

In actual conditions, server addition can also just pass mark in the request of the first biography of transmission, just pass mark and be used for table The bright request comprising just passing mark is just to pass mark, and if not comprising just passing mark in the received request of memory node, Memory node can determine that the request is retransmission request, so, the deformation of step 107 are as follows: memory node determines the first request not Comprising just passing mark.But the present invention is equally intended to protect this deformation technology scheme.

For first biography request, its request mark, memory node are not yet saved in the local cache of memory node Local cache in be only possible to preserve the request mark of received retransmission request.In the embodiment of the present invention, in local cache Before the request mark for retrieving received request, first determines that the request is retransmission request, avoid and passed in received request to be first Calculation resources waste and the waste of search time caused by its request mark are retrieved when request.

Optionally, in the embodiment of the present invention, in step 104: memory node will it is received in advance of the first request include It further include walking as follows before the first response results of second response results of the second request of one request mark as the first request It is rapid:

Step 108: memory node orients the second response results in local cache.

Specifically, preserving the response results of received request in the local cache of memory node.It is local slow determining When preserving the first request mark in depositing, show memory node before reception first is requested, has received comprising the first request Second request of mark, memory node can say the second response after obtaining formerly the second response results of received second request As a result it is stored in local cache, can directly to determine in retransmission request (that is, first request) for receiving the second request Position goes out the second response results, and the second response results are returned to server, to improve the efficiency of distributed system.

In actual conditions, when determining that the local cache of memory node preserves the first request mark by step 103, First the response process of received second request may not yet terminate, and in this case, the second sound not yet be saved in local cache It answers as a result, memory node can not search the second response results in local cache, memory node can wait for a period of time, so The second response results are searched in local cache again afterwards, until orienting the second response results.

Optionally, in the embodiment of the present invention, the included request mark of received request is stored in local by memory node Caching, including following several implementations:

Mode 1, memory node determine that received request is just to pass request, then the request mark for including by the request saves In local cache.

Specifically, memory node determines received request just to pass request, including following implementation:

First, server judges in received request in the first biography request of transmission added with just biography mark, memory node Whether comprising just passing mark, if comprising, it is determined that the request is just to pass mark.

Second, server identifies in the retransmission request of transmission added with re-transmission, memory node judges in received request Whether comprising retransmitting mark, if not including, it is determined that change request just to pass mark.

Mode 2, memory node obtains the included request mark of received request, and the request is retrieved in local cache Mark shows that the request is retransmission request if retrieving request mark, does not need to save its request mark.Conversely, such as Fruit does not retrieve request mark, then shows that the request is the received first request comprising request mark of memory node, deposit Request mark is stored in local cache by storage node.

In actual conditions, in aforesaid way 2, included request is requested if not retrieving and receiving in local cache Mark, the request may be just to pass request, it is also possible to and it is retransmission request, but due to link failure or data transmission fault, It includes the same first request for requesting mark that memory node, which is not received with the retransmission request,.

Optionally, in the embodiment of the present invention, the first request mark is not included if determined in local cache in step 103 Know, then execute following steps:

Step 109: the first request mark is stored in local cache by memory node, and the first request of response executes first Requested data manipulation is requested, and after having executed the first requested data manipulation of request, generates the first response results, And the first response results are stored in the local cache of memory node.

Specifically, determining do not wrapped in local cache in step 103 if having executed step 107 before step 103 It is identified containing the first request, although showing that the first request is retransmission request, what is sent before server includes the first request Formerly request, is not successfully transmitted to memory node.

It is determined if being not carried out step 107 before step 103, in step 103 in local cache and does not include the first request Mark, then the first request may be just biography request, it is also possible to although being retransmission request for the first request above-mentioned, but Memory node receive it is first include the first request mark request situation.

Which kind of either above-mentioned situation, memory node will not only respond the first request, execute the first requested of request First response results of the first request mark and the first request are also stored in local cache, so as in server by business When sending the retransmission request (might as well be known as: third request) comprising the first request mark again, memory node can be according to local The first request in caching identifies the first request for determining that memory node has been received comprising the first request mark, and directly will be local The response results that the first response results saved in caching are requested as third, return to server, to reduce server waiting Time improves system effectiveness.

Optionally, after step 108, step 105 is executed, the first response results of acquisition are sent to server.

Optionally, further include before step 101 following steps referring to Fig. 4 in the embodiment of the present invention:

Step 201: memory node receives the second request that server is sent;

Step 202: memory node determines that the second request is just to pass request;

Step 203: the first request mark that the second request is included by memory node is stored in local cache;

Step 204: the second request of memory node response executes the second requested data manipulation of request, and is executing After the second requested data manipulation of request, the second response results are generated, and the second response results are stored in memory node Local cache in.

Specifically, memory node is requested in reception second, determine that the second request is to execute the second request institute after just passing request The task of request, and the second response results of the first included request mark of the second request and the second request are stored in this In ground caching, when to send retransmission request (that is: the first request) comprising the second request mark again in server, storage section Point, which can request to identify according to first in local cache, determines that memory node has been received comprising the first request mark second asks It asks, and directly returns to server using the second response results saved in local cache as the response results of the first request, with Server latency is reduced, system effectiveness is improved.

Optionally, in the embodiment of the present invention, step 110: memory node determines that the second request is just biography request, including as follows Implementation: it does not include retransmitting mark that memory node, which determines the second request,;Or memory node determines that the second request includes just passing Mark just passes mark for showing that the second request is just to pass request.

In actual conditions, the second request, which may not be, just passes request, but retransmission request, but due to link failure or Person's data transmission fault, memory node do not receive formerly the asking comprising the first request mark sent before the second request It asks.

Below by taking the request of the first data is written for request in the first request in memory node as an example, to the embodiment of the present invention Technical solution introduced.

Firstly, server sends the second request to memory node at the first moment, the second request includes the first request mark Know, the first data are written in memory node for requesting.Server starts re-transmission timer after transmission second is requested.It can Choosing, server receives the request for the storing data that client is sent, and data to be stored is divided into multiple data blocks by server, will The data block of cutting is respectively stored in the different memory nodes in distributed system, wherein by one in multiple data blocks Data block is stored on the first memory node, and the first memory node is the memory node in the embodiment of the present invention, write-in first The data block of memory node is the first data.

Then, memory node receives the second request, determine the second request be it is received include the first request mark head A request.Its implementation can be with are as follows:

First, memory node searches for the first request mark directly in local cache, determine in local cache not comprising First request mark, that is, can determine the second request be memory node it is received include the first request mark first request.

Second, memory node is first (by judging whether the second request includes just to pass mark, or ask by judging second Seeking Truth is no comprising retransmitting mark) judge whether the second request is just to pass request, if it is determined that and the second request is just passes request, then not In local cache search first request mark i.e. can determine the second request be memory node it is received include the first request mark The first request known.Only after determining that the second request is retransmission request, just the first request of search is identified in local cache, And do not search the first request mark when, determine the second request be memory node it is received include the first request mark head A request.

Then, the first request mark is stored in local cache by memory node, and responds the second request, and the first data are write Enter memory node, and after data are written successfully, generates data and the successful message of the first data, the as second response knot is written Second response results are stored in local cache, and the second response results are returned to server by fruit.

But memory node, when the second response results are sent to server, the re-transmission timer of server has timed, out, Server will not receive the second response results of memory node return.

At the second moment of re-transmission timer time-out, server sends the retransmission request of the second request to memory node, i.e., For the first request, since the first request is the retransmission request of the second request, so the first request includes the comprising the second request One request mark.

Then, memory node receives server is sent second and requests, and is not identified comprising just passing according to the second request, or Person identifies according to the re-transmission that the second request includes, and determines that the second request is retransmission request, the first request is searched in local cache The the first request mark for being included.

Memory node searches the first request mark in local cache, and determining have received in advance of the first request includes Then the request of first request mark, the as second request, orient the second response results, i.e. write-in the in local cache Then as the first response results of the first request, the successful message of the first data will be written in the successful message of one data It is sent to server.

After server receives the write-in successful message of the first data, success message is written to client returned data.

In the above process, since the first data, storage section is written according to the second request in memory node in memory node Point does not have to that the first data are written in memory node again according to the first request, but directly returns to the first number of write-in to server According to successful message, the waiting time of server is not only reduced, also reduces the input/output (Input/ of memory node Output;Referred to as: the I/O) consumption of resource.

Optionally, in the embodiment of the present invention, the local cache of memory node can be a memory, be also possible to multiple The general designation of memory.In addition, local cache can be the memory of memory node, it is also possible to for storing request mark and asking The storage device for the response results asked.

Optionally, in the embodiment of the present invention, the second sound of the first included request mark and the second request of the second request Should result can store in the same memory of local cache, the different memory of local cache can also be stored in respectively In.In addition, storing with the second response results in the same memory in the first request mark, the two can be stored in same reflect In firing table, it can also be stored in respectively in two mapping tables.

Based on the same technical idea, the embodiment of the invention also provides a kind of information processing unit 300, Fig. 5 is information The structural schematic block diagram of processing unit 300, information processing unit 300 include:

Receiving module 301, for receiving the first request of server transmission, the first request is for requesting to information processing apparatus The data for setting storage are operated, and the first request includes the first request mark, and the first request mark is for characterizing the first request institute The content of request;

Judgment module 302 for obtaining the first request mark from the first request, and judges whether save in local cache There is the first request mark, wherein local cache preserves the included request mark of the received request of information processing unit;

Respond module 303, for local cache preserve the first request mark when, will be received in advance of the first request First response results of second response results of the second request comprising the first request mark as the first request;

Sending module 304, for returning to the first response results to server.

Optionally, in the embodiment of the present invention, judgment module 302 is specifically used for: determining that the first request includes retransmitting mark, weight Mark is passed for showing that the first request is retransmission request;After determining that the first request includes re-transmission mark, from the first request The first request mark is obtained, and judges whether preserve the first request mark in local cache.

Optionally, in the embodiment of the present invention, respond module 303 is specifically used for: preserving the first request mark in local cache When knowledge, the second response results are oriented in local cache, and using the second response results as the first response results.

Optionally, in the embodiment of the present invention, receiving module 301 is also used to: receiving the second request that server is sent;

Judgment module 302 is also used to: determining that the second request is just to pass request;

Respond module 303 is also used to: the first request mark for including by the second request is stored in local cache;Response the Two requests execute the second requested data manipulation of request;It is raw and after having executed the second requested data manipulation of request It is stored in local cache at the second response results, and by the second response results.

Optionally, in the embodiment of the present invention, judgment module 302 is specifically used for:

Determining the second request does not include retransmitting mark;Or

It determines that the second request includes just passing mark, just passes mark for showing that the second request is just to pass request.

Optionally, in the embodiment of the present invention, the first data are written for requesting in the second request in information processing unit;

Respond module is specifically used for: the target storage in the first data write information processing unit for including by the second request Position;And the write-in successful message of the first data being generated, and message is stored in local cache, the second response results are to disappear Breath.

Information processing unit 300 in the present embodiment and aforementioned information processing method be based on the same inventive concept under two A aspect is in front described in detail the implementation process of method, so those skilled in the art can be according to aforementioned The structure and implementation process of information processing unit 300 being well understood in the present embodiment are described, in order to illustrate the succinct of book, This is just repeated no more.

Based on identical inventive concept, the embodiment of the present invention provides a kind of server 400, and Fig. 6 is the structure of server 400 Schematic block diagram, server 600 include:

Sending module 401 is asked for failing reception second in the setting duration to after the second request of memory node transmission When the second response results asked, the first request is sent to memory node, wherein the first request stores memory node for requesting Data operated, first request with second request comprising first request identify, first request mark for characterize first Request requested content;

Receiving module 402, the first response results of the first request for receiving memory node return, wherein the first sound Should result be memory node after determining the retransmission request that the first request is the second request, using the second response results as the first sound It answers result and is formed.

Optionally, in the embodiment of the present invention, sending module 401 is specifically used for:

The first request comprising retransmitting mark is sent to memory node, retransmits mark for making memory node determine that first asks It asks as retransmission request.

Optionally, in the embodiment of the present invention, sending module 401 is specifically used for:

Before sending the first request to memory node, is sent to memory node and does not include the second request for retransmitting mark, To show that the second request is just to pass request;Or

The second request comprising just passing mark is sent to memory node, just passes mark for making memory node determine that second asks It asks just to pass request;

Wherein, first request mark of second request for making memory node include by the second request is stored in local cache In.

Server 400 in the present embodiment and aforementioned information processing method be based on the same inventive concept under two sides Face is in front described in detail the implementation process of method, so those skilled in the art can be according to foregoing description The structure and implementation process of the server 400 in the present embodiment is well understood, it is just no longer superfluous herein in order to illustrate the succinct of book It states.

Based on identical inventive concept, the embodiment of the present invention also provides a kind of memory node 500, and Fig. 7 is memory node 500 Schematic block diagram, memory node 500 includes: bus 501 and is connected respectively to the processor 502 of bus 501, storage unit 503 and transmission port 504.

Wherein, transmission port 504 is used to receive the request of server transmission, and the response knot of request is sent to server Fruit.

Storage unit 503 is for storing instruction.

Processor 502 is used to execute the instruction of the storage of storage unit 503, to execute following steps when executing instruction:

Indicate that transmission port 504 receives the first request that server is sent, first request is deposited for requesting to described The data of storage node storage are operated, and first request includes the first request mark, and the first request mark is used for table Levy the requested content of first request;

The first request mark is obtained from first request, and judges whether to preserve described the in local cache One request mark, wherein the local cache of the memory node preserves the received request of the memory node and included Request mark;

If the local cache of the memory node preserves the first request mark, will be in first request First sound of second response results of preceding received the second request comprising the first request mark as first request Answer result;

Indicate that transmission port 504 returns to first response results to the server.

Optionally, the local cache is storage unit 503.

Optionally, in the embodiment of the present invention, processor 502 is being used for: judging described whether is preserved in local cache Before one request mark, it is also used to:

Determine that first request includes retransmitting mark, the re-transmission mark is for showing that first request is asked to retransmit It asks.

Optionally, in the embodiment of the present invention, processor 502 is being used for: will received before first request include Before the first response results of second response results of the second request of the first request mark as first request, also For:

Second response results are oriented in local cache.

Optionally, in the embodiment of the present invention, processor 502 is being used for: instruction transmission port 504 receives what server was sent Before first request, it is also used to:

Indicate that transmission port 504 receives second request that the server is sent;

Second request is determined just to pass request;

The the first request mark for including by second request is stored in local cache;

Second request is responded, the requested data manipulation of second request is executed;

After having executed the requested data manipulation of second request, second response results are generated, and by institute The second response results are stated to be stored in the local cache of the memory node.

Optionally, in the embodiment of the present invention, processor 502 is used for: determining that second request is requested just to pass, specifically Are as follows:

Determine that second request does not include that the re-transmission identifies;Or

Determine that second request includes just passing mark, the mark that just passes is for showing that second request is asked for just biography It asks.

Optionally, in the embodiment of the present invention, second request is for requesting the first number of write-in in the memory node According to;

Processor 502 is used for: response second request executes the requested data manipulation of second request, specifically Are as follows:

First data that second request includes are written to the target storage position in the memory node;

Processor 502 is used for: after having executed the requested data manipulation of second request, generating second sound Answer as a result, specifically:

It generates and the successful message of the first data is written, second response results are the first data described in said write Successful message.

Memory node 500 in the present embodiment and aforementioned information processing method be based on the same inventive concept under two sides Face is in front described in detail the implementation process of method, so those skilled in the art can be according to foregoing description The structure and implementation process of the memory node 500 in the present embodiment is well understood, in order to illustrate the succinct of book, herein just no longer It repeats.

Based on identical inventive concept, the embodiment of the present invention also provides a kind of server 600, and Fig. 8 is showing for server 600 Anticipate block diagram, server 600 include: bus 601 and the processor 602 for being connected respectively to bus 601, storage unit 603 and Transmission port 604.

Wherein, transmission port 604 is used to send to memory node and request, and receives the response knot that memory node returns Fruit.

Storage unit 603 is for storing instruction.

Processor 602 is used to execute the instruction of the storage of storage unit 603, to execute following steps when executing instruction:

Indicate that transmission port 604 fails to receive described second in the setting duration to after the second request of memory node transmission When the second response results of request, Xiang Suoshu memory node sends the first request, wherein first request is for requesting to institute The data for stating memory node storage are operated, and first request is identified comprising the first request with second request, institute The first request mark is stated for characterizing the requested content of first request;

Indicate that transmission port 604 receives the first response results of first request that the memory node returns, wherein First response results are the memory node after determining the retransmission request that first request is second request, will Second response results are formed as first response results.

Optionally, in the embodiment of the present invention, processor 602 is used for: instruction transmission port 604 is sent to the memory node First request, comprising:

Indicate that transmission port 604 sends first request comprising retransmitting mark, the re-transmission to the memory node Mark is for making the memory node determine that first request is retransmission request.

Optionally, in the embodiment of the present invention, processor 602 is being used for: instruction transmission port 604 is sent out to the memory node Before sending first request, it is also used to:

It indicates that transmission port 604 is sent to the memory node and does not include second request for retransmitting mark, with Show second request just to pass request;Or

Indicate that transmission port 604 sends second request comprising just passing mark to the memory node, it is described just to pass Mark just passes request for making the memory node determine second request;

Wherein, first request of second request for making the memory node include by second request is marked Knowledge is stored in local cache.

Server 600 in the present embodiment and aforementioned information processing method be based on the same inventive concept under two sides Face is in front described in detail the implementation process of method, so those skilled in the art can be according to foregoing description The structure and implementation process of the server 600 in the present embodiment is well understood, it is just no longer superfluous herein in order to illustrate the succinct of book It states.

It should be noted that the above processor 502, processor 602 can be a processor, it is also possible to multiple processing The general designation of element.For example, processor 502, processor 602 can be central processing unit (Central Processing Unit; Referred to as: CPU), it is also possible to specific integrated circuit (Application Specific Intergrated Circuit;Referred to as: ASIC), or it is arranged to implement one or more integrated circuits of the embodiment of the present invention, such as: one or more micro- places Manage device (digital singnal processor;Referred to as: DSP), or, one or more field programmable gate array (Field Programmable Gate Array;Referred to as: FPGA).

Storage unit 503, storage unit 603 can be a storage device, be also possible to the general designation of multiple memory elements, And for storing parameter, data required for executable program code, resident's access network equipment or terminal operating etc..And storage unit It may include random access memory (Random-Access Memory;It referred to as: RAM), also may include nonvolatile memory (non-volatile memory;Referred to as: NVM), such as magnetic disk storage, flash memory (Flash) etc..

Bus 501, bus 601 can be industry standard architecture (Industry Standard Architecture; Referred to as: ISA) bus, external equipment interconnection (Peripheral Component;Referred to as: PCI) bus or extension industrial standard body Architecture (Extended Industry Standard Architecture;Referred to as: EISA) bus etc..Bus 501, bus 601 can be divided into address bus, data/address bus, control bus etc..Only to be indicated with a line in figure, but not convenient for indicating Indicate only have a bus or a type of bus.

The one or more technical solutions provided in the embodiment of the present invention, have at least the following technical effects or advantages:

In the embodiment of the present invention, memory node judges whether is preserved in local cache when receiving the first request Whether the first request mark of one request judges to have been received before and requests the second of same content to ask with the first request with this It asks, if memory node is not necessarily to execute the requested content of the first request comprising the first request mark in local cache, but Directly using the second response results of received second request before as the first response results of the first request, it is sent to service Device.

The first requested content of request is executed since memory node can not separately expend the time, is directly returned to server The response results of the second request identical with the first requested content of request, had not only been able to satisfy the request of server, but also can subtract The time and business that few server waits are time-consuming.

It should be understood by those skilled in the art that, the embodiment of the present invention can provide as method, system or computer program Product.Therefore, complete hardware embodiment, complete software embodiment or reality combining software and hardware aspects can be used in the present invention Apply the form of example.Moreover, it wherein includes the computer of computer usable program code that the present invention, which can be used in one or more, The computer program implemented in usable storage medium (including but not limited to magnetic disk storage, CD-ROM, optical memory etc.) produces The form of product.

The present invention be referring to according to the method for the embodiment of the present invention, the process of equipment (system) and computer program product Figure and/or block diagram describe.It should be understood that every one stream in flowchart and/or the block diagram can be realized by computer program instructions The combination of process and/or box in journey and/or box and flowchart and/or the block diagram.It can provide these computer programs Instruct the processor of general purpose computer, special purpose computer, Embedded Processor or other programmable data processing devices to produce A raw machine, so that being generated by the instruction that computer or the processor of other programmable data processing devices execute for real The device for the function of being specified in present one or more flows of the flowchart and/or one or more blocks of the block diagram.

These computer program instructions, which may also be stored in, is able to guide computer or other programmable data processing devices with spy Determine in the computer-readable memory that mode works, so that it includes referring to that instruction stored in the computer readable memory, which generates, Enable the manufacture of device, the command device realize in one box of one or more flows of the flowchart and/or block diagram or The function of being specified in multiple boxes.

Although preferred embodiments of the present invention have been described, it is created once a person skilled in the art knows basic Property concept, then additional changes and modifications may be made to these embodiments.So it includes excellent that the following claims are intended to be interpreted as It selects embodiment and falls into all change and modification of the scope of the invention.

Obviously, various changes and modifications can be made to the invention without departing from essence of the invention by those skilled in the art Mind and range.In this way, if these modifications and changes of the present invention belongs to the range of the claims in the present invention and its equivalent technologies Within, then the present invention is also intended to include these modifications and variations.

Claims (18)

1. a kind of information processing method characterized by comprising
Memory node receives the first request that server is sent, what first request was used to request to store the memory node Data are operated, and first request includes the first request mark, and the first request mark is asked for characterizing described first Seek requested content;
The memory node obtains the first request mark from first request, and judges whether save in local cache There is the first request mark, wherein the local cache of the memory node preserves the received request of the memory node The request mark for being included;
If the local cache of the memory node preserves the first request mark, the memory node will be described the Received before one request, the second response results of the second request comprising the first request mark are as first request The first response results, first request the setting after sending second request to the memory node that be the server It is sent when failing to receive second response results in timing is long;
The memory node returns to first response results to the server.
2. the method as described in claim 1, which is characterized in that judge whether preserve in local cache in the memory node Before the first request mark, further includes:
The memory node determines that first request includes retransmitting mark, and the re-transmission mark is for showing first request For retransmission request.
3. method according to claim 1 or 2, which is characterized in that the memory node will it is described first request before First response of second response results of received the second request comprising the first request mark as first request As a result before, further includes:
The memory node orients second response results in local cache.
4. method according to claim 2, which is characterized in that receive the first request that server is sent in the memory node Before, further includes:
The memory node receives second request that the server is sent;
The memory node determines second request just to pass request;
The first request mark that second request is included by the memory node is stored in local cache;
Memory node response second request, executes the requested data manipulation of second request;
The memory node generates the second response knot after having executed the requested data manipulation of second request Fruit, and second response results are stored in the local cache of the memory node.
5. method as claimed in claim 4, which is characterized in that the memory node determines that second request is asked for just biography It asks, comprising:
The memory node determines that second request does not include that the re-transmission identifies;Or
The memory node determines that second request includes just passing mark, and the mark that just passes is for showing second request Just to pass request.
6. method as described in claim 4 or 5, which is characterized in that second request is for requesting in the memory node The first data of middle write-in;
Memory node response second request, executes the requested data manipulation of second request, comprising:
The memory node stores the target that first data that second request includes are written in the memory node Position;
The memory node generates second response after having executed the requested data manipulation of second request As a result, comprising:
The memory node, which generates, is written the successful message of the first data, and second response results are described in said write The successful message of first data.
7. a kind of information processing method characterized by comprising
Server fails to receive the second sound of second request in the setting duration to after the second request of memory node transmission When answering result, Xiang Suoshu memory node sends the first request, wherein first request deposits the memory node for requesting The data of storage are operated, and first request is identified comprising the first request with second request, the first request mark Know for characterizing the requested content of first request;
The server receives the first response results of first request that the memory node returns, wherein described first Response results are the memory node after determining the retransmission request that first request is second request, by described second Response results are formed as first response results.
8. the method for claim 7, which is characterized in that the server sends described first to the memory node and asks It asks, comprising:
The server sends first request comprising retransmitting mark to the memory node, and the re-transmission mark is for making The memory node determines that first request is retransmission request.
9. method according to claim 8, which is characterized in that send described first to the memory node in the server Before request, further includes:
The server is sent to the memory node does not include second request for retransmitting mark, to show described the Two requests are requested just to pass;Or
The server sends second request comprising just passing mark to the memory node, and the mark that just passes is for making The memory node determines second request just to pass request;
Wherein, the first request mark of second request for making the memory node include by second request is protected There are in local cache.
10. a kind of information processing unit characterized by comprising
Receiving module, for receiving the first request of server transmission, first request is for requesting to the information processing The data of device storage are operated, and first request includes the first request mark, and the first request mark is for characterizing The requested content of first request;
Judgment module for obtaining the first request mark from first request, and judges whether protect in local cache There is the first request mark, wherein local cache preserves the received request of the information processing unit and included Request mark;
Respond module, for that will be received before first request when local cache preserves the first request mark Comprising it is described first request mark second request the second response results as it is described first request the first response results, First request, which is the server, to fail to connect sending to the memory node in the setting duration after second request It is sent when receiving second response results;
Sending module, for returning to first response results to the server.
11. device as claimed in claim 10, which is characterized in that the judgment module is specifically used for: determining that described first asks It asks and is identified including retransmitting, the re-transmission mark is retransmission request for showing first request;Determining first request Including the re-transmission mark after, from it is described first request in obtain it is described first request mark, and judge be in local cache It is no to preserve the first request mark.
12. device as described in claim 10 or 11, which is characterized in that the respond module is specifically used for: in local cache When preserving the first request mark, second response results are oriented in local cache, and described second is responded As a result first response results are used as.
13. device as claimed in claim 11, it is characterised in that:
The receiving module is also used to: receiving second request that the server is sent;
The judgment module is also used to: determining second request just to pass request;
The respond module is also used to: the first request mark for including by second request is stored in local cache; Second request is responded, the requested data manipulation of second request is executed;And it is asked having executed described second After the data manipulation asked, second response results are generated, and second response results are stored in local cache.
14. device as claimed in claim 13, which is characterized in that the judgment module is specifically used for:
Determine that second request does not include that the re-transmission identifies;Or
Determine that second request includes that first pass identifies, described just pass identifies for showing that second request is just to pass to request.
15. device according to claim 13 or 14, which is characterized in that second request is for requesting at the information The first data are written in reason device;
The respond module is specifically used for: the information processing unit is written in first data that second request includes In target storage position;And the write-in successful message of the first data is generated, and the message is stored in local cache In, second response results are the message.
16. a kind of server characterized by comprising
Sending module receives second request for failing in the setting duration to after the second request of memory node transmission When the second response results, Xiang Suoshu memory node sends the first request, wherein first request is for requesting to the storage The data of node storage are operated, and first request is identified comprising the first request with second request, and described first Request mark is for characterizing the requested content of first request;
Receiving module, for receiving the first response results of first request that the memory node returns, wherein described the One response results are the memory node after determining the retransmission request that first request is second request, by described the Two response results are formed as first response results.
17. server as claimed in claim 16, which is characterized in that the sending module is specifically used for:
First request comprising retransmitting mark is sent to the memory node, the re-transmission mark is for saving the storage Point determines that first request is retransmission request.
18. server as claimed in claim 17, which is characterized in that the sending module is specifically used for:
Before sending first request to the memory node, Xiang Suoshu memory node, which is sent, does not include re-transmission mark It is described second request, with show it is described second request for just pass request;Or
Second request comprising just passing mark is sent to the memory node, the mark that just passes is for saving the storage Point determines second request just to pass request;
Wherein, the first request mark of second request for making the memory node include by second request is protected There are in local cache.
CN201510642169.1A 2015-09-30 2015-09-30 A kind of information processing method and corresponding intrument CN105357271B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201510642169.1A CN105357271B (en) 2015-09-30 2015-09-30 A kind of information processing method and corresponding intrument

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201510642169.1A CN105357271B (en) 2015-09-30 2015-09-30 A kind of information processing method and corresponding intrument

Publications (2)

Publication Number Publication Date
CN105357271A CN105357271A (en) 2016-02-24
CN105357271B true CN105357271B (en) 2019-05-24

Family

ID=55333130

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201510642169.1A CN105357271B (en) 2015-09-30 2015-09-30 A kind of information processing method and corresponding intrument

Country Status (1)

Country Link
CN (1) CN105357271B (en)

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106527986A (en) * 2016-11-03 2017-03-22 北京百度网讯科技有限公司 Method and device for storing data

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101043303A (en) * 2006-03-20 2007-09-26 华为技术有限公司 Method and system for mixed retransmission in multi-input multi-output communication system
CN101146341A (en) * 2006-09-12 2008-03-19 华为技术有限公司 A method and device for avoiding duplicate transaction execution in media independent switching
CN101155014A (en) * 2006-09-28 2008-04-02 华为技术有限公司 Method and apparatus for data mixing and automatic requesting for retransmission
CN103269260A (en) * 2013-06-03 2013-08-28 腾讯科技(深圳)有限公司 Data transmission method, data receiving terminal, data sending terminal and data transmission system
CN103688551A (en) * 2011-05-31 2014-03-26 阿尔卡特朗讯 Method for authorising

Family Cites Families (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US8320248B2 (en) * 2006-09-13 2012-11-27 Broadcom Corporation Method and system for communicating data in xDSL using data retransmission

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101043303A (en) * 2006-03-20 2007-09-26 华为技术有限公司 Method and system for mixed retransmission in multi-input multi-output communication system
CN101146341A (en) * 2006-09-12 2008-03-19 华为技术有限公司 A method and device for avoiding duplicate transaction execution in media independent switching
CN101155014A (en) * 2006-09-28 2008-04-02 华为技术有限公司 Method and apparatus for data mixing and automatic requesting for retransmission
CN103688551A (en) * 2011-05-31 2014-03-26 阿尔卡特朗讯 Method for authorising
CN103269260A (en) * 2013-06-03 2013-08-28 腾讯科技(深圳)有限公司 Data transmission method, data receiving terminal, data sending terminal and data transmission system

Also Published As

Publication number Publication date
CN105357271A (en) 2016-02-24

Similar Documents

Publication Publication Date Title
US8452870B2 (en) Monitoring domain allocation performance
US5664091A (en) Method and system for a voiding unnecessary retransmissions using a selective rejection data link protocol
CN1777107B (en) Device and method for on-demand instantiation in a high-performance computing (HPC) system
CN1185843C (en) Method of monitoring Internet communication
US7457877B1 (en) System and method for measuring round trip times in a network using a TCP packet
EP0959601B1 (en) A system and method for server selection for mirrored sites
US20090003344A1 (en) Asyncronous broadcast for ordered delivery between compute nodes in a parallel computing system where packet header space is limited
JP6329139B2 (en) For providing content in a content centric network content name basis, content requestor, the content provider, and a node communication method
JP5788497B2 (en) Operating method, system and computer program
CN102340554B (en) Optimal application server selection method and device for domain name system (DNS)
US7685367B2 (en) Multi-cache cooperation for response output caching
EP0733971A2 (en) Method and apparatus for managing connections for communication among objects in a distributed object system
US8458298B2 (en) Failover in an internet location coordinate enhanced domain name system
US7502876B1 (en) Background memory manager that determines if data structures fits in memory with memory state transactions map
US9917889B2 (en) Enterprise service bus routing system
JP3798661B2 (en) Method of processing a received merged requested by the group members in the clustered computer system
JP5132770B2 (en) Dynamic configuration of the router to find the best dhcp server
CN102624920B (en) A method of accessing via a proxy server apparatus and
JP2008519362A (en) Content address storage device for maintaining a content address mapping
Puliafito et al. An analytical comparison of the client-server, remote evaluation and mobile agents paradigms
US8838723B2 (en) High availability management system for stateless components in a distributed master-slave component topology
US20100011091A1 (en) Network Storage
US9699260B2 (en) Scalable, real-time messaging system
US20080270412A1 (en) Tracking user clicks using ajax based beacons
US20120155468A1 (en) Multi-path communications in a data center environment

Legal Events

Date Code Title Description
C06 Publication
C10 Entry into substantive examination
GR01 Patent grant