CN116233252A - A CDN back-to-source method and device - Google Patents

Abstract

The embodiment of the present invention provides a CDN back-to-source method and device, which relate to the field of CDN back-to-source, and the method includes: after a content distribution network CDN edge node device receives a user request, it does not search in the local cache of the CDN edge node device When the user requests the corresponding cached data, use the upper-level node device of the CDN edge node device as the source-returning node device for back-to-source; In the case of , the CDN edge node device forwards the user request to the back-to-origin node device, obtains the cached data corresponding to the user request from the local cache of the back-to-source node device, and returns it to the user. The back-to-source conditions are set for the back-to-source node equipment, and only the back-to-source conditions can be used to perform back-to-source, without affecting other services and reducing the probability of failure.

Description

A CDN back-to-source method and device

technical field

The present invention relates to the field of CDN back-to-source, in particular to a CDN back-to-source method and device.

Background technique

CDN back-to-source is an action. This action includes common such as CDN edge node equipment, if there is no resource that can be returned to the user, then it needs to go back to the source to the second-level node device to get the resource. Similarly, if the second-level node device does not have this resource, then it needs to go back to the source of the third-level node. Devices, and so on, until the source is returned to the real source site to obtain resources, that is, every time the action of fetching resources is CDN return to the source. CDN currently has two back-to-origin logics: one is when back-to-origin is normal, and the other is when back-to-origin is abnormal. The normal access process of back-to-source refers to: when a user accesses a certain resource, it first arrives at the edge node device of the CDN. If the edge node device happens to have this resource, it will directly return it to the user; It will go back to the CDN secondary node device to download resources. If the CDN secondary node device happens to have this resource, then the CDN secondary node device will return the resource to the edge node device, and the CDN edge node device will return the resource to the user. Save a resource to your own storage, and the next time the user visits, it can be returned directly to the user; then if neither the edge node device nor the secondary node device of the CDN has this resource, it will go back to the real source site to store the resource, and then By analogy, the resource is finally returned to the user, and at the same time, the edge node device and the secondary node device of the CDN will also cache the resource. The abnormal access process of returning to the source refers to: the previous process is like the normal access process of returning to the source, but the difference is the last step. Abnormal, resulting in very slow back-to-origin, and finally because the back-to-origin timeout triggers the CDN back-to-origin retry logic, and then multiple CDN secondary node devices retry the origin site, and finally the retry may succeed, or it may retry If the retry fails, it is naturally best if the retry succeeds, and it will continue to retry after the retry fails.

The disadvantages of the existing technology are as follows: when the source site fails, the risk of CDN failure will be greatly increased. One reason is that the source site stores and returns resources very slowly, which occupies the number of connections of the CDN secondary node equipment. One reason is that if the source site The resources provided by the site are too slow to reach the timeout period set by the CDN secondary node device. At this time, the connection will be disconnected and retried. Such multiple CDN secondary node devices will have problems such as accumulation of connections and full CPU load. Eventually, the CDN secondary node equipment is unavailable, affecting other services served by the CDN, dragging down the CDN secondary node equipment, and causing an avalanche. That is, a service source site is abnormal, which affects the entire CDN, which in turn affects other services, resulting in the unavailability of CDN services.

Contents of the invention

Embodiments of the present invention provide a CDN back-to-source method and device, which can solve technical problems caused by CDN back-to-source in the prior art.

In order to achieve the above purpose, on the one hand, an embodiment of the present invention provides a CDN back-to-source method, including:

After receiving the user request, the content distribution network CDN edge node device sends the upper level of the CDN edge node device to the The node device is used as the back-to-source node device for back-to-source;

When it is determined that the origin-returning node device has the origin-returning node device, the CDN edge node device forwards the user request to the origin-returning node device, and obtains the The user requests corresponding cached data to be returned to the user.

On the other hand, an embodiment of the present invention provides a CDN back-to-source device, including a back-to-source startup module and a back-to-source module disposed in a CDN edge node device of a content distribution network, wherein:

The back-to-source starting module is configured to, after the CDN edge node device receives the user request, if the corresponding cached data requested by the user is not found in the local cache of the CDN edge node device, The upper-level node device of the above-mentioned CDN edge node device is used as the back-to-source node device for back-to-source;

The origin-returning module is configured to forward the user request to the origin-returning node device when it is determined that the origin-returning node device meets the origin-returning node device, and obtain the request from the local cache of the origin-returning node device The user requests corresponding cached data to be returned to the user.

The above technical solution has the following beneficial effects: by setting the back-to-source conditions for the back-to-source node equipment, the back-to-source conditions can only be performed, and if the back-to-source conditions are not met, the back-to-source will be terminated, and the back-to-source will not be performed unconditionally, realizing the back-to-source The isolation of services without affecting other services in the CDN greatly reduces the failure probability of the CDN; and the back-to-source is processed automatically, and the operation and maintenance cost is low.

Description of drawings

In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings that need to be used in the description of the embodiments or the prior art. Obviously, the accompanying drawings in the following description are only These are some embodiments of the present invention. Those skilled in the art can also obtain other drawings based on these drawings without creative work.

Fig. 1 is a flowchart of a CDN back-to-source method according to an embodiment of the present invention;

FIG. 2 is a structural diagram of a CDN back-to-source device according to an embodiment of the present invention;

Fig. 3 is a flowchart of another CDN back-to-source method according to an embodiment of the present invention;

Fig. 4 is a system architecture diagram of CDN back-to-source using a back-to-source device according to an embodiment of the present invention.

Detailed ways

The following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only some, not all, embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by persons of ordinary skill in the art without making creative efforts belong to the protection scope of the present invention.

As shown in Figure 1, in combination with the embodiment of the present invention, a CDN back-to-source method is provided, including:

S101: After the CDN edge node device of the content distribution network receives the user request, if the corresponding cached data requested by the user is not found in the local cache of the CDN edge node device, the CDN edge node device uploads the The first-level node device is used as the back-to-source node device for back-to-source;

S102: When it is determined that the origin-returning node device has the origin-returning node device, the CDN edge node device forwards the user request to the origin-returning node device, and obtains the request from the local cache of the origin-returning node device The user requests corresponding cached data to be returned to the user.

Wherein, the origin-returning node device can judge whether it has the origin-returning condition and notify the CDN edge node device of the judgment result. The origin-returning node device refers to the upper-level node device or origin station device adjacent to the CDN edge node device. It is also possible to judge whether the current back-to-source node device meets the back-to-source conditions through the CDN edge node device.

Preferably, the CDN back-to-source method further includes:

S103: When the origin-returning node device does not meet the origin-returning condition, stop performing origin-returning from the origin-returning node device.

Preferably, when there is at least one level of node device between the CDN edge node device and the source station device, the upper-level node device of the CDN edge node device is used as the source for returning to the source After the node device, also include:

S104: In the case that the back-to-source node device does not have the back-to-source condition, update the upper-level node device of the current back-to-source node device to the back-to-source node device, and based on whether the updated back-to-source node device has the back-to-source node device, The source condition determines whether to update the source node device until the updated source node device meets the source condition or the source station device is updated to the source node device.

Preferably, the CDN back-to-source method further includes:

S105: Determine whether the back-to-source node device meets the back-to-source conditions, which may specifically include:

S1051: Obtain the service domain name corresponding to the user request, and acquire at least one source-returning IP configured for the service domain name in the source-returning node device;

S1052: For each source-backing IP configured, determine whether the total number of parallel requests sent to each source-backing IP is greater than the first request number threshold, and confirm that the total number of parallel requests sent to each source-backing IP is When it is greater than the first request number threshold, it is determined that the back-to-source node device does not meet the back-to-source conditions;

S1053: If the total number of parallel requests sent to any one of the back-source IPs is not greater than the first request number threshold, further determine the total number of parallel requests sent to all configured back-source IPs through the business domain name Whether it is greater than the second request number threshold;

S1054: When confirming that the total number of parallel requests sent to all the configured origin-returning IPs through the service domain name is greater than the second request number threshold, determine that the origin-returning node device does not meet the origin-returning condition;

S1055: When it is confirmed that the total number of parallel requests sent to all the configured origin-returning IPs through the service domain name is not greater than the second request number threshold, determine that the origin-returning node device meets the origin-returning condition.

Preferably, the CDN back-to-source method further includes:

S106: When the origin-returning node device performs origin-returning through a certain origin-returning IP, update the total number of parallel requests sent to the origin-returning IP, and update all the configured origin-returning requests through the service domain name The total number of parallel requests sent by the IP;

S107: After returning the cached data corresponding to the user request to the CDN edge node device through the origin-returning IP, mark that the origin-returning corresponding to the user request is responded; update the parallel data sent to the origin-returning IP The total number of requests, and update the total number of parallel requests sent to all configured back-to-source IPs through the business domain name.

Preferably, the CDN back-to-source method further includes:

S108: In the case that the origin-returning node device has the origin-returning condition and is an origin station device, the CDN edge node device obtains the cached data corresponding to the user request from the local cache of the origin station device, and saves the corresponding Cache data is cached locally;

S109: In the case that the origin-returning node device has the origin-returning condition, and there is at least one node device that does not meet the origin-returning condition between the CDN edge node device and the origin-returning node device, set the origin-returning node The cache data returned by the device is returned to each of the node devices that do not have the back-to-source condition in turn, until it is returned to the CDN edge node device, each of the node devices that do not have the back-to-source condition and the CDN edge node device Save the cached data in their respective local caches.

As shown in Figure 2, in combination with the embodiments of the present invention, a CDN back-to-source device is provided, including a back-to-source startup module and a back-to-source module disposed in CDN (Content Distribution Network) edge node devices, wherein:

The back-to-source starting module 21 is configured to, after the CDN edge node device receives a user request,

When the corresponding cached data requested by the user is not found in the local cache of the edge node device, the upper-level node device of the CDN5 edge node device is used as the back-to-source node device for back-to-source;

The origin-returning module 22 is configured to forward the user request to the origin-returning node device by the CDN edge node device when it is determined that the origin-returning node device meets the origin-returning node device, and from the origin-returning node device Obtain the cached data corresponding to the user request from the local cache of the local cache, and return it to the user.

Preferably, the back-to-source module 22 is also used for:

0 If the origin-returning node device does not meet the origin-returning condition, stop performing origin-returning from the origin-returning node device.

Preferably, the back-to-source module 22 is also used for:

After the upper-level node device of the CDN edge node device is used as the origin-returning node device, if the origin-returning node device does not have the origin-returning condition, the CDN edge node device and the origin station device between

If one level of node equipment is missing, update the upper-level node equipment of the current back-to-source node device to the back-to-source node 5-point device, and judge whether it needs to be updated based on whether the updated back-to-source node device meets the back-to-source conditions Back to the source node device,

Until the updated back-to-source node device meets the back-to-source conditions or the source station device is updated to the back-to-source node device.

Preferably, the device further includes a back-to-origin judging module set in the back-to-origin node device or the CDN edge node device, and the back-to-origin judging module includes:

A condition acquisition submodule, configured to acquire the service domain name corresponding to the user request, and acquire at least one source-returning IP configured for the service domain name in the source-returning node device 0;

The first judging submodule is used to determine whether the total number of parallel requests sent to each of the source-backing IPs is greater than the first request number threshold for each configured source-backing IP, and to confirm that the request is sent to each of the source-backing IPs. When the total number of parallel requests is greater than the first request number threshold, it is determined that the back-to-source node device does not meet the back-to-source conditions;

The second judging sub-module is used to further judge all back-to-source configured through the service domain name when the total number of parallel requests sent to any one of the back-to-source IPs is not greater than the threshold of the first request number Total parallel requests sent by IP

Whether the number is greater than the second request number threshold;

When confirming that the total number of parallel requests sent to all the configured back-to-source IPs through the service domain name is greater than the second request number threshold, it is determined that the back-to-source node device does not meet the back-to-source conditions;

When it is confirmed that the total number of parallel requests sent to all the configured back-to-source IPs through the service domain name is not greater than the second request zero threshold, it is determined that the back-to-source node device meets the back-to-source conditions.

Preferably, the CDN back-to-source device further includes a first update module set in the back-to-source node device, and/or a second update module set in the CDN edge node device and each node device that does not have the back-to-source condition Update the module, where:

The first update module is configured to update the total number of parallel requests sent to the origin-returning IP while the origin-returning node device performs the origin-returning through a certain origin-returning IP, and update the number of requests passed through the service domain name The total number of parallel requests sent to all configured back-to-source IPs; after returning the cached data corresponding to the user request to the CDN edge node device through the back-to-source IP, mark the back-to-source corresponding to the user request Responded; update the total number of parallel requests sent to the source IP, and update the total number of parallel requests sent to all configured source IPs through the business domain name;

The second update module installed in the CDN edge node device is used to obtain the corresponding cached data requested by the user from the local cache of the origin-returning node device when the origin-returning node device meets the origin-returning condition , save the corresponding cached data in the local cache;

The second update module installed in each node device that does not have the back-to-source condition, where the back-to-source node device has the back-to-source condition, and there is at least one non-returning node device between the CDN edge node device and the back-to-source node device. In the case of a node device having the back-to-source condition, the cached data returned by the back-to-source node device is stored in respective local caches.

The beneficial technical effect that the embodiment of the present invention obtains is as follows:

(1) The CDN back-to-source device is directly attached to the CDN cache software, and the configuration (that is, the switch) can be directly turned on or off without secondary development of the original online environment. When the CDN back-to-source device is needed, it only needs to be configured Just turn on this module to achieve low coupling. When this CDN back-to-origin device is not needed, it only needs to be turned off through configuration. It is easy to expand and maintain, and its own program logic and configuration are relatively simple. Although it seems to be a relatively simple function, it plays an important role in returning to the source. Completely automated processing, no manual intervention is required to restore the fault after the fault, which not only reduces the operation and maintenance cost, but also greatly reduces the probability of failure.

(2) The CDN back-to-origin device achieves the function of back-to-source and current-limiting by limiting the "parallel request number" of back-to-source, so that each business domain name is back to the source independently of each other, without affecting each other, and will not affect other irrelevant services, which plays a role Important business isolation, thus protecting the CDN itself and the source site storage, greatly reducing the risk of failure.

(3) Double restrictions are adopted: the combination of domain name + back-to-source IP is strictly limited to the number of back-to-source parallel requests, and the overall number of back-to-source parallel requests is loosely limited, thereby reducing the back-to-source pressure and shortening the recovery time of the source station; back-to-source connection After the number is limited, the pressure on the source site will be correspondingly reduced, giving the source site enough recovery time so that it will not be knocked down again during the recovery process.

(4) Stand-alone deployment only needs to be deployed on each server (ie, node device), and the programs on each server work independently of each other without affecting each other.

The above technical solutions of the embodiments of the present invention will be described in detail below in conjunction with specific application examples. For technical details not introduced in the implementation process, refer to the relevant descriptions above.

An embodiment of the present invention provides a back-to-origin method for a content distribution network CDN, which can isolate back-to-origin services. Service isolation means that each service is independent of each other and does not interfere with each other during back-to-origin. In view of the fact that the CDN carries many services and the source sites required to return to the source are different for different access resources, the CDN distinguishes different services, and each service has an independent operating environment, so even if a service fails, it only affects the service itself , without affecting other businesses.

A back-to-source method of a content distribution network CDN is realized by a service isolation module, and the work flow chart is shown in FIG. 3 . Workflow steps include:

1. The user initiates a resource access request.

2. When the CDN edge node device receives the user request, it enters the back-to-source startup module: the CDN edge node device searches for the local cache, and if there is a cache locally, it directly returns the resource to the user; if there is no cache locally, the CDN edge node device The upper-level node device of the server is used as the source-back node device for back-to-source.

3. Judgment is made by each sub-module of the origin-return judgment module set in the origin-returning node device or the CDN edge node device.

The back-to-source rules have been set on the system. For a certain business domain name, when it is necessary to go back to the source, you can only go to the corresponding designated back-to-source IP to request resources to go back to the source. Obtain the service domain name corresponding to the user request, and obtain at least one source-returning IP configured for the service domain name in the source-returning node device; that is, obtain the service domain name (ie host) from the access resource before returning to the source , at the same time get the back-to-source IP according to the set rules, use the method of domain name + back-to-source IP to match the number of parallel requests A of the current business domain name in the current back-to-source IP of the secondary node device to be back to the source.

A condition acquisition submodule, configured to acquire the service domain name corresponding to the user request, and acquire at least one source-returning IP configured for the service domain name in the source-returning node device;

The first judging submodule is used to determine whether the total number of parallel requests sent to each of the source-backing IPs is greater than the first request number threshold for each configured source-backing IP, and to confirm that the request is sent to each of the source-backing IPs. When the total number of parallel requests is greater than the first request number threshold, it is determined that the back-to-source node device does not have the back-to-source condition; for example, it is judged whether the current number of parallel requests A is greater than A1, and if A is greater than A1, business isolation will be triggered. Refuse to return to the source, end.

Each business domain name will have a back-to-source IP, and there are one or more back-to-source IPs. If the attempt to go back to the source IP1 fails, it will try to go back to the source IP2, IP3, etc., then a business domain name will have n domain name + IP combination. The sum of the number of parallel requests generated by this combination is the overall number of parallel requests B.

The second judging submodule is used to further judge all the configured back-to-source IPs through the service domain name when the total number of parallel requests sent to any one of the back-to-source IPs is not greater than the first request number threshold Whether the total number of parallel requests sent is greater than the second request number threshold;

When confirming that the total number of parallel requests sent to all the configured back-to-source IPs through the service domain name is greater than the second request number threshold, it is determined that the back-to-source node device does not meet the back-to-source conditions;

When it is confirmed that the total number of parallel requests sent to all configured origin-returning IPs through the service domain name is not greater than the second request threshold, it is determined that the origin-returning node device meets the origin-returning condition.

That is, if there is one back-to-source IP, and the current number of parallel requests A is not greater than A1, then judge whether the total number of parallel requests B of the current business domain name is greater than B1, and if so, refuse to go back to the source, that is, the CDN edge node The device does not send the user request to the secondary node device, end. If the back-to-source conditions are met, the CDN edge node device initiates a request, carries the user request, and sends the user request to the secondary node device; the back-to-source is done by the CDN edge node device, and the CDN edge node device retrieves the resources and returns the resources to the user .

In the case that the origin-returning node device does not have the origin-returning condition, and there is at least one level of node device between the CDN edge node device and the origin station device, the upper-level node of the current origin-returning node device The device is updated as a back-to-source node device, and based on whether the updated back-to-source node device meets the back-to-source conditions, it is judged whether it is necessary to update the back-to-source node device until the updated back-to-source node device meets the back-to-source conditions or the source station device is updated to Back to the source node device.

4. The origin-returning module, when it is determined that the origin-returning node device has the origin-returning node device, the CDN edge node device forwards the user request to the origin-returning node device, and from the origin-returning node device The cached data corresponding to the user request is obtained from the local cache to return to the user. In the case that the origin-returning node device does not meet the origin-returning condition, the origin-returning from the origin-returning node device is stopped.

5. While the origin-returning node device is returning to the source through a certain origin-returning IP, update the total number of parallel requests sent to the origin-returning IP through the first update module installed in the origin-returning node device, and, Update the total number of parallel requests sent to all configured back-to-source IPs through the business domain name. That is: add 1 to the number of parallel requests A for update to form an updated number of parallel requests A; and add 1 to the number of parallel requests B for update to form an updated number of parallel requests B. And mark the request, and then process the request.

After the cached data corresponding to the user request is returned to the CDN edge node device through the back-to-source IP, the first update module installed in the back-to-source node device marks that the back-to-source corresponding to the user request is responded ; Updating the total number of parallel requests sent to the origin-returning IP, and updating the total number of parallel requests sent to all configured origin-returning IPs through the business domain name. That is: after the request processing is completed, check the request to see if there is a mark to be executed. If there is a mark to be executed, the number of parallel requests A is updated by subtracting 1 to form the updated number of parallel requests A and the number of parallel requests B Subtract 1 to update, form the updated merge request number B, and end.

4. In the case that the back-to-source node device has the back-to-source condition and is an origin site device, through the second update module installed in the CDN edge node device, in the case that the back-to-source node device has the back-to-source condition Next, after obtaining the cached data corresponding to the user request from the local cache of the back-to-source node device, the corresponding cached data is saved in the local cache.

In the case that the origin-returning node device has the origin-returning condition, and there is at least one node device that does not meet the origin-returning condition between the CDN edge node device and the origin-returning node device, by setting The second update module in the source-condition node device saves the cached data returned by the source-returning node device in their respective local caches.

The system architecture diagram of CDN back-to-source through CDN isolation device is shown in Figure 4. The CDN isolation device (CDN back-to-source device) is composed of multiple modules (also called business isolation modules), which are respectively integrated in existing CDN edge devices (edge node device), the node device between the edge node device and the source station device, and the cache software of the source station device. Configure whether the CDN isolation device is turned on or off, and whether to use the isolation device by directly turning it on or off does not require secondary development of the original online environment. When this business isolation module is needed, it only needs to be enabled through configuration to realize low coupling. When the business isolation module is not needed, it only needs to be disabled through configuration. The business isolation module mainly ensures the stable operation of the entire CDN system by limiting the number of back-to-source requests for each business. The main operating logic is: limit the "parallel request number" of a single business domain name, and each business can only have a specified number of back-to-source requests Requests are processed in parallel, and an error will be returned if the request is exceeded, stopping the return to the source. Take user access to resources as an example to describe the operation process of the module in detail, as follows:

A user opens a website to access an image resource, and the request goes directly to the CDN. When the CDN receives the request, it will search for the resource on the edge node device to see if there is a cache. If there is a cache, the resource will be directly returned to the user. If the edge node device checks that there is no cache locally, then through the CDN back-to-source device, it will go back to the CDN upper-level node device to get the resource. When returning to the source, it will first Check whether the current parallel request number A of the combination of the domain name (from the host header) and the back-to-source IP in the CDN upper-level node device is greater than A1, and if so, directly reject the back-to-source; if not, it will check out the domain name (from host header) Whether the current number of parallel requests B is greater than B1, if yes, directly refuse to return to the source; if not, check the CDN edge node device, and use the upper-level node device of the CDN as the source node device. In the same way, as the back-to-source node device, the CDN upper-level device first checks whether there is a local cache. If there is a local cache, the resource is returned to the CDN edge node device, and the CDN edge node device returns the resource to the user. Save a copy of the cache; if the CDN upper-level device does not have a local cache, then you need to go back to the source site to get the resources at this time.

That is, when the cache hit rate is low, set up CDN level-2 node devices, CDN level-3 node devices, and CDN level-4 node devices between the CDN edge node device and the source station device, in order to hit as much as possible in the cache of the node device, while Do not go back to the source station equipment. When there is a multi-level node device between the local cache and the source station, if there is no cache resource in the local memory of the node device at the current level, it will search for the next-level node device in turn until the source station is finally reached. Wherein, A1 of each node device may be the same or different; B1 of each node device may be the same or different. The set A1 and B1 are set in the cache configuration of the CDN.

The beneficial technical effect that the embodiment of the present invention obtains is as follows:

(1) The CDN back-to-source device is directly attached to the CDN cache software, and the configuration (that is, the switch) can be directly turned on or off without secondary development of the original online environment. When the CDN back-to-source device is needed, it only needs to be configured Just turn on this module to achieve low coupling. When this CDN back-to-origin device is not needed, it only needs to be turned off through configuration. It is easy to expand and maintain, and its own program logic and configuration are relatively simple. Although it seems to be a relatively simple function, it plays an important role in returning to the source. Completely automated processing, no manual intervention is required to restore the fault after the fault, which not only reduces the operation and maintenance cost, but also greatly reduces the probability of failure. Avoid technical problems "If the origin site is unavailable, but it is slowly recovering, at this time, due to the logic of CDN secondary retrying, there will be a wave of connections to the origin site. The connection pressure is impacted, and it is very likely to fail again, which will eventually lead to the failure of the origin station again and again" and "due to the accumulation of CDN secondary connections, the CPU load soars, and the excessive pressure of retrying the origin station will eventually cause the CDN system and the origin station system to fail. They are all in a paralyzed state. At this time, if you want to return to normal, you need human intervention to restart all the CDN secondary servers and cache software. At this time, the number of connections will be released. The CDN access can be restored to normal. This series of operations requires manual operation and multiple online servers, which will greatly increase the length of the failure and increase the operation and maintenance cost.”

(2) The CDN back-to-origin device achieves the function of back-to-source and current-limiting by limiting the "parallel request number" of back-to-source, so that each business domain name is back to the source independently of each other, without affecting each other, and will not affect other irrelevant services, which plays a role Important business isolation, thus protecting the CDN itself and the source site storage, greatly reducing the risk of failure. Avoid technical problems "CDN secondary node equipment also serves other services, and the entire secondary CDN is unavailable due to a failure of a certain service source site, which will inevitably affect other irrelevant services and expand the scope of failure."

(3) If you simply limit the number of concurrent back-to-origin requests for the combination of domain name + back-to-origin IP, it will lead to the following problem: "For example, the number of connections is full due to the exception of the back-to-origin source site 1, and then retry the source site 2, this source site 2 is good, but because the number of connections is full, it refuses to return to the source."

The present invention adopts double restrictions: it strictly limits the number of concurrent back-to-source requests combined by domain name + back-to-source IP, and loosely limits the overall number of back-to-source parallel requests, thereby reducing the back-to-source pressure and shortening the recovery time of the source station; the number of back-to-source connections After being restricted, the pressure on the source site will be correspondingly reduced, giving the source site enough recovery time so that it will not be knocked down again during the recovery process.

(4) Stand-alone deployment only needs to be deployed on each server (ie, node device), and the programs on each server work independently of each other without affecting each other.

It is understood that the specific order or hierarchy of steps in the processes disclosed is an example of exemplary approaches. Based upon design preferences, it is understood that the specific order or hierarchy of steps in the processes may be rearranged without departing from the scope of the present disclosure. The accompanying method claims present elements of the various steps in a sample order, and are not meant to be limited to the specific order or hierarchy described.

In the foregoing Detailed Description, various features are grouped together in a single embodiment to simplify the disclosure. This method of disclosure is not to be interpreted as reflecting an intention that the claimed embodiments of the subject matter require more features than are expressly recited in each claim. Rather, as the following claims reflect, the invention lies in less than all features of a single disclosed embodiment. Thus the following claims are hereby expressly incorporated into the Detailed Description, with each claim standing on its own as a separate preferred embodiment of this invention.

The foregoing description of the disclosed embodiments was provided to enable any person skilled in the art to make or use the invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be applied to other embodiments without departing from the spirit and scope of the disclosure. Thus, the present disclosure is not intended to be limited to the embodiments presented herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

The foregoing description includes illustrations of one or more embodiments. Of course, it is impossible to describe all possible combinations of components or methods to describe the above-mentioned embodiments, but those skilled in the art should recognize that various embodiments can be further combined and permuted. Accordingly, the embodiments described herein are intended to embrace all such alterations, modifications and variations that fall within the scope of the appended claims. Furthermore, to the extent that the term "comprises" is used in the specification or claims, the word is encompassed in a manner similar to the term "comprises" as interpreted when "comprises" is used as a link in the claims. Furthermore, any use of the term "or" in the specification of the claims is intended to mean a "non-exclusive or".

Those skilled in the art can also understand that various illustrative logical blocks, units, and steps listed in the embodiments of the present invention can be implemented by electronic hardware, computer software, or a combination of both. To clearly demonstrate the interchangeability of hardware and software, the various illustrative components, units and steps above have generally described their functions. Whether such functions are implemented by hardware or software depends on the specific application and overall system design requirements. Those skilled in the art may use various methods to implement the described functions for each specific application, but such implementation should not be understood as exceeding the protection scope of the embodiments of the present invention.

Various illustrative logic blocks or units described in the embodiments of the present invention can be discretely processed by a general-purpose processor, a digital signal processor, an application-specific integrated circuit (ASIC), a field programmable gate array or other programmable logic devices. Gate or transistor logic, discrete hardware components, or any combination of the above designed to implement or operate the described functions. The general-purpose processor may be a microprocessor, and optionally, the general-purpose processor may also be any conventional processor, controller, microcontroller or state machine. A processor may also be implemented by a combination of computing devices, such as a digital signal processor and a microprocessor, multiple microprocessors, one or more microprocessors combined with a digital signal processor core, or any other similar configuration to accomplish.

The steps of the method or algorithm described in the embodiments of the present invention may be directly embedded in hardware, a software module executed by a processor, or a combination of both. The software modules may be stored in RAM memory, flash memory, ROM memory, EPROM memory, EEPROM memory, registers, hard disk, removable disk, CD-ROM or any other storage medium in the art. Exemplarily, the storage medium can be connected to the processor, so that the processor can read information from the storage medium, and can write information to the storage medium. Optionally, the storage medium can also be integrated into the processor. The processor and the storage medium can be set in the ASIC, and the ASIC can be set in the user terminal. Optionally, the processor and the storage medium may also be set in different components in the user terminal.

In one or more exemplary designs, the above functions described in the embodiments of the present invention may be implemented in hardware, software, firmware or any combination of the three. If implemented in software, the functions can be stored on or transmitted over as one or more instructions or code on a computer-readable medium. Computer-readable media includes computer storage media and communication media that facilitate transfer of a computer program from one place to another. Storage media may be any available media that can be accessed by a general purpose or special computer. For example, such computer-readable media may include, but are not limited to, RAM, ROM, EEPROM, CD-ROM or other optical disk storage, magnetic disk storage or other magnetic storage devices, or any other device that can be used to carry or store instructions or data structures and Other medium of program code in a form readable by a general-purpose or special-purpose computer, or a general-purpose or special-purpose processor. In addition, any connection is properly defined as a computer-readable medium, for example, if the software is transmitted from a website site, server, or other remote source via a coaxial cable, fiber optic cable, twisted pair, digital subscriber line (DSL) Or transmitted by wireless means such as infrared, wireless and microwave are also included in the definition of computer readable media. Disks and discs include compact discs, laser discs, optical discs, DVDs, floppy discs, and Blu-ray discs. Disks usually reproduce data magnetically, while discs usually reproduce data optically with lasers. Combinations of the above can also be contained on a computer readable medium.

The specific embodiments described above have further described the purpose, technical solutions and beneficial effects of the present invention in detail. It should be understood that the above descriptions are only specific embodiments of the present invention and are not intended to limit the scope of the present invention. Protection scope, within the spirit and principles of the present invention, any modification, equivalent replacement, improvement, etc., shall be included in the protection scope of the present invention.

Claims (11)

1. A CDN back-to-source method, characterized in that, comprising: After receiving the user request, the content distribution network CDN edge node device sends the upper level of the CDN edge node device to the The node device is used as the back-to-source node device for back-to-source; When it is determined that the origin-returning node device has the origin-returning node device, the CDN edge node device forwards the user request to the origin-returning node device, and obtains the The user requests corresponding cached data to be returned to the user. 2. The CDN back-to-origin method according to claim 1, characterized in that, in the case that the back-to-origin node device does not meet the back-to-origin conditions, the back-to-origin from the back-to-origin node device is stopped. 3. The CDN back-to-source method according to claim 1, characterized in that, In the case where there is at least one level of node device between the CDN edge node device and the source station device, after using the upper-level node device of the CDN edge node device as the return-to-source node device for back-to-source ,Also includes: In the case that the source-returning node device does not meet the source-returning condition, update the upper-level node device of the current source-returning node device to the source-returning node device, and based on whether the updated source-returning node device has the source-returning condition Determine whether to update the source node device until the updated source node device meets the source condition or update the source station device to the source node device. 4. The CDN back-to-source method according to claim 1, further comprising: Obtain the service domain name corresponding to the user request, and obtain at least one source-returning IP configured for the service domain name in the source-returning node device; For each source-backing IP configured, determine whether the total number of parallel requests sent to each source-backing IP is greater than the first request threshold, and confirm that the total number of parallel requests sent to each source-backing IP is greater than the first When a request number threshold is reached, it is determined that the back-to-source node device does not meet the back-to-source conditions; If the total number of parallel requests sent to any of the source-backing IPs is not greater than the first request number threshold, it is further determined whether the total number of parallel requests sent to all the configured source-backing IPs through the business domain name is greater than The second request number threshold; When confirming that the total number of parallel requests sent to all the configured back-to-source IPs through the service domain name is greater than the second request number threshold, it is determined that the back-to-source node device does not meet the back-to-source conditions; When it is confirmed that the total number of parallel requests sent to all configured origin-returning IPs through the service domain name is not greater than the second request threshold, it is determined that the origin-returning node device meets the origin-returning condition. 5. The CDN back-to-source method according to claim 4, further comprising: While the origin-returning node device is performing origin-returning through a certain origin-returning IP, update the total number of parallel requests sent to the origin-returning IP, and update the number of requests sent to all configured origin-returning IPs through the service domain name The total number of parallel requests; After returning the cached data corresponding to the user request to the CDN edge node device through the origin-returning IP, mark the origin-returning corresponding to the user request as being responded; update the parallel total request sent to the origin-returning IP and update the total number of parallel requests sent to all the configured back-to-origin IPs through the business domain name. 6. The CDN back-to-origin method according to claim 3, wherein the upper-level node device of the CDN edge node device includes an origin site device; the method further comprises: In the case that the back-to-source node device has the back-to-source condition and is an origin station device, the CDN edge node device saves the corresponding cache data after obtaining the corresponding cache data requested by the user from the local cache of the origin station device cache locally; In the case that the origin-returning node device has the origin-returning condition, and there is at least one node device that does not meet the origin-returning condition between the CDN edge node device and the origin-returning node device, the origin-returning node device The returned cached data is returned to each of the node devices that do not have the back-to-source condition in turn until it is returned to the CDN edge node device, and each of the node devices that do not have the back-to-source condition and the CDN edge node device will The cached data are stored in respective local caches. 7. A CDN back-to-source device, characterized in that it includes a back-to-source startup module and a back-to-source module located in the content distribution network CDN edge node device, wherein: The back-to-source starting module is configured to, after the CDN edge node device receives the user request, if the corresponding cached data requested by the user is not found in the local cache of the CDN edge node device, The upper-level node device of the above-mentioned CDN edge node device is used as the back-to-source node device for back-to-source; The origin-returning module is configured to forward the user request to the origin-returning node device when it is determined that the origin-returning node device meets the origin-returning node device, and obtain the request from the local cache of the origin-returning node device The user requests corresponding cached data to be returned to the user. 8. The CDN back-to-source device according to claim 7, wherein the back-to-source module is also used for: In the case that the origin-returning node device does not meet the origin-returning condition, the origin-returning from the origin-returning node device is stopped. 9. The CDN back-to-source device according to claim 7, wherein the back-to-source module is also used for: In the case that the origin-returning node device does not have the origin-returning condition, and there is at least one level of node device between the CDN edge node device and the origin station device, the upper-level node of the current origin-returning node device The device is updated as a back-to-source node device, and based on whether the updated back-to-source node device meets the back-to-source conditions, it is judged whether it is necessary to update the back-to-source node device until the updated back-to-source node device meets the back-to-source conditions or the source station device is updated to Back to the source node device. 10. The CDN back-to-origin device according to claim 7, further comprising a back-to-origin judging module disposed in the back-to-origin node device or the CDN edge node device, the back-to-origin judging module comprising: A condition acquisition submodule, configured to acquire the service domain name corresponding to the user request, and acquire at least one source-returning IP configured for the service domain name in the source-returning node device; The first judging submodule is used to determine whether the total number of parallel requests sent to each of the source-backing IPs is greater than the first request number threshold for each configured source-backing IP, and to confirm that the request is sent to each of the source-backing IPs. When the total number of parallel requests is greater than the first request number threshold, it is determined that the back-to-source node device does not meet the back-to-source conditions; The second judging submodule is used to further judge all the configured back-to-source IPs through the service domain name when the total number of parallel requests sent to any one of the back-to-source IPs is not greater than the first request number threshold Whether the total number of parallel requests sent is greater than the second threshold of requests; when it is confirmed that the total number of parallel requests sent to all configured back-to-source IPs through the business domain name is greater than the second threshold of requests, it is determined that the back-to-source node device is not The back-to-source condition is met; when it is confirmed that the total number of parallel requests sent to all the configured back-to-source IPs through the business domain name is not greater than the second request threshold, it is determined that the back-to-source node device meets the back-to-source condition. 11. The CDN back-to-source device according to claim 7, further comprising a first update module installed in the back-to-source node device, and/or set in the CDN edge node device, and each without a back-to-source A second update module within the node device of the condition, wherein: The first update module is configured to update the total number of parallel requests sent to the origin-returning IP while the origin-returning node device performs the origin-returning through a certain origin-returning IP, and update the number of requests passed through the service domain name The total number of parallel requests sent to all configured back-to-source IPs; after returning the cached data corresponding to the user request to the CDN edge node device through the back-to-source IP, mark the back-to-source corresponding to the user request Responded; update the total number of parallel requests sent to the source IP, and update the total number of parallel requests sent to all configured source IPs through the business domain name; The second update module installed in the CDN edge node device is used to obtain the corresponding cached data requested by the user from the local cache of the origin-returning node device when the origin-returning node device meets the origin-returning condition , save the corresponding cached data in the local cache; The second update module installed in each node device that does not have the back-to-source condition, where the back-to-source node device has the back-to-source condition, and there is at least one non-returning node device between the CDN edge node device and the back-to-source node device. In the case of a node device having the back-to-source condition, the cached data returned by the back-to-source node device is stored in respective local caches.

Images