CN106375153A - Schedulability analysis method for real-time communication on network-on-chip - Google Patents

Abstract

The invention discloses a schedulability analysis method for real-time communication on a network-on-chip. The method comprises the following steps: taking a stream with the highest priority among streams that are not analyzed as a target stream; searching a direct interference stream, the direct interference stream having high priority and sharing link resources on a routing path of the target stream; searching an indirect interference stream and a downstream indirect interference stream of the indirect interference stream, wherein the indirect interference stream is the stream that has high priority, shares the link resources with the direct interference stream on a direct interference stream path of the target stream and does not share the link resources with the target stream, and the indirect interference stream is divided into an upstream indirect interference stream and the downstream indirect interference stream according to a relative position in which the indirect interference stream and the direct interference stream share the link resources; calculating the maximum indirect interference and the maximum downstream indirect interference; and calculating the maximum time delay of the target stream. The method makes a distinction between different effects of the upstream indirect interference stream and the downstream indirect interference stream upon the target stream when analyzing and calculating the maximum time delay of the target stream, thereby ensuring correctness of schedulability analysis for real-time communication on the network-on-chip.

Description

A kind of Schedulability Analysis method of real-time Communication for Power in network-on-chip

Technical field

The invention belongs to integrated circuit network-on-chip communication technical field, more particularly, to real in a kind of network-on-chip The Schedulability Analysis method of Shi Tongxin.

Background technology

Compared to non-realtime traffic, real-time Communication for Power, except requiring to transmit the logical correctness of result, also requires transmission delay Less than or equal to predetermined threshold value, to ensure service quality (quality of service, abbreviation qos).For critical system, If when running, real-time Communication for Power fails to meet corresponding predetermined threshold value, and result will be catastrophic.Therefore, in design Can the stage meet corresponding predetermined threshold value to real-time Communication for Power streams all in network-on-chip and verify, you can the analysis of scheduling property, It is particularly important.

For this problem, it is published in the tenth ieee/acm international symposium in 2008 " the real-time communication analysis for of the 161-170 page of networks-on-chip international conference On-chip networks with wormhole switching " uses Real-Time Scheduling analysis theories, establishes a model (hereinafter referred to as sb model) analyzing the maximum delay of each target stream, this model is easy to calculate, but is the introduction of excessive Non-existent interference, leads to that calculated maximum delay is excessive, and schedulability is too low.It is published in " ieee transactions On computers " 1177-1190 page of the 4th phase of volume 64 in 2015 " sla:a stage-level latency Analysis for real-time communication in a pipelined resource model " proposes one kind More fine-grained model (hereinafter referred to as sla model), introduce in model before can removing to a certain extent does not exist Interference so that the maximum delay being calculated and schedulability are closer to reality, but this model improves calculating Complexity.Meanwhile, the maximum delay that above-mentioned model calculates may be less than time delay in practice, by original non-scheduling Stream be considered to dispatch, real-time system causes catastrophic effect.

Content of the invention

Disadvantages described above for prior art or Improvement requirement, the invention provides real-time Communication for Power in a kind of network-on-chip Schedulability Analysis method, it is intended that the disturbance raw to target miscarriage to indirect interference stream by distinguishing upstream and downstream Effect, based on Real-Time Scheduling analysis theories, analysis obtains and actual schedulability result that be consistent, correct, thus solving Determine and may produce the technical problem of error analysis results in existing model.

For achieving the above object, according to one aspect of the present invention, there is provided in a kind of network-on-chip, real-time Communication for Power can Scheduling property analysis method, comprises the following steps:

Step a: the stream of limit priority in the stream do not analyzed in network-on-chip is defined as target stream；

Step b: the high priority flows of shared link resource are found on the routed path of target stream, and as direct Interference stream；

Step c: on the direct interference flow path of target stream, will with direct interference stream shared link resource, but not with mesh The high priority flows of mark stream shared link resource are defined as indirectly disturbing stream, share chain according to indirect interference stream with direct interference stream Indirect interference stream is divided into upstream and indirectly disturbs stream and downstream indirectly to disturb stream by the relative position of road resource；

Step d: stream is indirectly disturbed according to direct interference stream, upstream and downstream indirectly disturb the maximum interference indirectly of stream calculation and Maximum downstream is disturbed indirectly；

Step e: indirectly disturb i according to maximum_jiIndirectly disturb with maximum downstreamCalculate the maximum delay of target stream；

Step f: judge whether the maximum delay of target stream is less than or equal to predetermined threshold value, the value of this threshold value is according to clothes Business level protocol determines, if it is repeat step a to f is till all of stream is all disposed in the network-on-chip, no Then represent that the real-time Communication for Power in this network-on-chip can not be scheduled, process terminates.

Preferably, in step b, if there are one or more streams on the routed path of target stream, its priority ratio target The priority of stream is high, then this stream is just considered high priority flows.

Preferably, interference stream includes direct interference stream and indirect interference stream, and direct interference adfluxion is closedWherein, i and j is numbering, λ_iAnd λ_jIt is respectively target stream and direct interference Stream,WithIt is respectively λ_iAnd λ_jRouted path on link circuit resource set, p_iAnd p_jIt is respectively λ_iAnd λ_jPriority.

Preferably, if high priority flows refer to there is one or many on the routed path of direct interference stream in step c Individual stream, the priority of its priority ratio direct interference stream is high, then this stream is just considered high priority flows.

Preferably, in step c, interference adfluxion is closed indirectly Wherein k is numbering, λ_kFor indirect interference stream, upstream disturbs adfluxion to close indirectlyDownstream disturbs adfluxion to close indirectlyWherein, f_jiAnd f_jkIt is respectively λ_iAnd λ_kWith λ_jShared Article one, link is in λ_jRouted path on numbering.

Preferably, maximum interference i indirectly_jiIndirectly disturb with maximum downstreamIt is respectively as follows:

i_ji=r_j-c_j

$i_{ji}^d=\underset{{\mathrm{\λ}}_k\&element;s_{i_i}^{d_j}}{\mathrm{\σ}}{i}_{kj}$

Wherein, c_jFor λ_jMaximum delay when not being interfered, i_kjFor λ_kTo λ_jThe interference producing, r_jFor λ_jMaximum Time delay, its computing formula is as follows:

Wherein, t_kFor λ_kMiddle minimum is given out a contract for a project interval, c_kFor λ_kMaximum delay when not being interfered, j_kFor λ_kBetween giving out a contract for a project Every time jitter.

Preferably, in step e, the maximum delay computing formula of target stream is:

In general, by the contemplated above technical scheme of the present invention compared with prior art, can obtain down and show Beneficial effect:

(1) present invention can solve the problem that in existing model, mistake in the calculating due to maximum delay, leads to appearance in system This problem of catastrophic effect: due to employing step c, d and e, indirect interference stream is divided into upstream further and indirectly disturbs Stream is disturbed indirectly in stream and downstream, thus calculate maximum downstream indirectly disturbing, and applies to the calculating of maximum delay, therefore, it is possible to Revise mistake in computation present in existing model, obtain the Schedulability Analysis knot of real-time real-time Communication for Power in correct network-on-chip Really.

(2) present invention ensure that upstream disturbs stream and downstream indirectly to disturb the accuracy of stream differentiation indirectly: in step c In, flow, using indirect interference, first that first link shared with direct interference stream and direct interference stream are shared with target stream Relative position between link, as judgment condition, can quickly and accurately be distinguished upstream and indirectly disturb stream and downstream indirect Interference stream.

(3) present invention can solve correctly maximum downstream and indirectly disturb: in step d, by indirectly doing to downstream The flow-disturbing interference raw to direct interference miscarriage is sued for peace it is ensured that the result being obtained is indirect not less than downstream in any case Interference, i.e. maximum interference indirectly.

(4) calculating speed of the inventive method is fast, efficiency high.

Brief description

Fig. 1 is the flow chart of the Schedulability Analysis method of real-time Communication for Power in network-on-chip of the present invention；

Fig. 2 is the network-on-chip containing 5 real-time Communication for Power streams.

Specific embodiment

In order that the objects, technical solutions and advantages of the present invention become more apparent, below in conjunction with drawings and Examples, right The present invention is further elaborated.It should be appreciated that specific embodiment described herein is only in order to explain the present invention, and It is not used in the restriction present invention.As long as additionally, involved technical characteristic in each embodiment of invention described below The conflict of not constituting each other just can be mutually combined.

As shown in figure 1, the Schedulability Analysis method of real-time Communication for Power comprises the following steps in network-on-chip of the present invention:

Step a: the stream of limit priority in the stream do not analyzed in network-on-chip is defined as target stream；

Step b: the high priority flows of shared link resource are found on the routed path of target stream, and as direct Interference stream；Specifically, if one or more streams are existed on the routed path of target stream, its priority ratio target stream preferential Level is high, then this stream is just considered high priority flows；

Interference flow point is direct interference stream and indirect interference stream.Direct interference adfluxion is closedWherein, i and j is numbering, λ_iAnd λ_jIt is respectively target stream and direct interference Stream,WithIt is respectively λ_iAnd λ_jRouted path on link circuit resource set, p_iAnd p_jIt is respectively λ_iAnd λ_jPriority.

Step c: on the direct interference flow path of target stream, will with direct interference stream shared link resource, but not with mesh The high priority flows of mark stream shared link resource are defined as indirectly disturbing stream, share chain according to indirect interference stream with direct interference stream Indirect interference stream is divided into upstream and indirectly disturbs stream and downstream indirectly to disturb stream by the relative position of road resource；Specifically, originally The high priority flows being previously mentioned in step, if referring to there are one or more streams on the routed path of direct interference stream, its The priority of priority ratio direct interference stream is high, then this stream is just considered high priority flows；

Interference adfluxion is closed indirectlyWherein k is to compile Number, λ_kFor indirect interference stream.Indirectly interference stream according to the relative position with direct interference stream shared link resource be divided into upstream and Stream is disturbed in downstream indirectly.Upstream disturbs adfluxion to close indirectly Downstream disturbs adfluxion to close indirectlyWherein, f_jiAnd f_jkRespectively For λ_iAnd λ_kWith λ_jFirst shared link is in λ_jRouted path on numbering (one stream routed path on link compile Number along stream direction of advance from 1 beginning incremented by successively).Specifically, if indirect disturb stream and direct interference stream to share Article first, first link upstream that link is shared with target stream in direct interference stream, then this indirect interference is flowed and is indirectly done for upstream Flow-disturbing；Conversely, then indirectly disturbing stream for downstream.

Step d: stream is indirectly disturbed according to direct interference stream, upstream and downstream indirectly disturb the maximum interference indirectly of stream calculation and Maximum downstream is disturbed indirectly；

Maximum interference i indirectly_jiIndirectly disturb with maximum downstreamIt is respectively as follows:

i_ji=r_j-c_j

$i_{ji}^d=\underset{{\mathrm{\λ}}_k\&element;s_{i_i}^{d_j}}{\mathrm{\σ}}{i}_{kj}$

Wherein, c_jFor λ_jMaximum delay when not being interfered, i_kjFor λ_kTo λ_jThe interference producing, r_jFor λ_jMaximum Time delay, its computing formula is as follows:

Wherein, t_kFor λ_kMiddle minimum is given out a contract for a project interval, c_kFor λ_kMaximum delay when not being interfered, j_kFor λ_kBetween giving out a contract for a project Every time jitter.

Step e: indirectly disturb i according to maximum_jiIndirectly disturb with maximum downstreamCalculate the maximum delay of target stream；

The maximum delay computing formula of target stream is

Step f: judge whether the maximum delay of target stream is less than or equal to predetermined threshold value, the value of this threshold value is according to clothes Business level protocol (service level agreement) determines, if it is repeat step a to f, until in network-on-chip Till all of stream is all disposed, otherwise represent that the real-time Communication for Power in this network-on-chip can not be scheduled, process terminates.

First, embodiment:

Taking five real-time Communication for Power streams in Fig. 2 as a example, deriving analysis schedulability calculating process.It is 5 real-time streams in table 1 Parameter, wherein, c_i、t_i、p_i、d_iAnd j_iRespectively flow corresponding noiseless maximum delay, minimum is given out a contract for a project interval, priority, default Threshold value and the shake at interval of giving out a contract for a project.

Table 1

Because the quantity of real-time streams in the present embodiment is 5, therefore the process of the present invention should include 5 cyclic processes, Specific as follows:

(1) circulate for the first time:

Step a: the stream of limit priority in the stream do not analyzed in network-on-chip is defined as target stream.

The stream do not analyzed in network-on-chip has λ₁、λ₂、λ₃、λ₄And λ₅, wherein λ₁Highest priority.Therefore, λ₁For target Stream.

Step b: the high priority flows of shared link resource are found on the routed path of target stream, and as direct Interference stream.

For λ₁, there is not direct interference stream,

Step c: on the direct interference flow path of target stream, will with direct interference stream shared link resource, but not with mesh The high priority flows of mark stream shared link resource are defined as indirectly disturbing stream, share chain according to indirect interference stream with direct interference stream Indirect interference stream is divided into upstream and indirectly disturbs stream and downstream indirectly to disturb stream by the relative position of road resource.

For λ₁, there is not indirect interference stream, also in the absence of trip interference stream indirectly,

Step d: stream is indirectly disturbed according to direct interference stream, upstream and downstream indirectly disturb the maximum interference indirectly of stream calculation and Maximum downstream is disturbed indirectly.

For λ₁, interference is 0 indirectly for maximum interference indirectly and downstream.

Step e: indirectly disturb i according to maximum_jiIndirectly disturb with maximum downstreamCalculate the maximum delay of target stream.

For λ₁, maximum delay is r₁=c₁=30.

Step f: judge that whether the maximum delay of target stream is less than or equal to predetermined threshold value, if it is repeat step a is extremely F, till all of stream is all disposed in the network-on-chip, otherwise represents that in this network-on-chip, real-time Communication for Power can not be adjusted Degree, process terminates.

For λ₁, r₁=30 ＜ d₁=100, less than predetermined threshold value, also have the stream do not analyzed, therefore repeat step a extremely simultaneously f.

(2) circulate for second:

Step a: the stream of limit priority in the stream do not analyzed in network-on-chip is defined as target stream.

The stream do not analyzed in network-on-chip has λ₂、λ₃、λ₄And λ₅, wherein λ₂Highest priority.Therefore, λ₂For target stream.

Step b: the high priority flows of shared link resource are found on the routed path of target stream, and as direct Interference stream.

For λ₂, there is not direct interference stream,

Step c: on the direct interference flow path of target stream, will with direct interference stream shared link resource, but not with mesh The high priority flows of mark stream shared link resource are defined as indirectly disturbing stream, share chain according to indirect interference stream with direct interference stream Indirect interference stream is divided into upstream and indirectly disturbs stream and downstream indirectly to disturb stream by the relative position of road resource.

For λ₂, there is not indirect interference stream, also in the absence of trip interference stream indirectly,

Step d: stream is indirectly disturbed according to direct interference stream, upstream and downstream indirectly disturb the maximum interference indirectly of stream calculation and Maximum downstream is disturbed indirectly.

For λ₂, interference is 0 indirectly for maximum interference indirectly and downstream.

Step e: indirectly disturb i according to maximum_jiIndirectly disturb with maximum downstreamCalculate the maximum delay of target stream.

For λ₂, maximum delay is r₂=c₂=30.

Step f: judge that whether the maximum delay of target stream is less than or equal to predetermined threshold value, if it is repeat step a is extremely F, till all of stream is all disposed in the network-on-chip, otherwise represents that in this network-on-chip, real-time Communication for Power can not be adjusted Degree, process terminates.

For λ₂, r₂=30 ＜ d₂=100, less than predetermined threshold value, also have the stream do not analyzed, therefore repeat step a extremely simultaneously f.

(3) third time circulates:

Step a: the stream of limit priority in the stream do not analyzed in network-on-chip is defined as target stream.

The stream do not analyzed in network-on-chip has λ₃、λ₄And λ₅, wherein λ₃Highest priority.Therefore, λ₃For target stream.

Step b: the high priority flows of shared link resource are found on the routed path of target stream, and as direct Interference stream.

For λ₃, direct interference adfluxion is combined into

Step c: on the direct interference flow path of target stream, will with direct interference stream shared link resource, but not with mesh The high priority flows of mark stream shared link resource are defined as indirectly disturbing stream, share chain according to indirect interference stream with direct interference stream Indirect interference stream is divided into upstream and indirectly disturbs stream and downstream indirectly to disturb stream by the relative position of road resource.

For λ₃, there is not indirect interference stream, also in the absence of trip interference stream indirectly,

Step d: stream is indirectly disturbed according to direct interference stream, upstream and downstream indirectly disturb the maximum interference indirectly of stream calculation and Maximum downstream is disturbed indirectly.

For λ₃, interference is 0 indirectly for maximum interference indirectly and downstream,

Step e: indirectly disturb i according to maximum_jiIndirectly disturb with maximum downstreamCalculate the maximum delay of target stream.

For λ₃, maximum delay isSolve r₃=270.

Step f: judge that whether the maximum delay of target stream is less than or equal to predetermined threshold value, if it is repeat step a is extremely F, till all of stream is all disposed in the network-on-chip, otherwise represents that in this network-on-chip, real-time Communication for Power can not be adjusted Degree, process terminates.

For λ₃, r₃=270 ＜ d₃=300, less than predetermined threshold value, also have the stream do not analyzed, therefore repeat step a simultaneously To f.

(4) the 4th circulations:

Step a: the stream of limit priority in the stream do not analyzed in network-on-chip is defined as target stream.

The stream do not analyzed in network-on-chip has λ₄And λ₅, wherein λ₄Highest priority.Therefore, λ₄For target stream.

Step b: the high priority flows of shared link resource are found on the routed path of target stream, and as direct Interference stream.

For λ₄, direct interference adfluxion is combined into

Step c: on the direct interference flow path of target stream, will with direct interference stream shared link resource, but not with mesh The high priority flows of mark stream shared link resource are defined as indirectly disturbing stream, share chain according to indirect interference stream with direct interference stream Indirect interference stream is divided into upstream and indirectly disturbs stream and downstream indirectly to disturb stream by the relative position of road resource.

For λ₄, indirectly disturb adfluxion to be combined intoWith λ₁The direct interference stream of shared link is λ₃, due to f₃₁= 1 ＜ f₃₄=5, therefore λ₁Indirectly disturb stream for upstream, in the absence of trip indirectly interference stream,

Step d: stream is indirectly disturbed according to direct interference stream, upstream and downstream indirectly disturb the maximum interference indirectly of stream calculation and Maximum downstream is disturbed indirectly.

For λ₄, maximum disturbs indirectly as i₂₄=0 and i₃₄=120, maximum downstream is disturbed as 0 indirectly,

Step e: indirectly disturb i according to maximum_jiIndirectly disturb with maximum downstreamCalculate the maximum delay of target stream.

For λ₄, maximum delay isSolve r₄=340.

Step f: judge that whether the maximum delay of target stream is less than or equal to predetermined threshold value, if it is repeat step a is extremely F, till all of stream is all disposed in the network-on-chip, otherwise represents that in this network-on-chip, real-time Communication for Power can not be adjusted Degree, process terminates.

For λ₄, r₄=340 ＜ d₄=550, less than predetermined threshold value, also have the stream do not analyzed, therefore repeat step a simultaneously To f.

(5) the 5th circulations:

Step a: the stream of limit priority in the stream do not analyzed in network-on-chip is defined as target stream.

The stream do not analyzed in network-on-chip has λ₅, wherein λ₅Highest priority.Therefore, λ₅For target stream.

Step b: the high priority flows of shared link resource are found on the routed path of target stream, and as direct Interference stream.

For λ₅, direct interference adfluxion is combined into,

Step c: on the direct interference flow path of target stream, will with direct interference stream shared link resource, but not with mesh The high priority flows of mark stream shared link resource are defined as indirectly disturbing stream, share chain according to indirect interference stream with direct interference stream Indirect interference stream is divided into upstream and indirectly disturbs stream and downstream indirectly to disturb stream by the relative position of road resource.

For λ₅, indirectly disturb adfluxion to be combined intoWith λ₁And λ₂The direct interference stream of shared link is λ₃, Due to f₃₁=1 ＜ f₃₅=2 ＜ f₃₂=5, therefore λ₁Indirectly disturb stream, λ for upstream₂Indirectly disturb stream for downstream, downstream is disturbed indirectly Adfluxion is combined into

Step d: stream is indirectly disturbed according to direct interference stream, upstream and downstream indirectly disturb the maximum interference indirectly of stream calculation and Maximum downstream is disturbed indirectly.

For λ₅, maximum disturbs indirectly as i₃₅=120, maximum downstream is indirectly disturbed and is

Step e: indirectly disturb i according to maximum_jiIndirectly disturb with maximum downstreamCalculate the maximum delay of target stream.

For λ₅, maximum delay isSolve r₅=310.

Step f: judge that whether the maximum delay of target stream is less than or equal to predetermined threshold value, if it is repeat step a is extremely F, till all of stream is all disposed in the network-on-chip, otherwise represents that in this network-on-chip, real-time Communication for Power can not be adjusted Degree, process terminates.

For λ₅, r₂=310 ＜ d₅=260, more than predetermined threshold value, analysis terminates, and under this set of circumstances, this piece is surfed the Net In network, real-time Communication for Power can not be scheduled.

2nd, respectively examples detailed above is analyzed using sb model and sla model.

3rd, interpretation of result contrast:

Table 2

The analysis result of sb model, sla model and the inventive method, and the reality obtaining by emulation is listed in table 2 Test data.Simulation result shows, sb model and sla model have all obtained wrong analysis result, and the inventive method is correctly Analyze the schedulability of real-time Communication for Power in this network-on-chip under this set of circumstances.

As it will be easily appreciated by one skilled in the art that the foregoing is only presently preferred embodiments of the present invention, not in order to Limit the present invention, all any modification, equivalent and improvement made within the spirit and principles in the present invention etc., all should comprise Within protection scope of the present invention.

Claims (7)

1. in a kind of network-on-chip the Schedulability Analysis method of real-time Communication for Power it is characterised in that comprising the following steps:

Step a: the stream of limit priority in the stream do not analyzed in network-on-chip is defined as target stream；

Step b: the high priority flows of shared link resource are found on the routed path of target stream, and as direct interference Stream；

Step c: on the direct interference flow path of target stream, will with direct interference stream shared link resource, but not with target stream The high priority flows of shared link resource are defined as indirectly disturbing stream, according to indirect interference stream and direct interference stream shared link money Indirect interference stream is divided into upstream and indirectly disturbs stream and downstream indirectly to disturb stream by the relative position in source；

Step d: indirectly disturb stream and downstream indirectly to disturb the maximum interference indirectly of stream calculation and maximum according to direct interference stream, upstream Downstream is disturbed indirectly；

Step e: indirectly disturb i according to maximum_jiIndirectly disturb with maximum downstreamCalculate the maximum delay of target stream；

Step f: judge whether the maximum delay of target stream is less than or equal to predetermined threshold value, the value of this threshold value is according to service etc. Level agreement determines, if it is repeat step a to f, till all of stream is all disposed in the network-on-chip, otherwise table Show that the real-time Communication for Power in this network-on-chip can not be scheduled, process terminates.

2. Schedulability Analysis method according to claim 1 is it is characterised in that in step b, if the route of target stream One or more streams are existed on path, the priority of its priority ratio target stream is high, then this stream is just considered high priority flows.

3. Schedulability Analysis method according to claim 1 it is characterised in that interference stream include direct interference stream and Connect interference stream, direct interference adfluxion is closedWherein, i and j is numbering, λ_iAnd λ_j It is respectively target stream and direct interference stream,WithIt is respectively λ_iAnd λ_jRouted path on link circuit resource set, p_iAnd p_j It is respectively λ_iAnd λ_jPriority.

4. Schedulability Analysis method according to claim 3 is it is characterised in that in step c, be previously mentioned in this step High priority flows, if referring to there are one or more streams on the routed path of direct interference stream, its priority ratio is directly done The priority of flow-disturbing is high, then this stream is just considered high priority flows.

5. Schedulability Analysis method according to claim 4 is it is characterised in that in step c, interference adfluxion is closed indirectlyWherein k is numbering, λ_kFor indirect interference stream, upstream Interference adfluxion is closed indirectlyDownstream disturbs adfluxion to close indirectlyWherein, f_jiAnd f_jkIt is respectively λ_iAnd λ_kWith λ_jShared Article one, link is in λ_jRouted path on numbering.

6. Schedulability Analysis method according to claim 5 is it is characterised in that maximum disturb i indirectly_jiWith maximum downstream Indirectly disturbIt is respectively as follows:

i_ji=r_j-c_j

$i_{ji}^d=\underset{{\mathrm{\λ}}_k\&element;s_{i_i}^{d_j}}{\σ}{i}_{kj}$

Wherein, c_jFor λ_jMaximum delay when not being interfered, i_kjFor λ_kTo λ_jThe interference producing, r_jFor λ_jMaximum prolong When, its computing formula is as follows:

Wherein, t_kFor λ_kMiddle minimum is given out a contract for a project interval, c_kFor λ_kMaximum delay when not being interfered, j_kFor λ_kGive out a contract for a project interval Time jitter.

7. Schedulability Analysis method according to claim 6 it is characterised in that in step e target stream maximum delay Computing formula is: