Traffic Management for the Available Bit Rate (ABR) Service in ...
Traffic Management for the Available Bit Rate (ABR) Service in ... Traffic Management for the Available Bit Rate (ABR) Service in ...
Figure 5.2: Transmitted cell rate (controlled) and O ered Average Cell Rate (measured). only increase LAF. Increasing the LAF corresponds to decreasing the allowed source rate. Hence, successive switches only reduce the rate allowed to the source. Thus, the source receives the rate allowed by the bottleneck along the path 4. Averaging interval (AI): The OSU scheme primarily uses measured quantities instead of parameters for control. These quantities are measured at the source (eg., OCR) and the switch (eg., current load level z discussed in section 5.1.3). The measurements are done over intervals (called \averaging intervals") to smoothen out the variance in these quantities. To ensure coorelation of the measured quantities at the switch and at the source, we require the source av- eraging intervals to be the maximum of the averaging interval of the switches along the path. This maximum value is returned in the AI eld. The AI eld is initialized to zero at the source. 5. The direction of feedback (backward/forward) 6. Timestamp containing the time at which the control cell was generated at the source 97
The last two elds are used in the backward congestion noti cation option described in Section 5.2.8 and need not be present if that option is not used. 5.1.2 The Source Algorithm The source algorithm consists of three components: 1. How often to send control cells 2. How to measure the o ered average cell rate 3. How to respond to the feedback received from the network These three questions are answered in the next three subsections. Control-Cell Sending Algorithm The sources send a control cell into the network every T microseconds. The source initializes all the elds. The network reads only the OCR, LAF and AI elds and modi es only the LAF and AI elds. The TCR eld is used by the source to calculate the new TCR as discussed in the next section. LAF and AI are both initialized to zero as discussed earlier. The initialization of the OCR and TCR elds are discussed in the next section. Measuring O ered Average Load Unlike any other scheme proposed so far, each source also measures its own load. The measurement isdoneoverthesameaveraging interval that is used for sending the control cells. The transmission cell rate (TCR), as de ned, is the inverse of minimum inter-cell transmission time at the source. However, when the source is not always 98
- Page 73 and 74: mention this concept of fairness fo
- Page 75 and 76: control problem was also simpler. S
- Page 77 and 78: of such an occurrence is expected t
- Page 79 and 80: y giving only one feedback per meas
- Page 81 and 82: CHAPTER 4 SURVEY OF ATM SWITCH CONG
- Page 83 and 84: The adaptive FCVC algorithm [63] co
- Page 85 and 86: np. Thus, long path VCs have fewer
- Page 87 and 88: networks like ATM can have complete
- Page 89 and 90: scheme followed by a discussion of
- Page 91 and 92: exibility of decoupling the enforce
- Page 93 and 94: 4.6.1 Key Techniques In EPRCA, the
- Page 95 and 96: If the mean ACR is not a good estim
- Page 97 and 98: is the ratio of the input rate to t
- Page 99 and 100: which shares the link equally as al
- Page 101 and 102: proportional to the the unused ABR
- Page 103 and 104: The key technique in the scheme is
- Page 105 and 106: the bandwidth allocations to satis
- Page 107 and 108: 4.10 DMRCA scheme The Dynamic Max R
- Page 109 and 110: on its CCR. Further MAX times out i
- Page 111 and 112: other words, a di erent set of para
- Page 113 and 114: A combination of several ideas in a
- Page 115 and 116: 4.13 SP-EPRCA scheme The SP-EPRCA s
- Page 117 and 118: RTD and shuts o the source (for sta
- Page 119 and 120: 4.14.1 Common Drawbacks Though the
- Page 121 and 122: The ATM Tra c Management standard a
- Page 123: 5.1.1 Control-Cell Format The contr
- Page 127 and 128: Figure 5.3: Flow chart for updating
- Page 129 and 130: LAF in cell Max(LAF in cell, z) The
- Page 131 and 132: the time of departure (instant mark
- Page 133 and 134: the steady state. The system operat
- Page 135 and 136: 5.2.3 Use Measured Rather Than Decl
- Page 137 and 138: said about the maximum queue length
- Page 139 and 140: The key problem with some unipolar
- Page 141 and 142: Figure 5.6: Space time diagram show
- Page 143 and 144: As noted, these heuristics do not g
- Page 145 and 146: Transmitted Cell Rate ABR Queue Len
- Page 147 and 148: 4. The RM cell contains a timestamp
- Page 149 and 150: 1. The source o ered average cell r
- Page 151 and 152: Transmitted Cell Rate Link Utilizat
- Page 153 and 154: Transmitted Cell Rate Link Utilizat
- Page 155 and 156: Transmitted Cell Rate Link Utilizat
- Page 157 and 158: Figure 5.17: The parking lot fairne
- Page 159 and 160: Figure 5.19: Network con guration w
- Page 161 and 162: Transmitted Cell Rate Link Utilizat
- Page 163 and 164: Transmitted Cell Rate Link Utilizat
- Page 165 and 166: 5.8 Proof: Fairness Algorithm Impro
- Page 167 and 168: Region 2: y s and x s and U(1 + ) x
- Page 169 and 170: eing divided into eight non-overlap
- Page 171 and 172: Proof for Region 2 Triangular regio
- Page 173 and 174: have: and y 0 = y(1 ; ) z x + y 0 =
The last two elds are used <strong>in</strong> <strong>the</strong> backward congestion noti cation option described<br />
<strong>in</strong> Section 5.2.8 and need not be present if that option is not used.<br />
5.1.2 The Source Algorithm<br />
The source algorithm consists of three components:<br />
1. How often to send control cells<br />
2. How to measure <strong>the</strong> o ered average cell rate<br />
3. How to respond to <strong>the</strong> feedback received from <strong>the</strong> network<br />
These three questions are answered <strong>in</strong> <strong>the</strong> next three subsections.<br />
Control-Cell Send<strong>in</strong>g Algorithm<br />
The sources send a control cell <strong>in</strong>to <strong>the</strong> network every T microseconds. The source<br />
<strong>in</strong>itializes all <strong>the</strong> elds. The network reads only <strong>the</strong> OCR, LAF and AI elds and<br />
modi es only <strong>the</strong> LAF and AI elds. The TCR eld is used by <strong>the</strong> source to calculate<br />
<strong>the</strong> new TCR as discussed <strong>in</strong> <strong>the</strong> next section.<br />
LAF and AI are both <strong>in</strong>itialized to zero as discussed earlier. The <strong>in</strong>itialization of<br />
<strong>the</strong> OCR and TCR elds are discussed <strong>in</strong> <strong>the</strong> next section.<br />
Measur<strong>in</strong>g O ered Average Load<br />
Unlike any o<strong>the</strong>r scheme proposed so far, each source also measures its own load.<br />
The measurement isdoneover<strong>the</strong>sameaverag<strong>in</strong>g <strong>in</strong>terval that is used <strong>for</strong> send<strong>in</strong>g <strong>the</strong><br />
control cells. The transmission cell rate (TCR), as de ned, is <strong>the</strong> <strong>in</strong>verse of m<strong>in</strong>imum<br />
<strong>in</strong>ter-cell transmission time at <strong>the</strong> source. However, when <strong>the</strong> source is not always<br />
98