CA2281399C - High speed weighted fair queuing system for atm switches - Google Patents
High speed weighted fair queuing system for atm switches Download PDFInfo
- Publication number
- CA2281399C CA2281399C CA002281399A CA2281399A CA2281399C CA 2281399 C CA2281399 C CA 2281399C CA 002281399 A CA002281399 A CA 002281399A CA 2281399 A CA2281399 A CA 2281399A CA 2281399 C CA2281399 C CA 2281399C
- Authority
- CA
- Canada
- Prior art keywords
- bins
- bin
- connection
- potential
- sorting
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Expired - Fee Related
Links
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L47/00—Traffic control in data switching networks
- H04L47/50—Queue scheduling
- H04L47/62—Queue scheduling characterised by scheduling criteria
- H04L47/6215—Individual queue per QOS, rate or priority
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L47/00—Traffic control in data switching networks
- H04L47/50—Queue scheduling
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L47/00—Traffic control in data switching networks
- H04L47/50—Queue scheduling
- H04L47/52—Queue scheduling by attributing bandwidth to queues
- H04L47/522—Dynamic queue service slot or variable bandwidth allocation
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L47/00—Traffic control in data switching networks
- H04L47/50—Queue scheduling
- H04L47/62—Queue scheduling characterised by scheduling criteria
- H04L47/622—Queue service order
- H04L47/623—Weighted service order
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L47/00—Traffic control in data switching networks
- H04L47/50—Queue scheduling
- H04L47/62—Queue scheduling characterised by scheduling criteria
- H04L47/625—Queue scheduling characterised by scheduling criteria for service slots or service orders
- H04L47/6265—Queue scheduling characterised by scheduling criteria for service slots or service orders past bandwidth allocation
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L49/00—Packet switching elements
- H04L49/30—Peripheral units, e.g. input or output ports
- H04L49/3027—Output queuing
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L12/00—Data switching networks
- H04L12/54—Store-and-forward switching systems
- H04L12/56—Packet switching systems
- H04L12/5601—Transfer mode dependent, e.g. ATM
- H04L2012/5638—Services, e.g. multimedia, GOS, QOS
- H04L2012/5646—Cell characteristics, e.g. loss, delay, jitter, sequence integrity
- H04L2012/5651—Priority, marking, classes
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L12/00—Data switching networks
- H04L12/54—Store-and-forward switching systems
- H04L12/56—Packet switching systems
- H04L12/5601—Transfer mode dependent, e.g. ATM
- H04L2012/5678—Traffic aspects, e.g. arbitration, load balancing, smoothing, buffer management
- H04L2012/5679—Arbitration or scheduling
Abstract
Methods and apparatus for an ATM network for implementing a fair servicing of all connections during a back-logged condition through the use of a weighted fair queuing technique. The system is particularly suited for systems where the packets/cells ere of a fixed size. Although some important approximations are made in the proposed implementation, all of the properties of an ideal weighted fair queuing algorithm are preserved. The sorting methods and apparatus are advantageous in that it is possible to maintain appropriate servicing of connections without sorting all of the individual connections. This may be accomplished by pro-sorting each of the individual virtual circuit connections into a finite number of predetermined bins according to a weight associated with the connection. Thereafter, only the bins need be sorted without having to sort each of the individual connections. Further aspects of the invention include storing the bins in a matrix with an offset value dependent upon the current potential of the bin. In this manner, the overall sorting required to determine the next connection to service is substantially reduced. Accordingly, the invention is suitable for implementations having transmission speeds of multiple gigabits-per-second.
Description
HIGH SPEED WEIGHTED FAIR QUEUING SYSTEM FOR ATM SWITCHES
Field Of The Invention The invention relates generally to asynchronous transfer mode (ATM) network and, more particularly, to high speed weighted queuing systems for ATM
switches.
Background Weighted fair queuing, also known as packetized general processor sharing (PGPS), may be come important in the next generation of ATM switching system and routers in order to fairly share bandwidth while allowing for a guaranteed minimum delay to individual connections sharing a particular transmission facility. However, to date, the implementation of weighted fair queuing algorithms have been problematic and difficult to scale to a large number of connections. For example, in conventional weighted fair queuing, the complexity of an ideal implementation is 0(N) +0(logN) where N is the number of circuits, 0(N) represents the recalculation for all head-of line packets for all circuits, and 0(IogN) is the amount of calculations involved in resorting all of the reference finishing times. The next generation of ATM switches is expected to include tens of thousands of connections and operate at multi-gigabit rates.
Accordingly, a scalable, highly efficient implementation of a weighted fair queuing algorithm is necessary.
Summary Of The Invention The present invention provides improved algorithms for performing queuing in an ATM switch. In particular, the invention provides a highly efficient implementation of a weighted fair queuing algorithm in an ATM switch where the packets are of a fixed size.
Although some important approximations are made in the proposed implementation, all of the properties of an ideal weighted fair queuing algorithm are preserved.
The sorting algorithms in accordance with the present invention are advantageous in that it is possible to maintain appropriate servicing of connections without sorting all of the individual connections. This may be accomplished by presorting each of the individual virtual circuit connections into a finite number of predetermined bins according to a weight associated with the connection. Thereafter, only the bins need be sorted without having to sort each of the individual connections. Accordingly, the invention is suitable for implementations having transmission speeds of multiple gigabits-per-second.
In accordance with one aspect of the present invention there is provided a method of transmitting cells comprising: sorting cells associated with a plurality of virtual circuits into a plurality of bins dependent upon weights associated with the plurality of virtual circuits; sorting the bins based on connection potentials associated with the plurality of bins to determine which of the cells to transmit.
In accordance with another aspect of the present invention there is provided an ATM network comprising a plurality of ATM switches interconnected via a plurality of connections, each connection having one or more virtual circuits, each ATM
switch having a processor and a memory configured to sort incoming cells associated with the plurality of virtual circuits into a plurality of virtual circuit queues and for sorting the plurality of virtual circuit queues into a plurality of bins dependent upon weights associated with the plurality of virtual circuits, wherein cells are output from each of the ATM switches in accordance with connection potentials associated with the bins.
Brief Description of the Drawings The foregoing summary of the invention, as well as the following detailed description of preferred embodiments, is better understood when read in conjunction with the accompanying drawings, which are included by way of examples, and not by way of limitation with regard to the claimed invention.
Fig. 1 illustrates an embodiment of an ATM network.
Fig. 2 is a block diagram illustration of an embodiment of an output queue of an ATM switch.
Fig. 3 illustrates an embodiment of a mapping function.
2a Detailed Description of Preferred Embodiments Referring to F'ig. 1, an A'r149 network 1 muy include, for example, a plurality of interconnected ATM switches ATM A, ATM f3, and A'TNl C interconnecting one or :more pieces of equipment located on the customer's premises (e.g., customer premises equipment A (CPE A) and customer premises equipment B (,CPE 13)). The ATM network 1 may be configured to carry data over a wide area such as an entire country and/or globally. The data rate across the ATM network 1 is variable and data may be backed-up in one or more: queues in each of the ATM switches.
Each of tire individual ATM switches ATM A, .ATM E3, ATM C, array include an output queue for storing received cells prior to transmission on one or a plurality of output connections. Each output quoue may, from time to time, become back-logged due to congestion on a particular output connection. While the circuit is back-logged, cells cannot be sent out over the circuit without loss of the cell. Accordingly, cells for Chen 1-4-8 3 each of the various connections begin to build-up in the output queue. When capacity becomes available on the output connection, a choice must be made as to which cells to transmit. This choice may be made, for example, using one or more algorithms described below.
A first exemplary embodiment of the weighted fair queuing algorithm may store a connection potential Pi for each back-logged circuit. The connection potential Pi is the amount of service that the connection has received normalized to the weight of a particular connection. For any given instant in time for which service is available, the circuit with the minimum connection potential is services. When a circuit newly becomes back-logged, its potential must be initialized. This may be done by keeping track of a system potential Ps that is used for the initial value of Pi for any connection that newly becomes back-logged. TO maintain fairness, the system potential should always be kept within the range of the connection potentials of the back-logged connections.
In one exemplary embodiment, the connection potential of the circuit which newly becomes 1 S backlogged is set to be the connection potential of all other virtual circuits within the bin which have the same connection weight. Where the bin is empty, it may be desirable to set the connection potential of the virtual circuit to be: a) the average of the connection potentials of the two bins having the closest weight to the newly non-empty bin, b) the potential of the bin having the next lowest or next highest weight. The object is to service the connection with the lowest normalized past service (i.e., potential Pi). In this manner, the all connection are maintained to within a narrow normalized past service range and the system is fair.
An additional mechanism is needed for a new connection which has just been initiated. If the connection potential is set at zero, the new connection will receive all of the service. Accordingly, a weighting mechanism is required for new connections to assign an initialization potential to a new connection which is comparable to the existing connection potentials. Thereafter, the new connection is serviced like all other connections in accordance with its normalized connection potential. A
parameter Ps may Chen 1-4-8 a.
be utilized by the ATM switch to keep track of where the connection potentials are and to provide a reference for initializing the potentials of newly back-logged circuits.
Using the above described method, the complexity for sorting N connections is 0(logN) plus some overhead for updating the system potential. A further improvement may be made where there are only a finite number of discrete potentials such as when one cell is transmitted, the potential varies by a discrete amount.
Refernng to Fig. 2, in one exemplary embodiment the output queue 10 for a particular output connection 12 may have any number of bins (e.g., Bin X - Bin N). I~~
one exemplary embodiment, there are 64 bins which may correspond to 64 different weights. Thus, with reference to the description above, with 64 bins, the finite set of values for Wi is 64. Each bin may include a plurality of separate output queues VC
VCf, ..., each corresponding to a different virtual circuit to be output across output connection 12. Each of the separate output queues may contain one or more cells 14 waiting to be output on the output connection 12. Each virtual circuit VCa, VCb, ..., may be assigned a particular weight depending on the amount of relative service selected for a particular virtual circuit. In embodiments of the invention, virtual circuits with the same weight are assigned to the same Bin. For example, Bin 1 may include virtual circuits VCa, VCf, VCm, ..., VCq which may all have the same weight.
Similarly, Bin N
may include virtual circuit VCb, VCc, VCI, ..., VCt which also all may have the same weight. Each of the bins contain non-empty queues for virtual circuits having the sari-weight. The larger the weight of a virtual circuit, the more service may be associated with that virtual circuit. Thus, by pre-sorting virtual circuits with similar or equal weights into a predetermined number of bins, the overall performance of the switch may be substantially increased.
In the potential-based approach, every time a connection receives service (1 cell transmitted), its potential may be increased by 1/Wi, where Wi is its weight (i.e., the potential varies by a discrete amount). Where there are only a finite set of values for Wi, then for all connections with the same weight, their potentials are always incremented in the same fashion and intuitively, it is not necessary to keep track of the individual Chen 1-4-8 5 potentials and to sort them separately. In this manner, once a bin with the lowest potential is determined, it may be desirable to service all non-empty virtual circuits within that bin before resorting to find the bin with the new lowest potential. Where a empty virtual circuit within a bin becomes non-empty during servicing of a particular bin, it may be desirable to not service that virtual circuit until a new potential is recalculated. For example, where there are K different weights allowed, then the ATM switch may includC
K bins for each output connection 12. Within each bin, a linked-list of all the Vcs with weight Wk that are backlogged may be maintained. When a VC with weight Wk becomes newly backlogged, it joins the weight bin with weight Wk, meaning that the potential of this VC is initialized to the potential of all other VCs in this bin. This method may be more desirable (providing a tighter fairness bound) than other methods for updating the system potential. In exemplary embodiments, a potential is determined for each bin. The bins are then sorted to find the bin having the minimum potential.
Whenever the k-th weight bin is found to have the minimum potential, all connections 1 S within the bin may be served once. In this manner, the problem is converted from one that depends on the number of connection to one that depends on the number of different weights that are allowed, and hence the efficiency of the sorting process is greatly enhanced. Additionally, it becomes possible for a switch with a given processing power to handle a much faster output connection with substantially more virtual circuits.
Sorting Of Lead-Bins Where we have a plurality of weighted bins, each being associated with one of a plurality of finite weights, it may be desirable to sort the bins to determine which order the bins should be serviced. Fig. 3 shows one example of the present invention for two bins: Bins l and Bin 2. Initially, all bins may have the same potential, e.g., potential =
zero, or a potential assigned according to the weight of the bin. In some implementations, on initialization, cells contained in bins having the higher weight may be serviced first. With respect to Fig. 3, since bin 2 has a higher weight, it may be desirable, upon initialization, to send one or more cells from each non-empty virtual circuit queue in Bin 2 to the output connection 12. For example, referring to Fig. 3 cells Chen 1-4-8 VCbI and VCcI are sent to the output connection 12 first. Thereafter a new potential is calculated for Bin 2 as the current potential (0) plus the distance (1/8) such that the new potential of Bin 2 = 1/8.
Since Bin 1 now has the smallest potential (potential = 0 which is less than 1/8), Bin 1 is serviced next with one or more cells (e.g., VCaI, VCfI) from each non-empty queue in Bin 1 being sent to the output connection 12. Thereafter the potential for Bin 1 is recalculated as the current potential (0) plus the distance (1/4) such that the new potential of Bin 1 = 1/4.
Next the potentials among all non-empty bins are resorted. Since Bin 2 has the lowest potential 1/8 versus'/4, all non-empty queues in Bin 2 may be serviced next (e.g., VCb2). Note there is no service of VCc since the queue associated with this virtual connection has become empty. Next, the new potential for Bin 2 is calculated as current potential (1.8) plus the distance (1.8) which is equal to 1/4.
Again the potential for all non-empty bins are resorted. Since Bin 1 and Bin 2 now have the same potential 1/4, it may be desirable to service all non-empty queues from both Bin 1 and Bin 2 prior to recalculating and resorting. For example, cells VCa2, VCf2, and VCb3 may be sent to the output connection 12. Thereafter, the potential ~i Bin l and Bin 2 may be recalculated. For Bin 1, the new potential is the current potential 1 /4 plus the distance 1 /4 which is equal to 1 /2. For Bin 2, the new potential is the current potential 1/4 plus the distance 1/8 which is equal to 3/8. Since Bin 2 now has the lowest potential, bin 2 is again serviced by sending VCb4. Once VCb4 has been sent, Bin 2 has become empty. Thereafter, Bin 1 will be serviced until Bin 2 again becomes non-empty.
As is apparent from the above operational description, since Bin 2 has the greater weight, Bin 2 receives the greatest amount of service with the service being proportional to the weight. Additionally, even though there may be four virtual connections with different numbers of cell waiting, the weighted fair queuing algorithm only needs to sort Chen 1-4-8 two different potentials to determine which virtual circuit queue to service next. Thus, a high efficient and yet fair algorithm is made possible.
Storage of Pii In yet further aspect of the invention, it is possible to further increase the efficiency of the algorithm by organizing the data associated with the bins in memory in a predetermined arrangement. For example, the above method requires the storage of the potential values for each of the individual bins. An alternative is to keep track of the system virtual time which is a reference potential from which all of the potentials of the bins may be offset by one or more values. In this manner, all potential values associated with the bins can then be compared as offsets to the system virtual time. The value of the offsets can be deducted from the system virtual time since the progression of the potential value for each of the bin is known. Also, any potential values for two or more bins which are tied across a row can be determined by a simple operation. This alternative method of sorting requires an efficient and accurate division of the system time t. Second t may grow without bound as long as the system stays busy.
(Only when the system goes) idle can t be reset to zero. When t becomes large, the division or multiplication (if high speed division is utilized to implement the table look-up) becomes complex. Also, straightforward wraparound of t it not acceptable and hence the values may need to be reset as the system approaches wrap-around condition. However, for suitable environments, the table based sorting based on offset from a system time is a highly efficient~solution for sorting the bins.
Although the sorting of lead bins in a matrix arrangement may be accomplished using any suitable sorting mechanism, a two dimensional structure and algorithm may be useful. Alternatively, a three dimensional structure and algorithm may be used to store bins which have a tied potential with bins having the tied potential stored in the third dimension. For simplicity, the example given below will be shown in a two dimensional format. In this example, d may be set to the reciprocal of the weight, i.e., d = 1/w. It may also be desirable to represent d by a floating point number with an n-bit mantissa and m-bit exponent forming the two sides of the matrix. As shown below, the bins may Chen 1-4-8 8 be arranged as a two-dimensional structure where d has a two bit mantissa and a two bit exponent:
(1.) 00 D00 DO1 D02 D03 (1.) Ol D10 D11 D12 D13 (1.) 10 D20 D21 D22 D23 (l.) 11 D30 D31 D32 D33 00 Ol 10 11 _____>
Exponent In this arrangement, the bin in the upper left hand corner (or next full bin closest thereto) of the matrix is serviced first. Thereafter, a new potential is calculated for the bin and the bin is inserted into the matrix in an appropriate location for the new potential. Thus, there is no need to resort all of the bins, only to store the bin in the appropriate location in the matrix. Accordingly, the processing necessary to determine the bin with the least potential is substantially reduced.
In an exemplary embodiment, a processor in the ATM switch may be configured with a memory implementing the matrix arrangement described above. Although the matrix may be accessed and maintained in any suitable manner to accomplish the above function, one technique is described below.
Chen 1-4-8 9 If k > j, then Pij less than or equal to Pik at all times Where t is the potential of the bin being serviced, alter all non-empty weight bins with potential t are served, the system must find the next ~~~
of non-empty weight bin(s)) with the minimum potential to serve.
For row i, consider K = ceiling (t/l.i) (Using the shorthand notiation above (l.i)) If k is divisible by 2' , where r is an integer, then Pir = Pi(r-1 ) Otherwise, Pir > Pi(r-1 ) Since if k is divisible by 2', it is disisible by 2~r-'~, consequently:
Pir = pi(r-1) = Pi(r-2) _ .... = Pi0 In exemplary embodiments in accordance with this aspect of the invention, it is not necessary to sort all of the weighted bins. For example, it is suf~'icient to sort the first non-empty weight bin in each row. Where there are ties, it may be desirable to serve all of the tied bins. Further, it may be desirable to determine all non-empty bins in each winning row that are tied with the winning lead bin (i.e., the first non-empty bin on that row). Finding all the bins that are tied with the lead bin in a row is on the order of one operation since all that is required is to check the weight of the next non-empty bin Bim in row i to see if it is a tie with the first non-empty bin. If it is, then we serve bin Bim and check if Bim' (where Bim' is the next non-empty bin) is a tie with Bim.
Otherwise, we are done and sort the lead bins of all rows again. Note that where the bins are presorted, since if Bim is not tied with Bij, no subsequent bin Bik, k>m can be tied with Bij.
Chen 1-4-8 to In exemplary embodiments of the table based sorting method described above, the first step is to represent the potential for each bin as a floating point number having a mantissa and an exponent. The next step is to organize all of the bins in a memory of the ATM switch into rows (each having the same mantissa value) and columns (each having the same exponent value. In organizing the bins, it may be desirable to organize each row such that each adjacent column has a higher potential (or equal potential for a two dimensional matrix) than the preceding column in the same row. In this manner, only the lead bins in each row need be sorted. Bins with the largest weight (smallest distance) may be organized first in the row/column with bins with the smallest weight (largest distance) organized last in the rows/columns. The next step is to sort the first non-empty bin (lead bin) of each row in terms of potential. Once the table has been sorted as defined above, the next step is to service the lead bins in each of the rows and then to serve all of the non-empty bins with the same potential as the lead bin.
Thereafter, the potential for each of the serviced bins is recalculated, and the serviced bins are inserted into the table in an appropriate location. In this manner, the amount of sorting is reduced by the square root of the number of bins and the number of register loads are also decreased.
Pseudo-Code Exemplary embodiments of the present invention may be performed using methods and system as described above. In one embodiment, the methods and systems of the present-invention may be described using the following pseudo code:
Start:
System virtual time t = potential if bin currently being served Queue To Serve = the VC queue to be served L(i,j) = the linked list of all non-empty VC queues in weight bin Bij (We assume that a single bit comparator is used to quickly determine the lead bin, i.e., the first non-empty bin of each row.
Chen 1-4-8 11 Cell Arrival:
Put Cell into VC in Bin Bij based on weight of VE
If VC Queue has been empty link this VC Queue to Linked List L(ij) If Bin Bij is Empty then initialize Pij to ceiling[t/Dij]*Dij (In an alternate embodiment, Pij may simply be initialized to t, in which case it may be desirable to test for Pim >=Pij, m>j, Bim, Bij both non-empty to decide if we need to serve the next bin in a row. This should simply introduce an additional inaccuracy in potential initialization. As discussed above, the division t/Dij may grow to be problematic where the queue remains full of extended periods of time and the division makes the wraparound of t may be come more complex such that the remainder will need to be tracked for each wraparound operation.) Cell Departure:
1 S Send a Cell from Queue To Serve in weight Bin being Served Bkl If VC Queue becomes empty remove it from Link List of VC Queues in Bkl If VC Queue is not tail of L(k,l) Queue To Serve = next VC Queue in linked list L(k.l) else Find next non-empty bin Bkm on row k If Pkl >=Pkm then {Queue To-Serve = Head of L(k,m);
Pkl <- Okl + Dkl return }
else { Pkl <- Pkl + Dkl Chen 1-4-8 12 Sort lead fin of all rows;
QueueToServe = Head of L of the winning bin }
While exemplary systems and methods embodying the present invention are shown by way of example, it will be understood, of course, that the invention is not limited to these embodiments. Modifications may be made by those skilled in light of the foregoing teachings. For example, it will be well known in the art that a processor in each of the ATM switches in Fig. 1 implements the algorithms discussed herein.
Further, each of the steps of the aforementioned embodiments may be utilized alone or in combination with steps of the other embodiments.
Field Of The Invention The invention relates generally to asynchronous transfer mode (ATM) network and, more particularly, to high speed weighted queuing systems for ATM
switches.
Background Weighted fair queuing, also known as packetized general processor sharing (PGPS), may be come important in the next generation of ATM switching system and routers in order to fairly share bandwidth while allowing for a guaranteed minimum delay to individual connections sharing a particular transmission facility. However, to date, the implementation of weighted fair queuing algorithms have been problematic and difficult to scale to a large number of connections. For example, in conventional weighted fair queuing, the complexity of an ideal implementation is 0(N) +0(logN) where N is the number of circuits, 0(N) represents the recalculation for all head-of line packets for all circuits, and 0(IogN) is the amount of calculations involved in resorting all of the reference finishing times. The next generation of ATM switches is expected to include tens of thousands of connections and operate at multi-gigabit rates.
Accordingly, a scalable, highly efficient implementation of a weighted fair queuing algorithm is necessary.
Summary Of The Invention The present invention provides improved algorithms for performing queuing in an ATM switch. In particular, the invention provides a highly efficient implementation of a weighted fair queuing algorithm in an ATM switch where the packets are of a fixed size.
Although some important approximations are made in the proposed implementation, all of the properties of an ideal weighted fair queuing algorithm are preserved.
The sorting algorithms in accordance with the present invention are advantageous in that it is possible to maintain appropriate servicing of connections without sorting all of the individual connections. This may be accomplished by presorting each of the individual virtual circuit connections into a finite number of predetermined bins according to a weight associated with the connection. Thereafter, only the bins need be sorted without having to sort each of the individual connections. Accordingly, the invention is suitable for implementations having transmission speeds of multiple gigabits-per-second.
In accordance with one aspect of the present invention there is provided a method of transmitting cells comprising: sorting cells associated with a plurality of virtual circuits into a plurality of bins dependent upon weights associated with the plurality of virtual circuits; sorting the bins based on connection potentials associated with the plurality of bins to determine which of the cells to transmit.
In accordance with another aspect of the present invention there is provided an ATM network comprising a plurality of ATM switches interconnected via a plurality of connections, each connection having one or more virtual circuits, each ATM
switch having a processor and a memory configured to sort incoming cells associated with the plurality of virtual circuits into a plurality of virtual circuit queues and for sorting the plurality of virtual circuit queues into a plurality of bins dependent upon weights associated with the plurality of virtual circuits, wherein cells are output from each of the ATM switches in accordance with connection potentials associated with the bins.
Brief Description of the Drawings The foregoing summary of the invention, as well as the following detailed description of preferred embodiments, is better understood when read in conjunction with the accompanying drawings, which are included by way of examples, and not by way of limitation with regard to the claimed invention.
Fig. 1 illustrates an embodiment of an ATM network.
Fig. 2 is a block diagram illustration of an embodiment of an output queue of an ATM switch.
Fig. 3 illustrates an embodiment of a mapping function.
2a Detailed Description of Preferred Embodiments Referring to F'ig. 1, an A'r149 network 1 muy include, for example, a plurality of interconnected ATM switches ATM A, ATM f3, and A'TNl C interconnecting one or :more pieces of equipment located on the customer's premises (e.g., customer premises equipment A (CPE A) and customer premises equipment B (,CPE 13)). The ATM network 1 may be configured to carry data over a wide area such as an entire country and/or globally. The data rate across the ATM network 1 is variable and data may be backed-up in one or more: queues in each of the ATM switches.
Each of tire individual ATM switches ATM A, .ATM E3, ATM C, array include an output queue for storing received cells prior to transmission on one or a plurality of output connections. Each output quoue may, from time to time, become back-logged due to congestion on a particular output connection. While the circuit is back-logged, cells cannot be sent out over the circuit without loss of the cell. Accordingly, cells for Chen 1-4-8 3 each of the various connections begin to build-up in the output queue. When capacity becomes available on the output connection, a choice must be made as to which cells to transmit. This choice may be made, for example, using one or more algorithms described below.
A first exemplary embodiment of the weighted fair queuing algorithm may store a connection potential Pi for each back-logged circuit. The connection potential Pi is the amount of service that the connection has received normalized to the weight of a particular connection. For any given instant in time for which service is available, the circuit with the minimum connection potential is services. When a circuit newly becomes back-logged, its potential must be initialized. This may be done by keeping track of a system potential Ps that is used for the initial value of Pi for any connection that newly becomes back-logged. TO maintain fairness, the system potential should always be kept within the range of the connection potentials of the back-logged connections.
In one exemplary embodiment, the connection potential of the circuit which newly becomes 1 S backlogged is set to be the connection potential of all other virtual circuits within the bin which have the same connection weight. Where the bin is empty, it may be desirable to set the connection potential of the virtual circuit to be: a) the average of the connection potentials of the two bins having the closest weight to the newly non-empty bin, b) the potential of the bin having the next lowest or next highest weight. The object is to service the connection with the lowest normalized past service (i.e., potential Pi). In this manner, the all connection are maintained to within a narrow normalized past service range and the system is fair.
An additional mechanism is needed for a new connection which has just been initiated. If the connection potential is set at zero, the new connection will receive all of the service. Accordingly, a weighting mechanism is required for new connections to assign an initialization potential to a new connection which is comparable to the existing connection potentials. Thereafter, the new connection is serviced like all other connections in accordance with its normalized connection potential. A
parameter Ps may Chen 1-4-8 a.
be utilized by the ATM switch to keep track of where the connection potentials are and to provide a reference for initializing the potentials of newly back-logged circuits.
Using the above described method, the complexity for sorting N connections is 0(logN) plus some overhead for updating the system potential. A further improvement may be made where there are only a finite number of discrete potentials such as when one cell is transmitted, the potential varies by a discrete amount.
Refernng to Fig. 2, in one exemplary embodiment the output queue 10 for a particular output connection 12 may have any number of bins (e.g., Bin X - Bin N). I~~
one exemplary embodiment, there are 64 bins which may correspond to 64 different weights. Thus, with reference to the description above, with 64 bins, the finite set of values for Wi is 64. Each bin may include a plurality of separate output queues VC
VCf, ..., each corresponding to a different virtual circuit to be output across output connection 12. Each of the separate output queues may contain one or more cells 14 waiting to be output on the output connection 12. Each virtual circuit VCa, VCb, ..., may be assigned a particular weight depending on the amount of relative service selected for a particular virtual circuit. In embodiments of the invention, virtual circuits with the same weight are assigned to the same Bin. For example, Bin 1 may include virtual circuits VCa, VCf, VCm, ..., VCq which may all have the same weight.
Similarly, Bin N
may include virtual circuit VCb, VCc, VCI, ..., VCt which also all may have the same weight. Each of the bins contain non-empty queues for virtual circuits having the sari-weight. The larger the weight of a virtual circuit, the more service may be associated with that virtual circuit. Thus, by pre-sorting virtual circuits with similar or equal weights into a predetermined number of bins, the overall performance of the switch may be substantially increased.
In the potential-based approach, every time a connection receives service (1 cell transmitted), its potential may be increased by 1/Wi, where Wi is its weight (i.e., the potential varies by a discrete amount). Where there are only a finite set of values for Wi, then for all connections with the same weight, their potentials are always incremented in the same fashion and intuitively, it is not necessary to keep track of the individual Chen 1-4-8 5 potentials and to sort them separately. In this manner, once a bin with the lowest potential is determined, it may be desirable to service all non-empty virtual circuits within that bin before resorting to find the bin with the new lowest potential. Where a empty virtual circuit within a bin becomes non-empty during servicing of a particular bin, it may be desirable to not service that virtual circuit until a new potential is recalculated. For example, where there are K different weights allowed, then the ATM switch may includC
K bins for each output connection 12. Within each bin, a linked-list of all the Vcs with weight Wk that are backlogged may be maintained. When a VC with weight Wk becomes newly backlogged, it joins the weight bin with weight Wk, meaning that the potential of this VC is initialized to the potential of all other VCs in this bin. This method may be more desirable (providing a tighter fairness bound) than other methods for updating the system potential. In exemplary embodiments, a potential is determined for each bin. The bins are then sorted to find the bin having the minimum potential.
Whenever the k-th weight bin is found to have the minimum potential, all connections 1 S within the bin may be served once. In this manner, the problem is converted from one that depends on the number of connection to one that depends on the number of different weights that are allowed, and hence the efficiency of the sorting process is greatly enhanced. Additionally, it becomes possible for a switch with a given processing power to handle a much faster output connection with substantially more virtual circuits.
Sorting Of Lead-Bins Where we have a plurality of weighted bins, each being associated with one of a plurality of finite weights, it may be desirable to sort the bins to determine which order the bins should be serviced. Fig. 3 shows one example of the present invention for two bins: Bins l and Bin 2. Initially, all bins may have the same potential, e.g., potential =
zero, or a potential assigned according to the weight of the bin. In some implementations, on initialization, cells contained in bins having the higher weight may be serviced first. With respect to Fig. 3, since bin 2 has a higher weight, it may be desirable, upon initialization, to send one or more cells from each non-empty virtual circuit queue in Bin 2 to the output connection 12. For example, referring to Fig. 3 cells Chen 1-4-8 VCbI and VCcI are sent to the output connection 12 first. Thereafter a new potential is calculated for Bin 2 as the current potential (0) plus the distance (1/8) such that the new potential of Bin 2 = 1/8.
Since Bin 1 now has the smallest potential (potential = 0 which is less than 1/8), Bin 1 is serviced next with one or more cells (e.g., VCaI, VCfI) from each non-empty queue in Bin 1 being sent to the output connection 12. Thereafter the potential for Bin 1 is recalculated as the current potential (0) plus the distance (1/4) such that the new potential of Bin 1 = 1/4.
Next the potentials among all non-empty bins are resorted. Since Bin 2 has the lowest potential 1/8 versus'/4, all non-empty queues in Bin 2 may be serviced next (e.g., VCb2). Note there is no service of VCc since the queue associated with this virtual connection has become empty. Next, the new potential for Bin 2 is calculated as current potential (1.8) plus the distance (1.8) which is equal to 1/4.
Again the potential for all non-empty bins are resorted. Since Bin 1 and Bin 2 now have the same potential 1/4, it may be desirable to service all non-empty queues from both Bin 1 and Bin 2 prior to recalculating and resorting. For example, cells VCa2, VCf2, and VCb3 may be sent to the output connection 12. Thereafter, the potential ~i Bin l and Bin 2 may be recalculated. For Bin 1, the new potential is the current potential 1 /4 plus the distance 1 /4 which is equal to 1 /2. For Bin 2, the new potential is the current potential 1/4 plus the distance 1/8 which is equal to 3/8. Since Bin 2 now has the lowest potential, bin 2 is again serviced by sending VCb4. Once VCb4 has been sent, Bin 2 has become empty. Thereafter, Bin 1 will be serviced until Bin 2 again becomes non-empty.
As is apparent from the above operational description, since Bin 2 has the greater weight, Bin 2 receives the greatest amount of service with the service being proportional to the weight. Additionally, even though there may be four virtual connections with different numbers of cell waiting, the weighted fair queuing algorithm only needs to sort Chen 1-4-8 two different potentials to determine which virtual circuit queue to service next. Thus, a high efficient and yet fair algorithm is made possible.
Storage of Pii In yet further aspect of the invention, it is possible to further increase the efficiency of the algorithm by organizing the data associated with the bins in memory in a predetermined arrangement. For example, the above method requires the storage of the potential values for each of the individual bins. An alternative is to keep track of the system virtual time which is a reference potential from which all of the potentials of the bins may be offset by one or more values. In this manner, all potential values associated with the bins can then be compared as offsets to the system virtual time. The value of the offsets can be deducted from the system virtual time since the progression of the potential value for each of the bin is known. Also, any potential values for two or more bins which are tied across a row can be determined by a simple operation. This alternative method of sorting requires an efficient and accurate division of the system time t. Second t may grow without bound as long as the system stays busy.
(Only when the system goes) idle can t be reset to zero. When t becomes large, the division or multiplication (if high speed division is utilized to implement the table look-up) becomes complex. Also, straightforward wraparound of t it not acceptable and hence the values may need to be reset as the system approaches wrap-around condition. However, for suitable environments, the table based sorting based on offset from a system time is a highly efficient~solution for sorting the bins.
Although the sorting of lead bins in a matrix arrangement may be accomplished using any suitable sorting mechanism, a two dimensional structure and algorithm may be useful. Alternatively, a three dimensional structure and algorithm may be used to store bins which have a tied potential with bins having the tied potential stored in the third dimension. For simplicity, the example given below will be shown in a two dimensional format. In this example, d may be set to the reciprocal of the weight, i.e., d = 1/w. It may also be desirable to represent d by a floating point number with an n-bit mantissa and m-bit exponent forming the two sides of the matrix. As shown below, the bins may Chen 1-4-8 8 be arranged as a two-dimensional structure where d has a two bit mantissa and a two bit exponent:
(1.) 00 D00 DO1 D02 D03 (1.) Ol D10 D11 D12 D13 (1.) 10 D20 D21 D22 D23 (l.) 11 D30 D31 D32 D33 00 Ol 10 11 _____>
Exponent In this arrangement, the bin in the upper left hand corner (or next full bin closest thereto) of the matrix is serviced first. Thereafter, a new potential is calculated for the bin and the bin is inserted into the matrix in an appropriate location for the new potential. Thus, there is no need to resort all of the bins, only to store the bin in the appropriate location in the matrix. Accordingly, the processing necessary to determine the bin with the least potential is substantially reduced.
In an exemplary embodiment, a processor in the ATM switch may be configured with a memory implementing the matrix arrangement described above. Although the matrix may be accessed and maintained in any suitable manner to accomplish the above function, one technique is described below.
Chen 1-4-8 9 If k > j, then Pij less than or equal to Pik at all times Where t is the potential of the bin being serviced, alter all non-empty weight bins with potential t are served, the system must find the next ~~~
of non-empty weight bin(s)) with the minimum potential to serve.
For row i, consider K = ceiling (t/l.i) (Using the shorthand notiation above (l.i)) If k is divisible by 2' , where r is an integer, then Pir = Pi(r-1 ) Otherwise, Pir > Pi(r-1 ) Since if k is divisible by 2', it is disisible by 2~r-'~, consequently:
Pir = pi(r-1) = Pi(r-2) _ .... = Pi0 In exemplary embodiments in accordance with this aspect of the invention, it is not necessary to sort all of the weighted bins. For example, it is suf~'icient to sort the first non-empty weight bin in each row. Where there are ties, it may be desirable to serve all of the tied bins. Further, it may be desirable to determine all non-empty bins in each winning row that are tied with the winning lead bin (i.e., the first non-empty bin on that row). Finding all the bins that are tied with the lead bin in a row is on the order of one operation since all that is required is to check the weight of the next non-empty bin Bim in row i to see if it is a tie with the first non-empty bin. If it is, then we serve bin Bim and check if Bim' (where Bim' is the next non-empty bin) is a tie with Bim.
Otherwise, we are done and sort the lead bins of all rows again. Note that where the bins are presorted, since if Bim is not tied with Bij, no subsequent bin Bik, k>m can be tied with Bij.
Chen 1-4-8 to In exemplary embodiments of the table based sorting method described above, the first step is to represent the potential for each bin as a floating point number having a mantissa and an exponent. The next step is to organize all of the bins in a memory of the ATM switch into rows (each having the same mantissa value) and columns (each having the same exponent value. In organizing the bins, it may be desirable to organize each row such that each adjacent column has a higher potential (or equal potential for a two dimensional matrix) than the preceding column in the same row. In this manner, only the lead bins in each row need be sorted. Bins with the largest weight (smallest distance) may be organized first in the row/column with bins with the smallest weight (largest distance) organized last in the rows/columns. The next step is to sort the first non-empty bin (lead bin) of each row in terms of potential. Once the table has been sorted as defined above, the next step is to service the lead bins in each of the rows and then to serve all of the non-empty bins with the same potential as the lead bin.
Thereafter, the potential for each of the serviced bins is recalculated, and the serviced bins are inserted into the table in an appropriate location. In this manner, the amount of sorting is reduced by the square root of the number of bins and the number of register loads are also decreased.
Pseudo-Code Exemplary embodiments of the present invention may be performed using methods and system as described above. In one embodiment, the methods and systems of the present-invention may be described using the following pseudo code:
Start:
System virtual time t = potential if bin currently being served Queue To Serve = the VC queue to be served L(i,j) = the linked list of all non-empty VC queues in weight bin Bij (We assume that a single bit comparator is used to quickly determine the lead bin, i.e., the first non-empty bin of each row.
Chen 1-4-8 11 Cell Arrival:
Put Cell into VC in Bin Bij based on weight of VE
If VC Queue has been empty link this VC Queue to Linked List L(ij) If Bin Bij is Empty then initialize Pij to ceiling[t/Dij]*Dij (In an alternate embodiment, Pij may simply be initialized to t, in which case it may be desirable to test for Pim >=Pij, m>j, Bim, Bij both non-empty to decide if we need to serve the next bin in a row. This should simply introduce an additional inaccuracy in potential initialization. As discussed above, the division t/Dij may grow to be problematic where the queue remains full of extended periods of time and the division makes the wraparound of t may be come more complex such that the remainder will need to be tracked for each wraparound operation.) Cell Departure:
1 S Send a Cell from Queue To Serve in weight Bin being Served Bkl If VC Queue becomes empty remove it from Link List of VC Queues in Bkl If VC Queue is not tail of L(k,l) Queue To Serve = next VC Queue in linked list L(k.l) else Find next non-empty bin Bkm on row k If Pkl >=Pkm then {Queue To-Serve = Head of L(k,m);
Pkl <- Okl + Dkl return }
else { Pkl <- Pkl + Dkl Chen 1-4-8 12 Sort lead fin of all rows;
QueueToServe = Head of L of the winning bin }
While exemplary systems and methods embodying the present invention are shown by way of example, it will be understood, of course, that the invention is not limited to these embodiments. Modifications may be made by those skilled in light of the foregoing teachings. For example, it will be well known in the art that a processor in each of the ATM switches in Fig. 1 implements the algorithms discussed herein.
Further, each of the steps of the aforementioned embodiments may be utilized alone or in combination with steps of the other embodiments.
Claims (20)
1. A method of transmitting cells comprising:
sorting cells associated with a plurality of virtual circuits into a plurality of bins dependent upon weights associated with the plurality of virtual circuits;
sorting the bins based on connection potentials associated with the plurality of bins to determine which of the cells to transmit.
sorting cells associated with a plurality of virtual circuits into a plurality of bins dependent upon weights associated with the plurality of virtual circuits;
sorting the bins based on connection potentials associated with the plurality of bins to determine which of the cells to transmit.
2. The method of claim 1 including storing the connection potential for each of the bins which contain at least one back-logged virtual circuit.
3. The method of claim 1 including initializing a newly back-logged virtual circuit to a connection potential matching connection potentials of other virtual circuits having the same weight.
4. The method of claim 1 including servicing all non-empty virtual circuits within a first of the plurality of bins having the lowest of the connection potentials prior to sorting the plurality of bins.
5. The method of claim 4 including servicing all non-empty virtual circuits within a second of the plurality of bins when the connection potential of the second bin is the same as the connection potential of the first of the plurality of bins.
6. The method of claim 4 comprising adjusting the connection potential of the first of the plurality of bins by an amount proportional to an inverse of the weight associated with the bin.
7. The method of claim 1 wherein sorting includes sorting using a two-dimensional matrix where bins are organized according to their associated connection potentials.
8. An ATM network comprising a plurality of ATM switches interconnected via a plurality of connections, each connection having one or more virtual circuits, each ATM
switch having a processor and a memory configured to sort incoming cells associated with the plurality of virtual circuits into a plurality of virtual circuit queues and for sorting the plurality of virtual circuit queues into a plurality of bins dependent upon weights associated with the plurality of virtual circuits, wherein cells are output from each of the ATM switches in accordance with connection potentials associated with the bins.
switch having a processor and a memory configured to sort incoming cells associated with the plurality of virtual circuits into a plurality of virtual circuit queues and for sorting the plurality of virtual circuit queues into a plurality of bins dependent upon weights associated with the plurality of virtual circuits, wherein cells are output from each of the ATM switches in accordance with connection potentials associated with the bins.
9. The ATM network of claim 8 wherein the processor and memory are configured to service all virtual circuits associated with a single bin having the lowest of the connection potentials.
10. The ATM network of claim 9 wherein the processor and memory are configured to sort the bins to determine a new first bin with a connection potential lower than all other bins after at least one cell is sent from each virtual circuit within a first bin which currently has a connection potential lower than or equal to all other bins.
11. An ATM switch having a processor and a memory configured to sort incoming cells associated with a plurality of virtual circuits into a plurality of virtual circuit queues and for sorting the plurality of virtual circuit queues into a plurality of bins dependent upon weights associated with the plurality of virtual circuits, wherein cells are output from each of the ATM switches in accordance with connection potentials associated with the bins.
12. The method of claim 1, wherein each of the connection potentials indicates an amount of service received by one or more of the cells in the associated bin.
13. The ATM network of claim 8, wherein each of the connection potentials indicates an amount of service received by one or more of the cells in the associated bin.
14. The ATM switch of claim 11, wherein each of the connection potentials indicates an amount of service received by one or more of the cells in the associated bin.
15. The method of claim 1 wherein each of the bins is associated with two or more of the virtual circuits.
16. The ATM network of claim 8, wherein each of the bins is associated with two or more of the virtual circuits.
17. The ATM switch of claim 11, wherein each of the bins is associated with two or more of the virtual circuits.
18. The ATM network of claim 9, wherein the processor and memory are configured to adjust the connection potential of the single bin by an amount proportional to an inverse of its weight.
19. The ATM switch of claim 11, wherein the processor and memory are configured to service all virtual circuits associated with a single bin having the lowest connection potential.
20. The ATM switch of claim 19, wherein the processor and memory are configured to adjust the connection of the single bin by an amount proportional to an inverse of its weight.
Applications Claiming Priority (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| US09/153,352 US6829218B1 (en) | 1998-09-15 | 1998-09-15 | High speed weighted fair queuing system for ATM switches |
| US09/153,352 | 1998-09-15 |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CA2281399A1 CA2281399A1 (en) | 2000-03-15 |
| CA2281399C true CA2281399C (en) | 2005-11-08 |
Family
ID=22546847
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CA002281399A Expired - Fee Related CA2281399C (en) | 1998-09-15 | 1999-09-02 | High speed weighted fair queuing system for atm switches |
Country Status (4)
| Country | Link |
|---|---|
| US (2) | US6829218B1 (en) |
| EP (1) | EP1021060B1 (en) |
| CA (1) | CA2281399C (en) |
| DE (1) | DE69940592D1 (en) |
Families Citing this family (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7284111B1 (en) | 2002-04-17 | 2007-10-16 | Dinochip, Inc. | Integrated multidimensional sorter |
| GB0226249D0 (en) * | 2002-11-11 | 2002-12-18 | Clearspeed Technology Ltd | Traffic handling system |
| US7362765B1 (en) * | 2003-12-15 | 2008-04-22 | Dinochip, Inc. | Network traffic management system with floating point sorter |
| US7352697B1 (en) | 2004-06-23 | 2008-04-01 | Dinochip, Inc. | Network processing using fractional time stamp values |
| US7801164B2 (en) * | 2006-04-27 | 2010-09-21 | Agere Systems Inc. | Two dimensional timeout table mechanism with optimized delay characteristics |
| US8165033B1 (en) | 2007-08-30 | 2012-04-24 | Altera Corporation | Method and apparatus for performing generalized processor sharing scheduling |
| US8462802B2 (en) * | 2010-09-13 | 2013-06-11 | Juniper Networks, Inc. | Hybrid weighted round robin (WRR) traffic scheduling |
Family Cites Families (37)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US4616359A (en) | 1983-12-19 | 1986-10-07 | At&T Bell Laboratories | Adaptive preferential flow control for packet switching system |
| EP0487235B1 (en) | 1990-11-21 | 1999-02-03 | AT&T Corp. | Bandwidth and congestion management in accessing broadband ISDN networks |
| US5179556A (en) | 1991-08-02 | 1993-01-12 | Washington University | Bandwidth management and congestion control scheme for multicast ATM networks |
| JPH06169320A (en) | 1992-10-02 | 1994-06-14 | Toshiba Corp | Atm cell making device |
| FI92361C (en) * | 1992-12-14 | 1994-10-25 | Nokia Telecommunications Oy | Procedure for controlling overload situations in a frame switching network and a node for a frame switching network |
| US5457687A (en) | 1993-09-02 | 1995-10-10 | Network Equipment Technologies, Inc. | Method and apparatus for backward explicit congestion notification (BECN) in an ATM network |
| GB2288096B (en) | 1994-03-23 | 1999-04-28 | Roke Manor Research | Apparatus and method of processing bandwidth requirements in an ATM switch |
| US5583861A (en) | 1994-04-28 | 1996-12-10 | Integrated Telecom Technology | ATM switching element and method having independently accessible cell memories |
| KR0161613B1 (en) | 1994-09-02 | 1998-12-01 | 가나이 쓰토무 | Atm interface and shaping method |
| US5535201A (en) | 1995-05-10 | 1996-07-09 | Mitsubishi Electric Research Laboratories, Inc. | Traffic shaping system using two dimensional timing chains |
| US5675576A (en) | 1995-06-05 | 1997-10-07 | Lucent Technologies Inc. | Concestion control system and method for packet switched networks providing max-min fairness |
| EP0748086A1 (en) | 1995-06-09 | 1996-12-11 | Siemens Aktiengesellschaft | Method for scheduling message cells leaving an ATM node |
| US5737314A (en) | 1995-06-16 | 1998-04-07 | Hitachi, Ltd. | ATM exchange, ATM multiplexer and network trunk apparatus |
| US5805577A (en) | 1995-07-20 | 1998-09-08 | Jain; Raj | Erica: explicit rate indication for congestion avoidance in ATM networks |
| KR0147136B1 (en) | 1995-11-04 | 1998-08-17 | 양승택 | Equipment and method for congestion control in atm network |
| JP2723097B2 (en) | 1995-12-04 | 1998-03-09 | 日本電気株式会社 | QOS routing device |
| US5689508A (en) * | 1995-12-21 | 1997-11-18 | Xerox Corporation | Reservation ring mechanism for providing fair queued access in a fast packet switch networks |
| US5737313A (en) | 1996-03-15 | 1998-04-07 | Nec Usa, Inc. | Design of a closed loop feed back control for ABR service |
| US5812527A (en) | 1996-04-01 | 1998-09-22 | Motorola Inc. | Simplified calculation of cell transmission rates in a cell based netwook |
| US5859835A (en) * | 1996-04-15 | 1999-01-12 | The Regents Of The University Of California | Traffic scheduling system and method for packet-switched networks |
| US5754530A (en) | 1996-04-18 | 1998-05-19 | Northern Telecom Limited | Flow control of ABR traffic in ATM networks |
| JP2927340B2 (en) | 1996-05-15 | 1999-07-28 | 日本電気株式会社 | Rate control method in ATM network |
| US6064677A (en) * | 1996-06-27 | 2000-05-16 | Xerox Corporation | Multiple rate sensitive priority queues for reducing relative data transport unit delay variations in time multiplexed outputs from output queued routing mechanisms |
| US6064651A (en) * | 1996-06-27 | 2000-05-16 | Xerox Corporation | Rate shaping in per-flow output queued routing mechanisms for statistical bit rate service |
| US6038217A (en) * | 1996-06-27 | 2000-03-14 | Xerox Corporation | Rate shaping in per-flow output queued routing mechanisms for available bit rate (ABR) service in networks having segmented ABR control loops |
| US5901147A (en) | 1996-08-30 | 1999-05-04 | Mmc Networks, Inc. | Apparatus and methods to change thresholds to control congestion in ATM switches |
| US5959993A (en) | 1996-09-13 | 1999-09-28 | Lsi Logic Corporation | Scheduler design for ATM switches, and its implementation in a distributed shared memory architecture |
| US5949789A (en) * | 1996-11-21 | 1999-09-07 | Xerox Corporation | Arbitration ring for accessing a limited bandwidth switching network |
| US5805599A (en) | 1996-12-04 | 1998-09-08 | At&T Corp. | Adaptive channel allocation system for communication network |
| US6167030A (en) * | 1997-03-20 | 2000-12-26 | Nokia Telecommunications, Oy | Buffer-based traffic measurement system and method for nominal bit rate (NBR) service |
| US5864540A (en) * | 1997-04-04 | 1999-01-26 | At&T Corp/Csi Zeinet(A Cabletron Co.) | Method for integrated traffic shaping in a packet-switched network |
| FR2766592B1 (en) * | 1997-07-23 | 1999-08-27 | Bull Sa | DEVICE AND METHOD FOR DYNAMICALLY REGULATING THE ALLOCATION OF RESOURCES ON A COMPUTER SYSTEM |
| US5956340A (en) * | 1997-08-05 | 1999-09-21 | Ramot University Authority For Applied Research And Industrial Development Ltd. | Space efficient fair queuing by stochastic Memory multiplexing |
| US6408005B1 (en) * | 1997-09-05 | 2002-06-18 | Nec Usa, Inc. | Dynamic rate control scheduler for ATM networks |
| US6069872A (en) | 1997-11-20 | 2000-05-30 | Cabletron Systems, Inc. | Explicit rate congestion control system and method |
| US6091730A (en) * | 1998-03-30 | 2000-07-18 | Lucent Technologies Inc. | Control of asynchronous transfer mode (ATM) switching networks |
| US6198723B1 (en) * | 1998-04-14 | 2001-03-06 | Paxonet Communications, Inc. | Asynchronous transfer mode traffic shapers |
-
1998
- 1998-09-15 US US09/153,352 patent/US6829218B1/en not_active Expired - Fee Related
-
1999
- 1999-09-02 CA CA002281399A patent/CA2281399C/en not_active Expired - Fee Related
- 1999-09-07 DE DE69940592T patent/DE69940592D1/en not_active Expired - Lifetime
- 1999-09-07 EP EP99307086A patent/EP1021060B1/en not_active Expired - Lifetime
-
2004
- 2004-11-12 US US10/985,927 patent/US7817644B2/en not_active Expired - Fee Related
Also Published As
| Publication number | Publication date |
|---|---|
| EP1021060A3 (en) | 2003-01-02 |
| DE69940592D1 (en) | 2009-04-30 |
| US7817644B2 (en) | 2010-10-19 |
| CA2281399A1 (en) | 2000-03-15 |
| EP1021060A2 (en) | 2000-07-19 |
| EP1021060B1 (en) | 2009-03-18 |
| US20050083946A1 (en) | 2005-04-21 |
| US6829218B1 (en) | 2004-12-07 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US5956340A (en) | Space efficient fair queuing by stochastic Memory multiplexing | |
| EP0785699B1 (en) | Multicast routing in multistage networks | |
| US7418523B2 (en) | Operation of a multiplicity of time sorted queues with reduced memory | |
| US6810012B1 (en) | Queue service interval based cell schedular with hierarchical queuing configurations | |
| US5689500A (en) | Multistage network having multicast routing congestion feedback | |
| US5732087A (en) | ATM local area network switch with dual queues | |
| EP0785698B1 (en) | Buffering of multicast cells in switching networks | |
| US6259698B1 (en) | Input buffer controller using back-pressure signals in ATM switches and a method for determining the logical queue size | |
| AU4854799A (en) | System and method for switching packets in a network | |
| US7110358B1 (en) | Method and apparatus for managing data traffic between a high capacity source and multiple destinations | |
| US6694388B1 (en) | Dynamic queuing system incorporating multiple queues sharing a single memory | |
| US6510160B1 (en) | Accurate computation of percent utilization of a shared resource and fine resolution scaling of the threshold based on the utilization | |
| US6904047B2 (en) | Cell scheduling method of input and output buffered switch using simple iterative matching algorithm | |
| US20070140285A1 (en) | Weighted fair queue having extended effective range | |
| CA2281399C (en) | High speed weighted fair queuing system for atm switches | |
| EP1488600B1 (en) | Scheduling using quantum and deficit values | |
| US6760331B1 (en) | Multicast routing with nearest queue first allocation and dynamic and static vector quantization | |
| US6829224B1 (en) | Method and apparatus for smoothing the rate of packet discards for random early detection in an ATM switch | |
| CA2632538A1 (en) | Sorting apparatus and method | |
| US6625122B1 (en) | Selection of data for network transmission | |
| WO2001084776A2 (en) | Memory management with data discard | |
| EP0870415A1 (en) | Switching apparatus | |
| US6859432B2 (en) | Packet switch for providing a minimum cell rate guarantee | |
| Nong et al. | Analysis of non-blocking ATM switches with multiple input queues | |
| US7349418B1 (en) | Residue-based encoding of packet lengths of particular use in processing and scheduling packets |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| EEER | Examination request | ||
| MKLA | Lapsed |