M. Mizuno, M. Raynal, and J.Z. Zhou. Sequential Consistency in Distributed Systems. Proc. Int. Workshop " Theory and Practice in Dist. Systems", Dagstuhl, Germany, LNCS 938:224--241, 1994.  Home/Search   Document Not in Database   Summary   Related Articles   Check

....b H if 6 9e s i : w(x)v H e s i H r(x)v where e s i = r(x)u or e s i = w(x)u and u 6= v. A computation b H is legal if all its read events are legal. Two consistency criteria for shared memory are usually considered: ffl Sequential consistency. A computation b H is sequentially consistent [6, 9] if it has a linear extension 1 in which all read events are legal. Intuitively, this consistency criterion defines b H as correct if it could have been produced by multiplexing processes on a monoprocessor system. Actually, a sequentially consistent computation totally orders write events. ffl ....

M. Mizuno, M. Raynal, and J.Z. Zhou. Sequential Consistency in Distributed Systems. Proc. Int. Workshop " Theory and Practice in Dist. Systems", Dagstuhl, Germany, LNCS 938:224--241, 1994.

....criterion for shared data. Remark. Let us note that if every transaction is reduced to include either a single read or a single write operation, serializability is the same as sequential consistency [14] which is the most used criterion to define semantics of memories in shared memory systems [1, 20]. 3.3 Causal Consistency While serializability considers that all processes must have the same sequential view of the whole execution b H (the view defined by a legal linear extension) causal consistency is weaker in the following sense: it allows each process to have its own sequential view of ....

M. Mizuno, M. Raynal, and J.Z. Zhou. Sequential Consistency in Distributed Systems. Proc. Int. Workshop "Theory and Practice in Dist. Systems", Dagstuhl, Germany, Springer-Verlag LNCS 938, (K. Birman, F. Mattern and A. Schiper Eds), pp.227-241, 1994.

....issued by P 1 . It is also easy to see that the history c H 2 (Figure 2) is not sequentially consistent, as no legal linear extension of c H 2 can be built. 3. 2 Protocols Various cache based protocols implementing sequential consistency have been proposed in the context of parallel machines [2, 7, 27]. In most of these protocols, 3 In his definition, Lamport assumes that the process order relation defined by the program (see point (2) of the definition) is maintained in the equivalent sequential execution, but not necessarily in the execution itself. As we do not consider programs but only ....

....order is built by an underlying atomic broadcast primitive (messages sent with this primitive are delivered in the same order to each procesor [14] Read operations issued by a process are appropriately scheduled by its processor in order to ensure their legality. In the protocol presented in [27], a process P i issuing a write operation sends a write message to a central manager and waits for an answer. The central manager totally orders write operations. After receiving a write message from a process P i , the central manager sends back an answer informing P i about its set of copies of ....

M. Mizuno, M. Raynal, and J.Z. Zhou. Sequential Consistency in Distributed Systems. Proc. Int. Workshop "Theory and Practice in Dist. Systems", Dagstuhl, Germany, Springer-Verlag LNCS 938, (K.Birman, F. Mattern and A. Schiper Eds), pp.227-241, 1994.

....in the context of 2 A linear extension b S = S; S ) of a partial order b H = H; H ) is a topological sort of this partial order, i.e. i) S = H, ii) op 1 H op 2 ) op 1 S op 2 ( b S maintains the order of all ordered pairs of b H) and (iii) S defines a total order. parallel machines [2, 5, 14]. In most of these protocols, every processor local memory contains a copy of the whole shared memory. Read operations are local, while write operations issued by processes are totally ordered. In [2] and in the fast read protocol of [5] this total order is built by an underlying atomic broadcast ....

M. Mizuno, M. Raynal, and J.Z. Zhou. Sequential Consistency in Distributed Systems. Proc. Int. Workshop "Theory and Practice in Dist. Systems", Dagstuhl, Germany, Springer-Verlag LNCS 938, (K. Birman, F. Mattern and A. Schiper Eds), pp. 227-241, 1994.

....consistent, as no equivalent legal sequential history can be built. w 1 (x)0 r 1 (x)0 r 1 (y)2 r 2 (x)1 w 2 (x)1 w 2 (y)2 Fig. 1. A sequentially consistent history c H1 Various cache based protocols implementingsequential consistency have been proposed in the context of parallel machines [1, 5, 10]. The protocols presented in [1, 10] allow several read operations and one write operation to concurrently access a same variable (reading of cached values and writing into the main memory) but do not allow concurrent write operations on a same variable. One of the protocols (called fast write) ....

....legal sequential history can be built. w 1 (x)0 r 1 (x)0 r 1 (y)2 r 2 (x)1 w 2 (x)1 w 2 (y)2 Fig. 1. A sequentially consistent history c H1 Various cache based protocols implementingsequential consistency have been proposed in the context of parallel machines [1, 5, 10] The protocols presented in [1, 10] allow several read operations and one write operation to concurrently access a same variable (reading of cached values and writing into the main memory) but do not allow concurrent write operations on a same variable. One of the protocols (called fast write) presented in [5] allows write ....

M. Mizuno, M. Raynal, and J.Z. Zhou. Sequential Consistency in Distributed Systems. Proc. Int. Workshop "Theory and Practice in Dist. Systems", Dagstuhl, Germany, Springer-verlag LNCS 938 (K.Birman, F. Mattern and A. Schiper Eds), 1994, pp.224-241.

Online articles have much greater impact   More about CiteSeer.IST   Add search form to your site   Submit documents   Feedback  

CiteSeer.IST - Copyright Penn State and NEC