Skip to main content

Explain Thrashing

Thrashing is said to occur when the system spends a large amount of time transferring shared data blocks from one node to another, compared to the time spent doing the useful work of executing application  processes. It is serious performance problem with DSM systems that allow data blocks to migrate from one node to another. Thrashing may occur in the following situations:

a.  When interleaved data accesses made by processes on two or more nodes causes a data block to move back and forth from one node to another in quick succession.

b.  When blocks with read-only permissions are invalidated soon after they are replicated. Following methods may be used to solve the thrashing problem in DSM systems:

a.  Providing  application-controlled  locks.  Locking  data  to  prevent  other  nodes  from accessing that data for a short period of time can reduce thrashing.

b.  Nailing a block to a node for a minimum amount of time. Another method to reduce thrashing is to disallow a block to be taken away from a node until a minimum amount of time t elapses after its allocation to that node. The time can either be fixed statically or be tuned dynamically on the basis of access patterns.

c.  Tailoring the coherence algorithm to the shared-data usage patterns. Thrashing can be minimized  by  using  different  coherence  protocols  for  shared  data  having  different characteristics.
Labels:

Comments

Post a Comment

Your Comment Here!.....

Popular posts from this blog

CIVIL SERVICES' (I.A.S.) EXAMINATION

The Union Public Service Commission (U.P.S.C.)  conducts Civil Services' Examination once a year in two stages. The Preliminary Examination (Objective Type) for selection of candidates for the Main Examination is held in the month of May. The Civil Services Main Examination  is held in the months of October/November. Blank application forms and other particulars are published in the Employment News, generally in the month of December. The last date for the submission of applications to the Secretary, Union Public Service Commission, Dholpur House, Shahjahan Road, NewDelhi-11001 1 is usually the last week of January of the year of examination. The Combined Civil Services Examination is conducted for Recruitment to the following Services/Posts: 1. Indian Administrative Service. 2. Indian Foreign Service. 3. Indian Police Service. 4. Indian P & T Accounts & Finance Service, Group 'A'. 5. Indian Audit and Accounts Service, Group 'A'. 6. Indian Customs and Centr...
1 comment
Read more

Predict the output or error(s) for the following:

1 . void main(){ int const * p=5; printf("%d",++(*p)); } Answer: Compiler error: Cannot modify a constant value. Explanation: p is a pointer to a "constant integer". But we tried tochange the value of the "constant integer". 2. main() {  char s[ ]="man"; int i;  for(i=0;s[ i ];i++) printf("\n%c%c%c%c",s[i],*(s+i),*(i+s),i[s]); } Answer: mmmm aaaa nnnn Explanation: s[i], *(i+s), *(s+i), i[s] are all different ways of expressing the same idea. Generally array name is the base address for that array. Here s is the base address. i is the index number/displacement from the base address. So, indirecting it with * is same as s[i]. i[s] may be surprising. But in the case of C it is same as s[i]. 3 . main(){  float me = 1.1;  double you = 1.1;  if(me==you) printf("I love U"); else printf("I hate U"); } Answer: I hate U Explanation : For floating point numbers (float, double, long double) ...
Post a Comment
Read more

How do I "get" a null pointer in my programs?

Answer : According to the language definition, a constant 0 in a pointer context is converted into a null pointer at compile time. That is, in an initialization, assignment, or comparison when one side is a variable or expression of pointer type, the compiler can tell that a constant 0 on the other side requests a null pointer, and generate the correctly-typed null pointer value. Therefore, the following fragments are perfectly legal: char *p = 0; if(p != 0) However, an argument being passed to a function is not necessarily recognizable as a pointer context, and the compiler may not be able to tell that an unadorned 0 "means" a null pointer. For instance, the Unix system call "execl" takes a variable-length, null-pointer-terminated list of character pointer arguments. To generate a null pointer in a function call context, an explicit cast is typically required: execl("/bin/sh", "sh", "-c", "ls", (char *)0); If the (c...
Post a Comment
Read more