Apparatus and method for capacity planning for data center server consolidation and workload reassignment

• US 20080077366A1
• Filed: 09/22/2006
• Published: 03/27/2008
• Est. Priority Date: 09/22/2006
• Status: Active Grant

• Current Assignee: HyPerformix, Inc. (Broadcom, Inc.)
• Original Assignee: HyPerformix, Inc. (Broadcom, Inc.)
• Inventors: Matchett, Douglas K., Neuse, Douglas M., Walton, Chris
• Granted Patent: US 7,769,843 B2
• Time in Patent Office: Days
• US Class Current: 703/2
• CPC Class Codes: G06Q 30/0283 Price estimation or determination
• CPC Class Codes: H04L 41/145 involving simulating, designing, planning or modelling of a network
• CPC Class Codes: H04L 41/147 for predicting network behaviour
• CPC Class Codes: H04L 41/22 comprising specially adapted graphical user interfaces [GUI]
• CPC Class Codes: H04L 43/0876 Network utilisation, e.g. volume of load or congestion level

Abstract

A server migration tool used to construct data center migration scenarios allowing for a user to rapidly manipulate a large number of input parameters required to describe a transformation from one data center configuration to a new data center configuration. The tool then performs the transformation and allows the user to interact with new data center configuration to understand its performance. A novel parameterization, speed independent service demand (SISD), greatly facilitates scaling performance metrics between different hardware platforms.

Claims

1. A server migration tool for predictive analysis of a computer network comprising:

(a) a source data center configuration;

(b) a source parameter set;

(c) a graphical user interface adapted to generate a desired data center configuration;

(d) a transform engine, in communication with the graphical user interface, for modifying the source parameter set into a destination parameter set by reference to the desired data center configuration; and

,

(e) the destination parameter set providing a basis for submission to a modeling tool for predictive analysis.

2. The server migration tool of claim 1 wherein the source data center configuration is drawn from the group of measured data and estimated data.

3. The server migration tool of claim 1 wherein the source parameter set is drawn from the group of:

4. The server migration tool of claim 1 wherein the destination parameter set is drawn from the group of:

5. The server migration tool of claim 1 wherein the source data center configuration includes a data server cluster and a workload.

6. The server migration tool of claim 1 wherein the destination data center configuration includes a data server cluster and workload.

7. The server migration tool of claim 1 wherein the graphical user interface is a module programmed to carry out the steps of:

(a) selecting a source server;

(b) selecting a destination server; and

,

(c) creating a destination server.

8. The server migration tool of claim 1 wherein the graphical user interface is a module programmed to carry out the steps of:

(a) modifying a workload; and

,

(b) reassigning a workload.

9. The server migration tool of claim 8 wherein the graphical user interface is a module programmed to carry out the step of fractionating the workload.

10. The server migration tool of claim 8 wherein the graphical user interface is a module programmed to carry out the step of assigning a workload to a destination server.

11. The server migration tool of claim 1 wherein the graphical user interface is a module programmed to carry out the step of assigning a single server as a source server and a destination server.

12. The server migration tool of claim 1 wherein the graphical user interface is a module programmed to carry out the steps of

(a) reassigning a workload;

and

(b) consolidating a set of servers.

13. The server migration tool of claim 12 wherein steps may be performed in any order.

14. The server migration tool of claim 1 wherein the transform engine scales a set of parameters to account for the desired data center configuration.

15. The server migration tool of claim 1 wherein the transform engine utilizes a speed independent service demand parameter.

16. The server migration tool of claim 15 wherein the speed independent service demand parameter includes a weighted average.

17. The server migration tool of claim 1 wherein the desired data center configuration includes an existing server and a hypothetical server.

18. The server migration tool of claim 1 wherein the graphical user interface organizes and displays a set of scenarios into a tree structure.

19. The server migration tool of claim 1 wherein the graphical user interface provides for relocation to an existing server.

20. The server migration tool of claim 1 wherein the graphical user interface provides for relocation to a hypothetical server.

21. The server migration tool of claim 1 wherein the transform engine adjusts a performance parameter according to a desired number of CPUs.

22. The server migration tool of claim 1 wherein the transform engine adjusts a performance parameter according to a desired number of network streams.

23. The server migration tool of claim 1 wherein the transform engine uses a speed independent service demand in association with a relocation scenario.

24. The server migration tool of claim 1 wherein the transform engine uses a speed independent service demand to evaluate a hypothetical server.

25. The server migration tool of claim 1 wherein the transform engine uses a speed independent service demand to evaluate a consolidation scenario.

26. The server migration tool of claim 1 wherein the transform engine models an increased memory usage as a result of a workload change.

27. The server migration tool of claim 1 wherein the transform engine models changes in a memory after a configuration change.

28. The server migration tool of claim 1 wherein a workload relocation changes in a memory after a configuration change.

29. The server migration tool of claim 1 wherein the graphical user interface provides for changes to the source data configuration drawn from the group of a CPU change, a memory change, a disk drive change and a NIC change.

30. The server migration tool of claim 1 wherein the graphical user interface provides for a change in workload in the source data center configuration.

31. The server migration tool of claim 30 wherein the change in workload is a growth specified by a time interval.

32. The server migration tool of claim 1 wherein the graphical user interface provides for a change to a server parameter drawn from the group of a name, an attached device, a threshold profile and a thread level parallelism.

33. The server migration tool of claim 1 wherein the graphical user interface provides for a change in a hardware configuration.

34. The server migration tool of claim 33 wherein the graphical user interface provides for a change in a hardware configuration according to a set of stored hardware models.

35. The server migration tool of claim 33 wherein the change in hardware configuration is drawn from the group of;

a number of CPUs, a number of servers, a memory capacity, a static memory usage, a number of NICs, a disk transfer rate and a RAID disk storage model.

36. The server migration of claim 1 wherein the modeling tool implements a standard queuing theory solver.

49. The server migration tool of claim 1 wherein the source data center configuration and the desired data center configuration include the definition of a first server.

37. A method of capacity planning for server migration comprising the steps of:

(a) providing a source configuration having a corresponding set of source parameters;

(b) specifying a destination configuration;

(c) performing a transformation to obtain a set of destination parameters from the set of source parameters; and

(d) submitting the set of destination parameters to a standard queuing theory enabled modeling engine.

38. The method of claim 37 wherein the step of specifying a destination configuration further comprises the steps of:

(a) consolidating a server;

(b) reassigning a workload;

(c) changing a configuration; and

(d) changing a workload.

39. The method of claim 38 wherein the step of consolidating a server further comprises the further steps of:

(a) naming a destination scenario;

(b) describing a destination scenario;

(c) creating a new workload reassignment; and

(d) choosing a reassignment from a list of premises defined reassignments.

40. The method of claim 39 wherein the step of creating a new workload reassignment further comprises the steps of:

(a) naming a reassignment;

(b) describing a reassignment;

(c) choosing a source server from which a workload will be removed; and

(d) choosing a destination server to which the workload will be reassigned.

41. The method of claim 39 further comprising the additional step of adding a hypothetical server to the destination scenario.

42. The method of claim 38 wherein the step of reassigning a workload comprises the further steps of:

(a) naming a destination scenario;

(b) describing a destination scenario;

(c) choosing a workload to reassign from a first server; and

(d) reassigning the workload to a second server.

43. The method of claim 42 wherein the second server is a hypothetical server.

44. The method of claim 42 wherein the step of reassigning the workload includes the further step of reassigning the workload to a set of two or more third servers.

45. The method of claim 42 wherein the workload comprises a first workload subset and a second workload subset and the step of reassigning a workload further comprises reassigning the first workload subset and the second workload subset to the second server.

46. A method of scaling a work parameter into a speed independent service demand parameter comprising the steps of:

(a) choosing a speed benchmark parameter associated with a device element;

(b) choosing a work demand parameter associated with the device element; and

(c) multiplying the speed benchmark parameter by the work demand parameter to arrive at a speed independent service demand parameter.

47. The method of claim 46 wherein the step of choosing a work demand parameter includes the further step of choosing a work demand parameter from the group of CPU seconds and disk seconds.

48. The method of claim 46 wherein the step of choosing a speed benchmark parameter includes the further step of choosing a speed benchmark parameter from the group of CPU SPEC, revolutions per minute, man hours and horsepower.

50. A server migration tool for predictive analysis of a computer network comprising:

(a) a source data center configuration;

(b) a source parameter set;

(c) a graphical user interface adapted to generate a desired data center configuration;

(d) a transform module, in communication with the graphical user interface, programmed to modify the source parameter set into a destination parameter set by reference to the desired data center configuration; and

,

(e) the destination parameter set providing a basis for submission to a modeling tool for predictive analysis.

51. The server migration tool of claim 50 wherein the transform module is a program module programmed to carry out the further steps of:

(a) Calculating a throughput for a set of source servers and a set of source devices for a set of source workloads in the source data center configuration;

(b) Estimating a service demand for the set of source servers, the set of source devices and a source memory in the source data center configuration;

(c) Computing a server transformation matrix;

(d) Computing a fraction of a workload reassignment moved between the set of source devices and a set of destination devices;

(e) Computing an arrival rate for the desired data center configuration;

(f) Computing a source speed independent service demand parameter for the set of source servers and the set of source devices in the source data center configuration;

(g) Adjusting a device visit count according to the workload reassignment;

(h) Computing a weighted average speed independent service demand parameter for a set of destination servers and a set of destination devices in the desired data center configuration;

(i) Computing a service demand for the set of destination servers and the set of destination devices in the desired data center configuration;

(j) Computing a memory service demand and a consumption of destination servers in the desired data center configuration; and

(k) computing a set of destination parameters for a queuing theory solver from the server transformation matrix.

52. The server migration tool of claim 50 wherein the transform module is programmed to carry out the further steps of:

(a) Sending the set of destination parameters to the queuing theory solver;

(b) Invoking the queuing theory solver to calculate a set of desired performance results;

(c) Retrieving the set of desired performance results from the queuing theory solver; and

(d) Displaying the set of desired performance results.

53. The server migration tool of claim 50 wherein the step (a) is further comprised of the substep of applying the equation

TPUT(k,w)=AB(w)*DV(k,w)

for all k where k is an index for a set of devices, and, for all w where w is an index for a set of source workloads.

54. The server migration tool of claim 50 wherein the step (b) is further comprised of the substeps of:

(a) Calculating a source server service demand according to the equation;

55. The server migration tool of claim 50 wherein a fraction of a memory utilization on a set of servers s assigned to a set of workloads w.

56. The server migration tool of claim 54 wherein the fraction of memory utilization is measured from a workload-memory usage statistic.

57. The server migration tool of claim 50 wherein the step c) is further comprised of the substeps of:

(a) Specifying that a set of source servers s in source data center configuration is to be consolidated onto a set NDS(s) of destination servers defined by the parameter NDS(s) in the desired data center configuration,

(b) Computing F(s,d,w) according to the equation;

58. The server migration tool of claim 50 wherein the step c) is further comprised of the substeps of:

(a) Specifying that a set of source servers s in source data center configuration is to be consolidated onto a set of destination servers defined by the parameter NDS(s) in the desired data center configuration,

(b) Specifying that for each source server of the set of source servers s and for a set of workloads w in the source data center configuration that a relocation percentage RP(s, w) of the set of workloads w is reassigned to the set of destination servers,

(c) Computing a matrix F(s, d, w) according to;

59. The server migration tool of claim 50 wherein the number of destination servers is specified in the graphical user interface.

60. The server migration tool of claim 50 wherein the number of destination servers and the relocation percentage are specified in the graphical user interface.

61. The server migration tool of claim 50 wherein the step d) further comprises the substeps of:

(a) Calculating a fraction of reassigned workload w moved from a disk i to a disk j according to the equation;

62. The server migration tool of claim 50 wherein the step e) comprises the substep of calculating a new arrival rate A(w, p) in the desired data center configuration for the set of workloads w at time interval p from the base arrival rate AB(w) for workload w in the source data center configuration

A(w,p)=AB(w)·

G(p,w)

where G(p,w) is a specified growth multiplier.

63. The server migration tool of claim 50 in which the growth multiplier is specified in the graphical user interface.

64. The server migration tool of claim 50 wherein the step f) comprises the substeps of:

(a) Calculating a source CPU speed independent service demand for the set of workloads w according to;

SIDC(t,w)=CS(t)·

PDC(t,w)

 

where CS(t) is a CPU rating of source server t and PDC(t,w) is a service demand for source server t;

(b) Calculating a disk speed independent service demand for the set of workloads w according to;

SIDD(k,w)=DS(k)·

PDD(k,w)

 

where DS(k) is a source disk speed rating of disk k and PDD(k,w) is a service demand for source disk k; and

(c) Calculating a NIC speed independent service demand for the set of workloads w according to;

SIDN(k,w)=NS(k)·

PDN(k,w)

 

where NS(k) is a source NIC speed rating of NIC k and PDN(k,w) is a service demand for source NIC k.

65. The server migration tool of claim 50 wherein the step g) includes the substeps:

(a) Calculating a number of server visit counts, RSVU(d,w), for each destination server d in the desired data center configuration for the set of workloads w after a workload reassignment according to;

66. The server migration tool of claim 50 wherein the step h) comprises the substeps of:

(a) Computing a weighted server speed independent service demand SIDC(d,w) for the set of destination servers d and the set of workloads w given the speed independent service demands SIDC(s,w) for the set of source servers s in the source data center configuration according to;

67. The server migration tool of claim 50 wherein the step i) comprises the further substeps of:

(a) Summing the destination workload arrival rates A(w) which is the arrival rate for workload w in a given time interval to find a total arrival rate A(0) for all workloads in the desired data center configuration according to

68. The server migration tool of claim 50 including the further step of computing the total service demand for servers by:

(a) Calculating the total relative throughput, Y(d,0) of destination server d

69. The server migration tool of claim 50 including the further step of computing the total service demand for disks by:

(a) Calculating the total relative throughput, Y′

(d,0) of destination disk k according to

70. The server migration tool of claim 50 including the further step of computing the total service demand for NICs by:

(a) Calculating the total relative throughput, Y″

(k,0) of destination NIC k according to,

71. The server migration tool of claim 50 including the further step of computing the total service demand for network delay devices by:

(a) Computing the service demand for all workloads w and for every network delay device n according to PDL(n, w)=R(n, w)·

DVCD(n, w) where R(n,w) is the network response time for network delay device n and workload w;

DVCD(n,w) is the dimensionalized device visit count for network delay device n and workload w; and

(b) Calculating the total service demand, PDL(n,0) for network delay device n and destination server d according to

72. The server migration tool of claim 50 including the further step of computing the total service demand for network transmission devices by:

(a) Computing the network transmission utilization, UMT(n,w) for network transmission device n and workload w according to

UMT(n,w)=UDR(n,w)/TS(n),

 

where UDR(n,w) is the data rate for workload w on network transmission device n and TS(n) is the network transmission speed of device n; and

(b) Calculating the total service demand, PDT(n,0) for network transmission device n according to

73. The server migration tool of claim 50 wherein the step j) comprises the substeps:

(a) Computing the memory service demand, PDM(d,w) for every destination server d and all workloads w according to;