Estimating migration costs for migrating logical partitions within a virtualized computing environment based on a migration cost history
원문보기
IPC분류정보
국가/구분
United States(US) Patent
등록
국제특허분류(IPC7판)
G06F-009/455
G06F-009/50
G06F-009/48
출원번호
US-0534481
(2014-11-06)
등록번호
US-9110705
(2015-08-18)
발명자
/ 주소
Cawlfield, Kevin J.
Chen, Chang W.
Harding, Mitchell P.
Hollinger, Michael C.
Reddock, Michael R.
출원인 / 주소
INTERNATIONAL BUSINESS MACHINES CORPORATION
대리인 / 주소
Kalaitzis, Parashos T.
인용정보
피인용 횟수 :
1인용 특허 :
60
초록▼
Responsive to a hypervisor determining that insufficient local resources are available for reservation to meet a performance parameter for at least one resource specified in a reservation request for a particular logical partition managed by the hypervisor in a host system, the hypervisor identifies
Responsive to a hypervisor determining that insufficient local resources are available for reservation to meet a performance parameter for at least one resource specified in a reservation request for a particular logical partition managed by the hypervisor in a host system, the hypervisor identifies another logical partition managed by the hypervisor in the host system that is assigned at the least one resource meeting the performance parameter specified in the reservation request. The hypervisor estimates a first cost of migrating the particular logical partition and a second cost of migrating the another logical partition to at least one other host system communicatively connected in a peer-to-peer network based on at least one previously recorded cost stored by the host system of migrating a previous logical partition to the at least one other host system.
대표청구항▼
1. A method for managing requests for resources, comprising: responsive to a hypervisor determining that insufficient local resources are available for reservation to meet a performance parameter for at least one resource specified in a reservation request for a particular logical partition managed
1. A method for managing requests for resources, comprising: responsive to a hypervisor determining that insufficient local resources are available for reservation to meet a performance parameter for at least one resource specified in a reservation request for a particular logical partition managed by the hypervisor in a host system, identifying another logical partition managed by the hypervisor in the host system that is assigned at the least one resource meeting the performance parameter specified in the reservation request;estimating, by the hypervisor, a first cost of migrating the particular logical partition and a second cost of migrating the another logical partition to at least one other host system communicatively connected in a peer-to-peer network based on at least one previously recorded cost stored by the host system of migrating a previous logical partition to the at least one other host system;selecting, by the hypervisor, one of the particular logical partition and the another logical partition as a migration candidate based on a comparison of the first cost with the second cost, wherein the hypervisor negotiates for offers to migrate the migration candidate to the at least one other host system;responsive to selecting a remote host system from among the at least one other host system to migrate the migration candidate to, calling, by the hypervisor, a cost estimator of the host system to create a migration header;selecting, by the cost estimator, a selection of most recent previously recorded migration costs by the host system for a target logical partition and for the remote host system;encoding, by the cost estimator, a migration data header with the selection of most recent previously recorded migration costs; andencoding, by the hypervisor, the migration candidate with the migration data header, wherein the remote host system receives the migration candidate with the migration data header, removes the migration data header from the migration candidate, and records the selection of most recently previous recorded migration costs for the target logical partition and for the remote host system for estimating the cost of migrations from the remote host system. 2. The method according to claim 1, wherein estimating, by the hypervisor, a first cost of migrating the particular logical partition and a second cost of migrating the another logical partition to at least one other host system based on at least one previously recorded cost stored by the host system of migrating a previous logical partition to the at least one other host system further comprises: identifying a plurality of previously recorded costs for migrations to the at least one other host system;identifying a pricing policy applied by the host system;responsive to the host system applying an average pricing policy, selecting a mean cost of the plurality of previously recorded costs to estimate the first cost and the second cost;responsive to the host system applying an optimist pricing policy, selecting a best case cost of the plurality of previously recorded costs to estimate the first cost and the second cost; andresponsive to the host system applying a pessimist pricing policy, selecting a worst case cost of the plurality of previously recorded costs to estimate the first cost and the second cost. 3. The method according to claim 1, further comprising: negotiating, by the hypervisor, to reserve at least one available local resource in the host system that meets the performance parameter for the at least one resource specified in the reservation request by the particular logical partition from among a plurality of logical partitions of virtualized pools of resources managed by the hypervisor in the host system, wherein the at least one performance parameter is specified by a particular application initiating the reservation request from the particular logical partition; andresponsive to determining that the at least one available resource is not available in the host system, negotiating, by the hypervisor, for offers to migrate the migration candidate to the at least one other host system, wherein the at least one other host system is managed by at least one other hypervisor that manages one or more other logical partitions of virtualized pools of resources. 4. The method according to claim 1, further comprising: broadcasting a request for bids for migrating the migration candidate to the at least one other host system communicatively connected without a central management device in the peer-to-peer network;responsive to receiving at least one offer from at least one of the at least one other host system, selecting a particular offer from among the at least one offer from a selected remote host system from among the at least one other host system;migrating the migration candidate logical partition to the selected remote host system via the peer-to-peer network; andresponsive to migrating the another logical partition marked as the migration candidate, reserving at least one freed resource previously assigned to the another logical partition for satisfying the reservation request for the particular logical partition. 5. A logically partitioned host system having a plurality of logical partitions of pools of virtualized resources and an operating system operating in each of the logical partitions, comprising: a hypervisor operative on the host system, wherein the host system comprises at least one memory and at least one processor coupled to the memory, to manage the plurality of logical partitions of pools of virtualized resources and operative, responsive to determining that insufficient local resources are available for reservation to meet a performance parameter for at least one resource specified in a reservation request for a particular logical partition managed by the hypervisor in the host system, to identify another logical partition from among the plurality of logical partitions that is assigned the at least one resource meeting the performance parameter specified in the reservation request;the hypervisor operative to estimate a first cost of migrating the particular logical partition and a second cost of migrating the another logical partition to at least one other host system communicatively connected in a peer-to-peer network based on at least one previously recorded cost stored by the host system of migrating a previous logical partition to the at least one other host system; andthe hypervisor operative to select one of the particular logical partition and the another logical partition as a migration candidate based on a comparison of the first cost with the second cost, wherein the hypervisor negotiates for offers from the at least one other host system to migrate the migration candidate to the at least one other host system;the hypervisor, responsive to selecting a remote host system from among the at least one other host system to migrate the migration candidate to, operative to call a cost estimator of the host system to create a migration header;the cost estimator operative to select a selection of most recent previously recorded migration costs by the host system for a target logical partition and for the remote host system;the cost estimator operative to encode a migration data header with the selection of most recent previously recorded migration costs; andthe hypervisor operative to encode the migration candidate with the migration data header, wherein the remote host system receives the migration candidate with the migration data header, removes the migration data header from the migration candidate, and records the selection of most recently previous recorded migration costs for the target logical partition and for the remote host system for estimating the cost of migrations from the remote host system. 6. The logically partitioned host system according to claim 5, further comprising: a partition controller of the hypervisor, responsive to receiving a logical partition migration with a migration data header, operative to remove the migration data header from the logical partition migration;a cost estimator of the host system operative to decode the migration data header into at least one identifier of at least one of a source host system, a destination host system, and a logical partition and at least one cost of at least one of an estimated cost and an actual cost; andthe cost estimator operative to store the decoded migration data header in a history table comprising a plurality of records of migration costs for at least one migration from the host system to at least one of the at least one other host system and the at least one previously recorded migration cost. 7. The logically partitioned host system according to claim 5, further comprising: the hypervisor operative to identify the at least one previously recorded migration cost for migrations to the at least one other host system from a history table;the hypervisor operative to identify a pricing policy applied by the host system;the hypervisor, responsive to the host system applying an average pricing policy, operative to select a mean cost of the at least one previously recorded migration cost to estimate the first cost and the second cost;the hypervisor, responsive to the host system applying an optimist pricing policy, operative to select a best case cost of the at least one previously recorded migration cost to estimate the first cost and the second cost; andthe hypervisor, responsive to the host system applying a pessimist pricing policy, operative to select a worst case cost of the at least one previously recorded migration cost to estimate the first cost and the second cost. 8. The logically partitioned host system according to claim 5, further comprising: the hypervisor operative to negotiate to reserve at least one available local resource in the host system that meets the performance parameter for the at least one resource specified in the reservation request by the particular logical partition from among a plurality of logical partitions of virtualized pools of resources managed by the hypervisor in the host system, wherein the at least one performance parameter is specified by a particular application initiating the reservation request from the particular logical partition; andthe hypervisor, responsive to determining that the at least one available resource is not available in the host system, operative to negotiate for offers to migrate the migration candidate to the at least one other host system, wherein the at least one other host system is managed by at least one other hypervisor that manages one or more other logical partitions of virtualized pools of resources. 9. The logically partitioned host system according to claim 5, further comprising: the hypervisor operative to broadcast a request for bids for migrating the migration candidate to the at least one other host system;the hypervisor, responsive to receiving at least one offer from at least one of the at least one other host system, operative to select a particular offer from among the at least one offer from a selected remote host system from among the at least one other host system;the hypervisor operative to migrate the migration candidate logical partition to the selected remote host system; andthe hypervisor, responsive to migrating the another logical partition marked as the migration candidate, operative to reserve at least one freed resource previously assigned to the another logical partition for satisfying the reservation request for the particular logical partition. 10. A computer program product for managing requests for resources, said computer program product tangibly embodied in a computer-readable storage medium, wherein the computer-readable storage medium is not a transitory signal per se, and comprising computer executable instructions which cause a computer to: responsive to a hypervisor determining that insufficient local resources are available for reservation to meet a performance parameter for at least one resource specified in a reservation request for a particular logical partition managed by the hypervisor in a host system, identify another logical partition managed by the hypervisor in the host system that is assigned at the least one resource meeting the performance parameter specified in the reservation request;estimate, by the hypervisor, a first cost of migrating the particular logical partition and a second cost of migrating the another logical partition to at least one other host system based on at least one previously recorded cost stored by the host system of migrating a previous logical partition to the at least one other host system;select, by the hypervisor, one of the particular logical partition and the another logical partition as a migration candidate based on a comparison of the first cost with the second cost, wherein the hypervisor negotiates for offers to migrate the migration candidate to the at least one other host system;responsive to selecting a remote host system from among the at least one other host system to migrate the migration candidate to, call, by the hypervisor a cost estimator of the host system to create a migration header;select, by the cost estimator, a selection of most recent previously recorded migration costs by the host system for a target logical partition and for the remote host system;encode, by the cost estimator, a migration data header with the selection of most recent previously recorded migration costs; andencode, by the hypervisor, the migration candidate with the migration data header, wherein the remote host system receives the migration candidate with the migration data header, removes the migration data header from the migration candidate, and records the selection of most recently previous recorded migration costs for the target logical partition and for the remote host system for estimating the cost of migrations from the remote host system. 11. The computer program product according to claim 10, further comprising computer executable instructions which cause a computer to: identify a plurality of previously recorded costs for migrations to the at least one other host system;identify a pricing policy applied by the host system;responsive to the host system applying an average pricing policy, select a mean cost of the plurality of previously recorded costs to estimate the first cost and the second cost;responsive to the host system applying an optimist pricing policy, select a best case cost of the plurality of previously recorded costs to estimate the first cost and the second cost; andresponsive to the host system applying a pessimist pricing policy, select a worst case cost of the plurality of previously recorded costs to estimate the first cost and the second cost.
연구과제 타임라인
LOADING...
LOADING...
LOADING...
LOADING...
LOADING...
이 특허에 인용된 특허 (60)
Abramson Kenneth D. (Seattle WA) Butts ; Jr. H. Bruce (Redmond WA) Orbits David A. (Redmond WA), Affinity scheduling of processes on symmetric multiprocessing systems.
Tsuchiva Kenichi (New Brighton MN) Kregness Glen R. (Minnetonka MN) Price deceased Ferris T. (late of Mayer MN by Robert Howe Price ; legal representative) Lucas Gary J. (Pine Springs MN), Apparatus and method for controlling exclusive access to portions of addressable memory in a multiprocessor system.
Cawlfield, Kevin J.; Chen, Chang W.; Harding, Mitchell P.; Hollinger, Michael C.; Reddock, Michael R., Application initiated negotiations for resources meeting a performance parameter in a virtualized computing environment.
Cawlfield, Kevin J.; Chen, Chang W.; Harding, Mitchell P.; Hollinger, Michael C.; Reddock, Michael R., Application initiated negotiations for resources meeting a performance parameter in a virtualized computing environment.
Saito, Takeshi; Takabatake, Yoshiaki; Hashimoto, Mikio; Kamatani, Yukio, Data transmitting node and network inter-connection node suitable for home network environment.
Cawlfield, Kevin J.; Chen, Chang W.; Harding, Mitchell P.; Hollinger, Michael C.; Reddock, Michael R., Estimating migration costs for migrating logical partitions within a virtualized computing environment based on a migration cost history.
Chu Lynn H. (Piscataway NJ) Dragoni ; Jr. Anthony H. (Warren NJ) Eichelman ; II Fredric R. (Princeton NJ) Huleatt Thomas O. (Neshanic Station NJ) Irgon Adam E. (East Brunswick NJ) Langion Martha S. (, Expert system for computer system resource management.
Liana Liyow Fong ; Ajei Sarat Gopal ; Nayeem Islam ; Andreas Leonidas Prodromidis ; Mark Steven Squillante, Flexible dynamic partitioning of resources in a cluster computing environment.
Dumarot Daniel P. (Washingtonville NY) Garcia Armando (Yorktown Heights NY), High-performance, multi-bank global memory card for multiprocessor systems.
Allon David (Jerusalem ILX) Bach Moshe (Haifa ILX) Moatti Yosef (Haifa ILX) Teperman Abraham (Haifa ILX), Load balancing of network by maintaining in each computer information regarding current load on the computer and load on.
Odnert Daryl (Boulder Creek CA) Santhanam Vatsa (Sunnyvale CA), Method and apparatus for compiling computer programs with interprocedural register allocation.
Bryant Barbara J. (Clinton Corners NY) Garrison Glen E. (Wallkill NY), Method and apparatus for providing token controlled access to protected pages of memory.
Dickerman Robert Frank ; Furgason Shawn Paul ; Bartels Patty Marie, Method and computer program logic for providing an intelligent network operator console with enhanced services.
Kinsey, Jeffrey Brian; Garg, Pankaj; Traut, Eric P.; Green, Dustin L.; Chakraborty, Parag, Method and system for a resource negotiation between virtual machines.
Sheets, Kitrick B.; Smith, Philip S.; Engel, Stephen J.; Deng, Yuefan; Guistozzi, Joseph; Korobka, Alexander, Method and system for providing dynamic hosted service management across disparate accounts/sites.
Aras Caglan M. ; Guerin Roch A. ; Lebizay Gerald,FRX ; Onvural Raif O. ; Shippy Gary Roy ; Tai Ling-Ching Wang, Method system and article of manufacture for multi-casting audio visual material.
Eilert, Catherine K.; Kubala, Jeffrey P.; Nick, Jeffrey M.; Yocom, Peter B., Method, system and program products for managing central processing unit resources of a computing environment.
Brooks James E. ; Collins Robert R. ; Shiell Jonathan H., Microprocessor with circuits, systems, and methods for selectively bypassing external interrupts past the monitor progr.
van Rietschote,Hans F.; Hobbs,Craig W.; Saptarshi,Mahesh P., Migrating virtual machines among computer systems to balance load caused by virtual machines.
Ahuja Sudhir Raman (Aberdeen NJ) Aravamudan Murali (Berkley Heights NJ) Ensor James Robert (Red Bank NJ) Kuthyar Ashok K. (Holmdel NJ) Ramamurthy Ram S. (Manalapan NJ) Stuntebeck Peter H. (Little Sil, Multimedia telecommunications network and service.
Harkins Larry E. (Rochester NY) Hayward Ken (Brockport NY) Herceg Thomas J. (Pittsford NY) Levine Jonathan D. (Rochester NY) Parsons David M. (Fairport NY), Network having selectively accessible recipient prioritized communication channel profiles.
Horne Stephen P. (Austin TX) Song Seungyoon (Austin TX), Processing system and method including lock buffer for controlling exclusive critical problem accesses by each processor.
Harkins Larry E. (Rochester NY) Hayward Ken (North Brockport NY) Herceg Thomas J. (Pittsford NY) Levine Jonathan D. (Rochester NY) Parsons David M. (Victor NY), Recipient prioritized communication channel profiles.
Earnshaw William E. (N. Lauderdale FL) McKinney Steven J. (Coral Springs FL), Semaphore memory to reduce common bus contention to global memory with localized semaphores in a multiprocessor system.
Wang, Hong; Chinya, Gautham N.; Hankins, Richard A.; Kaushik, Shivnandan D.; Bigbee, Bryant; Shen, John; Hammarlund, Per; Zou, Xiang; Brandt, Jason W.; Sethi, Prashant; Carmean, Douglas M.; Patel, Baiju V.; Rodgers, Scott Dion; Rakvic, Ryan N.; Reid, John L.; Poulsen, David K.; Shah, Sanjiv M.; Held, James Paul; Abel, James Charles, Sequencer address management.
Singhal, Ashok; Hagersten, Erik, System and method for accessing a shared computer resource using a lock featuring different spin speeds corresponding to multiple states.
Danknick Daniel A. (Orange CA), System for reducing bus contention using counter of outstanding acknowledgement in sending processor and issuing of ackn.
Aman Jeffrey D. (Wappingers Falls NY) Cotner Curt L. (Gilroy CA) Dillenberger Donna N. T. (Yorktown Heights NY) Emmes David B. (Poughkeepsie NY), System of assigning work requests based on classifying into an eligible class where the criteria is goal oriented and ca.
Landis, John A.; Powderly, Terrence V.; Subrahmanian, Rajagopalan; Puthiyaparambil, Aravindh, Virtual data center that allocates and manages system resources across multiple nodes.
Brendel Juergen ; Kring Charles J. ; Liu Zaide ; Marino Christopher C., World-wide-web server with delayed resource-binding for resource-based load balancing on a distributed resource multi-n.
Chen, Ping; Muralidharan, Hariganesh; Shaw, Anu P.; Vallabhaneni, Vasu, Migration of a logical partition or virtual machine with inactive input/output hosting server.
※ AI-Helper는 부적절한 답변을 할 수 있습니다.