Entanglement of pages and guest threads
Entanglement of pages and threads is disclosed. An indication is received of a stalling event caused by a requested portion of memory being inaccessible. It is determined that the requested portion of memory is an entangled portion of memory that is entangled with a physical node in a plurality of physical nodes. A type of the entangled portion of memory is determined. The stalling event is handled based at least in part on the determined type of the entangled portion of memory.
1. A system, comprising:
a plurality of physical nodes;
wherein an indication is received of a stalling event caused by a requested portion of memory being inaccessible;
wherein it is determined that the requested portion of memory is an entangled portion of memory that is designated as entangled with a physical node in the plurality of physical nodes;
wherein it is determined that the entangled portion of memory is a portion of memory that is specific to a given thread;
wherein, based at least in part on the determination that the entangled portion of memory is specific to the given thread, it is determined that a thread context switch has occurred; and
wherein the stalling event is handled based at least in part on the determination that the entangled portion of memory is specific to the given thread.
2. The system recited in claim 1 wherein the portion of memory comprises at least one of a thread state page and a top of stack page.
3. The system recited in claim 1 wherein based at least in part on the determination that the entangled portion of memory is a portion of memory that is specific to the given thread, the stalling event is handled at least in part by migrating a virtual processor to the physical node with which the portion of memory is entangled.
4. A method, comprising:
receiving an indication of a stalling event caused by a requested portion of memory being inaccessible;
determining that the requested portion of memory is an entangled portion of memory that is designated as entangled with a physical node in a plurality of physical nodes;
determining that the entangled portion of memory is a portion of memory that is specific to a given thread;
based at least in part on the determination that the entangled portion of memory is specific to the given thread, determining that a thread context switch has occurred; and
handling the stalling event based at least in part on the determination that the entangled portion of memory is specific to the given thread.
5. The method of claim 4 wherein the portion of memory comprises at least one of a thread state page and a top of stack page.
6. The method of claim 4 wherein based at least in part on the determination that the entangled portion of memory is a portion of memory that is specific to the given thread, the stalling event is handled at least in part by migrating a virtual processor to the physical node with which the portion of memory is entangled.
7. A system, comprising:
a plurality of physical nodes;
wherein an indication is received of a stalling event caused by a requested portion of memory being inaccessible;
wherein it is determined that the requested portion of memory is an entangled portion of memory that is designated as entangled with a physical node in the plurality of physical nodes;
wherein it is determined that the entangled portion of memory is a portion of memory that is specific to a given thread, and wherein the portion of memory comprises at least one of a thread state page and a top of stack page; and
wherein the stalling event is handled based at least in part on the determination that the entangled portion of memory is specific to the given thread.
8. The system recited in claim 7 wherein, based at least in part on the determination that the entangled portion of memory is specific to the given thread, it is determined that a thread context switch has occurred.
9. The system recited in claim 7 wherein based at least in part on the determination that the entangled portion of memory is a portion of memory that is specific to the given thread, the stalling event is handled at least in part by migrating a virtual processor to the physical node with which the portion of memory is entangled.
10. A method, comprising:
receiving an indication of a stalling event caused by a requested portion of memory being inaccessible;
determining that the requested portion of memory is an entangled portion of memory that is designated as entangled with a physical node in a plurality of physical nodes;
determining that the entangled portion of memory is a portion of memory that is specific to a given thread, wherein the portion of memory comprises at least one of a thread state page and a top of stack page; and
handling the stalling event based at least in part on the determination that the entangled portion of memory is specific to the given thread.
11. The method of claim 10 wherein, based at least in part on the determination that the entangled portion of memory is specific to the given thread, it is determined that a thread context switch has occurred.
12. The method of claim 10 wherein based at least in part on the determination that the entangled portion of memory is a portion of memory that is specific to the given thread, the stalling event is handled at least in part by migrating a virtual processor to the physical node with which the portion of memory is entangled.
13. A system, comprising:
a plurality of physical nodes;
wherein an indication is received of a stalling event caused by a requested portion of memory being inaccessible;
wherein it is determined that the requested portion of memory is an entangled portion of memory that is designated as entangled with a physical node in the plurality of physical nodes;
wherein it is determined that the entangled portion of memory is a portion of memory that is specific to a given thread; and
wherein based at least in part on the determination that the entangled portion of memory is a portion of memory that is specific to the given thread, the stalling event is handled at least in part by migrating a virtual processor to the physical node with which the portion of memory is entangled.
14. The system recited in claim 13 wherein, based at least in part on the determination that the entangled portion of memory is specific to the given thread, it is determined that a thread context switch has occurred.
15. The system recited in claim 13 wherein the portion of memory comprises at least one of a thread state page and a top of stack page.
16. A method, comprising:
receiving an indication of a stalling event caused by a requested portion of memory being inaccessible;
determining that the requested portion of memory is an entangled portion of memory that is designated as entangled with a physical node in a plurality of physical nodes;
determining that the entangled portion of memory is a portion of memory that is specific to a given thread; and
based at least in part on the determination that the entangled portion of memory is a portion of memory that is specific to a given thread, handling the stalling event at least in part by migrating a virtual processor to the physical node with which the portion of memory is entangled.
17. The method of claim 16 wherein, based at least in part on the determination that the entangled portion of memory is specific to the given thread, it is determined that a thread context switch has occurred.
18. The method of claim 16 wherein the portion of memory comprises at least one of a thread state page and a top of stack page.