This collective group of indigenous American tribes, historically situated to the east of the Mississippi River, speaks either Algonquian, Siouan, or Iroquoian.
Potpourri Consider the following lock algorithm using T&S: w…
Potpourri Consider the following lock algorithm using T&S: while ((L == locked) or (T&S(L) == locked)) { while (L == locked); // spin delay (d); // different delays for different processors } // success if we are here (Answer True/False with justification) (No credit without justification) This algorithm does not rely on hardware cache coherence.
Full Virtualization The context for this question is the sam…
Full Virtualization The context for this question is the same as the previous question. An engineering firm is running a critical, unmodified legacy CAD application inside a fully virtualized VM on an older x86 server. The application frequently makes privileged calls that interact directly with the hardware. An administrator notices poor performance and learns that this specific, older x86 architecture has a “quirk” where certain privileged instructions, when executed by the guest OS (which is running in an unprivileged mode), fail silently instead of causing a trap to the hypervisor. What technique does VMware ESX use to overcome this architectural limitation and ensure the guest OS functions correctly?
LRPC and Scheduling The context for this question is the sam…
LRPC and Scheduling The context for this question is the same as the previous question. A server provides the following procedure via LRPC uint64_t sum_array(const uint64_t *arr, size_t len) { uint64_t sum = 0; for (size_t i = 0; i < len; ++i) { sum += arr; } return sum;} The kernel will create an A-stack and map that into the client and server address spaces. Assume the following: (uint64_t is 8 bytes and size_t is 4 bytes) There is programming language support for the server to access the A-stack directly. During the actual call what is the action on the client side so far as A-stack is concerned?
Potpourri Answer the following questions with respect to the…
Potpourri Answer the following questions with respect to the MCS barrier algorithm: (Answer True/False with justification) (No credit without justification) For the correct functioning of the algorithm, it requires an atomic read-modify-write instruction to be supported in the architecture.
Paravirtualization The context for this question is the same…
Paravirtualization The context for this question is the same as the previous question. Above picture shows the I/O ring data structure used in Xen to facilitate communication between the guest OS and Xen. Guest-OS places a request in the I/O ring using the “Request Producer” pointer. Xen places a response in the I/O ring using the “Response Producer” pointer. Why does Xen typically not run out of space to place a response on this ring? State the invariant briefly.
Tornado The context for this question is the same as the pre…
Tornado The context for this question is the same as the previous question. How might Tornado decide to implement “Region” objects shown in the figure?
Memory Management [2 points] Mention one advantage and one d…
Memory Management Mention one advantage and one disadvantage of having a high tax rate for reclaiming unused memory from the VMs.
Memory Management [3 points] A datacenter uses ballooning to…
Memory Management A datacenter uses ballooning to allocate or reclaim memory from VMs. The hypervisor has a policy that taxes 20% of a VM’s idle memory, starting with the VM that has the most idle memory. The hypervisor can tax over multiple rounds until the request of a VM is met. Consider this scenario: VM1 requests 100 MB of additional memory. The hypervisor has no free machine memory VM2 has an idle memory of 140 MB VM3 has an idle memory of 200 MB List the steps taken by the hypervisor to satisfy VM1’s request.
LRPC and Scheduling The context for this question is the sam…
LRPC and Scheduling The context for this question is the same as the previous question. A server provides the following procedure via LRPC uint64_t sum_array(const uint64_t *arr, size_t len) { uint64_t sum = 0; for (size_t i = 0; i < len; ++i) { sum += arr; } return sum;} The kernel will create an A-stack and map that into the client and server address spaces. Assume the following: (uint64_t is 8 bytes and size_t is 4 bytes) There is programming language support for the server to access the A-stack directly. If the server wishes to entertain simultaneous calls from multiple clients, how big should the A-stack be?