公开(公告)号：GB2519294A

公开(公告)日：2015-04-22

申请号：GB201318218

申请日：2013-10-15

Applicant: IBM

Inventor： JARVIS MATTHEW JAMES ,  NORTH GERAINT

IPC: G06F11/30

Abstract: A storage network controller, monitoring data transfer rates and thresholds for transferring data between storage and one or more applications; collects feedback on the suitability of the transfer data rate from the application(s); and changes data transfer thresholds for the application(s) based on monitored data transfer rate and the collected feedback. The data transfer thresholds used to maintain a quality of service, may be in a network switch, where application programming interface (API) messages are sent to declare that a required performance has been reached, using the same communication channels as data transfer, or out of bound with storage traffic via a separate network. This enables balance between applications undergoing heavy load to be reached that does not negatively impact performance of other applications using storage system.

公开(公告)号：CA2776184A1

公开(公告)日：2013-01-18

申请号：CA2776184

申请日：2012-05-07

Applicant: IBM

Inventor： NORTH GERAINT

IPC: H04L29/06

Abstract: A method, system, and computer program product enhances resource/process availability by providing hardware based buffering of network packets during checkpointing in a virtualized environment. A High Availability Checkpoint (HAC) utility pre-configures a physical network adapter to buffer outgoing network packets from virtual machines that employ a checkpointing technology. In response to receiving an outgoing network packet from a virtual machine and determining that the virtual machine employs a pre-specified checkpointing technology, the physical network adapter buffers the outgoing network packet. In addition, a primary host performs/facilitates checkpoint operations (associated with the virtual machine) with a secondary host. When checkpoint operations are successfully completed, the HAC utility triggers the transmission of the buffered network packets from the network adapter to a network destination. The physical network adapter minimizes checkpointing network latency by pre-assigning a higher priority to a buffered network packet from a checkpointing virtual machine than to a new network packet that originates from a non-checkpointing virtual machine.

公开(公告)号：GB2490221A

公开(公告)日：2012-10-24

申请号：GB201206643

申请日：2012-04-16

Applicant: IBM

Inventor： NORTH GERAINT

IPC: G06F9/455 ,  G06F12/1045

Abstract: Emulating a source application with two or more emulator processes executing on respective processors of a multi-processor platform with a shared code heap and virtual trampoline memory where each emulator process has a respective private trampoline memory. The emulation may be a dynamic binary translation which begins by fetching 602 a fragment of source instructions from emulated physical memory then generates 604 equivalent target instructions and writes 606 these to the code heap at a location indexed by its corresponding emulated physical address. Each jump instruction in the fragment is translated 608 to a jump to a slot in the virtual trampoline memory and a trap is written 612 in each private trampoline at that slot. When the trap is encountered during execution a trap handling method (figure 9) replaces the trap with a physical address in the code heap corresponding to the start of the target instruction fragment.

公开(公告)号：GB2519549A

公开(公告)日：2015-04-29

申请号：GB201318780

申请日：2013-10-24

Applicant: IBM

Inventor： SHERWOOD DAVID ,  BODEN IAN ,  SANDERS LEE JASON ,  NORTH GERAINT

IPC: G06F12/08 ,  G06F12/0804 ,  G06F12/0806 ,  G06F12/0868 ,  G06F12/0871

Abstract: A controller (24) is adapted to issue write permissions to a plurality of data storage devices (32), the write permissions including a permission to perform a data destage operation from a cache (22) to a data storage device (32); wherein each cache has a first performance score expressed as the difference between the number of data destage operations the cache has in flight and the maximum number of data destage actions the cache is permitted to issue in parallel; and wherein the controller is adapted to offer a data destage operation permission to the cache in the plurality of caches associated with the highest first performance score.

公开(公告)号：HK1113212A1

公开(公告)日：2008-09-26

申请号：HK08108916

申请日：2008-08-12

Applicant: IBM

Inventor： ANDREWS JONATHAN JAY ,  NORTH GERAINT

IPC: G06F20060101

Abstract: In program code conversion, particularly dynamic binary translation, subject code 17 is translated into target code 21 through a translator 19 for execution on a target processor 13. Selected portions of subject code, such as library functions SFuncA 172, are replaced by instead executing a portion of native code such as a native function NFuncA 282. The native function is native to the target processor 13. The method further includes executing a subject code portion such as a subject function SFuncB 173 in place of a native code portion such library function NFuncB 283. This reverse binding technique substitutes subject code for selected portions of the native code, particularly native library functions in order to keep control within the translator 19. This helps to maintain an accurate subject state in the translator 19, amongst other advantages.

公开(公告)号：CA2776184C

公开(公告)日：2019-05-07

申请号：CA2776184

申请日：2012-05-07

Applicant: IBM

Inventor： NORTH GERAINT

IPC: H04L29/06

Abstract: A method, system, and computer program product enhances resource/process availability by providing hardware based buffering of network packets during checkpointing in a virtualized environment. A High Availability Checkpoint (HAC) utility pre-configures a physical network adapter to buffer outgoing network packets from virtual machines that employ a checkpointing technology. In response to receiving an outgoing network packet from a virtual machine and determining that the virtual machine employs a pre-specified checkpointing technology, the physical network adapter buffers the outgoing network packet. In addition, a primary host performs/facilitates checkpoint operations (associated with the virtual machine) with a secondary host. When checkpoint operations are successfully completed, the HAC utility triggers the transmission of the buffered network packets from the network adapter to a network destination. The physical network adapter minimizes checkpointing network latency by pre- assigning a higher priority to a buffered network packet from a checkpointing virtual machine than to a new network packet that originates from a non-checkpointing virtual machine.

公开(公告)号：GB2520503A

公开(公告)日：2015-05-27

申请号：GB201320537

申请日：2013-11-21

Applicant: IBM

Inventor： NORTH GERAINT ,  STARKE WILLIAM ,  NAYAR NARESH ,  NORSTRAND ALBERT JAMES VAN JR ,  GUTHRIE GUY LYNN

IPC: G06F11/14 ,  G06F9/455 ,  G06F11/20 ,  G06F12/08 ,  G06F12/0804 ,  G06F12/0806 ,  G06F12/0831 ,  G06F12/0855 ,  G06F12/128

Abstract: System comprising: a processor running a hypervisor for virtual machines (VMs); a cache, e.g. write-back cache; and a memory storing VM images and a log for a differential check-pointing failover. Cache rows comprise a memory address, cache line, and image modification flag. A cache controller sets the modification flag when a cache line is modified by a backed-up VM. Flagged cache lines addresses are written in the log upon eviction or during periodic checkpoints. The log is a circular buffer 200 and its free space is monitored, e.g. by a guard band. If the head of the log entries moves within the guard-band an interrupt is triggered and a cash flush initiated. This avoids full memory re-synch or failover if a consumer core cannot keep-up with a producer core. Replication of the VM image in another memory can be obtained by fetching the cache lines stored at the logged addresses.

公开(公告)号：GB2516087A

公开(公告)日：2015-01-14

申请号：GB201312422

申请日：2013-07-11

Applicant: IBM

Inventor： NORTH GERAINT ,  STARKE WILLIAM ,  GUTHRIE GUY LYNN ,  WILLIAMS PHILLIP ,  SHEN HUGH ,  NAYAR NARESH

IPC: G06F12/08 ,  G06F9/455 ,  G06F11/14 ,  G06F11/20 ,  G06F12/0804 ,  G06F12/0806 ,  G06F12/0842 ,  G06F12/0891 ,  G06F12/0895

Abstract: A system comprises: a processor running a hypervisor for virtual machines (VMs) and multiple threads; a cache, e.g. a write-back cache; and a memory storing VM images for a differential check-pointing failover technique. Cache rows comprise a memory address, a cache line, an image modification flag, and a thread ID. A cache controller sets the modification flag (430) when a cache line is modified (420) by a backed-up VM (425). It also sets the thread ID of the thread corresponding to the backed-up VM and responsible for the modified cache line. Flagged cache lines addresses are written in a log of the memory upon eviction (440) or during periodic checkpoints. Replication of the VM image in another memory can be obtained by fetching the cache lines stored at the logged addresses. Using thread IDs in the logs allows the update of the correct VM memory image.

公开(公告)号：DE102012212511A1

公开(公告)日：2013-01-24

申请号：DE102012212511

申请日：2012-07-17

Applicant: IBM

Inventor： NORTH GERAINT

IPC: G06F13/00 ,  G06F5/06 ,  G06F11/14

Abstract: Ein Verfahren, ein System und ein Computerprogrammprodukt optimieren die Verfügbarkeit von Ressourcen/Prozessen durch die Bereitstellung hardwarebasierter Pufferung von Netzwerkpaketen während der Durchführung von Checkpoints in einer virtualisierten Umgebung. Ein High-Availability-Checkpoint-(HAC bzw. Hochverfügbarkeits-Checkpoint)-Dienstprogramm konfiguriert einen physischen Netzwerkadapter vorab, um ausgehende Netzwerkpakete von virtuellen Maschinen zu puffern, die eine Checkpointing-Technologie einsetzen. Als Reaktion auf den Empfang eines ausgehenden Netzwerkpakets von einer virtuellen Maschine und der Bestimmung, dass die virtuelle Maschine eine vorgegebene Checkpointing-Technologie einsetzt, puffert der physische Netzwerkadapter das ausgehende Netzwerkpaket. Darüber hinaus führt ein primärer Host Checkpoint-Operationen mit einem sekundären Host durch bzw. unterstützt diese (in Verbindung mit der virtuellen Maschine). Wenn die Checkpoint-Operationen erfolgreich abgeschlossen sind, löst das HAC-Dienstprogramm die Übertragung der gepufferten Netzwerkpakete vom Netzwerkadapter an ein Ziel im Netzwerk aus. Der physische Netzwerkadapter minimiert die Netzwerklatenz beim Checkpointing, indem einem gepufferten Netzwerkpaket von einer virtuellen Maschine mit Checkpointing vorab eine höhere Priorität als einem neuen Netzwerkpaket, das von einer virtuellen Maschine ohne Checkpointing stammt, zugewiesen wird.

公开(公告)号：GB2493047A

公开(公告)日：2013-01-23

申请号：GB201208269

申请日：2012-05-11

Applicant: IBM

Inventor： NORTH GERAINT

IPC: G06F15/173 ,  G06F11/14

Abstract: Disclosed is a method and system of operating a data processing system with a virtualization management component generating a plurality of operating system partitions. The method includes receiving at a physical network adapter configuration information including an indication that at least one of the virtual machines employs checkpointing technology. Receiving at the adapter outgoing network packets from a virtual machine. In response to receipt by the adapter of the outgoing packets the adapter determines if the virtual machine sending the packet employs checkpointing and if the VM does then buffering the packets. Receiving a notification the a checkpointing operation has successfully completed then triggering transmission of the buffered network packet from the network adapter to its destination. The method may include facilitating a checkpointing operation of the state information of the VM to a second VM on a secondary host, by forwarding memory and CPU state information of the first VM to the second VM and providing to the secondary host an indication of an expected transmission of the outgoing network packets.