بعض محتويات هذا التطبيق غير متوفرة في الوقت الحالي.
إذا استمرت هذه الحالة ، يرجى الاتصال بنا علىتعليق وإتصال
1. (WO2018183733) INPUT/OUTPUT(I/O) FENCING WITHOUT DEDICATED ARBITRATORS
ملاحظة: نص مبني على عمليات التَعرف الضوئي على الحروف. الرجاء إستخدام صيغ PDF لقيمتها القانونية

WHAT IS CLAIMED IS:

1. A computer-implemented method, comprising:

storing a coordination storage identifier in a storage device as metadata, wherein

the coordination storage identifier is associated with a node of a cluster coupled to the storage device; and

performing an input/output (I/O) fencing operation using the coordination storage

identifier.

2. The computer- implemented method of claim 1, further comprising:

accessing a configuration file, wherein

the configuration file comprises fencing mode metadata, and

the fencing mode metadata identifies the coordination storage identifier, and the coordination storage identifier identifies a coordinator and data disk.

3. The computer- implemented method of claim 2, wherein

the coordination storage identifier is a data key,

the data key is generated by a volume manager, and

the volume manager is executed by the node.

4. The computer- implemented method of claim 3, wherein

identifying one or more storage identifiers other than the coordination storage identifier to identify one or more data disks.

5. The computer-implemented method of claim 4, further comprising:

determining that another node other than the node has lost a fencing race;

determining whether the data key has been ejected from the coordinator and data disk by a fencing engine; and

if the data key has not been ejected from the coordinator and data disk by the fencing engine, ejecting the data key from the coordinator and data disk.

The computer- implemented method of claim 5, further comprising:

detecting that the cluster is partitioned into a plurality of network partitions; and ejecting the data key from the coordinator and data disk.

The computer-implemented method of claim 6, further comprising:

upon ejecting the data key from the coordinator and data disk, determining a result of a fencing race, wherein

the fencing race is performed as part of the I O fencing operation;

determining another node is a loser node;

sending a notification to the volume manager of the node to eject the data key of the loser node from the one or more data disks other than coordinator and data disk; and receiving confirmation from the volume manager that the data key has been ejected from the one or more data disks.

The computer- implemented method of claim 7, wherein

the coordinator and data disk and the one or more data disks are shared by the node and the another node,

the I/O fencing operation is performed without one or more dedicated arbitrators, and the I/O fencing operation is performed by the fencing engine and the volume manager on a same set of Small Computer System Interface (SCSI)-3 compliant disks.

A non-transitory computer readable storage medium comprising program instructions executable to:

store a coordination storage identifier in a storage device as metadata, wherein

the coordination storage identifier is associated with a node of a cluster coupled to the storage device; and

perform an input/output (I/O) fencing operation using the coordination storage identifier.

The non-transitory computer readable storage medium of claim 9, further comprising: accessing a configuration file, wherein

the configuration file comprises fencing mode metadata, and

the fencing mode metadata identifies the coordination storage identifier, and the coordination storage identifier identifies a coordinator and data disk.

The non-transitory computer readable storage medium of claim 10, wherein

the coordination storage identifier is a data key,

the data key is generated by a volume manager, and

the volume manager is executed by the node.

The non-transitory computer readable storage medium of claim 11, wherein

identifying one or more storage identifiers other than the coordination storage identifier to identify one or more data disks.

The non-transitory computer readable storage medium of claim 12, further comprising: determining that another node other than the node has lost a fencing race;

determining whether the data key has been ejected from the coordinator and data disk by a fencing engine;

if the data key has not been ejected from the coordinator and data disk by the fencing engine, ejecting the data key from the coordinator and data disk;

detecting that the cluster is partitioned into a plurality of network partitions;

ejecting the data key from the coordinator and data disk;

upon ejecting the data key from the coordinator and data disk, determining a result of a fencing race, wherein

the fencing race is performed as part of the I/O fencing operation;

determining another node is a loser node;

sending a notification to the volume manager of the node to eject the data key of the loser node from the one or more data disks other than coordinator and data disk; and

receiving confirmation from the volume manager that the data key has been ejected from the one or more data disks.

The non-transitory computer readable storage medium of claim 13, wherein

the coordinator and data disk and the one or more data disks are shared by the node and the another node,

the I/O fencing operation is performed without one or more dedicated arbitrators, and the I/O fencing operation is performed by the fencing engine and the volume manager on a same set of Small Computer System Interface (SCSI)-3 compliant disks.

A system comprising:

one or more processors; and

a memory coupled to the one or more processors, wherein the memory stores program instructions executable by the one or more processors to:

store a coordination storage identifier in a storage device as metadata, wherein

the coordination storage identifier is associated with a node of a cluster coupled to the storage device; and

perform an input/output (I/O) fencing operation using the coordination storage identifier.

The system of claim 15, further comprising:

accessing a configuration file, wherein

the configuration file comprises fencing mode metadata, and

the fencing mode metadata identifies the coordination storage identifier, and the coordination storage identifier identifies a coordinator and data disk.

The system of claim 16, wherein

the coordination storage identifier is a data key,

the data key is generated by a volume manager, and

the volume manager is executed by the node.

The system of claim 17, wherein

identifying one or more storage identifiers other than the coordination storage identifier to identify one or more data disks.

The system of claim 18, further comprising:

determining that another node other than the node has lost a fencing race;

determining whether the data key has been ejected from the coordinator and data disk by a fencing engine;

if the data key has not been ejected from the coordinator and data disk by the fencing engine, ejecting the data key from the coordinator and data disk;

detecting that the cluster is partitioned into a plurality of network partitions;

ejecting the data key from the coordinator and data disk;

upon ejecting the data key from the coordinator and data disk, determining a result of a fencing race, wherein

the fencing race is performed as part of the I O fencing operation;

determining another node is a loser node;

sending a notification to the volume manager of the loser node to eject the data key from the one or more data disks other than coordinator and data disk; and

receiving confirmation from the volume manager that the data key has been ejected from the one or more data disks.

The system of claim 19, wherein

the coordinator and data disk and the one or more data disks are shared by the node and the another node,

the I/O fencing operation is performed without one or more dedicated arbitrators, and the I/O fencing operation is performed by the fencing engine and the volume manager on a same set of Small Computer System Interface (SCSI)-3 compliant disks.