Techniques to manage non-disruptive SAN availability in a partitioned cluster
US-9639437-B2 · May 2, 2017 · US
US10346063B2 · US · B2
| Field | Value |
|---|---|
| Publication number | US-10346063-B2 |
| Application number | US-201615356413-A |
| Country | US |
| Kind code | B2 |
| Filing date | Nov 18, 2016 |
| Priority date | Nov 18, 2016 |
| Publication date | Jul 9, 2019 |
| Grant date | Jul 9, 2019 |
A practical reading order for non-experts. Skip the full description unless you need deep technical detail.
What the patent document calls the invention.
A short plain-language summary of the technical disclosure.
Who owns or filed the patent and who is credited as inventor.
Filing, priority, publication, and grant dates set the timeline.
The legal scope of protection — read this for what is actually claimed.
Technology tags used to group this patent with similar filings.
Prior art links and similar publications in this corpus.
Official abstract text for this publication.
Exemplary methods, apparatuses, and systems determine that quorum can be maintained for a storage object in a distributed storage system in the event a defined maximum number of first partitions in a first level of storage and a second partitions in a second level of storage fail. When it is determined that there are insufficient numbers of first partitions and/or second partitions, additional first partitions and/or second partitions are associated with the storage object in the distributed storage system. A number of votes is calculated for distribution and an allocation is defined for assigning the votes to each component and witness component of the storage object.
Opening claim text (preview).
What is claimed is: 1. A computer-implemented method, comprising: determining a threshold number of first partitions of a first level of storage required for each of a plurality of second partitions of a second level of storage to maintain a quorum for a first storage object across the plurality of second partitions, each second partition of the plurality of second partitions including one or more of the first partitions, a plurality of the first partitions storing components of the first storage object across a plurality of storage devices in a distributed storage system, wherein each second partition corresponds to a storage site in the distributed storage system and each first partition corresponds to a host on a corresponding storage site; adding one or more additional first partitions within each of one or more second partitions to reach the determined threshold number of first partitions required for each of the plurality of second partitions, wherein each of the one or more additional first partitions includes a witness component that participates in quorum voting for the first storage object but does not include a component of the first storage object; determining a number of votes to assign to each first partition, including the one or more additional first partitions, to maintain the quorum when a failure of up to a first number of first partitions of the first level and a second number of second partitions of the second level occurs; and allocating the determined number of votes to each of the components of the first storage object and to the witness components within each additional first partition, wherein voting by the components determines whether the quorum exists to access the first storage object. 2. The computer-implemented method of claim 1 , wherein allocating the determined number of votes to each of the components of the first storage object and the witness components comprises: assigning a number of votes to each first partition, including the one or more additional first partitions, such that each first partition has a same first number of votes as each other first partition and wherein each second partition has a same second number of votes as each other second partition. 3. The computer-implemented method of claim 2 , further comprising: assigning an additional vote to one of the components of the first storage object or one of the witness components when a combined number of votes for the components of the first storage object and the witness components across the second partitions is an even number. 4. The computer-implemented method of claim 1 , further comprising: determining that up to the first number of first partitions of the first level and the second number of second partitions of the second level have failed; and determining that the quorum is maintained when a first number of votes associated with the failed first partitions is less than a second number of votes associated with non-failed first partitions, the first storage object being accessible when the quorum for the first storage object is maintained. 5. The computer-implemented method of claim 1 , further comprising: determining a threshold number of second partitions of the second level of storage of a distributed storage system required to maintain the quorum for the first storage object by calculating the threshold number of second partitions from a first sum of twice the second number of second partitions plus one. 6. The computer-implemented method of claim 5 , further comprising: determining that there are less than the threshold number of second partitions; and in response to determining that there are less than the threshold number of second partitions of the second level, adding additional second partitions to the second level to reach the threshold number of second partitions. 7. The computer-implemented method of claim 1 , wherein determining the threshold number of first partitions of the first level of storage required for each of the plurality of second partitions of the second level of storage to maintain the quorum for the first storage object across the second partitions comprises: calculating a first value from a second sum of twice the first number of first partitions plus one; calculating a second value of from a difference between a total number of second partitions and twice the second number of second partitions; and calculating the threshold number of first partitions of the first level of storage by dividing the first value by the second value. 8. A non-transitory computer-readable medium storing instructions, which when executed by a processing device, cause the processing device to perform a method comprising: determining a threshold number of first partitions of a first level of storage required for each of a plurality of second partitions of a second level of storage to maintain a quorum for a first storage object across the plurality of second partitions, each second partition of the plurality of second partitions including one or more of the first partitions, a plurality of the first partitions storing components of the first storage object across a plurality of storage devices in a distributed storage system, wherein each second partition corresponds to a storage site in the distributed storage system and each first partition corresponds to a host on a corresponding storage site; adding one or more additional first partitions within each of one or more second partitions to reach the determined threshold number of first partitions required for each of the plurality of second partitions, wherein each of the one or more additional first partitions includes a witness component that participates in quorum voting for the first storage object but does not include a component of the first storage object; determining a number of votes to assign to each first partition, including the one or more additional first partitions, to maintain the quorum when a failure of up to a first number of first partitions of the first level and a second number of second partitions of the second level occurs; and allocating the determined number of votes to each of the components of the first storage object and to the witness components within each additional first partition, wherein voting by the components determines whether the quorum exists to access the first storage object. 9. The non-transitory computer-readable medium of claim 8 , wherein allocating the determined number of votes to each of the components of the first storage object and the witness components comprises: assigning a number of votes to each first partition, including the one or more additional first partitions, such that each first partition has a same first number of votes as each other first partition and each second partition has a same second number of votes as each other second partition. 10. The non-transitory computer-readable medium of claim 9 , further comprising: assigning an additional vote to one of the components of the first storage object or one of the witness components when a combined number of votes for the components of the first storage object and the witness components across the second partitions is an even number. 11. The non-transitory computer-readable medium of claim 8 , further comprising: determining that up to the first number of first partitions of the first level and the second number of second partitions of the second level have failed; and determining that the quorum is maintained when a first number of votes associated with the failed first partitions is less than a second number of votes associated with non-failed first partitions, the first storage object being accessible
Management of space entities, e.g. partitions, extents, pools · CPC title
by allocating resources to storage systems · CPC title
in relation to data integrity, e.g. data losses, bit errors · CPC title
at device level, e.g. emulation of a storage device or system · CPC title
Voting techniques · CPC title
Related publications grouped by family.
Answers are generated from the same data shown on this page.