Container space management in a data storage system
View Patent ↗Technologies are described for implementing container space management (CSM) in a data storage system. Performance may be improved by ensuring that the maximum number of drive spindles is made available to I/O loads. This may be accomplished by distributing data equally amongst all drive spindles, even if the drive spindles are in different logical drives. A workflow analysis may be performed to determine when the I/O load on the storage system is low and thus identify preferred times for background data re-striping. Data may be re-striped in a minimum number of movements using a data placement algorithm and data placement maps to select data to be re-striped. The data may be re-striped such that the most frequently accessed data within a tier is moved first. Such re-striping can be performed in a manner which optimizes the performance of the storage system both during, and after, the re-striping process.
1. A method for re-striping data between logical drives in a data storage container, the method comprising:
partitioning the logical drives into a plurality of tiers where the logical drives within a common tier comprise a similar performance characteristic;
storing a plurality of data placement maps that each define a stripe pattern for storing data in accordance with a number of logical drives;
adding a new logical drive to the data storage container;
determining a performance characteristic of the new logical drive;
determining a tier of the plurality of tiers for the new logical drive based on the determined performance characteristic;
determining to re-stripe data between the logical drives within the determined tier in response to the addition of the new logical drive;
selecting which data to re-stripe between the logical drives within the determined tier in accordance with a data placement map from the plurality of data placement maps that corresponds to a new number of logical drives that includes the new logical drive; and
imposing a preferred time ordering on the data selected to be re-striped.
2. The method of claim 1 , further comprising determining to re-stripe data in response to receiving a periodic data migration indicator.
3. The method of claim 1 , wherein selecting which data to re-stripe comprises establishing a maximum quota of data to migrate, dividing the maximum quota among the tiers as tier quotas, and dividing each tier quota among the logical drives within the respective tier.
4. The method of claim 1 , wherein imposing a preferred time ordering comprises ordering data to be migrated earlier in response to the data having a higher access frequency.
5. The method of claim 1 , wherein selecting which data to re-stripe comprises migrating data of a size granularity equal to a territory of the storage container.
6. A computer storage medium having computer-executable instructions stored thereon which, when executed by a computer system, cause the computer system to:
partition a set of logical drives into a plurality of tiers where the logical drives within a common tier comprise a similar performance characteristic;
store a plurality of data placement maps that each define a stripe pattern for storing data in accordance with a number of logical drives;
add a new logical drive to the data storage container;
determine a performance characteristic of the new logical drive;
determine a tier of the plurality of tiers for the new logical drive based on the determined performance characteristic;
determine to re-stripe data between the logical drives within the determined tier in response to the addition of the new logical drive;
select which data to re-stripe between the logical drives within the determined tier in accordance with a data placement map from the plurality of data placement maps that corresponds to a new number of logical drives that includes the new logical drive; and
impose a preferred time ordering on the data selected to be re-striped.
7. The computer storage medium of claim 6 , further comprising determining to re-stripe data in response to receiving a periodic data migration indicator.
8. The computer storage medium of claim 6 , wherein selecting which data to re-stripe comprises establishing a maximum quota of data to migrate, dividing the maximum quota among the tiers as tier quotas, and dividing each tier quota among the logical drives within the respective tier.
9. The computer storage medium of claim 6 , wherein imposing a preferred time ordering comprises ordering data to be migrated earlier in response to the data having a higher access frequency.
10. The computer storage medium of claim 6 , wherein selecting which data to re-stripe comprises migrating data of a size granularity equal to a territory of the storage container.
11. A data storage system comprising:
a storage subsystem;
a storage container associated with the storage subsystem;
a set of logical drives associated with the storage container; and
one or more container space management modules operable to cause the storage subsystem to:
partition the set of logical drives into a plurality of tiers where the logical drives within a common tier comprise a similar performance characteristic;
store a plurality of data placement maps that each define a stripe pattern for storing data in accordance with a number of logical drives;
add a new logical drive to the data storage container;
determine a performance characteristic of the new logical drive;
determine a tier of the plurality of tiers for the new logical drive based on the determined performance characteristic;
determine to re-stripe data between the logical drives within the determined tier in response to the addition of the new logical drive tier;
select which data to re-stripe between the logical drives within the determined tier in response to the addition of the new logical drive in accordance with a data placement map from the plurality of data placement maps that corresponds to a new number of logical drives that includes the new logical drive; and
impose a preferred time ordering on the data selected to be re-striped.
12. The data storage system of claim 11 , further comprising determining to re-stripe data in response to receiving a periodic data migration indicator.
13. The data storage system of claim 11 , wherein selecting which data to re-stripe comprises establishing a maximum quota of data to migrate, dividing the maximum quota among the tiers as tier quotas, and dividing each tier quota among the logical drives within the respective tier.
14. The data storage system of claim 11 , wherein imposing a preferred time ordering comprises ordering data to be migrated earlier in response to the data having a higher access frequency.