release notes | Book: 1.9.5, 1.9.12 (opt, FHS), 2.11 (FHS), 2.12 (FHS), 2.13 (FHS), 2.14 (FHS), | Wiki | Q&A black_bg
Web: Multi-page, Single page | PDF: A4-size, Letter-size | eBook: epub black_bg
Partition Parameters
Prev Chapter 11. dCache Partitioning Next
The dCache Book > Configuration of dCache > dCache Partitioning > Partition Parameters

Partition Parameters

The following list describes which parameters may be used in conjunction with dCache partitioning.

Recall that the total cost of a pool is a linear combination of the performance and space cost. It is calculated by

totalCost = ccf * perfCost + scf * spaceCost

where the cpu cost factor ccf and the space cost factor scf are configurable with the command pm set.

pm set -spacecostfactor=<value> -cpucostfactor=<value>

Note

Using the command pm set without specifying a partition leads to changes in the default partition.

To set these and more values see the table below.

<value> = 0.0 implies that the feature is disabled.

<value> = off implies that the value is inherited from the default section.

CommandMeaningType

pm set [<partitionName>] -spacecostfactor=<scf>

Sets the space cost factor for the partition.

The default value is 1.0.

float

pm set [<partitionName>] -cpucostfactor=<ccf>

Sets the cpu cost factor for the partition.

The default value is 1.0.

float

pm set [<partitionName>] -idle=<idle-value>

The concept of the idle value will be turned on if <idle-value> > 0.0.

A pool is idle if its performance cost is smaller than the <idle-value>. Otherwise it is not idle.

If one or more pools that satisfy the read request are idle then only one of them is chosen for a particular file irrespective of total cost. I.e. if the same file is requested more than once it will always be taken from the same pool. This allowes the copies on the other pools to age and be garbage collected.

The default value is 0.0, which disables this feature.

float

pm set [<partitionName>] -p2p=<p2p-value>

Sets the static replication threshold for the partition.

If the performance cost on the best pool exceeds <p2p-value> and the value for <slope> = 0.0 then this pool is called hot and a pool to pool replication may be triggered.

The default value is 0.0, which disables this feature.

float

pm set [<partitionName>] -alert=<value>

Sets the alert value for the partition.

If the best pool’s performance cost exceeds the p2p value and the alert value then no pool to pool copy is triggered and a message will be logged stating that no pool to pool copy will be made.

The default value is 0.0, which disables this feature.

float

pm set [<partitionName>] -panic=<value>

Sets the panic cost cut level for the partition.

If the performance cost of the best pool exceeds the panic cost cut level the request will fail.

The default value is 0.0, which disables this feature.

float

pm set [<partitionName>] -fallback=<value>

Sets the fallback cost cut level for the partition.

If the best pool’s performance cost exceeds the fallback cost cut level then a pool of the next level will be chosen. This means for example that instead of choosing a pool with readpref = 20 a pool with readpref < 20 will be chosen.

The default value is 0.0, which disables this feature.

float

pm set [<partitionName>] -slope=<slope>

Sets the dynamic replication threshold value for the partition.

If <slope>> 0.01 then the product of best pool’s performance cost and <slope> is used as threshold for pool to pool replication.

If the performance cost on the best pool exceeds this threshold then this pool is called hot.

The default value is 0.0, which disables this feature.

float

pm set [<partitionName>] -p2p-allowed=<value>

This value can be specified if an HSM is attached to the dCache.

If a partition has no HSM connected, then this option is overridden. This means that no matter which value is set for p2p-allowed the pool to pool replication will always be allowed.

By setting <value> = off the values for p2p-allowed, p2p-oncost and p2p-fortransfer will take over the value of the default partition.

If <value> = yes then pool to pool replication is allowed.

As a side effect of setting <value> = no the values for p2p-oncost and p2p-fortransfer will also be set to no.

The default value is yes.

boolean

pm set [<partitionName>] -p2p-oncost=<value>

Determines whether pool to pool replication is allowed if the best pool for a read request is hot.

The default value is no.

boolean

pm set [<partitionName>] -p2p-fortransfer=<value>

If the best pool is hot and the requested file will be copied either from the hot pool or from tape to another pool, then the requested file will be read from the pool where it just had been copied to if <value> = yes. If <value> = no then the requested file will be read from the hot pool.

The default value is no.

boolean

pm set [<partitionName>] -stage-allowed=<value>

Set the stage allowed value to yes if a tape system is connected and to no otherwise.

As a side effect, setting the value for stage-allowed to no changes the value for stage-oncost to no.

The default value is no.

boolean

pm set [<partitionName>] -stage-oncost=<value>

If the best pool is hot, p2p-oncost is disabled and an HSM is connected to a pool then this parameter determines whether to stage the requested file to a different pool.

The default value is no.

boolean

pm set [<partitionName>] -max-copies=<copies>

Sets the maximal number of replicas of one file. If the maximum is reached no more replicas will be created.

The default value is 500.

integer
Prev Up Next
Parameters, partitions and inheritance Home Partitions and Links