Amazon FSx for Lustre metrics and dimensions
Amazon FSx for Lustre publishes the metrics described in the following tables in the
AWS/FSx
namespace in Amazon CloudWatch for all FSx for Lustre file systems.
Topics
FSx for Lustre network I/O metrics
The AWS/FSx
namespace includes the following network I/O metrics.
All of these metrics take one dimension, FileSystemId
.
Metric | Description |
---|---|
DataReadBytes |
The number of bytes from reads by clients to the file system. The To calculate the average throughput (bytes per second)for a period, divide the
Units:
Valid statistics: |
DataWriteBytes |
The number of bytes from writes by clients to the file system. The To calculate the average throughput (bytes per second) for a period, divide the
Units:
Valid statistics: |
DataReadOperations |
The number of read operations. The To calculate the average number of read operations
(operations per second) for a period, divide the Units:
Valid statistics: |
DataWriteOperations |
The number of write operations. The To calculate the average number of write operations
(operations per second) for a period, divide the Units:
Valid statistics: |
MetadataOperations |
The number of metadata operations. The To calculate the average number of metadata operations
(operations per second) for a period, divide the Units:
Valid statistics: |
ClientConnections |
The number of active connections between clients and the file system. Unit: Count |
FSx for Lustre object storage server metrics
The AWS/FSx
namespace includes the following object storage server (OSS) metrics.
All of these metrics take two dimensions, FileSystemId
and FileServer
.
FileSystemId
– Your file system's Amazon resource ID.FileServer
– The name of the object storage server (OSS) in your Lustre file system. Each OSS is provisioned with one or more object storage targets (OSTs). OSS use the naming convention of OSS<HostIndex>, whereHostIndex
represents a 4-digit hexadecimal value (for example,OSS0001
). An OSS's ID is the ID of the first OST attached to it. For example, the first OSS attached toOST0000
andOST0001
, will useOSS0000
, and the second OSS attached toOST0002
,OST0003
will useOSS0002
.
Metric | Description |
---|---|
NetworkThroughputUtilization |
Network throughput utilization as a percentage of available network
throughput for your file system. This metric is equivalent to the sum of
The The The Unit: Percent Valid statistics: |
NetworkSentBytes |
The number of bytes sent by the file system. All traffic is considered in this metric, including data movement to and from linked data repositories. There is one metric emitted each minute for each of your file system's OSSs. The The The The To calculate sent throughput (bytes per second) for any statistic, divide the statistic by the seconds in the specified period. Unit: Bytes Valid statistics: |
NetworkReceivedBytes |
The number of bytes received by the file system. All traffic is considered in this metric, including data movement to and from linked data repositories. There is one metric emitted each minute for each of your file system's OSSs. The The The The To calculate throughput (bytes per second) for any statistic, divide the statistic by the seconds in the specified period. Unit: Bytes Valid statistics: |
FileServerDiskThroughputUtilization |
The disk throughput between your OSS and associated OSTs, as a percentage of the
provisioned limit determined by throughput capacity. This metric is equivalent to the
sum of The The The Unit: Percent Valid statistics: |
FSx for Lustre object storage target metrics
The AWS/FSx
namespace includes the following object storage target
(OST) metrics. All of these metrics take two dimensions, FileSystemId
and
StorageTargetId
.
Note
DiskReadOperations
and DiskWriteOperations
metrics are
not available on Scratch file systems, and DiskIopsUtilization
metrics are not
available on Scratch and Persistent HDD file systems.
Metric | Description |
---|---|
DiskReadBytes |
The number of bytes (disk IO) from any disk reads from this OST. There is one metric emitted each minute for each of your file system's OSTs. The The The The To calculate read disk throughput (bytes per second) for any statistic, divide the statistic by the seconds in the period. Unit: Bytes Valid statistics: |
DiskWriteBytes |
The number of bytes (disk IO) from any disk writes from this OST. There is one metric emitted each minute for each of your file system's OSTs. The The The The To calculate read disk throughput (bytes per second) for any statistic, divide the statistic by the seconds in the period Unit: Bytes Valid statistics: |
DiskReadOperations |
The number of read operations (disk IO) to this OST. There is one metric emitted each minute for each of your file system's OSTs. The The The The To calculate average disk IOPS over the period, use the Units: Count Valid statistics: |
DiskWriteOperations |
The number of write operations (disk IO) to this OST. There is one metric emitted each minute for each of your file system's OSTs. The The The The To calculate average disk IOPS over the period, use the Units: Count Valid statistics: |
DiskIopsUtilization |
The disk IOPS utilization of one OST, as a percentage of the OST's disk IOPS limit. There is one metric emitted each minute for each of your file system's OSTs. The The The Unit: Percent Valid statistics: |
FSx for Lustre metadata metrics
The AWS/FSx
namespace includes the following metadata metrics. The CPUUtilization
metric takes the FileSystemId
and FileServer
dimensions, while the other metrics
take the FileSystemId
and StorageTargetId
dimensions.
FileSystemId
– Your file system's Amazon resource ID.StorageTargetId
– The name of the metadata target (MDT). MDTs use the naming convention of MDT<MDTIndex> (for example,MDT0001
).FileServer
– The name of the metadata server (MDS) in your Lustre file system. Each MDS is provisioned with one metadata target (MDT). MDS use the naming convention of MDS<HostIndex>, whereHostIndex
represents a 4-digit hexadecimal value derived using the MDT index on the server. For example, the first MDS provisioned withMDT0000
will useMDS0000
, and the second MDS provisioned withMDT0001
will useMDS0001
. Your file system contains multiple metadata servers if your file system has a metadata configuration specified.
Metric | Description |
---|---|
CPUUtilization |
The percent utilization of your file system's MDS CPU resources. There is one metric emitted each minute for each of your file system's MDSs. The The The Unit: Percent Valid statistics: |
FileCreateOperations |
Total number of file create operations. Unit: Count |
FileOpenOperations |
Total number of file open operations. Unit: Count |
FileDeleteOperations |
Total number of file delete operations. Unit: Count |
StatOperations |
Total number of stat operations. Unit: Count |
RenameOperations |
Total number of directory renames, whether in-place directory renames or cross directory renames. Unit: Count |
FSx for Lustre storage capacity metrics
The AWS/FSx
namespace includes the following storage capacity
metrics. All of these metrics take two dimensions, FileSystemId
and
StorageTargetId
except LogicalDiskUsage
and
PhysicalDiskUsage
which take the FileSystemId
dimension.
Metric | Description |
---|---|
FreeDataStorageCapacity |
The amount of available storage capacity in this OST. There is one metric emitted each minute for each of your file system's OSTs. The The The The Unit: Bytes Valid statistics: |
|
The storage capacity utilization for a given file system OST. There is one metric emitted each minute for each of your file system's OSTs. The The The Unit: Percent Valid statistics: |
|
The storage capacity utilization for a given file system OST including space reserved for cached writes on the client. There is one metric emitted each minute for each of your file system's OSTs. The The The Unit: Percent Valid statistics: |
LogicalDiskUsage |
The amount of logical data stored (uncompressed). The Units:
Valid statistics: |
PhysicalDiskUsage |
The amount of storage physically occupied by file system data (compressed). The Units:
Valid statistics: |
FSx for Lustre S3 repository metrics
FSx for Lustre publishes the following AutoImport
(automatic import) and AutoExport
(automatic export) metrics into the FSx
namespace in CloudWatch. These metrics use dimensions
to enable more granular measurements of your data. All AutoImport
and AutoExport
metrics have the FileSystemId
and Publisher
dimensions.
Metric | Description |
---|---|
Dimension: |
The age, in seconds, of the oldest message waiting to be exported. The Units: Seconds Valid statistics: |
Dimension: |
The number of renames processed by the file system in response to a larger directory rename. The Units: Count Valid statistics: |
Dimension: |
The age, in seconds, of the oldest message waiting to be imported. The Units: Seconds Valid statistics: |
FSx for Lustre dimensions
Amazon FSx for Lustre metrics use the AWS/FSx
namespace and use the following dimensions.
The
FileSystemId
dimension denotes a file system's ID and filters the metrics that you request to that individual file system. You can find the ID on the Amazon FSx console on the Summary panel of the file system details page, in the File system ID field. The file system ID takes the form offs-01234567890123456
. You can also see the ID in the response of adescribe-file-systems
CLI command (the equivalent API action isDescribeFileSystems
).The
StorageTargetId
dimension denotes which OST (object storage target) or MDT (metadata target) published the metadata metrics. AStorageTargetId
takes the form ofOSTxxxx
(for example,OST0001
) orMDTxxxx
(for example,MDT0001
).The
FileServer
dimension denotes the followingFor OSS metrics: the name of the object storage server (OSS). OSS use the
OSSxxxx
naming convention (for example,OSS0002
).For the CPUUtilization metric: the name of a metadata server (MDS). MDS use the
MDSxxxx
naming convention (for example,MDS0002
).
The
Publisher
dimension is available in CloudWatch and Amazon CLI for theAutoImport
andAutoImport
metrics to denote which service published the metrics.
For more information about dimensions, see Dimensions in the Amazon CloudWatch User Guide.