Hadoop Azure 支援：ABFS — Azure Data Lake Storage Gen2

az extension add --name storage-preview

$  az storage account
usage: az storage account create [-h] [--verbose] [--debug]
     [--output {json,jsonc,table,tsv,yaml,none}]
     [--query JMESPATH] --resource-group
     RESOURCE_GROUP_NAME --name ACCOUNT_NAME
     [--sku {Standard_LRS,Standard_GRS,Standard_RAGRS,Standard_ZRS,Premium_LRS,Premium_ZRS}]
     [--location LOCATION]
     [--kind {Storage,StorageV2,BlobStorage,FileStorage,BlockBlobStorage}]
     [--tags [TAGS [TAGS ...]]]
     [--custom-domain CUSTOM_DOMAIN]
     [--encryption-services {blob,file,table,queue} [{blob,file,table,queue} ...]]
     [--access-tier {Hot,Cool}]
     [--https-only [{true,false}]]
     [--file-aad [{true,false}]]
     [--hierarchical-namespace [{true,false}]]
     [--bypass {None,Logging,Metrics,AzureServices} [{None,Logging,Metrics,AzureServices} ...]]
     [--default-action {Allow,Deny}]
     [--assign-identity]
     [--subscription _SUBSCRIPTION]

$ az account list-locations -o table

DisplayName          Latitude    Longitude    Name
-------------------  ----------  -----------  ------------------
East Asia            22.267      114.188      eastasia
Southeast Asia       1.283       103.833      southeastasia
Central US           41.5908     -93.6208     centralus
East US              37.3719     -79.8164     eastus
East US 2            36.6681     -78.3889     eastus2
West US              37.783      -122.417     westus
North Central US     41.8819     -87.6278     northcentralus
South Central US     29.4167     -98.5        southcentralus
North Europe         53.3478     -6.2597      northeurope
West Europe          52.3667     4.9          westeurope
Japan West           34.6939     135.5022     japanwest
Japan East           35.68       139.77       japaneast
Brazil South         -23.55      -46.633      brazilsouth
Australia East       -33.86      151.2094     australiaeast
Australia Southeast  -37.8136    144.9631     australiasoutheast
South India          12.9822     80.1636      southindia
Central India        18.5822     73.9197      centralindia
West India           19.088      72.868       westindia
Canada Central       43.653      -79.383      canadacentral
Canada East          46.817      -71.217      canadaeast
UK South             50.941      -0.799       uksouth
UK West              53.427      -3.084       ukwest
West Central US      40.890      -110.234     westcentralus
West US 2            47.233      -119.852     westus2
Korea Central        37.5665     126.9780     koreacentral
Korea South          35.1796     129.0756     koreasouth
France Central       46.3772     2.3730       francecentral
France South         43.8345     2.1972       francesouth
Australia Central    -35.3075    149.1244     australiacentral
Australia Central 2  -35.3075    149.1244     australiacentral2

az storage account create --verbose \
    --name abfswales1 \
    --resource-group devteam2 \
    --kind StorageV2 \
    --hierarchical-namespace true \
    --location ukwest \
    --sku Standard_LRS \
    --https-only true \
    --encryption-services blob \
    --access-tier Hot \
    --tags owner=engineering \
    --assign-identity \
    --output jsonc

{
  "primaryEndpoints": {
    "blob": "https://abfswales1.blob.core.windows.net/",
    "dfs": "https://abfswales1.dfs.core.windows.net/",
    "file": "https://abfswales1.file.core.windows.net/",
    "queue": "https://abfswales1.queue.core.windows.net/",
    "table": "https://abfswales1.table.core.windows.net/",
    "web": "https://abfswales1.z35.web.core.windows.net/"
  }
}

az storage account  show-connection-string --name abfswales1
{
  "connectionString": "DefaultEndpointsProtocol=https;EndpointSuffix=core.windows.net;AccountName=abfswales1;AccountKey=ZGlkIHlvdSByZWFsbHkgdGhpbmsgSSB3YXMgZ29pbmcgdG8gcHV0IGEga2V5IGluIGhlcmU/IA=="
}

<property>
  <name>fs.azure.account.key.abfswales1.dfs.core.windows.net</name>
  <value>ZGlkIHlvdSByZWFsbHkgdGhpbmsgSSB3YXMgZ29pbmcgdG8gcHV0IGEga2V5IGluIGhlcmU/IA==</value>
</property>

$ hadoop fs -ls abfs://container1@abfswales1.dfs.core.windows.net/

ls: `abfs://container1@abfswales1.dfs.core.windows.net/': No such file or directory

$ hadoop fs -D fs.azure.createRemoteFileSystemDuringInitialization=true \
 -ls abfs://container1@abfswales1.dfs.core.windows.net/

<property>
  <name>fs.azure.account.auth.type.abfswales1.dfs.core.windows.net</name>
  <value>SharedKey</value>
  <description>
  </description>
</property>
<property>
  <name>fs.azure.account.key.abfswales1.dfs.core.windows.net</name>
  <value>ZGlkIHlvdSByZWFsbHkgdGhpbmsgSSB3YXMgZ29pbmcgdG8gcHV0IGEga2V5IGluIGhlcmU/IA==</value>
  <description>
  The secret password. Never share these.
  </description>
</property>

<property>
  <name>fs.azure.account.auth.type</name>
  <value>OAuth</value>
  <description>
  Use OAuth authentication
  </description>
</property>
<property>
  <name>fs.azure.account.oauth.provider.type</name>
  <value>org.apache.hadoop.fs.azurebfs.oauth2.ClientCredsTokenProvider</value>
  <description>
  Use client credentials
  </description>
</property>
<property>
  <name>fs.azure.account.oauth2.client.endpoint</name>
  <value></value>
  <description>
  URL of OAuth endpoint
  </description>
</property>
<property>
  <name>fs.azure.account.oauth2.client.id</name>
  <value></value>
  <description>
  Client ID
  </description>
</property>
<property>
  <name>fs.azure.account.oauth2.client.secret</name>
  <value></value>
  <description>
  Secret
  </description>
</property>

<property>
  <name>fs.azure.account.auth.type</name>
  <value>OAuth</value>
  <description>
  Use OAuth authentication
  </description>
</property>
<property>
  <name>fs.azure.account.oauth.provider.type</name>
  <value>org.apache.hadoop.fs.azurebfs.oauth2.UserPasswordTokenProvider</value>
  <description>
  Use user and password
  </description>
</property>
<property>
  <name>fs.azure.account.oauth2.client.endpoint</name>
  <value></value>
  <description>
  URL of OAuth 2.0 endpoint
  </description>
</property>
<property>
  <name>fs.azure.account.oauth2.user.name</name>
  <value></value>
  <description>
  username
  </description>
</property>
<property>
  <name>fs.azure.account.oauth2.user.password</name>
  <value></value>
  <description>
  password for account
  </description>
</property>

<property>
  <name>fs.azure.account.auth.type</name>
  <value>OAuth</value>
  <description>
  Use OAuth 2.0 authentication
  </description>
</property>
<property>
  <name>fs.azure.account.oauth.provider.type</name>
  <value>org.apache.hadoop.fs.azurebfs.oauth2.RefreshTokenBasedTokenProvider</value>
  <description>
  Use the Refresh Token Provider
  </description>
</property>
<property>
  <name>fs.azure.account.oauth2.refresh.token</name>
  <value></value>
  <description>
  Refresh token
  </description>
</property>
<property>
  <name>fs.azure.account.oauth2.refresh.endpoint</name>
  <value></value>
  <description>
  Refresh token endpoint
  </description>
</property>
<property>
  <name>fs.azure.account.oauth2.client.id</name>
  <value></value>
  <description>
  Optional Client ID
  </description>
</property>

<property>
  <name>fs.azure.account.auth.type</name>
  <value>OAuth</value>
  <description>
  Use OAuth authentication
  </description>
</property>
<property>
  <name>fs.azure.account.oauth.provider.type</name>
  <value>org.apache.hadoop.fs.azurebfs.oauth2.MsiTokenProvider</value>
  <description>
  Use MSI for issuing OAuth tokens
  </description>
</property>
<property>
  <name>fs.azure.account.oauth2.msi.tenant</name>
  <value></value>
  <description>
  Optional MSI Tenant ID
  </description>
</property>
<property>
  <name>fs.azure.account.oauth2.msi.endpoint</name>
  <value></value>
  <description>
   MSI endpoint
  </description>
</property>
<property>
  <name>fs.azure.account.oauth2.client.id</name>
  <value></value>
  <description>
  Optional Client ID
  </description>
</property>

<property>
  <name>fs.azure.account.auth.type</name>
  <value>Custom</value>
  <description>
  Custom Authentication
  </description>
</property>
<property>
  <name>fs.azure.account.oauth.provider.type</name>
  <value></value>
  <description>
  classname of Custom Authentication Provider
  </description>
</property>

<property>
  <name>fs.azure.enable.delegation.token</name>
  <value>true</value>
  <description>Make this true to use delegation token provider</description>
</property>
<property>
  <name>fs.azure.delegation.token.provider.type</name>
  <value>{fully-qualified-class-name-for-implementation-of-CustomDelegationTokenManager-interface}</value>
</property>

<property>
  <name>fs.azure.account.auth.type</name>
  <value>SAS</value>
</property>
<property>
  <name>fs.azure.sas.token.provider.type</name>
  <value>{fully-qualified-class-name-for-implementation-of-SASTokenProvider-interface}</value>
</property>

# this variable is only here to avoid typing the same values twice.
# It's name is not important.
export DISTCP_PROXY_OPTS="-Dhttps.proxyHost=web-proxy.example.com -Dhttps.proxyPort=80"

hadoop distcp \
  -D mapreduce.map.java.opts="$DISTCP_PROXY_OPTS" \
  -D mapreduce.reduce.java.opts="$DISTCP_PROXY_OPTS" \
  -update -skipcrccheck -numListstatusThreads 40 \
  hdfs://namenode:8020/users/alice abfs://backups@account.dfs.core.windows.net/users/alice

java.lang.RuntimeException: java.lang.ClassNotFoundException:
    Class org.apache.hadoop.fs.azurebfs.AzureBlobFileSystem not found
  at org.apache.hadoop.conf.Configuration.getClass(Configuration.java:2625)
  at org.apache.hadoop.fs.FileSystem.getFileSystemClass(FileSystem.java:3290)
  at org.apache.hadoop.fs.FileSystem.createFileSystem(FileSystem.java:3322)
  at org.apache.hadoop.fs.FileSystem.access$200(FileSystem.java:136)
  at org.apache.hadoop.fs.FileSystem$Cache.getInternal(FileSystem.java:3373)
  at org.apache.hadoop.fs.FileSystem$Cache.get(FileSystem.java:3341)
  at org.apache.hadoop.fs.FileSystem.get(FileSystem.java:491)
  at org.apache.hadoop.fs.Path.getFileSystem(Path.java:361)
Caused by: java.lang.ClassNotFoundException:
    Class org.apache.hadoop.fs.azurebfs.AzureBlobFileSystem not found
  at org.apache.hadoop.conf.Configuration.getClassByName(Configuration.java:2529)
  at org.apache.hadoop.conf.Configuration.getClass(Configuration.java:2623)
  ... 16 more

export HADOOP_SHELL_SCRIPT_DEBUG=true

Operation failed: "Server failed to authenticate the request.
 Make sure the value of Authorization header is formed correctly including the signature.",
 403, HEAD, https://account.dfs.core.windows.net/container2?resource=filesystem&timeout=90
  at org.apache.hadoop.fs.azurebfs.services.AbfsRestOperation.execute(AbfsRestOperation.java:135)
  at org.apache.hadoop.fs.azurebfs.services.AbfsClient.getFilesystemProperties(AbfsClient.java:209)
  at org.apache.hadoop.fs.azurebfs.AzureBlobFileSystemStore.getFilesystemProperties(AzureBlobFileSystemStore.java:259)
  at org.apache.hadoop.fs.azurebfs.AzureBlobFileSystem.fileSystemExists(AzureBlobFileSystem.java:859)
  at org.apache.hadoop.fs.azurebfs.AzureBlobFileSystem.initialize(AzureBlobFileSystem.java:110)

$ hadoop fs -ls abfs://container@abfswales2.dfs.core.windows.net/

ls: Configuration property abfswales2.dfs.core.windows.net not found.

$ hadoop fs -ls abfs://container@abfswales1.dfs.core.windows.net/

ls: `abfs://container@abfswales1.dfs.core.windows.net/': No such file or directory

$ bin/hadoop fs -ls abfs://container@abfswales1.dfs.core.windows.net/

 ...

ls: HTTP Error 200;
  url='https://login.microsoftonline.com/02a07549-0a5f-4c91-9d76-53d172a638a2/oauth2/authorize'
  AADToken: HTTP connection to
  https://login.microsoftonline.com/02a07549-0a5f-4c91-9d76-53d172a638a2/oauth2/authorize
  failed for getting token from AzureAD.
  Unexpected response.
  Check configuration, URLs and proxy settings.
  proxies=none;
  requestId='dd9d526c-8b3d-4b3f-a193-0cf021938600';
  contentType='text/html; charset=utf-8';

<property>
  <name>fs.azure.identity.transformer.service.principal.id</name>
  <value>service principal object id</value>
  <description>
  An Azure Active Directory object ID (oid) used as the replacement for names contained
  in the list specified by “fs.azure.identity.transformer.service.principal.substitution.list”.
  Notice that instead of setting oid, you can also set $superuser here.
  </description>
</property>
<property>
  <name>fs.azure.identity.transformer.service.principal.substitution.list</name>
  <value>user1</value>
  <description>
  A comma separated list of names to be replaced with the service principal ID specified by
  “fs.azure.identity.transformer.service.principal.id”.  This substitution occurs
  when setOwner, setAcl, modifyAclEntries, or removeAclEntries are invoked with identities
  contained in the substitution list. Notice that when in non-secure cluster, asterisk symbol *
  can be used to match all user/group.
  </description>
</property>