Configuring the HPE Ezmeral Data Fabric POSIX Client
Explains how to set the number of RPC requests that POSIX clients send to a cluster.
About this task
The default RPC requests configuration can negatively impact performance and memory. To avoid performance and memory issues, configure the number of outstanding RPC requests to the cluster to be 128.
Perform the following steps as the root user on each POSIX client machine:
Procedure
-
Issue the following commands to create the sunrpc.conf file under
/etc/modprobe.d with the recommended configuration:
These commands enable the configuration to persist after a reboot of the NFS client machine.echo "options sunrpc tcp_slot_table_entries=128" >> /etc/modprobe.d/sunrpc.conf echo "options sunrpc tcp_max_slot_table_entries=128" >> /etc/modprobe.d/sunrpc.conf
-
Issue the following echo commands:
The commands enable the configuration to take effect after you remount the POSIX client to the HPE Ezmeral Data Fabric cluster.echo 128 > /proc/sys/sunrpc/tcp_slot_table_entries echo 128 > /proc/sys/sunrpc/tcp_max_slot_table_entries
-
Remount the POSIX client to the HPE Ezmeral Data Fabric cluster. For example, the following commands unmount
and mount the NFS assuming that the cluster is mounted at /mapr:
umount /mapr mount -o hard,nolock 127.0.0.1:/mapr /mapr
NOTEFailure to configure this property may result in the following error in /usr/local/mapr-loopbacknfs/log:ERROR nfsserver[38960] fs/nfsd/requesthandle.cc:791 0.0.0.0[0] cannot allocate more OncRpcContexts: [numDropped=2556001] dropping connection from nfsc=10.13.64.225:0
CentOS Troubleshooting Tip
After the reboot of the node, if the /proc/sys/sunrpc directory is not available, or if
rpcidmapd
is not running, start therpcidmapd
service using the following command:service rpcidmapd start
.