Managing NFS and KRPC Kernel Configurations in HP-UX 11i v3 (762807-001, March 2014)

results in increased throughput. However, if the server response is delayed or the network is
overloaded, the number of timeouts can increase.
HP recommends leaving this tunable enabled because it helps the system minimize NFS packet loss
on congested networks.
2.1.22 nfs3_enable_async_directio_read
Description
The nfs3_enable_async_directio_read tunable controls whether NFS clients perform direct I/O read
operations synchronously, where only a single read operation is performed at a time, or
asynchronously, where the client may issue multiple read operations in parallel. Enabling this feature
may improve read performance on NFS v3 filesystems mounted with the forcedirectio option.
forcedirectio is an NFS mount option that typically benefits large sequential data transfers and
database workloads. Most database applications, such as Oracle, prefer to manage their own data
cache resources and will benefit from bypassing any system file cache (such as the Unified File Cache
on HP-UX 11i v3). When an NFS client mounts a filesystem with the forcedirectio option, data is
transferred directly between the client and server without buffering on the client.
By default the direct I/O data transfers are synchronous, where the client sends a single read request
to the server and waits for the server to respond with the requested data before initiating a new
request. Enabling the nfs3_enable_async_directio_read tunable allows the client to send several I/O
requests in parallel before waiting for the server's response. The number of parallel direct I/O
requests is configurable via the nfs3_max_async_directio_requests tunable. This can greatly improve
read performance for applications that use direct I/O. Currently this feature is supported only for TCP
traffic.
Tested Values
Default: 0 (Tunable is disabled)
Min: 0
Max: 1 (Tunable is enabled)
Restrictions on Changing
• The nfs3_enable_async_directio_read tunable is dynamic. System reboot is not required to
activate a change made to this tunable.
• Only NFSv3 TCP mount points that are mounted with forcedirectio options are affected by
changing the value of this tunable.
Modifying the Value
If an application experiences poor read performance on an NFS filesystem mounted with the
forcedirectio option, enabling the nfs3_enable_async_directio_read tunable can improve the read
performance.
2.1.23 nfs3_enable_async_directio_write
Description
The nfs3_enable_async_directio_write tunable controls whether NFS clients perform direct I/O write
operations synchronously, where only a single write operation is performed at a time, or
asynchronously, where the client may issue multiple write operations in parallel. Enabling this feature
may improve write performance on NFS v3 filesystems mounted with the forcedirectio option.
forcedirectio is an NFS mount option that typically benefits large sequential data transfers and
database workloads. Most database applications, such as Oracle, prefer to manage their own data
cache resources and will benefit from bypassing any system file cache (such as the Unified File Cache