HP-UX HB v13.00 Ch-14 - JFS

HP-UX Handbook – Rev 13.00 Page 23 (of 47)
Chapter 14 Journaled File System (JFS)
October 29, 2013
read_ahead
The default for all VxFS read operations is to perform sequential read ahead. You can specify the
read_ahead cache advisory to implement the VxFS enhanced read ahead functionality. This
allows read aheads to detect more elaborate patterns, such as increasing or decreasing read
offsets or multithreaded file accesses, in addition to simple sequential reads. You can specify the
following values for read_ahead:
0—Disables read ahead functionality
1—Retains traditional sequential read ahead behavior
2—Enables enhanced read ahead for all reads
The default is 1
vx_era_nthreads
VxFS detects only sequential patterns, read_ahead detects patterns on a per-thread basis, up to a
maximum determined by vx_era_nthreads parameter.
The default number of threads is 5, but you can change the default value by setting the
vx_era_nthreads parameter in the /etc/system configuration file.
write_throttle
The write_throttle parameter is useful in special situations where a computer system has a
combination of a large amount of memory and slow storage devices.
In this configuration, sync operations, such as fsync(),may take long enough to complete that a
system appears to hang. This behavior occurs because the file system is creating dirty buffers (in-
memory updates) faster than they can be asynchronously flushed to disk without slowing system
performance.
Lowering the value of write_throttle limits the number of dirty buffers per file that a file system
generates before flushing the buffers to disk. After the number of dirty buffers for a file reaches
the write_throttle threshold, the file system starts flushing buffers to disk even if free memory is
still available.
The default value of write_throttle is zero, which puts no limit on the number of dirty buffers per
file.
If non-zero, VxFS limits the number of dirty buffers per file to write_throttle buffers. The default
value typically generates a large number of dirty buffers, but maintains fast user writes.