I wouldn't expect the noatime option to make much difference; though using direct I/O in BerkeleyDB could help a little. It's important to remember that the BDB cache files aren't read or written like normal files, they're just serving as backing store for a mapped memory region. BDB won't actually issue reads or writes to the individual database files unless it needs to flush the BDB cache or pull something in that's not in the cache. Solaris will generally only update the atime once after the first mmap reference.
On Fri, 20 Jan 2006, Spicer, Kevin wrote:
From: Daniel Henninger [mailto:daniel@ncsu.edu]It may be worth adding the noatime flag to the filesystems that hold data and (bdb) logs. You are indexing a lot of attributes, do you need
No atime? That's interesting. I've never heard of that, what does that do? From mount_ufs(1M)noatime By default, the file system is mounted with normal access time (atime) recording. If noatime is specified, the file system will ignore access time updates on files, except when they coincide with updates to the ctime or mtime. See stat(2). This option reduces disk activity on file systems where access times are unimportant (for example, a Usenet news spool).
noatime turns off access time recording regardless of dfratime or nodfratime.
The POSIX standard requires that access times be marked on files. -noatime ignores them unless the file is also modified. I think this was introduced in Sol7 or 8,
This is still not a lot files to really make a difference.
You are better off looking at forcedirectio if it is available on solaris 8. This certainly helps with sql db performance.
-- -- Howard Chu Chief Architect, Symas Corp. http://www.symas.com Director, Highland Sun http://highlandsun.com/hyc OpenLDAP Core Team http://www.openldap.org/project/