dillon 057e33d02c Change the write-behind code to take more care when starting
async I/O's.  The sequential read heuristic has been extended to
    cover writes as well.  We continue to call cluster_write() normally,
    thus blocks in the file will still be reallocated for large (but still
    random) I/O's, but I/O will only be initiated for truely sequential
    writes.

    This solves a number of annoying situations, especially with DBM (hash
    method) writes, and also has the side effect of fixing a number of
    (stupid) benchmarks.

Reviewed-by: mckusick
2000-04-02 00:55:28 +00:00
..
1999-08-28 01:08:13 +00:00
1999-11-21 12:38:21 +00:00
1999-10-29 18:09:36 +00:00
1999-10-29 18:09:36 +00:00
1999-08-28 01:08:13 +00:00
1999-08-28 01:08:13 +00:00
1999-11-14 13:54:44 +00:00
1999-10-05 21:19:41 +00:00
1999-08-28 01:08:13 +00:00
1999-08-28 01:08:13 +00:00
1999-11-21 19:03:20 +00:00
1999-08-28 01:08:13 +00:00
1999-08-28 01:08:13 +00:00
1999-08-28 01:08:13 +00:00
1999-08-28 01:08:13 +00:00
2000-03-20 16:28:35 +00:00
2000-03-20 16:28:35 +00:00