update replay_align and replay_scale documentation

Options replay_align and replay_scale both happen after sector to byte
translation. This can cause the offset scaling to be unaligned. Make a
note that both options operate on the byte level and replay_align should
most likely be used when replay_scale is used.

Signed-off-by: Dennis Zhou <dennis@kernel.org>
Signed-off-by: Jens Axboe <axboe@kernel.dk>

diff --git a/HOWTO b/HOWTO
index 95289040dd3fd58a0bb70dfb0a94fadf1475e175..a2503e9a6b73b093aee91c65ba2255f9cc690746 100644 (file)
--- a/HOWTO
+++ b/HOWTO
@@ -2559,12 +2559,13 @@ I/O replay
 
 .. option:: replay_align=int
 
-       Force alignment of I/O offsets and lengths in a trace to this power of 2
-       value.
+       Force alignment of the byte offsets in a trace to this value. The value
+       must be a power of 2.
 
 .. option:: replay_scale=int
 
-       Scale sector offsets down by this factor when replaying traces.
+       Scale byte offsets down by this factor when replaying traces. Should most
+       likely use :option:`replay_align` as well.
 
 .. option:: replay_skip=str
 

diff --git a/fio.1 b/fio.1
index 5c11d963d93dc02d0bf5fd34a3ac6dd633784acb..bf181b345548414865d7d138ba38c372b1619941 100644 (file)
--- a/fio.1
+++ b/fio.1
@@ -2257,11 +2257,12 @@ Unfortunately this also breaks the strict time ordering between multiple
 device accesses.
 .TP
 .BI replay_align \fR=\fPint
-Force alignment of I/O offsets and lengths in a trace to this power of 2
-value.
+Force alignment of the byte offsets in a trace to this value. The value
+must be a power of 2.
 .TP
 .BI replay_scale \fR=\fPint
-Scale sector offsets down by this factor when replaying traces.
+Scale bye offsets down by this factor when replaying traces. Should most
+likely use \fBreplay_align\fR as well.
 .SS "Threads, processes and job synchronization"
 .TP
 .BI replay_skip \fR=\fPstr