block: document iostat changes for disk busy time accounting

Commit Message

Konstantin Khlebnikov June 9, 2019, 11:14 a.m. UTC

Since commit 5b18b5a73760 ("block: delete part_round_stats and switch to
less precise counting") io_ticks is approximated by adding one at each
start and end of requests if jiffies has changed.

This works perfectly for requests shorter than a jiffy. If requests runs
more than 2 jiffies some I/O time will not be accounted unless there are
other reuqests.

Fixes: 5b18b5a73760 ("block: delete part_round_stats and switch to less precise counting")
Signed-off-by: Konstantin Khlebnikov <[e-mail]>
Links: https://lore.kernel.org/lkml/155413438824.3201.15254568091182734151.stgit@buzz/
---
 Documentation/iostats.txt |    4 ++++
 1 file changed, 4 insertions(+)

Patch

diff --git a/Documentation/iostats.txt b/Documentation/iostats.txt
index 49df45f90e8a..5d63b18bd6d1 100644
--- a/Documentation/iostats.txt
+++ b/Documentation/iostats.txt
@@ -97,6 +97,10 @@  Field  9 -- # of I/Os currently in progress
 Field 10 -- # of milliseconds spent doing I/Os
     This field increases so long as field 9 is nonzero.
 
+    Since 5.0 this field counts jiffies when at least one request was
+    started or completed. If request runs more than 2 jiffies then some
+    I/O time will not be accounted unless there are other requests.
+
 Field 11 -- weighted # of milliseconds spent doing I/Os
     This field is incremented at each I/O start, I/O completion, I/O
     merge, or read of these stats by the number of I/Os in progress