Handle 32-bit overflows in disk utilization stats

Linux prints [1] some of the values reported in block device's `stat`
sysfs file as 32-bit unsigned integers. fio interprets them as 64-bit
integers when reading that sysfs file and performs further arithmetics
on them in 64-bits. If the reported value overflows during fio run,
a huge bogus value is reported in the "disk utilization" block instead.

[1] https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/tree/block/genhd.c#n962

Signed-off-by: Alexey Neyman <aneyman@google.com>

diff --git a/diskutil.c b/diskutil.c
index 40f2c260308aafece4128b9aca21c1abc175b0ad..69b3dd263f7b11b83b544c394e3d7920150540a7 100644 (file)
--- a/diskutil.c
+++ b/diskutil.c
@@ -77,6 +77,23 @@ static int get_io_ticks(struct disk_util *du, struct disk_util_stat *dus)
        return ret != 10;
 }
 
+static uint64_t safe_32bit_diff(uint64_t nval, uint64_t oval)
+{
+       /* Linux kernel prints some of the stat fields as 32-bit integers. It is
+        * possible that the value overflows, but since fio uses unsigned 64-bit
+        * arithmetic in update_io_tick_disk(), it instead results in a huge
+        * bogus value being added to the respective accumulating field. Just
+        * in case Linux starts reporting these metrics as 64-bit values in the
+        * future, check that overflow actually happens around the 32-bit
+        * unsigned boundary; assume overflow only happens once between
+        * successive polls.
+        */
+       if (oval <= nval || oval >= (1ull << 32))
+               return nval - oval;
+       else
+               return (1ull << 32) + nval - oval;
+}
+
 static void update_io_tick_disk(struct disk_util *du)
 {
        struct disk_util_stat __dus, *dus, *ldus;
@@ -96,10 +113,11 @@ static void update_io_tick_disk(struct disk_util *du)
        dus->s.ios[1] += (__dus.s.ios[1] - ldus->s.ios[1]);
        dus->s.merges[0] += (__dus.s.merges[0] - ldus->s.merges[0]);
        dus->s.merges[1] += (__dus.s.merges[1] - ldus->s.merges[1]);
-       dus->s.ticks[0] += (__dus.s.ticks[0] - ldus->s.ticks[0]);
-       dus->s.ticks[1] += (__dus.s.ticks[1] - ldus->s.ticks[1]);
-       dus->s.io_ticks += (__dus.s.io_ticks - ldus->s.io_ticks);
-       dus->s.time_in_queue += (__dus.s.time_in_queue - ldus->s.time_in_queue);
+       dus->s.ticks[0] += safe_32bit_diff(__dus.s.ticks[0], ldus->s.ticks[0]);
+       dus->s.ticks[1] += safe_32bit_diff(__dus.s.ticks[1], ldus->s.ticks[1]);
+       dus->s.io_ticks += safe_32bit_diff(__dus.s.io_ticks, ldus->s.io_ticks);
+       dus->s.time_in_queue +=
+                       safe_32bit_diff(__dus.s.time_in_queue, ldus->s.time_in_queue);
 
        fio_gettime(&t, NULL);
        dus->s.msec += mtime_since(&du->time, &t);