To figure out how much data we missed when doing a thinktime sleep,
we're currently dividing by the time slept. This is wrong, it should
be multiplied by the time slept and divided by
1000000 to go from
usec to a second base.
Additionally, don't ever subtract more than a block of data, and
adjust down depending on sleep.
Fixes:
1aa39b0c ("rate: ensure IO issue restarts right after sleep")
Signed-off-by: Jens Axboe <axboe@kernel.dk>
* start issuing immediately after the sleep.
*/
if (total && td->rate_bps[ddir] && td->o.rate_ign_think) {
- td->rate_io_issue_bytes[ddir] += (td->rate_bps[ddir] * 1000000) / total;
- td->rate_io_issue_bytes[ddir] -= td->o.min_bs[ddir];
+ uint64_t missed = (td->rate_bps[ddir] * total) / 1000000ULL;
+ uint64_t over;
+
+ if (total >= 1000000)
+ over = td->o.min_bs[ddir];
+ else
+ over = (td->o.min_bs[ddir] * total) / 1000000ULL;
+
+ td->rate_io_issue_bytes[ddir] += (missed - over);
}
}