Fix a rate limit issue.

In the current implementation, should_check_rate() returns false
if ddir_rw_sum(td->bytes_done)==0. Therefore, a thread may violate
the rate if iodepth*bs > rate.

This patch addresses the issue by not checking td->bytes_done in should_check_rate.

An example of the issue:

[root@localhost test]# cat fio_randwrite
[global]
thread
kb_base=1000
direct=1
size=28GiB
group_reporting
io_size=16384
ioengine=libaio
iodepth=2
bs=4096
iodepth_batch_submit=1
iodepth_batch_complete=1
filename=/dev/qblkdev

[fio_randwrite]
rw=randwrite
rate_iops=,1
iodepth_batch_submit=1
thinktime_blocks=1
rate_cycle=1000
thinktime=3s
rate_ignore_thinktime=1

[root@localhost test]# fio fio_randwrite

blktrace output:
259,1   11        1     0.100550729  6135  Q  WS 3541608 + 8 [fio]
259,1   11        2     0.100552183  6135  G  WS 3541608 + 8 [fio]
259,1   11        3     0.100560373  6135  D  WS 3541608 + 8 [fio]
259,1   11        4     0.100570436  6135  C  WS 3541608 + 8 [0]
259,1   11        5     0.100599816  6135  Q  WS 43470024 + 8 [fio]
259,1   11        6     0.100600513  6135  G  WS 43470024 + 8 [fio]
259,1   11        7     0.100601579  6135  D  WS 43470024 + 8 [fio]
259,1   11        8     0.100612750  6135  C  WS 43470024 + 8 [0]
259,1   11        9     3.101034407  6135  Q  WS 49511928 + 8 [fio]
259,1   11       10     3.101036067  6135  G  WS 49511928 + 8 [fio]
259,1   11       11     3.101054487  6135  D  WS 49511928 + 8 [fio]
259,1   11       12     3.101068699  6135  C  WS 49511928 + 8 [0]
259,1   11       13     6.101267480  6135  Q  WS 27599368 + 8 [fio]
259,1   11       14     6.101269216  6135  G  WS 27599368 + 8 [fio]
259,1   11       15     6.101277050  6135  D  WS 27599368 + 8 [fio]
259,1   11       16     6.101287956  6135  C  WS 27599368 + 8 [0]

Signed-off-by: HongweiQin <glqinhongwei@gmail.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>

diff --git a/backend.c b/backend.c
index 2e6a377cfb4cb4317294eb854cd61712f402caf7..e20a2e07766eabf4ea0f86dfde6db40e9ed621f7 100644 (file)
--- a/backend.c
+++ b/backend.c
@@ -439,7 +439,7 @@ static int wait_for_completions(struct thread_data *td, struct timespec *time)
        if ((full && !min_evts) || !td->o.iodepth_batch_complete_min)
                min_evts = 1;
 
-       if (time && __should_check_rate(td))
+       if (time && should_check_rate(td))
                fio_gettime(time, NULL);
 
        do {
@@ -494,7 +494,7 @@ int io_queue_event(struct thread_data *td, struct io_u *io_u, int *ret,
                        requeue_io_u(td, &io_u);
                } else {
 sync_done:
-                       if (comp_time && __should_check_rate(td))
+                       if (comp_time && should_check_rate(td))
                                fio_gettime(comp_time, NULL);
 
                        *ret = io_u_sync_complete(td, io_u);

diff --git a/fio.h b/fio.h
index 4d439d988f088fba797ca858a5f0b8b0b1104910..ee582a7241f1710bcd3b82681932c764f8cd14df 100644 (file)
--- a/fio.h
+++ b/fio.h
@@ -757,17 +757,9 @@ static inline bool option_check_rate(struct thread_data *td, enum fio_ddir ddir)
        return false;
 }
 
-static inline bool __should_check_rate(struct thread_data *td)
-{
-       return (td->flags & TD_F_CHECK_RATE) != 0;
-}
-
 static inline bool should_check_rate(struct thread_data *td)
 {
-       if (!__should_check_rate(td))
-               return false;
-
-       return ddir_rw_sum(td->bytes_done) != 0;
+       return (td->flags & TD_F_CHECK_RATE) != 0;
 }
 
 static inline unsigned long long td_max_bs(struct thread_data *td)