Currently, io_submit tries to execute the io requests on the
same thread, which could block because of various reaons (eg.
allocation of disk blocks). So, essentially, io_submit ends
up being a blocking call.
With this patch, io_submit prepares all the kiocbs and then
adds (kicks) them to ctx->run_list (kicked) in one go and then
schedules the workqueue. The actual operations are not executed
on io_submit's process context, so it can return very quickly.
This run_list is processed either on a workqueue or in response to
an io_getevents call. This utilizes the existing retry infrastructure.
It uses override_creds/revert_creds to use the submitting process'
credentials when processing the iocb request from the workqueue. This
is required for proper support of quota and reserved block access.
Currently, we use block plugging in io_submit, since most of the IO
was being done there itself. This patch moves it to aio_kick_handler
and aio_run_all_iocbs, where the IO gets submitted.
All the tests were run with ext4.
I tested the patch with fio
(fio rand-rw-disk.fio --max-jobs=2 --latency-log
--bandwidth-log)
**Unpatched**
read : io=102120KB, bw=618740 B/s, iops=151 , runt=169006msec
slat (usec): min=275 , max=87560 , avg=6571.88, stdev=2799.57
write: io=102680KB, bw=622133 B/s, iops=151 , runt=169006msec
slat (usec): min=2 , max=196 , avg=24.66, stdev=20.35
**Patched**
read : io=102864KB, bw=504885 B/s, iops=123 , runt=208627msec
slat (usec): min=0 , max=120 , avg= 1.65, stdev= 3.46
write: io=101936KB, bw=500330 B/s, iops=122 , runt=208627msec
slat (usec): min=0 , max=131 , avg= 1.85, stdev= 3.27
>From above, it can be seen that submit latencies improve a lot with the
patch. The full fio results for the "old"(unpatched) and "new"(patched)
cases are attached. Results with both ramdisk (*rd*) and disk attached,
and also the corresponding fio files.
Some variations I tried:
1. I tried to submit one iocb at a time (lock/unlock ctx->lock), and
that had good performance for a regular disk, but when I tested with a
ramdisk (to simulate very fast disk), performance was extremely bad.
Submitting all the iocbs from an io_submit in one go, restored the
performance (latencies+bandwidth).
2. I was earlier trying to use queue_delayed_work with 0 timeout, but
that worsened the submit latencies a bit but improved bandwidth.
3. Also, I tried not using aio_queue_work from io_submit call, and instead
depending on an already scheduled one or the iocbs being run when
io_getevents gets called. This seemed to give improved perfomance. But
does this constitute as change of api semantics?
Signed-off-by: Ankit Jain <jankit@xxxxxxx>
--
diff --git a/fs/aio.c b/fs/aio.c
index 71f613c..79801096b 100644
--- a/fs/aio.c
+++ b/fs/aio.c
@@ -563,6 +563,11 @@ static int __aio_put_req(struct kioctx *ctx, struct kiocb *req)
req->ki_cancel = NULL;
req->ki_retry = NULL;
+ if (likely(req->submitter_cred)) {
+ put_cred(req->submitter_cred);
+ req->submitter_cred = NULL;
+ }
+
fput(req->ki_filp);
req->ki_filp = NULL;
really_put_req(ctx, req);
@@ -659,6 +664,7 @@ static ssize_t aio_run_iocb(struct kiocb *iocb)
struct kioctx *ctx = iocb->ki_ctx;
ssize_t (*retry)(struct kiocb *);
ssize_t ret;
+ const struct cred *old_cred = NULL;
if (!(retry = iocb->ki_retry)) {
printk("aio_run_iocb: iocb->ki_retry = NULL\n");
@@ -703,12 +709,19 @@ static ssize_t aio_run_iocb(struct kiocb *iocb)
goto out;
}
+ if (iocb->submitter_cred)
+ /* setup creds */
+ old_cred = override_creds(iocb->submitter_cred);
+
/*
* Now we are all set to call the retry method in async
* context.
*/
ret = retry(iocb);
+ if (old_cred)
+ revert_creds(old_cred);
+
if (ret != -EIOCBRETRY && ret != -EIOCBQUEUED) {
/*
* There's no easy way to restart the syscall since other AIO's
@@ -804,10 +817,14 @@ static void aio_queue_work(struct kioctx * ctx)
*/
static inline void aio_run_all_iocbs(struct kioctx *ctx)
{
+ struct blk_plug plug;
+
+ blk_start_plug(&plug);
spin_lock_irq(&ctx->ctx_lock);
while (__aio_run_iocbs(ctx))
;
spin_unlock_irq(&ctx->ctx_lock);
+ blk_finish_plug(&plug);
}
/*
@@ -825,13 +842,16 @@ static void aio_kick_handler(struct work_struct *work)
mm_segment_t oldfs = get_fs();
struct mm_struct *mm;
int requeue;
+ struct blk_plug plug;
set_fs(USER_DS);
use_mm(ctx->mm);
+ blk_start_plug(&plug);
spin_lock_irq(&ctx->ctx_lock);
requeue =__aio_run_iocbs(ctx);
mm = ctx->mm;
spin_unlock_irq(&ctx->ctx_lock);
+ blk_finish_plug(&plug);
unuse_mm(mm);
set_fs(oldfs);
/*
@@ -1506,12 +1526,14 @@ static ssize_t aio_setup_iocb(struct kiocb *kiocb, bool compat)
static int io_submit_one(struct kioctx *ctx, struct iocb __user *user_iocb,
struct iocb *iocb, struct kiocb_batch *batch,
- bool compat)
+ bool compat, struct kiocb **req_entry)
{
struct kiocb *req;
struct file *file;
ssize_t ret;
+ *req_entry = NULL;
+
/* enforce forwards compatibility on users */
if (unlikely(iocb->aio_reserved1 || iocb->aio_reserved2)) {
pr_debug("EINVAL: io_submit: reserve field set\n");
@@ -1537,6 +1559,7 @@ static int io_submit_one(struct kioctx *ctx, struct iocb __user *user_iocb,
fput(file);
return -EAGAIN;
}
+
req->ki_filp = file;
if (iocb->aio_flags & IOCB_FLAG_RESFD) {
/*
@@ -1567,38 +1590,16 @@ static int io_submit_one(struct kioctx *ctx, struct iocb __user *user_iocb,
req->ki_left = req->ki_nbytes = iocb->aio_nbytes;
req->ki_opcode = iocb->aio_lio_opcode;
+ req->submitter_cred = get_current_cred();
+
ret = aio_setup_iocb(req, compat);
if (ret)
goto out_put_req;
- spin_lock_irq(&ctx->ctx_lock);
- /*
- * We could have raced with io_destroy() and are currently holding a
- * reference to ctx which should be destroyed. We cannot submit IO
- * since ctx gets freed as soon as io_submit() puts its reference. The
- * check here is reliable: io_destroy() sets ctx->dead before waiting
- * for outstanding IO and the barrier between these two is realized by
- * unlock of mm->ioctx_lock and lock of ctx->ctx_lock. Analogously we
- * increment ctx->reqs_active before checking for ctx->dead and the
- * barrier is realized by unlock and lock of ctx->ctx_lock. Thus if we
- * don't see ctx->dead set here, io_destroy() waits for our IO to
- * finish.
- */
- if (ctx->dead) {
- spin_unlock_irq(&ctx->ctx_lock);
- ret = -EINVAL;
- goto out_put_req;
- }
- aio_run_iocb(req);
- if (!list_empty(&ctx->run_list)) {
- /* drain the run list */
- while (__aio_run_iocbs(ctx))
- ;
- }
- spin_unlock_irq(&ctx->ctx_lock);
-
aio_put_req(req); /* drop extra ref to req */
+
+ *req_entry = req;
return 0;
out_put_req:
@@ -1613,8 +1614,10 @@ long do_io_submit(aio_context_t ctx_id, long nr,
struct kioctx *ctx;
long ret = 0;
int i = 0;
- struct blk_plug plug;
struct kiocb_batch batch;
+ struct kiocb **req_arr = NULL;
+ int nr_submitted = 0;
+ int req_arr_cnt = 0;
if (unlikely(nr < 0))
return -EINVAL;
@@ -1632,8 +1635,8 @@ long do_io_submit(aio_context_t ctx_id, long nr,
}
kiocb_batch_init(&batch, nr);
-
- blk_start_plug(&plug);
+ req_arr = kmalloc(sizeof(struct kiocb *) * nr, GFP_KERNEL);
+ memset(req_arr, 0, sizeof(req_arr));
/*
* AKPM: should this return a partial result if some of the IOs were
@@ -1653,15 +1656,51 @@ long do_io_submit(aio_context_t ctx_id, long nr,
break;
}
- ret = io_submit_one(ctx, user_iocb, &tmp, &batch, compat);
+ ret = io_submit_one(ctx, user_iocb, &tmp, &batch, compat,
+ &req_arr[i]);
if (ret)
break;
+ req_arr_cnt++;
}
- blk_finish_plug(&plug);
+ spin_lock_irq(&ctx->ctx_lock);
+ /*
+ * We could have raced with io_destroy() and are currently holding a
+ * reference to ctx which should be destroyed. We cannot submit IO
+ * since ctx gets freed as soon as io_submit() puts its reference. The
+ * check here is reliable: io_destroy() sets ctx->dead before waiting
+ * for outstanding IO and the barrier between these two is realized by
+ * unlock of mm->ioctx_lock and lock of ctx->ctx_lock. Analogously we
+ * increment ctx->reqs_active before checking for ctx->dead and the
+ * barrier is realized by unlock and lock of ctx->ctx_lock. Thus if we
+ * don't see ctx->dead set here, io_destroy() waits for our IO to
+ * finish.
+ */
+ if (ctx->dead) {
+ spin_unlock_irq(&ctx->ctx_lock);
+ for (i = 0; i < req_arr_cnt; i++)
+ /* drop i/o ref to the req */
+ __aio_put_req(ctx, req_arr[i]);
+
+ ret = -EINVAL;
+ goto out;
+ }
+
+ for (i = 0; i < req_arr_cnt; i++) {
+ struct kiocb *req = req_arr[i];
+ if (likely(!kiocbTryKick(req)))
+ __queue_kicked_iocb(req);
+ nr_submitted++;
+ }
+ if (likely(nr_submitted > 0))
+ aio_queue_work(ctx);
+ spin_unlock_irq(&ctx->ctx_lock);
+
+out:
kiocb_batch_free(ctx, &batch);
+ kfree(req_arr);
put_ioctx(ctx);
- return i ? i : ret;
+ return nr_submitted ? nr_submitted : ret;
}
/* sys_io_submit:
diff --git a/include/linux/aio.h b/include/linux/aio.h
index b1a520e..bcd6a5e 100644
--- a/include/linux/aio.h
+++ b/include/linux/aio.h
@@ -124,6 +124,8 @@ struct kiocb {
* this is the underlying eventfd context to deliver events to.
*/
struct eventfd_ctx *ki_eventfd;
+
+ const struct cred *submitter_cred;
};
#define is_sync_kiocb(iocb) ((iocb)->ki_key == KIOCB_SYNC_KEY)
--
Ankit Jain
SUSE Labs
random_rw: (g=0): rw=randrw, bs=4K-4K/4K-4K, ioengine=libaio, iodepth=32
fio-2.0.8-9-gfb9f0
Starting 1 process
random_rw: (groupid=0, jobs=1): err= 0: pid=2021: Tue Jul 24 15:37:25 2012
read : io=102864KB, bw=504885 B/s, iops=123 , runt=208627msec
slat (usec): min=0 , max=120 , avg= 1.65, stdev= 3.46
clat (msec): min=29 , max=619 , avg=134.15, stdev=53.04
lat (msec): min=29 , max=619 , avg=134.15, stdev=53.04
clat percentiles (msec):
| 1.00th=[ 63], 5.00th=[ 78], 10.00th=[ 87], 20.00th=[ 98],
| 30.00th=[ 106], 40.00th=[ 114], 50.00th=[ 123], 60.00th=[ 130],
| 70.00th=[ 143], 80.00th=[ 163], 90.00th=[ 198], 95.00th=[ 231],
| 99.00th=[ 302], 99.50th=[ 363], 99.90th=[ 619], 99.95th=[ 619],
| 99.99th=[ 619]
bw (KB/s) : min= 153, max= 761, per=100.00%, avg=497.88, stdev=128.35
write: io=101936KB, bw=500330 B/s, iops=122 , runt=208627msec
slat (usec): min=0 , max=131 , avg= 1.85, stdev= 3.27
clat (usec): min=97 , max=619552 , avg=126590.22, stdev=50338.80
lat (usec): min=108 , max=619553 , avg=126592.26, stdev=50338.83
clat percentiles (msec):
| 1.00th=[ 59], 5.00th=[ 72], 10.00th=[ 80], 20.00th=[ 91],
| 30.00th=[ 100], 40.00th=[ 108], 50.00th=[ 116], 60.00th=[ 125],
| 70.00th=[ 137], 80.00th=[ 155], 90.00th=[ 188], 95.00th=[ 225],
| 99.00th=[ 293], 99.50th=[ 334], 99.90th=[ 578], 99.95th=[ 619],
| 99.99th=[ 619]
bw (KB/s) : min= 127, max= 842, per=100.00%, avg=493.55, stdev=140.80
lat (usec) : 100=0.01%, 250=0.01%
lat (msec) : 50=0.25%, 100=26.26%, 250=70.61%, 500=2.69%, 750=0.19%
cpu : usr=0.07%, sys=1.25%, ctx=27318, majf=0, minf=24
IO depths : 1=0.1%, 2=0.1%, 4=0.1%, 8=0.1%, 16=0.1%, 32=99.9%, >=64=0.0%
submit : 0=0.0%, 4=100.0%, 8=0.0%, 16=0.0%, 32=0.0%, 64=0.0%, >=64=0.0%
complete : 0=0.0%, 4=100.0%, 8=0.0%, 16=0.0%, 32=0.1%, 64=0.0%, >=64=0.0%
issued : total=r=25716/w=25484/d=0, short=r=0/w=0/d=0
Run status group 0 (all jobs):
READ: io=102864KB, aggrb=493KB/s, minb=493KB/s, maxb=493KB/s, mint=208627msec, maxt=208627msec
WRITE: io=101936KB, aggrb=488KB/s, minb=488KB/s, maxb=488KB/s, mint=208627msec, maxt=208627msec
Disk stats (read/write):
sda: ios=25681/22647, merge=0/70, ticks=204770/98179832, in_queue=99369560, util=98.97%
fio rand-rw-disk-2.fio --output=/home/radical/src/play/ios-test/new-logs/ext4-disk-2-b73147d.log --max-jobs=2 --latency-log --bandwidth-log
b73147d remove unused ki_colln
random_rw: (g=0): rw=randrw, bs=4K-4K/4K-4K, ioengine=libaio, iodepth=32
fio-2.0.8-9-gfb9f0
Starting 1 process
random_rw: Laying out IO file(s) (1 file(s) / 200MB)
random_rw: (groupid=0, jobs=1): err= 0: pid=2011: Tue Jul 24 01:00:02 2012
read : io=102120KB, bw=618740 B/s, iops=151 , runt=169006msec
slat (usec): min=275 , max=87560 , avg=6571.88, stdev=2799.57
clat (usec): min=294 , max=214745 , avg=102349.31, stdev=21957.26
lat (msec): min=9 , max=225 , avg=108.92, stdev=22.21
clat percentiles (msec):
| 1.00th=[ 54], 5.00th=[ 68], 10.00th=[ 76], 20.00th=[ 84],
| 30.00th=[ 91], 40.00th=[ 96], 50.00th=[ 102], 60.00th=[ 108],
| 70.00th=[ 114], 80.00th=[ 121], 90.00th=[ 131], 95.00th=[ 141],
| 99.00th=[ 157], 99.50th=[ 161], 99.90th=[ 182], 99.95th=[ 198],
| 99.99th=[ 210]
bw (KB/s) : min= 474, max= 817, per=99.90%, avg=603.38, stdev=47.87
write: io=102680KB, bw=622133 B/s, iops=151 , runt=169006msec
slat (usec): min=2 , max=196 , avg=24.66, stdev=20.35
clat (usec): min=42 , max=221533 , avg=102260.25, stdev=21825.38
lat (usec): min=85 , max=221542 , avg=102285.38, stdev=21825.25
clat percentiles (msec):
| 1.00th=[ 53], 5.00th=[ 69], 10.00th=[ 76], 20.00th=[ 85],
| 30.00th=[ 91], 40.00th=[ 96], 50.00th=[ 102], 60.00th=[ 108],
| 70.00th=[ 114], 80.00th=[ 121], 90.00th=[ 131], 95.00th=[ 139],
| 99.00th=[ 157], 99.50th=[ 163], 99.90th=[ 184], 99.95th=[ 206],
| 99.99th=[ 215]
bw (KB/s) : min= 318, max= 936, per=99.86%, avg=606.14, stdev=100.63
lat (usec) : 50=0.01%, 250=0.01%, 500=0.01%
lat (msec) : 10=0.01%, 20=0.02%, 50=0.60%, 100=46.62%, 250=52.75%
cpu : usr=0.41%, sys=1.58%, ctx=27474, majf=0, minf=22
IO depths : 1=0.1%, 2=0.1%, 4=0.1%, 8=0.1%, 16=0.1%, 32=99.9%, >=64=0.0%
submit : 0=0.0%, 4=100.0%, 8=0.0%, 16=0.0%, 32=0.0%, 64=0.0%, >=64=0.0%
complete : 0=0.0%, 4=100.0%, 8=0.0%, 16=0.0%, 32=0.1%, 64=0.0%, >=64=0.0%
issued : total=r=25530/w=25670/d=0, short=r=0/w=0/d=0
Run status group 0 (all jobs):
READ: io=102120KB, aggrb=604KB/s, minb=604KB/s, maxb=604KB/s, mint=169006msec, maxt=169006msec
WRITE: io=102680KB, aggrb=607KB/s, minb=607KB/s, maxb=607KB/s, mint=169006msec, maxt=169006msec
Disk stats (read/write):
sda: ios=25533/4, merge=23/18, ticks=164781/112, in_queue=164823, util=97.51%
random_rw: (g=0): rw=randrw, bs=4K-4K/4K-4K, ioengine=libaio, iodepth=32
fio-2.0.8-9-gfb9f0
Starting 1 process
random_rw: Laying out IO file(s) (1 file(s) / 1700MB)
random_rw: (groupid=0, jobs=1): err= 0: pid=2002: Tue Jul 24 15:31:47 2012
read : io=870504KB, bw=558373KB/s, iops=139593 , runt= 1559msec
slat (usec): min=0 , max=32 , avg= 0.38, stdev= 0.52
clat (usec): min=62 , max=597 , avg=114.05, stdev=18.96
lat (usec): min=63 , max=599 , avg=114.49, stdev=19.03
clat percentiles (usec):
| 1.00th=[ 103], 5.00th=[ 105], 10.00th=[ 106], 20.00th=[ 107],
| 30.00th=[ 108], 40.00th=[ 108], 50.00th=[ 109], 60.00th=[ 110],
| 70.00th=[ 115], 80.00th=[ 123], 90.00th=[ 126], 95.00th=[ 129],
| 99.00th=[ 145], 99.50th=[ 151], 99.90th=[ 438], 99.95th=[ 462],
| 99.99th=[ 580]
bw (KB/s) : min=550016, max=572568, per=100.00%, avg=560584.00, stdev=11342.49
write: io=870296KB, bw=558240KB/s, iops=139559 , runt= 1559msec
slat (usec): min=0 , max=65 , avg= 0.42, stdev= 0.53
clat (usec): min=62 , max=595 , avg=113.45, stdev=18.91
lat (usec): min=63 , max=597 , avg=113.93, stdev=18.99
clat percentiles (usec):
| 1.00th=[ 103], 5.00th=[ 104], 10.00th=[ 105], 20.00th=[ 106],
| 30.00th=[ 107], 40.00th=[ 108], 50.00th=[ 108], 60.00th=[ 110],
| 70.00th=[ 115], 80.00th=[ 122], 90.00th=[ 125], 95.00th=[ 129],
| 99.00th=[ 145], 99.50th=[ 149], 99.90th=[ 438], 99.95th=[ 462],
| 99.99th=[ 564]
bw (KB/s) : min=547456, max=575144, per=100.00%, avg=559728.00, stdev=14109.21
lat (usec) : 100=0.02%, 250=99.72%, 500=0.24%, 750=0.03%
cpu : usr=18.73%, sys=80.76%, ctx=175, majf=0, minf=22
IO depths : 1=0.1%, 2=0.1%, 4=0.1%, 8=0.1%, 16=0.1%, 32=100.0%, >=64=0.0%
submit : 0=0.0%, 4=100.0%, 8=0.0%, 16=0.0%, 32=0.0%, 64=0.0%, >=64=0.0%
complete : 0=0.0%, 4=100.0%, 8=0.0%, 16=0.0%, 32=0.1%, 64=0.0%, >=64=0.0%
issued : total=r=217626/w=217574/d=0, short=r=0/w=0/d=0
Run status group 0 (all jobs):
READ: io=870504KB, aggrb=558373KB/s, minb=558373KB/s, maxb=558373KB/s, mint=1559msec, maxt=1559msec
WRITE: io=870296KB, aggrb=558239KB/s, minb=558239KB/s, maxb=558239KB/s, mint=1559msec, maxt=1559msec
Disk stats (read/write):
ram0: ios=0/0, merge=0/0, ticks=0/0, in_queue=0, util=0.00%
fio rand-rw-rd.fio --output=/home/radical/src/play/ios-test/new-logs/ext4-rd-b73147d.log --max-jobs=2 --latency-log --bandwidth-log
b73147d remove unused ki_colln
random_rw: (g=0): rw=randrw, bs=4K-4K/4K-4K, ioengine=libaio, iodepth=32
fio-2.0.8-9-gfb9f0
Starting 1 process
random_rw: Laying out IO file(s) (1 file(s) / 1700MB)
random_rw: (groupid=0, jobs=1): err= 0: pid=1999: Tue Jul 24 00:55:56 2012
read : io=869872KB, bw=489517KB/s, iops=122379 , runt= 1777msec
slat (usec): min=2 , max=78 , avg= 3.46, stdev= 0.87
clat (usec): min=16 , max=604 , avg=126.83, stdev=16.35
lat (usec): min=19 , max=617 , avg=130.40, stdev=16.74
clat percentiles (usec):
| 1.00th=[ 119], 5.00th=[ 121], 10.00th=[ 122], 20.00th=[ 123],
| 30.00th=[ 124], 40.00th=[ 124], 50.00th=[ 125], 60.00th=[ 126],
| 70.00th=[ 127], 80.00th=[ 129], 90.00th=[ 133], 95.00th=[ 135],
| 99.00th=[ 149], 99.50th=[ 155], 99.90th=[ 490], 99.95th=[ 524],
| 99.99th=[ 548]
bw (KB/s) : min=487648, max=493224, per=100.00%, avg=490160.00, stdev=2828.69
write: io=870928KB, bw=490111KB/s, iops=122527 , runt= 1777msec
slat (usec): min=2 , max=171 , avg= 2.78, stdev= 0.90
clat (usec): min=23 , max=606 , avg=126.77, stdev=16.22
lat (usec): min=26 , max=616 , avg=129.65, stdev=16.57
clat percentiles (usec):
| 1.00th=[ 118], 5.00th=[ 120], 10.00th=[ 121], 20.00th=[ 123],
| 30.00th=[ 124], 40.00th=[ 124], 50.00th=[ 125], 60.00th=[ 126],
| 70.00th=[ 127], 80.00th=[ 129], 90.00th=[ 133], 95.00th=[ 135],
| 99.00th=[ 149], 99.50th=[ 155], 99.90th=[ 490], 99.95th=[ 516],
| 99.99th=[ 548]
bw (KB/s) : min=484072, max=496464, per=100.00%, avg=490920.00, stdev=6298.07
lat (usec) : 20=0.01%, 50=0.01%, 100=0.01%, 250=99.80%, 500=0.11%
lat (usec) : 750=0.08%
cpu : usr=24.21%, sys=75.34%, ctx=185, majf=0, minf=22
IO depths : 1=0.1%, 2=0.1%, 4=0.1%, 8=0.1%, 16=0.1%, 32=100.0%, >=64=0.0%
submit : 0=0.0%, 4=100.0%, 8=0.0%, 16=0.0%, 32=0.0%, 64=0.0%, >=64=0.0%
complete : 0=0.0%, 4=100.0%, 8=0.0%, 16=0.0%, 32=0.1%, 64=0.0%, >=64=0.0%
issued : total=r=217468/w=217732/d=0, short=r=0/w=0/d=0
Run status group 0 (all jobs):
READ: io=869872KB, aggrb=489517KB/s, minb=489517KB/s, maxb=489517KB/s, mint=1777msec, maxt=1777msec
WRITE: io=870928KB, aggrb=490111KB/s, minb=490111KB/s, maxb=490111KB/s, mint=1777msec, maxt=1777msec
Disk stats (read/write):
ram0: ios=0/0, merge=0/0, ticks=0/0, in_queue=0, util=0.00%
[random_rw]
rw=randrw
size=200m
directory=/misc/rd
ioengine=libaio
iodepth=32
[random_rw]
rw=randrw
size=1700m
directory=/mnt/rd
ioengine=libaio
iodepth=32
