With zonemode=zbd, for random read operations with read_beyond_wp=0,
the zbd code will always adjust an I/O offset so that the I/O hits a
non empty zone. However, the adjustment always sets the I/O offset to
the start of the zone, resulting in a high device read cache hit rate
if the device has few zones written.
Improve randomness of read I/Os by adjusting the I/O offset to a random
value within the range of written data of the chosen zone. Also ensure
that the modified I/O does not cross over the zone wp position by
adjusting its size.
Signed-off-by: Damien Le Moal <damien.lemoal@xxxxxxx>
---
zbd.c | 35 +++++++++++++++++++++++++++++++++--
1 file changed, 33 insertions(+), 2 deletions(-)
diff --git a/zbd.c b/zbd.c
index 56197693..19511454 100644
--- a/zbd.c
+++ b/zbd.c
@@ -1122,7 +1122,7 @@ enum io_u_action zbd_adjust_block(struct thread_data *td, struct io_u *io_u)
struct fio_zone_info *zb, *zl;
uint32_t orig_len = io_u->buflen;
uint32_t min_bs = td->o.min_bs[io_u->ddir];
- uint64_t new_len;
+ uint64_t new_len, zofst;
int64_t range;
if (!f->zbd_info)
@@ -1168,6 +1168,8 @@ enum io_u_action zbd_adjust_block(struct thread_data *td, struct io_u *io_u)
}
if (zb->cond == BLK_ZONE_COND_OFFLINE ||
(io_u->offset + io_u->buflen) >> 9 > zb->wp) {
+ struct fio_zone_info *orig_zb = zb;
+
pthread_mutex_unlock(&zb->mutex);
zl = &f->zbd_info->zone_info[zbd_zone_idx(f,
f->file_offset + f->io_size)];
@@ -1179,7 +1181,36 @@ enum io_u_action zbd_adjust_block(struct thread_data *td, struct io_u *io_u)
io_u->buflen);
goto eof;
}
- io_u->offset = zb->start << 9;
+ /*
+ * zbd_find_zone() returned a zone with a range of at
+ * least min_bs, but range may be less than the I/O
+ * size. Handle this case here and also make sure that
+ * the I/O does not the cross the zone wp.
+ */
+ range = ((zb->wp - zb->start) << 9) / min_bs * min_bs;
+ if ((!td_random(td)) || range <= io_u->buflen) {
+ io_u->offset = zb->start << 9;
+ } else {
+ zofst = ((io_u->offset - (orig_zb->start << 9)) %
+ range) / min_bs * min_bs;
+ if (zofst >= range)
+ io_u->offset =
+ ((zb->wp << 9) / min_bs - 1) *
+ min_bs;
+ else
+ io_u->offset = (zb->start << 9) + zofst;
+ }
+ new_len = min((unsigned long long)io_u->buflen,
+ (unsigned long long)(zb->wp << 9) -
+ io_u->offset);
+ new_len = new_len / min_bs * min_bs;
+ if (new_len < io_u->buflen) {
+ io_u->buflen = new_len;
+ dprint(FD_IO, "Changed length from %u into %llu\n",
+ orig_len, io_u->buflen);
+ }
+ assert(zb->start << 9 <= io_u->offset);
+ assert(io_u->offset + io_u->buflen <= zb->wp << 9);
}
if ((io_u->offset + io_u->buflen) >> 9 > zb->wp) {
dprint(FD_ZBD, "%s: %lld + %lld > %" PRIu64 "\n",
--
2.17.1
