[Qemu-devel] [RFC v9 20/27] virtio-blk: Add ioscheduler to detect mergable requests

[Stefan Hajnoczi <stefanha@linux.vnet.ibm.com>]

---
 hw/dataplane/iosched.h |   78 ++++++++++++++++++++++++++++++++++++++++++++++++
 hw/virtio-blk.c        |    5 ++++
 2 files changed, 83 insertions(+)
 create mode 100644 hw/dataplane/iosched.h

diff --git a/hw/dataplane/iosched.h b/hw/dataplane/iosched.h
new file mode 100644
index 0000000..12ebccc
--- /dev/null
+++ b/hw/dataplane/iosched.h
@@ -0,0 +1,78 @@
+#ifndef IOSCHED_H
+#define IOSCHED_H
+
+#include "hw/dataplane/ioq.h"
+
+typedef struct {
+    unsigned long iocbs;
+    unsigned long merges;
+    unsigned long sched_calls;
+} IOSched;
+
+static int iocb_cmp(const void *a, const void *b)
+{
+    const struct iocb *iocb_a = a;
+    const struct iocb *iocb_b = b;
+
+    /*
+     * Note that we can't simply subtract req2->sector from req1->sector
+     * here as that could overflow the return value.
+     */
+    if (iocb_a->u.c.offset > iocb_b->u.c.offset) {
+        return 1;
+    } else if (iocb_a->u.c.offset < iocb_b->u.c.offset) {
+        return -1;
+    } else {
+        return 0;
+    }
+}
+
+static size_t iocb_nbytes(struct iocb *iocb)
+{
+    struct iovec *iov = iocb->u.c.buf;
+    size_t nbytes = 0;
+    size_t i;
+    for (i = 0; i < iocb->u.c.nbytes; i++) {
+        nbytes += iov->iov_len;
+        iov++;
+    }
+    return nbytes;
+}
+
+static void iosched_init(IOSched *iosched)
+{
+    memset(iosched, 0, sizeof *iosched);
+}
+
+static void iosched_print_stats(IOSched *iosched)
+{
+    fprintf(stderr, "iocbs = %lu merges = %lu sched_calls = %lu\n",
+            iosched->iocbs, iosched->merges, iosched->sched_calls);
+    memset(iosched, 0, sizeof *iosched);
+}
+
+static void iosched(IOSched *iosched, struct iocb *unsorted[], unsigned int count)
+{
+    struct iocb *sorted[count];
+    struct iocb *last;
+    unsigned int i;
+
+    if ((++iosched->sched_calls % 1000) == 0) {
+        iosched_print_stats(iosched);
+    }
+
+    memcpy(sorted, unsorted, sizeof sorted);
+    qsort(sorted, count, sizeof sorted[0], iocb_cmp);
+
+    iosched->iocbs += count;
+    last = sorted[0];
+    for (i = 1; i < count; i++) {
+        if (last->aio_lio_opcode == sorted[i]->aio_lio_opcode &&
+            last->u.c.offset + iocb_nbytes(last) == sorted[i]->u.c.offset) {
+            iosched->merges++;
+        }
+        last = sorted[i];
+    }
+}
+
+#endif /* IOSCHED_H */
diff --git a/hw/virtio-blk.c b/hw/virtio-blk.c
index f67fdb7..75cb0f2 100644
--- a/hw/virtio-blk.c
+++ b/hw/virtio-blk.c
@@ -22,6 +22,7 @@
 #include "hw/dataplane/event-poll.h"
 #include "hw/dataplane/vring.h"
 #include "hw/dataplane/ioq.h"
+#include "hw/dataplane/iosched.h"
 #include "kvm.h"
 
 enum {
@@ -57,6 +58,7 @@ typedef struct {
     EventHandler notify_handler;    /* virtqueue notify handler */
 
     IOQueue ioqueue;                /* Linux AIO queue (should really be per dataplane thread) */
+    IOSched iosched;                /* I/O scheduler */
     VirtIOBlockRequest requests[REQ_MAX]; /* pool of requests, managed by the queue */
 } VirtIOBlock;
 
@@ -249,6 +251,8 @@ static bool handle_notify(EventHandler *handler)
         }
     }
 
+    iosched(&s->iosched, s->ioqueue.queue, s->ioqueue.queue_idx);
+
     /* Submit requests, if any */
     int rc = ioq_submit(&s->ioqueue);
     if (unlikely(rc < 0)) {
@@ -289,6 +293,7 @@ static void data_plane_start(VirtIOBlock *s)
 {
     int i;
 
+    iosched_init(&s->iosched);
     vring_setup(&s->vring, &s->vdev, 0);
 
     /* Set up guest notifier (irq) */
-- 
1.7.10.4