[Qemu-devel] [RFC 11/12] qorum: Add qorum mechanism.

[Benoît Canet]

Signed-off-by: Benoit Canet <ben...@irqsave.net>
---
 block/qorum.c |   84 ++++++++++++++++++++++++++++++++++++++++++++++++++++-----
 1 file changed, 78 insertions(+), 6 deletions(-)

diff --git a/block/qorum.c b/block/qorum.c
index 772d138..1f307b6 100644
--- a/block/qorum.c
+++ b/block/qorum.c
@@ -175,7 +175,7 @@ static int qorum_check_ret(QorumAIOCB *acb)
 static void qorum_aio_bh(void *opaque)
 {
     QorumAIOCB *acb = opaque;
-    int i;
+    int i, ret;
 
     for (i = 0; i <= 2; i++) {
         if (acb->aios[i].buf) {
@@ -185,7 +185,12 @@ static void qorum_aio_bh(void *opaque)
     }
 
     qemu_bh_delete(acb->bh);
-    acb->common.cb(acb->common.opaque, qorum_check_ret(acb));
+    if (acb->vote_ret) {
+        ret = acb->vote_ret;
+    } else {
+        ret = qorum_check_ret(acb);
+    }
+    acb->common.cb(acb->common.opaque, ret);
     if (acb->finished) {
         *acb->finished = true;
     }
@@ -229,10 +234,75 @@ static void qorum_aio_cb(void *opaque, int ret)
     sacb->ret = ret;
     acb->count++;
     assert(acb->count <= 3);
-    if (acb->count == 3) {
-        acb->bh = qemu_bh_new(qorum_aio_bh, acb);
-        qemu_bh_schedule(acb->bh);
+    if (acb->count < 3) {
+        return;
     }
+
+    /* Do the qorum */
+    if (acb->vote) {
+        acb->vote(acb);
+    }
+
+    acb->bh = qemu_bh_new(qorum_aio_bh, acb);
+    qemu_bh_schedule(acb->bh);
+}
+
+static void qorum_print_bad(QorumAIOCB *acb, const char *filename)
+{
+    fprintf(stderr, "qorum: corrected error in qorum file %s: sector_num=%"
+            PRId64 " nb_sectors=%i\n", filename, acb->sector_num,
+            acb->nb_sectors);
+}
+
+static void qorum_print_failure(QorumAIOCB *acb)
+{
+    fprintf(stderr, "qorum: failure sector_num=%" PRId64 " nb_sectors=%i\n",
+            acb->sector_num, acb->nb_sectors);
+}
+
+static void qorum_copy_qiov(QEMUIOVector *dest, QEMUIOVector *source)
+{
+    int i;
+    for (i = 0; i < source->niov; i++) {
+        memcpy(dest->iov[i].iov_base,
+               source->iov[i].iov_base,
+               source->iov[i].iov_len);
+        dest->iov[i].iov_len = source->iov[i].iov_len;
+    }
+    dest->niov = source->niov;
+    dest->nalloc = source->nalloc;
+    dest->size = source->size;
+}
+
+static void qorum_vote(QorumAIOCB *acb)
+{
+    ssize_t a_b, b_c, a_c;
+    a_b = blkverify_iovec_compare(&acb->qiovs[0], &acb->qiovs[1]);
+    b_c = blkverify_iovec_compare(&acb->qiovs[1], &acb->qiovs[2]);
+
+    /* Three vector identical -> qorum */
+    if (a_b == b_c && a_b == -1) {
+        qorum_copy_qiov(acb->qiov, &acb->qiovs[0]); /*clone a */
+        return;
+    }
+    if (a_b == -1) {
+        qorum_print_bad(acb, "C");
+        qorum_copy_qiov(acb->qiov, &acb->qiovs[0]); /*clone a */
+        return;
+    }
+    if (b_c == -1) {
+        qorum_print_bad(acb, "A");
+        qorum_copy_qiov(acb->qiov, &acb->qiovs[1]); /*clone b */
+        return;
+    }
+    a_c = blkverify_iovec_compare(&acb->qiovs[0], &acb->qiovs[2]);
+    if (a_c == -1) {
+        qorum_print_bad(acb, "B");
+        qorum_copy_qiov(acb->qiov, &acb->qiovs[0]); /*clone a */
+        return;
+    }
+    qorum_print_failure(acb);
+    acb->vote_ret = -EIO;
 }
 
 static BlockDriverAIOCB *qorum_aio_readv(BlockDriverState *bs,
@@ -247,6 +317,8 @@ static BlockDriverAIOCB *qorum_aio_readv(BlockDriverState 
*bs,
                                     nb_sectors, cb, opaque);
     int i;
 
+    acb->vote = qorum_vote;
+
     for (i = 0; i <= 2; i++) {
         acb->aios[i].buf = qemu_blockalign(bs->file, qiov->size);
         qemu_iovec_init(&acb->qiovs[i], qiov->niov);
@@ -254,7 +326,7 @@ static BlockDriverAIOCB *qorum_aio_readv(BlockDriverState 
*bs,
     }
 
     for (i = 0; i <= 2; i++) {
-        bdrv_aio_readv(s->bs[i], sector_num, qiov, nb_sectors,
+        bdrv_aio_readv(s->bs[i], sector_num, &acb->qiovs[i], nb_sectors,
                        qorum_aio_cb, &acb->aios[i]);
     }
 
-- 
1.7.9.5