block/nvme: optimize the performance of nvme driver based on vfio-pci

When the IO size is larger than 2 pages, we move the the pointer one by
one in the pagelist, this is inefficient.

This is a simple benchmark result:

Before:
$ qemu-io -c 'write 0 1G' nvme://0000:00:04.0/1

wrote 1073741824/1073741824 bytes at offset 0
1 GiB, 1 ops; 0:00:02.41 (424.504 MiB/sec and 0.4146 ops/sec)

 $ qemu-io -c 'read 0 1G' nvme://0000:00:04.0/1

read 1073741824/1073741824 bytes at offset 0
1 GiB, 1 ops; 0:00:02.03 (503.055 MiB/sec and 0.4913 ops/sec)

After:
$ qemu-io -c 'write 0 1G' nvme://0000:00:04.0/1

wrote 1073741824/1073741824 bytes at offset 0
1 GiB, 1 ops; 0:00:02.17 (471.517 MiB/sec and 0.4605 ops/sec)

 $ qemu-io -c 'read 0 1G' nvme://0000:00:04.0/1

read 1073741824/1073741824 bytes at offset 0
1 GiB, 1 ops; 0:00:01.94 (526.770 MiB/sec and 0.5144 ops/sec)

Signed-off-by: Li Feng <lifeng1519@gmail.com>
Message-Id: <20181101103807.25862-1-lifeng1519@gmail.com>
Signed-off-by: Fam Zheng <famz@redhat.com>

diff --git a/block/nvme.c b/block/nvme.c
index 29294038fcc21ab9698311f793e8820b03baef7e..982097b5b1c91631083c65d4edcd2d12008b44c8 100644 (file)
--- a/block/nvme.c
+++ b/block/nvme.c
@@ -837,7 +837,7 @@ try_map:
         }
 
         for (j = 0; j < qiov->iov[i].iov_len / s->page_size; j++) {
-            pagelist[entries++] = iova + j * s->page_size;
+            pagelist[entries++] = cpu_to_le64(iova + j * s->page_size);
         }
         trace_nvme_cmd_map_qiov_iov(s, i, qiov->iov[i].iov_base,
                                     qiov->iov[i].iov_len / s->page_size);
@@ -850,20 +850,16 @@ try_map:
     case 0:
         abort();
     case 1:
-        cmd->prp1 = cpu_to_le64(pagelist[0]);
+        cmd->prp1 = pagelist[0];
         cmd->prp2 = 0;
         break;
     case 2:
-        cmd->prp1 = cpu_to_le64(pagelist[0]);
-        cmd->prp2 = cpu_to_le64(pagelist[1]);;
+        cmd->prp1 = pagelist[0];
+        cmd->prp2 = pagelist[1];
         break;
     default:
-        cmd->prp1 = cpu_to_le64(pagelist[0]);
-        cmd->prp2 = cpu_to_le64(req->prp_list_iova);
-        for (i = 0; i < entries - 1; ++i) {
-            pagelist[i] = cpu_to_le64(pagelist[i + 1]);
-        }
-        pagelist[entries - 1] = 0;
+        cmd->prp1 = pagelist[0];
+        cmd->prp2 = cpu_to_le64(req->prp_list_iova + sizeof(uint64_t));
         break;
     }
     trace_nvme_cmd_map_qiov(s, cmd, req, qiov, entries);