[Qemu-devel] [RFC] vhost-blk implementation

[Badari Pulavarty]

Hi,

Inspired by vhost-net implementation, I did initial prototype 
of vhost-blk to see if it provides any benefits over QEMU virtio-blk.
I haven't handled all the error cases, fixed naming conventions etc.,
but the implementation is stable to play with. I tried not to deviate
from vhost-net implementation where possible.

NOTE:  Only change I had to make to vhost core code is to 
increase VHOST_NET_MAX_SG to 130 (128+2) in vhost.h 

Performance:
=============

I have done simple tests to see how it performs. I got very
encouraging results on sequential read tests. But on sequential
write tests, I see degrade over virtio-blk. I can't figure out and
explain why. Can some one shed light on whats happening here ?

Read Results:
=============
Test does read of 84GB file from the host (through virtio). I unmount
and mount the filesystem on the host to make sure there is nothing
in the page cache..


with vhost-blk:
----------------

# time dd if=/dev/vda of=/dev/null bs=128k iflag=direct
640000+0 records in
640000+0 records out
83886080000 bytes (84 GB) copied, 126.135 seconds, 665 MB/s

real    2m6.137s
user    0m0.281s
sys     0m14.725s

without vhost-blk: (virtio)
---------------------------

# time dd if=/dev/vda of=/dev/null bs=128k iflag=direct
640000+0 records in
640000+0 records out
83886080000 bytes (84 GB) copied, 275.466 seconds, 305 MB/s

real    4m35.468s
user    0m0.373s
sys     0m48.074s



Write Results:
==============

I see degraded IO performance when doing sequential IO write
tests with vhost-blk compared to virtio-blk.

# time dd of=/dev/vda if=/dev/zero bs=2M oflag=direct

I get ~110MB/sec with virtio-blk, but I get only ~60MB/sec with
vhost-blk. Wondering why ?

Comments/flames ? 

Thanks,
Badari


vhost-blk is in-kernel accelerator for virtio-blk. 
At this time, this is a prototype based on virtio-net.
Lots of error handling and clean up needs to be done.
Read performance is pretty good over QEMU virtio-blk, but
write performance is not anywhere close to QEMU virtio-blk.
Why ?

Signed-off-by: Badari Pulavarty <address@hidden>
---
 drivers/vhost/blk.c |  242 ++++++++++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 242 insertions(+)

Index: net-next/drivers/vhost/blk.c
===================================================================
--- /dev/null   1970-01-01 00:00:00.000000000 +0000
+++ net-next/drivers/vhost/blk.c        2010-03-22 18:07:18.156584400 -0400
@@ -0,0 +1,242 @@
+ /*
+  * virtio-block server in host kernel.
+  * Inspired by vhost-net and shamlessly ripped code from it :)
+  */
+
+#include <linux/compat.h>
+#include <linux/eventfd.h>
+#include <linux/vhost.h>
+#include <linux/virtio_net.h>
+#include <linux/virtio_blk.h>
+#include <linux/mmu_context.h>
+#include <linux/miscdevice.h>
+#include <linux/module.h>
+#include <linux/mutex.h>
+#include <linux/workqueue.h>
+#include <linux/rcupdate.h>
+#include <linux/file.h>
+
+#include "vhost.h"
+
+#define VHOST_BLK_VQ_MAX 1
+
+struct vhost_blk {
+       struct vhost_dev dev;
+       struct vhost_virtqueue vqs[VHOST_BLK_VQ_MAX];
+       struct vhost_poll poll[VHOST_BLK_VQ_MAX];
+};
+
+static int do_handle_io(struct file *file, uint32_t type, uint64_t sector,
+                       struct iovec *iov, int in)
+{
+       loff_t pos = sector << 8;
+       int ret = 0;
+
+       if (type & VIRTIO_BLK_T_FLUSH)  {
+               ret = vfs_fsync(file, file->f_path.dentry, 1);
+       } else if (type & VIRTIO_BLK_T_OUT) {
+               ret = vfs_writev(file, iov, in, &pos);
+       } else {
+               ret = vfs_readv(file, iov, in, &pos);
+       }
+       return ret;
+}
+
+static void handle_blk(struct vhost_blk *blk)
+{
+       struct vhost_virtqueue *vq = &blk->dev.vqs[0];
+       unsigned head, out, in;
+       struct virtio_blk_outhdr hdr;
+       int r, nvecs;
+       uint8_t status = 0;
+
+       use_mm(blk->dev.mm);
+       mutex_lock(&vq->mutex);
+
+       vhost_disable_notify(vq);
+
+       for (;;) {
+               head = vhost_get_vq_desc(&blk->dev, vq, vq->iov,
+                                        ARRAY_SIZE(vq->iov),
+                                        &out, &in, NULL, NULL);
+               if (head == vq->num) {
+                       if (unlikely(vhost_enable_notify(vq))) {
+                               vhost_disable_notify(vq);
+                               continue;
+                       }
+                       break;
+               }
+
+               BUG_ON(vq->iov[0].iov_len != 16);
+
+               r = copy_from_user(&hdr, vq->iov[0].iov_base, sizeof hdr);
+               if (r < 0) {
+                       printk("copy from user failed\n");
+                       vhost_discard_vq_desc(vq);
+                       break;
+               }
+
+               nvecs = out - 1;
+               if (hdr.type == VIRTIO_BLK_T_IN)
+                       nvecs = in - 1;
+
+               r = do_handle_io(vq->private_data, hdr.type, hdr.sector, 
&vq->iov[1], nvecs);
+               status = (r < 0) ? VIRTIO_BLK_S_IOERR : VIRTIO_BLK_S_OK;
+
+               nvecs++;
+               BUG_ON(vq->iov[nvecs].iov_len != 1);
+
+               if (copy_to_user(vq->iov[nvecs].iov_base, &status, sizeof 
status) < 0) {
+                       printk("copy to user failed\n");
+                       vhost_discard_vq_desc(vq);
+                       break;
+               }
+               vhost_add_used_and_signal(&blk->dev, vq, head, r);
+       }
+        mutex_unlock(&vq->mutex);
+        unuse_mm(blk->dev.mm);
+}
+
+static void vhost_blk_flush(struct vhost_blk *n)
+{
+       vhost_poll_flush(n->poll);
+       vhost_poll_flush(&n->dev.vqs[0].poll);
+}
+
+static void handle_blk_kick(struct work_struct *work)
+{
+       struct vhost_virtqueue *vq;
+       struct vhost_blk *blk;
+       vq = container_of(work, struct vhost_virtqueue, poll.work);
+       blk = container_of(vq->dev, struct vhost_blk, dev);
+       handle_blk(blk);
+}
+
+static void handle_rq_blk(struct work_struct *work)
+{
+       struct vhost_blk *blk;
+       blk = container_of(work, struct vhost_blk, poll[0].work);
+       handle_blk(blk);
+}
+
+static int vhost_blk_open(struct inode *inode, struct file *f)
+{
+       struct vhost_blk *n = kmalloc(sizeof *n, GFP_KERNEL);
+       int r;
+       if (!n)
+               return -ENOMEM;
+       n->vqs[0].handle_kick = handle_blk_kick;
+       r = vhost_dev_init(&n->dev, n->vqs, VHOST_BLK_VQ_MAX);
+       if (r < 0) {
+               kfree(n);
+               return r;
+       }
+
+       vhost_poll_init(n->poll, handle_rq_blk, POLLOUT|POLLIN);
+       f->private_data = n;
+       return 0;
+}
+
+static int vhost_blk_release(struct inode *inode, struct file *f)
+{
+       struct vhost_blk *n = f->private_data;
+
+       fput(n->vqs->private_data);
+       kfree(n);
+       return 0;
+}
+
+static long vhost_blk_set_backend(struct vhost_blk *n, unsigned index, int fd)
+{
+       struct file *file;
+       struct vhost_virtqueue *vq;
+
+       file = fget(fd);
+       if (!file)
+               return -EBADF;
+
+       vq = n->vqs + index;
+       mutex_lock(&vq->mutex);
+       rcu_assign_pointer(vq->private_data, file);
+       mutex_unlock(&vq->mutex);
+       return 0;
+}
+
+
+static long vhost_blk_ioctl(struct file *f, unsigned int ioctl,
+                            unsigned long arg)
+{
+       struct vhost_blk *n = f->private_data;
+       void __user *argp = (void __user *)arg;
+       struct vhost_vring_file backend;
+       int r;
+
+       switch (ioctl) {
+        case VHOST_NET_SET_BACKEND:
+                r = copy_from_user(&backend, argp, sizeof backend);
+                if (r < 0)
+                        return r;
+                return vhost_blk_set_backend(n, backend.index, backend.fd);
+       default:
+               mutex_lock(&n->dev.mutex);
+               r = vhost_dev_ioctl(&n->dev, ioctl, arg);
+               vhost_blk_flush(n);
+               mutex_unlock(&n->dev.mutex);
+               return r;
+       }
+}
+
+const static struct file_operations vhost_blk_fops = {
+       .owner          = THIS_MODULE,
+       .release        = vhost_blk_release,
+       .open           = vhost_blk_open,
+       .unlocked_ioctl = vhost_blk_ioctl,
+};
+
+static struct miscdevice vhost_blk_misc = {
+       234,
+       "vhost-blk",
+       &vhost_blk_fops,
+};
+
+int vhost_blk_init(void)
+{
+       int r = vhost_init();
+       if (r)
+               goto err_init;
+       r = misc_register(&vhost_blk_misc);
+       if (r)
+               goto err_reg;
+       return 0;
+err_reg:
+       vhost_cleanup();
+err_init:
+       return r;
+
+}
+module_init(vhost_blk_init);
+
+void vhost_blk_exit(void)
+{
+       misc_deregister(&vhost_blk_misc);
+       vhost_cleanup();
+}
+module_exit(vhost_blk_exit);
+
+MODULE_VERSION("0.0.1");
+MODULE_LICENSE("GPL v2");
+MODULE_DESCRIPTION("Host kernel accelerator for virtio blk");