From: Stefan Hajnoczi <stefanha@linux.vnet.ibm.com>
To: qemu-devel@nongnu.org
Cc: Kevin Wolf <kwolf@redhat.com>,
Anthony Liguori <aliguori@us.ibm.com>,
Stefan Hajnoczi <stefanha@linux.vnet.ibm.com>,
kvm@vger.kernel.org, "Michael S. Tsirkin" <mst@redhat.com>,
Khoa Huynh <khoa@us.ibm.com>, Paolo Bonzini <pbonzini@redhat.com>,
Asias He <asias@redhat.com>
Subject: [Qemu-devel] [RFC v9 09/27] virtio-blk: Add Linux AIO queue
Date: Wed, 18 Jul 2012 16:07:36 +0100 [thread overview]
Message-ID: <1342624074-24650-10-git-send-email-stefanha@linux.vnet.ibm.com> (raw)
In-Reply-To: <1342624074-24650-1-git-send-email-stefanha@linux.vnet.ibm.com>
Requests read from the vring will be placed in a queue where they can be
merged as necessary. Once all requests have been read from the vring,
the queue can be submitted.
Signed-off-by: Stefan Hajnoczi <stefanha@linux.vnet.ibm.com>
---
hw/dataplane/ioq.h | 104 ++++++++++++++++++++++++++++++++++++++++++++++++++++
hw/virtio-blk.c | 33 ++++++++---------
2 files changed, 120 insertions(+), 17 deletions(-)
create mode 100644 hw/dataplane/ioq.h
diff --git a/hw/dataplane/ioq.h b/hw/dataplane/ioq.h
new file mode 100644
index 0000000..26ca307
--- /dev/null
+++ b/hw/dataplane/ioq.h
@@ -0,0 +1,104 @@
+#ifndef IO_QUEUE_H
+#define IO_QUEUE_H
+
+typedef struct {
+ int fd; /* file descriptor */
+ unsigned int maxreqs; /* max length of freelist and queue */
+
+ io_context_t io_ctx; /* Linux AIO context */
+ EventNotifier notifier; /* Linux AIO eventfd */
+
+ /* Requests can complete in any order so a free list is necessary to manage
+ * available iocbs.
+ */
+ struct iocb **freelist; /* free iocbs */
+ unsigned int freelist_idx;
+
+ /* Multiple requests are queued up before submitting them all in one go */
+ struct iocb **queue; /* queued iocbs */
+ unsigned int queue_idx;
+} IOQueue;
+
+static void ioq_init(IOQueue *ioq, int fd, unsigned int maxreqs)
+{
+ ioq->fd = fd;
+ ioq->maxreqs = maxreqs;
+
+ if (io_setup(maxreqs, &ioq->io_ctx) != 0) {
+ fprintf(stderr, "ioq io_setup failed\n");
+ exit(1);
+ }
+
+ if (event_notifier_init(&ioq->notifier, 0) != 0) {
+ fprintf(stderr, "ioq io event notifier creation failed\n");
+ exit(1);
+ }
+
+ ioq->freelist = g_malloc0(sizeof ioq->freelist[0] * maxreqs);
+ ioq->freelist_idx = 0;
+
+ ioq->queue = g_malloc0(sizeof ioq->queue[0] * maxreqs);
+ ioq->queue_idx = 0;
+}
+
+static void ioq_cleanup(IOQueue *ioq)
+{
+ g_free(ioq->freelist);
+ g_free(ioq->queue);
+
+ event_notifier_cleanup(&ioq->notifier);
+ io_destroy(ioq->io_ctx);
+}
+
+static EventNotifier *ioq_get_notifier(IOQueue *ioq)
+{
+ return &ioq->notifier;
+}
+
+static struct iocb *ioq_get_iocb(IOQueue *ioq)
+{
+ if (unlikely(ioq->freelist_idx == 0)) {
+ fprintf(stderr, "ioq underflow\n");
+ exit(1);
+ }
+ struct iocb *iocb = ioq->freelist[--ioq->freelist_idx];
+ ioq->queue[ioq->queue_idx++] = iocb;
+}
+
+static __attribute__((unused)) void ioq_put_iocb(IOQueue *ioq, struct iocb *iocb)
+{
+ if (unlikely(ioq->freelist_idx == ioq->maxreqs)) {
+ fprintf(stderr, "ioq overflow\n");
+ exit(1);
+ }
+ ioq->freelist[ioq->freelist_idx++] = iocb;
+}
+
+static __attribute__((unused)) void ioq_rdwr(IOQueue *ioq, bool read, struct iovec *iov, unsigned int count, long long offset)
+{
+ struct iocb *iocb = ioq_get_iocb(ioq);
+
+ if (read) {
+ io_prep_preadv(iocb, ioq->fd, iov, count, offset);
+ } else {
+ io_prep_pwritev(iocb, ioq->fd, iov, count, offset);
+ }
+ io_set_eventfd(iocb, event_notifier_get_fd(&ioq->notifier));
+}
+
+static __attribute__((unused)) void ioq_fdsync(IOQueue *ioq)
+{
+ struct iocb *iocb = ioq_get_iocb(ioq);
+
+ io_prep_fdsync(iocb, ioq->fd);
+ io_set_eventfd(iocb, event_notifier_get_fd(&ioq->notifier));
+}
+
+static __attribute__((unused)) int ioq_submit(IOQueue *ioq)
+{
+ int rc = io_submit(ioq->io_ctx, ioq->queue_idx, ioq->queue);
+ ioq->queue_idx = 0; /* reset */
+ return rc;
+}
+
+#endif /* IO_QUEUE_H */
diff --git a/hw/virtio-blk.c b/hw/virtio-blk.c
index 91f1bab..5e1ed79 100644
--- a/hw/virtio-blk.c
+++ b/hw/virtio-blk.c
@@ -13,12 +13,14 @@
#include <libaio.h>
#include "qemu-common.h"
+#include "block_int.h"
#include "qemu-thread.h"
#include "qemu-error.h"
#include "blockdev.h"
#include "virtio-blk.h"
#include "hw/dataplane/event-poll.h"
#include "hw/dataplane/vring.h"
+#include "hw/dataplane/ioq.h"
#include "kvm.h"
enum {
@@ -42,9 +44,9 @@ typedef struct VirtIOBlock
Vring vring; /* virtqueue vring */
+ IOQueue ioqueue; /* Linux AIO queue (should really be per dataplane thread) */
+
EventPoll event_poll; /* event poller */
- io_context_t io_ctx; /* Linux AIO context */
- EventNotifier io_notifier; /* Linux AIO eventfd */
EventHandler io_handler; /* Linux AIO completion handler */
EventHandler notify_handler; /* virtqueue notify handler */
} VirtIOBlock;
@@ -128,6 +130,14 @@ static void *data_plane_thread(void *opaque)
return NULL;
}
+/* Normally the block driver passes down the fd, there's no way to get it from
+ * above.
+ */
+static int get_raw_posix_fd_hack(VirtIOBlock *s)
+{
+ return *(int*)s->bs->file->opaque;
+}
+
static void data_plane_start(VirtIOBlock *s)
{
vring_setup(&s->vring, &s->vdev, 0);
@@ -138,23 +148,13 @@ static void data_plane_start(VirtIOBlock *s)
fprintf(stderr, "virtio-blk failed to set host notifier, ensure -enable-kvm is set\n");
exit(1);
}
-
event_poll_add(&s->event_poll, &s->notify_handler,
virtio_queue_get_host_notifier(s->vq),
handle_notify);
- /* Create aio context */
- if (io_setup(SEG_MAX, &s->io_ctx) != 0) {
- fprintf(stderr, "virtio-blk io_setup failed\n");
- exit(1);
- }
-
- if (event_notifier_init(&s->io_notifier, 0) != 0) {
- fprintf(stderr, "virtio-blk io event notifier creation failed\n");
- exit(1);
- }
-
- event_poll_add(&s->event_poll, &s->io_handler, &s->io_notifier, handle_io);
+ ioq_init(&s->ioqueue, get_raw_posix_fd_hack(s), REQ_MAX);
+ /* TODO populate ioqueue freelist */
+ event_poll_add(&s->event_poll, &s->io_handler, ioq_get_notifier(&s->ioqueue), handle_io);
qemu_thread_create(&s->data_plane_thread, data_plane_thread, s, QEMU_THREAD_JOINABLE);
@@ -167,8 +167,7 @@ static void data_plane_stop(VirtIOBlock *s)
/* TODO stop data plane thread */
- event_notifier_cleanup(&s->io_notifier);
- io_destroy(s->io_ctx);
+ ioq_cleanup(&s->ioqueue);
s->vdev.binding->set_host_notifier(s->vdev.binding_opaque, 0, false);
--
1.7.10.4
next prev parent reply other threads:[~2012-07-18 15:08 UTC|newest]
Thread overview: 45+ messages / expand[flat|nested] mbox.gz Atom feed top
2012-07-18 15:07 [Qemu-devel] [RFC v9 00/27] virtio: virtio-blk data plane Stefan Hajnoczi
2012-07-18 15:07 ` [Qemu-devel] [RFC v9 01/27] virtio-blk: Remove virtqueue request handling code Stefan Hajnoczi
2012-07-18 15:07 ` [Qemu-devel] [RFC v9 02/27] virtio-blk: Set up host notifier for data plane Stefan Hajnoczi
2012-07-18 15:07 ` [Qemu-devel] [RFC v9 03/27] virtio-blk: Data plane thread event loop Stefan Hajnoczi
2012-07-18 15:07 ` [Qemu-devel] [RFC v9 04/27] virtio-blk: Map vring Stefan Hajnoczi
2012-07-18 15:07 ` [Qemu-devel] [RFC v9 05/27] virtio-blk: Do cheapest possible memory mapping Stefan Hajnoczi
2012-07-18 15:07 ` [Qemu-devel] [RFC v9 06/27] virtio-blk: Take PCI memory range into account Stefan Hajnoczi
2012-07-18 18:29 ` Michael S. Tsirkin
2012-07-19 9:14 ` Stefan Hajnoczi
2012-07-19 9:16 ` Stefan Hajnoczi
2012-07-19 9:29 ` Avi Kivity
2012-07-18 15:07 ` [Qemu-devel] [RFC v9 07/27] virtio-blk: Put dataplane code into its own directory Stefan Hajnoczi
2012-07-18 15:07 ` [Qemu-devel] [RFC v9 08/27] virtio-blk: Read requests from the vring Stefan Hajnoczi
2012-07-18 15:07 ` Stefan Hajnoczi [this message]
2012-07-18 15:07 ` [Qemu-devel] [RFC v9 10/27] virtio-blk: Stop data plane thread cleanly Stefan Hajnoczi
2012-07-18 15:07 ` [Qemu-devel] [RFC v9 11/27] virtio-blk: Indirect vring and flush support Stefan Hajnoczi
2012-07-18 18:28 ` Michael S. Tsirkin
2012-07-18 19:02 ` Michael S. Tsirkin
2012-07-18 15:07 ` [Qemu-devel] [RFC v9 12/27] virtio-blk: Add workaround for BUG_ON() dependency in virtio_ring.h Stefan Hajnoczi
2012-07-18 19:03 ` Michael S. Tsirkin
2012-07-18 15:07 ` [Qemu-devel] [RFC v9 13/27] virtio-blk: Increase max requests for indirect vring Stefan Hajnoczi
2012-07-18 15:07 ` [Qemu-devel] [RFC v9 14/27] virtio-blk: Use pthreads instead of qemu-thread Stefan Hajnoczi
2012-07-18 15:07 ` [Qemu-devel] [RFC v9 15/27] notifier: Add a function to set the notifier Stefan Hajnoczi
2012-07-18 15:07 ` [Qemu-devel] [RFC v9 16/27] virtio-blk: Kick data plane thread using event notifier set Stefan Hajnoczi
2012-07-18 15:07 ` [Qemu-devel] [RFC v9 17/27] virtio-blk: Use guest notifier to raise interrupts Stefan Hajnoczi
2012-07-18 15:07 ` [Qemu-devel] [RFC v9 18/27] virtio-blk: Call ioctl() directly instead of irqfd Stefan Hajnoczi
2012-07-18 15:40 ` Michael S. Tsirkin
2012-07-19 9:11 ` Stefan Hajnoczi
2012-07-19 9:19 ` Michael S. Tsirkin
2012-07-18 15:07 ` [Qemu-devel] [RFC v9 19/27] virtio-blk: Disable guest->host notifies while processing vring Stefan Hajnoczi
2012-07-18 15:07 ` [Qemu-devel] [RFC v9 20/27] virtio-blk: Add ioscheduler to detect mergable requests Stefan Hajnoczi
2012-07-18 15:07 ` [Qemu-devel] [RFC v9 21/27] virtio-blk: Add basic request merging Stefan Hajnoczi
2012-07-18 15:07 ` [Qemu-devel] [RFC v9 22/27] virtio-blk: Fix " Stefan Hajnoczi
2012-07-18 19:04 ` Michael S. Tsirkin
2012-07-18 15:07 ` [Qemu-devel] [RFC v9 23/27] virtio-blk: Stub out SCSI commands Stefan Hajnoczi
2012-07-18 19:05 ` Michael S. Tsirkin
2012-07-18 15:07 ` [Qemu-devel] [RFC v9 24/27] virtio-blk: fix incorrect length Stefan Hajnoczi
2012-07-18 15:07 ` [Qemu-devel] [RFC v9 25/27] msix: fix irqchip breakage in msix_try_notify_from_thread() Stefan Hajnoczi
2012-07-18 15:07 ` [Qemu-devel] [RFC v9 26/27] msix: use upstream kvm_irqchip_set_irq() Stefan Hajnoczi
2012-07-18 15:07 ` [Qemu-devel] [RFC v9 27/27] virtio-blk: add EVENT_IDX support to dataplane Stefan Hajnoczi
2012-07-18 15:43 ` [Qemu-devel] [RFC v9 00/27] virtio: virtio-blk data plane Michael S. Tsirkin
2012-07-18 16:18 ` Khoa Huynh
2012-07-18 16:41 ` Khoa Huynh
2012-07-18 15:49 ` Michael S. Tsirkin
2012-07-19 9:48 ` Stefan Hajnoczi
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=1342624074-24650-10-git-send-email-stefanha@linux.vnet.ibm.com \
--to=stefanha@linux.vnet.ibm.com \
--cc=aliguori@us.ibm.com \
--cc=asias@redhat.com \
--cc=khoa@us.ibm.com \
--cc=kvm@vger.kernel.org \
--cc=kwolf@redhat.com \
--cc=mst@redhat.com \
--cc=pbonzini@redhat.com \
--cc=qemu-devel@nongnu.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).