public inbox for netdev@vger.kernel.org 
 help / color / mirror / Atom feed
From: Rusty Russell <rusty@rustcorp•com.au>
To: "Michael S. Tsirkin" <mst@redhat•com>
Cc: Krishna Kumar2 <krkumar2@in•ibm.com>,
	David Miller <davem@davemloft•net>,
	kvm@vger•kernel.org, Shirley Ma <mashirle@us•ibm.com>,
	netdev@vger•kernel.org, steved@us•ibm.com
Subject: Re: Network performance with small packets
Date: Wed, 9 Feb 2011 11:07:20 +1030	[thread overview]
Message-ID: <201102091107.20270.rusty@rustcorp.com.au> (raw)
In-Reply-To: <20110202044222.GC3818@redhat.com>

On Wed, 2 Feb 2011 03:12:22 pm Michael S. Tsirkin wrote:
> On Wed, Feb 02, 2011 at 10:09:18AM +0530, Krishna Kumar2 wrote:
> > > "Michael S. Tsirkin" <mst@redhat•com> 02/02/2011 03:11 AM
> > >
> > > On Tue, Feb 01, 2011 at 01:28:45PM -0800, Shirley Ma wrote:
> > > > On Tue, 2011-02-01 at 23:21 +0200, Michael S. Tsirkin wrote:
> > > > > Confused. We compare capacity to skb frags, no?
> > > > > That's sg I think ...
> > > >
> > > > Current guest kernel use indirect buffers, num_free returns how many
> > > > available descriptors not skb frags. So it's wrong here.
> > > >
> > > > Shirley
> > >
> > > I see. Good point. In other words when we complete the buffer
> > > it was indirect, but when we add a new one we
> > > can not allocate indirect so we consume.
> > > And then we start the queue and add will fail.
> > > I guess we need some kind of API to figure out
> > > whether the buf we complete was indirect?

I've finally read this thread... I think we need to get more serious
with our stats gathering to diagnose these kind of performance issues.

This is a start; it should tell us what is actually happening to the
virtio ring(s) without significant performance impact...

Subject: virtio: CONFIG_VIRTIO_STATS

For performance problems we'd like to know exactly what the ring looks
like.  This patch adds stats indexed by how-full-ring-is; we could extend
it to also record them by how-used-ring-is if we need.

Signed-off-by: Rusty Russell <rusty@rustcorp•com.au>

diff --git a/drivers/virtio/Kconfig b/drivers/virtio/Kconfig
--- a/drivers/virtio/Kconfig
+++ b/drivers/virtio/Kconfig
@@ -7,6 +7,14 @@ config VIRTIO_RING
 	tristate
 	depends on VIRTIO
 
+config VIRTIO_STATS
+	bool "Virtio debugging stats (EXPERIMENTAL)"
+	depends on VIRTIO_RING
+	select DEBUG_FS
+	---help---
+	  Virtio stats collected by how full the ring is at any time,
+	  presented under debugfs/virtio/<name>-<vq>/<num-used>/
+
 config VIRTIO_PCI
 	tristate "PCI driver for virtio devices (EXPERIMENTAL)"
 	depends on PCI && EXPERIMENTAL
diff --git a/drivers/virtio/virtio_ring.c b/drivers/virtio/virtio_ring.c
--- a/drivers/virtio/virtio_ring.c
+++ b/drivers/virtio/virtio_ring.c
@@ -21,6 +21,7 @@
 #include <linux/virtio_config.h>
 #include <linux/device.h>
 #include <linux/slab.h>
+#include <linux/debugfs.h>
 
 /* virtio guest is communicating with a virtual "device" that actually runs on
  * a host processor.  Memory barriers are used to control SMP effects. */
@@ -95,6 +96,11 @@ struct vring_virtqueue
 	/* How to notify other side. FIXME: commonalize hcalls! */
 	void (*notify)(struct virtqueue *vq);
 
+#ifdef CONFIG_VIRTIO_STATS
+	struct vring_stat *stats;
+	struct dentry *statdir;
+#endif
+
 #ifdef DEBUG
 	/* They're supposed to lock for us. */
 	unsigned int in_use;
@@ -106,6 +112,87 @@ struct vring_virtqueue
 
 #define to_vvq(_vq) container_of(_vq, struct vring_virtqueue, vq)
 
+#ifdef CONFIG_VIRTIO_STATS
+/* We have an array of these, indexed by how full the ring is. */
+struct vring_stat {
+	/* How many interrupts? */
+	size_t interrupt_nowork, interrupt_work;
+	/* How many non-notify kicks, how many notify kicks, how many add notify? */
+	size_t kick_no_notify, kick_notify, add_notify;
+	/* How many adds? */
+	size_t add_direct, add_indirect, add_fail;
+	/* How many gets? */
+	size_t get;
+	/* How many disable callbacks? */
+	size_t disable_cb;
+	/* How many enables? */
+	size_t enable_cb_retry, enable_cb_success;
+};
+
+static struct dentry *virtio_stats;
+
+static void create_stat_files(struct vring_virtqueue *vq)
+{
+	char name[80];
+	unsigned int i;
+
+	/* Racy in theory, but we don't care. */
+	if (!virtio_stats)
+		virtio_stats = debugfs_create_dir("virtio-stats", NULL);
+
+	sprintf(name, "%s-%s", dev_name(&vq->vq.vdev->dev), vq->vq.name);
+	vq->statdir = debugfs_create_dir(name, virtio_stats);
+
+	for (i = 0; i < vq->vring.num; i++) {
+		struct dentry *dir;
+
+		sprintf(name, "%i", i);
+		dir = debugfs_create_dir(name, vq->statdir);
+		debugfs_create_size_t("interrupt_nowork", 0400, dir,
+				      &vq->stats[i].interrupt_nowork);
+		debugfs_create_size_t("interrupt_work", 0400, dir,
+				      &vq->stats[i].interrupt_work);
+		debugfs_create_size_t("kick_no_notify", 0400, dir,
+				      &vq->stats[i].kick_no_notify);
+		debugfs_create_size_t("kick_notify", 0400, dir,
+				      &vq->stats[i].kick_notify);
+		debugfs_create_size_t("add_notify", 0400, dir,
+				      &vq->stats[i].add_notify);
+		debugfs_create_size_t("add_direct", 0400, dir,
+				      &vq->stats[i].add_direct);
+		debugfs_create_size_t("add_indirect", 0400, dir,
+				      &vq->stats[i].add_indirect);
+		debugfs_create_size_t("add_fail", 0400, dir,
+				      &vq->stats[i].add_fail);
+		debugfs_create_size_t("get", 0400, dir,
+				      &vq->stats[i].get);
+		debugfs_create_size_t("disable_cb", 0400, dir,
+				      &vq->stats[i].disable_cb);
+		debugfs_create_size_t("enable_cb_retry", 0400, dir,
+				      &vq->stats[i].enable_cb_retry);
+		debugfs_create_size_t("enable_cb_success", 0400, dir,
+				      &vq->stats[i].enable_cb_success);
+	}
+}
+
+static void delete_stat_files(struct vring_virtqueue *vq)
+{
+	debugfs_remove_recursive(vq->statdir);
+}
+
+#define add_stat(vq, name)						\
+	do {								\
+		struct vring_virtqueue *_vq = (vq);			\
+		_vq->stats[_vq->num_free - _vq->vring.num].name++;	\
+	} while (0)
+
+#else
+#define add_stat(vq, name)
+static void delete_stat_files(struct vring_virtqueue *vq)
+{
+}
+#endif
+
 /* Set up an indirect table of descriptors and add it to the queue. */
 static int vring_add_indirect(struct vring_virtqueue *vq,
 			      struct scatterlist sg[],
@@ -121,6 +208,8 @@ static int vring_add_indirect(struct vri
 	if (!desc)
 		return -ENOMEM;
 
+	add_stat(vq, add_indirect);
+
 	/* Transfer entries from the sg list into the indirect page */
 	for (i = 0; i < out; i++) {
 		desc[i].flags = VRING_DESC_F_NEXT;
@@ -183,17 +272,22 @@ int virtqueue_add_buf_gfp(struct virtque
 	BUG_ON(out + in == 0);
 
 	if (vq->num_free < out + in) {
+		add_stat(vq, add_fail);
 		pr_debug("Can't add buf len %i - avail = %i\n",
 			 out + in, vq->num_free);
 		/* FIXME: for historical reasons, we force a notify here if
 		 * there are outgoing parts to the buffer.  Presumably the
 		 * host should service the ring ASAP. */
-		if (out)
+		if (out) {
+			add_stat(vq, add_notify);
 			vq->notify(&vq->vq);
+		}
 		END_USE(vq);
 		return -ENOSPC;
 	}
 
+	add_stat(vq, add_direct);
+
 	/* We're about to use some buffers from the free list. */
 	vq->num_free -= out + in;
 
@@ -248,9 +342,12 @@ void virtqueue_kick(struct virtqueue *_v
 	/* Need to update avail index before checking if we should notify */
 	virtio_mb();
 
-	if (!(vq->vring.used->flags & VRING_USED_F_NO_NOTIFY))
+	if (!(vq->vring.used->flags & VRING_USED_F_NO_NOTIFY)) {
+		add_stat(vq, kick_notify);
 		/* Prod other side to tell it about changes. */
 		vq->notify(&vq->vq);
+	} else
+		add_stat(vq, kick_no_notify);
 
 	END_USE(vq);
 }
@@ -294,6 +391,8 @@ void *virtqueue_get_buf(struct virtqueue
 
 	START_USE(vq);
 
+	add_stat(vq, get);
+
 	if (unlikely(vq->broken)) {
 		END_USE(vq);
 		return NULL;
@@ -333,6 +432,7 @@ void virtqueue_disable_cb(struct virtque
 {
 	struct vring_virtqueue *vq = to_vvq(_vq);
 
+	add_stat(vq, disable_cb);
 	vq->vring.avail->flags |= VRING_AVAIL_F_NO_INTERRUPT;
 }
 EXPORT_SYMBOL_GPL(virtqueue_disable_cb);
@@ -348,10 +448,12 @@ bool virtqueue_enable_cb(struct virtqueu
 	vq->vring.avail->flags &= ~VRING_AVAIL_F_NO_INTERRUPT;
 	virtio_mb();
 	if (unlikely(more_used(vq))) {
+		add_stat(vq, enable_cb_retry);
 		END_USE(vq);
 		return false;
 	}
 
+	add_stat(vq, enable_cb_success);
 	END_USE(vq);
 	return true;
 }
@@ -387,10 +489,12 @@ irqreturn_t vring_interrupt(int irq, voi
 	struct vring_virtqueue *vq = to_vvq(_vq);
 
 	if (!more_used(vq)) {
+		add_stat(vq, interrupt_nowork);
 		pr_debug("virtqueue interrupt with no work for %p\n", vq);
 		return IRQ_NONE;
 	}
 
+	add_stat(vq, interrupt_work);
 	if (unlikely(vq->broken))
 		return IRQ_HANDLED;
 
@@ -451,6 +555,15 @@ struct virtqueue *vring_new_virtqueue(un
 	}
 	vq->data[i] = NULL;
 
+#ifdef CONFIG_VIRTIO_STATS
+	vq->stats = kzalloc(sizeof(*vq->stats) * num, GFP_KERNEL);
+	if (!vq->stats) {
+		kfree(vq);
+		return NULL;
+	}
+	create_stat_files(vq);
+#endif
+
 	return &vq->vq;
 }
 EXPORT_SYMBOL_GPL(vring_new_virtqueue);
@@ -458,6 +571,7 @@ EXPORT_SYMBOL_GPL(vring_new_virtqueue);
 void vring_del_virtqueue(struct virtqueue *vq)
 {
 	list_del(&vq->list);
+	delete_stat_files(to_vvq(vq));
 	kfree(to_vvq(vq));
 }
 EXPORT_SYMBOL_GPL(vring_del_virtqueue);

  reply	other threads:[~2011-02-09  0:37 UTC|newest]

Thread overview: 79+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
     [not found] <OFD293DCD2.7F0260F0-ON86257823.0061DC39-86257823.00743BB3@us.ibm.com>
     [not found] ` <20110126151700.GA14113@redhat.com>
     [not found]   ` <1296153874.1640.27.camel@localhost.localdomain>
     [not found]     ` <20110127190031.GC5228@redhat.com>
     [not found]       ` <1296155340.1640.34.camel@localhost.localdomain>
     [not found]         ` <20110127193131.GD5228@redhat.com>
     [not found]           ` <1296157547.1640.45.camel@localhost.localdomain>
2011-01-27 20:05             ` Network performance with small packets Michael S. Tsirkin
2011-01-27 20:15               ` Shirley Ma
2011-01-28 18:29                 ` Steve Dobbelstein
2011-01-28 22:51                   ` Steve Dobbelstein
2011-02-01 15:52                   ` [PATCHv2 dontapply] vhost-net tx tuning Michael S. Tsirkin
2011-02-01 23:07                     ` Sridhar Samudrala
2011-02-01 23:27                       ` Shirley Ma
2011-02-02  4:36                       ` Michael S. Tsirkin
2011-01-27 21:02               ` Network performance with small packets David Miller
2011-01-27 21:30                 ` Shirley Ma
2011-01-28 12:16                   ` Michael S. Tsirkin
2011-02-01  0:24                     ` Steve Dobbelstein
2011-02-01  1:30                       ` Sridhar Samudrala
2011-02-01  5:56                         ` Michael S. Tsirkin
2011-02-01 21:09                         ` Shirley Ma
2011-02-01 21:24                           ` Michael S. Tsirkin
2011-02-01 21:32                             ` Shirley Ma
2011-02-01 21:42                               ` Michael S. Tsirkin
2011-02-01 21:53                                 ` Shirley Ma
2011-02-01 21:56                                   ` Michael S. Tsirkin
2011-02-01 22:59                                     ` Shirley Ma
2011-02-02  4:40                                       ` Michael S. Tsirkin
2011-02-02  6:05                                         ` Shirley Ma
2011-02-02  6:19                                           ` Shirley Ma
2011-02-02  6:29                                             ` Michael S. Tsirkin
2011-02-02  7:14                                               ` Shirley Ma
2011-02-02  7:33                                                 ` Shirley Ma
2011-02-02 10:49                                                   ` Michael S. Tsirkin
2011-02-02 15:42                                                     ` Shirley Ma
2011-02-02 15:48                                                       ` Michael S. Tsirkin
2011-02-02 17:12                                                         ` Shirley Ma
2011-02-02 18:20                                                       ` Michael S. Tsirkin
2011-02-02 18:26                                                         ` Shirley Ma
2011-02-02 10:48                                                 ` Michael S. Tsirkin
2011-02-02  6:34                                             ` Krishna Kumar2
2011-02-02  7:03                                               ` Shirley Ma
2011-02-02  7:37                                                 ` Krishna Kumar2
2011-02-02 10:48                                               ` Michael S. Tsirkin
2011-02-02 15:39                                                 ` Shirley Ma
2011-02-02 15:47                                                   ` Michael S. Tsirkin
2011-02-02 17:10                                                     ` Shirley Ma
2011-02-02 17:32                                                       ` Michael S. Tsirkin
2011-02-02 18:11                                                         ` Shirley Ma
2011-02-02 18:27                                                           ` Michael S. Tsirkin
2011-02-02 19:29                                                             ` Shirley Ma
2011-02-02 20:17                                                               ` Michael S. Tsirkin
2011-02-02 21:03                                                                 ` Shirley Ma
2011-02-02 21:20                                                                   ` Michael S. Tsirkin
2011-02-02 21:41                                                                     ` Shirley Ma
2011-02-03  5:59                                                                       ` Michael S. Tsirkin
2011-02-03  6:09                                                                         ` Shirley Ma
2011-02-03  6:16                                                                           ` Michael S. Tsirkin
2011-02-03  5:05                                                                     ` Shirley Ma
2011-02-03  6:13                                                                       ` Michael S. Tsirkin
2011-02-03 15:58                                                                         ` Shirley Ma
2011-02-03 16:20                                                                           ` Michael S. Tsirkin
2011-02-03 17:18                                                                             ` Shirley Ma
2011-02-01  5:54                       ` Michael S. Tsirkin
2011-02-01 17:23                   ` Michael S. Tsirkin
     [not found]                     ` <1296590943.26937.797.camel@localhost.localdomain>
     [not found]                       ` <20110201201715.GA30050@redhat.com>
2011-02-01 20:25                         ` Shirley Ma
2011-02-01 21:21                           ` Michael S. Tsirkin
2011-02-01 21:28                             ` Shirley Ma
2011-02-01 21:41                               ` Michael S. Tsirkin
2011-02-02  4:39                                 ` Krishna Kumar2
2011-02-02  4:42                                   ` Michael S. Tsirkin
2011-02-09  0:37                                     ` Rusty Russell [this message]
2011-02-09  0:53                                       ` Michael S. Tsirkin
2011-02-09  1:39                                         ` Rusty Russell
2011-02-09  1:55                                           ` Michael S. Tsirkin
2011-02-09  7:43                                             ` Stefan Hajnoczi
2011-03-08 21:57                                       ` Shirley Ma
2011-03-09  2:21                                         ` Andrew Theurer
2011-03-09 15:42                                           ` Shirley Ma
2011-03-10  1:49                                           ` Rusty Russell
2011-04-12 20:01                                             ` Michael S. Tsirkin
2011-04-14 11:28                                               ` Rusty Russell
2011-04-14 12:40                                                 ` Michael S. Tsirkin
2011-04-14 16:03                                                 ` Michael S. Tsirkin
2011-04-19  0:33                                                   ` Rusty Russell

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=201102091107.20270.rusty@rustcorp.com.au \
    --to=rusty@rustcorp$(echo .)com.au \
    --cc=davem@davemloft$(echo .)net \
    --cc=krkumar2@in$(echo .)ibm.com \
    --cc=kvm@vger$(echo .)kernel.org \
    --cc=mashirle@us$(echo .)ibm.com \
    --cc=mst@redhat$(echo .)com \
    --cc=netdev@vger$(echo .)kernel.org \
    --cc=steved@us$(echo .)ibm.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html
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