From: Maxime Coquelin <maxime.coquelin@redhat.com>
To: dev@dpdk.org, chenbo.xia@intel.com, david.marchand@redhat.com,
i.maximets@ovn.org
Cc: Maxime Coquelin <maxime.coquelin@redhat.com>
Subject: [PATCH v2 5/5] vhost: add statistics for IOTLB
Date: Thu, 24 Mar 2022 13:46:38 +0100 [thread overview]
Message-ID: <20220324124638.32672-6-maxime.coquelin@redhat.com> (raw)
In-Reply-To: <20220324124638.32672-1-maxime.coquelin@redhat.com>
This patch adds statistics for IOTLB hits and misses.
Signed-off-by: Maxime Coquelin <maxime.coquelin@redhat.com>
---
lib/vhost/vhost.c | 10 +++++++++-
lib/vhost/vhost.h | 3 +++
2 files changed, 12 insertions(+), 1 deletion(-)
diff --git a/lib/vhost/vhost.c b/lib/vhost/vhost.c
index 58b58fc40e..7f4fafdcb0 100644
--- a/lib/vhost/vhost.c
+++ b/lib/vhost/vhost.c
@@ -43,6 +43,8 @@ static const struct vhost_vq_stats_name_off vhost_vq_stat_strings[] = {
{"size_1024_1518_packets", offsetof(struct vhost_virtqueue, stats.size_bins[6])},
{"size_1519_max_packets", offsetof(struct vhost_virtqueue, stats.size_bins[7])},
{"guest_notifications", offsetof(struct vhost_virtqueue, stats.guest_notifications)},
+ {"iotlb_hits", offsetof(struct vhost_virtqueue, stats.iotlb_hits)},
+ {"iotlb_misses", offsetof(struct vhost_virtqueue, stats.iotlb_misses)},
};
#define VHOST_NB_VQ_STATS RTE_DIM(vhost_vq_stat_strings)
@@ -60,8 +62,14 @@ __vhost_iova_to_vva(struct virtio_net *dev, struct vhost_virtqueue *vq,
tmp_size = *size;
vva = vhost_user_iotlb_cache_find(vq, iova, &tmp_size, perm);
- if (tmp_size == *size)
+ if (tmp_size == *size) {
+ if (dev->flags & VIRTIO_DEV_STATS_ENABLED)
+ vq->stats.iotlb_hits++;
return vva;
+ }
+
+ if (dev->flags & VIRTIO_DEV_STATS_ENABLED)
+ vq->stats.iotlb_misses++;
iova += tmp_size;
diff --git a/lib/vhost/vhost.h b/lib/vhost/vhost.h
index 13c5c2266d..e876fc157b 100644
--- a/lib/vhost/vhost.h
+++ b/lib/vhost/vhost.h
@@ -134,6 +134,9 @@ struct virtqueue_stats {
/* Size bins in array as RFC 2819, undersized [0], 64 [1], etc */
uint64_t size_bins[8];
uint64_t guest_notifications;
+ uint64_t iotlb_hits;
+ uint64_t iotlb_misses;
+ uint64_t iotlb_errors;
};
/**
--
2.35.1
next prev parent reply other threads:[~2022-03-24 12:47 UTC|newest]
Thread overview: 12+ messages / expand[flat|nested] mbox.gz Atom feed top
2022-03-24 12:46 [PATCH v2 0/5] vhost: introduce per-virtqueue stats API Maxime Coquelin
2022-03-24 12:46 ` [PATCH v2 1/5] vhost: fix missing virtqueue lock protection Maxime Coquelin
2022-03-28 8:07 ` David Marchand
2022-03-28 14:59 ` Maxime Coquelin
2022-03-24 12:46 ` [PATCH v2 2/5] vhost: add per-virtqueue statistics support Maxime Coquelin
2022-03-24 12:46 ` [PATCH v2 3/5] net/vhost: move to Vhost library stats API Maxime Coquelin
2022-04-25 12:06 ` Xia, Chenbo
2022-03-24 12:46 ` [PATCH v2 4/5] vhost: add statistics for guest notifications Maxime Coquelin
2022-04-25 12:09 ` Xia, Chenbo
2022-03-24 12:46 ` Maxime Coquelin [this message]
2022-04-25 12:10 ` [PATCH v2 5/5] vhost: add statistics for IOTLB Xia, Chenbo
2022-05-10 14:15 ` Maxime Coquelin
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=20220324124638.32672-6-maxime.coquelin@redhat.com \
--to=maxime.coquelin@redhat.com \
--cc=chenbo.xia@intel.com \
--cc=david.marchand@redhat.com \
--cc=dev@dpdk.org \
--cc=i.maximets@ovn.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).