DPDK patches and discussions
 help / color / mirror / Atom feed
From: Yuanhan Liu <yuanhan.liu@linux.intel.com>
To: dev@dpdk.org
Cc: huawei.xie@intel.com, Traynor Kevin <kevin.traynor@intel.com>,
	marcandre.lureau@redhat.com,
	Yuanhan Liu <yuanhan.liu@linux.intel.com>,
	"Michael S. Tsirkin" <mst@redhat.com>
Subject: [dpdk-dev] [PATCH v2 4/6] vhost: workaround stale vring base
Date: Thu, 12 May 2016 23:16:30 -0700	[thread overview]
Message-ID: <1463120192-24200-5-git-send-email-yuanhan.liu@linux.intel.com> (raw)
In-Reply-To: <1463120192-24200-1-git-send-email-yuanhan.liu@linux.intel.com>

When DPDK app crashes (or quits, or gets killed), a restart of DPDK
app would get stale vring base from QEMU. That would break the kernel
virtio net completely, making it non-work any more, unless a driver
reset is done.

So, instead of getting the stale vring base from QEMU, Huawei suggested
we could get a much saner (and may not the most accurate) vring base
from used->idx. That would work because:

- there is a memory barrier between updating used ring entries and
  used->idx. So, even though we crashed at updating the used ring
  entries, it will not cause any issue, as the guest driver will not
  process those stale used entries, for used-idx is not updated yet.

- DPDK process vring in order, that means a crash may just lead some
  packet retransmission for Tx and drop for Rx.

Cc: "Michael S. Tsirkin" <mst@redhat.com>
Suggested-by: Huawei Xie <huawei.xie@intel.com>
Signed-off-by: Yuanhan Liu <yuanhan.liu@linux.intel.com>
Acked-by: "Michael S. Tsirkin" <mst@redhat.com>
Acked-by: Huawei Xie <huawei.xie@intel.com>
---

v2: log on packets resent for Tx and drop for Rx
---
 lib/librte_vhost/virtio-net.c | 9 +++++++++
 1 file changed, 9 insertions(+)

diff --git a/lib/librte_vhost/virtio-net.c b/lib/librte_vhost/virtio-net.c
index 835ab3a..bd7e55e 100644
--- a/lib/librte_vhost/virtio-net.c
+++ b/lib/librte_vhost/virtio-net.c
@@ -561,6 +561,15 @@ vhost_set_vring_addr(int vid, struct vhost_vring_addr *addr)
 		return -1;
 	}
 
+	if (vq->last_used_idx != vq->used->idx) {
+		RTE_LOG(WARNING, VHOST_CONFIG,
+			"last_used_idx (%u) and vq->used->idx (%u) mismatches; "
+			"some packets maybe resent for Tx and dropped for Rx\n",
+			vq->last_used_idx, vq->used->idx);
+		vq->last_used_idx     = vq->used->idx;
+		vq->last_used_idx_res = vq->used->idx;
+	}
+
 	vq->log_guest_addr = addr->log_guest_addr;
 
 	LOG_DEBUG(VHOST_CONFIG, "(%d) mapped address desc: %p\n",
-- 
1.9.0

  parent reply	other threads:[~2016-05-13  6:11 UTC|newest]

Thread overview: 50+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2016-05-07  6:40 [dpdk-dev] [PATCH 0/6] vhost: add vhost-user client mode and reconnect ability Yuanhan Liu
2016-05-07  6:40 ` [dpdk-dev] [PATCH 1/6] vhost: rename structs for enabling client mode Yuanhan Liu
2016-05-07  6:40 ` [dpdk-dev] [PATCH 2/6] vhost: add vhost-user " Yuanhan Liu
2016-05-09 10:33   ` Victor Kaplansky
2016-05-09 20:33     ` Yuanhan Liu
2016-05-09 20:30       ` Michael S. Tsirkin
2016-05-07  6:40 ` [dpdk-dev] [PATCH 3/6] vhost: add reconnect ability Yuanhan Liu
2016-05-09 16:47   ` Xie, Huawei
2016-05-09 18:12     ` Yuanhan Liu
2016-05-10  7:24       ` Xie, Huawei
2016-05-10  7:54         ` Michael S. Tsirkin
2016-05-10  8:07           ` Xie, Huawei
2016-05-10  8:42             ` Michael S. Tsirkin
2016-05-10  9:00               ` Xie, Huawei
2016-05-10  9:17                 ` Michael S. Tsirkin
2016-05-10 17:17                   ` Loftus, Ciara
2016-05-11 21:46                     ` Michael S. Tsirkin
2016-05-07  6:40 ` [dpdk-dev] [PATCH 4/6] vhost: workaround stale vring base Yuanhan Liu
2016-05-09 10:45   ` Victor Kaplansky
2016-05-09 13:39     ` Xie, Huawei
2016-05-09 18:23       ` Yuanhan Liu
2016-05-09 12:19   ` Michael S. Tsirkin
2016-05-09 16:25   ` Xie, Huawei
2016-05-09 18:22     ` Yuanhan Liu
2016-06-13 20:47       ` Michael S. Tsirkin
2016-05-10  8:21   ` Xie, Huawei
2016-05-07  6:40 ` [dpdk-dev] [PATCH 5/6] examples/vhost: add client and reconnect option Yuanhan Liu
2016-05-09 10:47   ` Victor Kaplansky
2016-05-07  6:40 ` [dpdk-dev] [PATCH 6/6] vhost: add pmd " Yuanhan Liu
2016-05-09 10:54   ` Victor Kaplansky
2016-05-09 18:26     ` Yuanhan Liu
2016-05-10  3:23 ` [dpdk-dev] [PATCH 0/6] vhost: add vhost-user client mode and reconnect ability Xu, Qian Q
2016-05-10 17:41   ` Yuanhan Liu
2016-05-13  6:16 ` [dpdk-dev] [PATCH v2 " Yuanhan Liu
2016-05-13  6:16   ` [dpdk-dev] [PATCH v2 1/6] vhost: rename structs for enabling client mode Yuanhan Liu
2016-05-13  6:16   ` [dpdk-dev] [PATCH v2 2/6] vhost: add vhost-user " Yuanhan Liu
2016-05-13  6:16   ` [dpdk-dev] [PATCH v2 3/6] vhost: add reconnect ability Yuanhan Liu
2016-05-13  6:16   ` Yuanhan Liu [this message]
2016-05-13  6:16   ` [dpdk-dev] [PATCH v2 5/6] examples/vhost: add client and reconnect option Yuanhan Liu
2016-05-13  6:16   ` [dpdk-dev] [PATCH v2 6/6] vhost: add pmd " Yuanhan Liu
2016-05-25 17:45     ` Rich Lane
2016-05-26  8:01       ` Yuanhan Liu
2016-06-07  4:05   ` [dpdk-dev] [PATCH v3 0/6] vhost: add vhost-user client mode and reconnect ability Yuanhan Liu
2016-06-07  4:05     ` [dpdk-dev] [PATCH v3 1/6] vhost: rename structs for enabling client mode Yuanhan Liu
2016-06-07  4:05     ` [dpdk-dev] [PATCH v3 2/6] vhost: add vhost-user " Yuanhan Liu
2016-06-07  4:05     ` [dpdk-dev] [PATCH v3 3/6] vhost: add reconnect ability Yuanhan Liu
2016-06-07  4:05     ` [dpdk-dev] [PATCH v3 4/6] vhost: workaround stale vring base Yuanhan Liu
2016-06-07  4:05     ` [dpdk-dev] [PATCH v3 5/6] examples/vhost: add client option Yuanhan Liu
2016-06-07  4:05     ` [dpdk-dev] [PATCH v3 6/6] vhost: add pmd " Yuanhan Liu
2016-06-14 12:00     ` [dpdk-dev] [PATCH v3 0/6] vhost: add vhost-user client mode and reconnect ability Yuanhan Liu

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=1463120192-24200-5-git-send-email-yuanhan.liu@linux.intel.com \
    --to=yuanhan.liu@linux.intel.com \
    --cc=dev@dpdk.org \
    --cc=huawei.xie@intel.com \
    --cc=kevin.traynor@intel.com \
    --cc=marcandre.lureau@redhat.com \
    --cc=mst@redhat.com \
    /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).