From: Jason Wang <jasowang@redhat.com>
To: peter.maydell@linaro.org
Cc: qemu-devel@nongnu.org, Zhang Chen <zhangchen.fnst@cn.fujitsu.com>,
Li Zhijian <lizhijian@cn.fujitsu.com>,
Jason Wang <jasowang@redhat.com>
Subject: [Qemu-devel] [PULL 3/5] colo-compare: sort TCP packet queue by sequence number
Date: Wed, 15 Feb 2017 11:53:20 +0800 [thread overview]
Message-ID: <1487130802-27953-4-git-send-email-jasowang@redhat.com> (raw)
In-Reply-To: <1487130802-27953-1-git-send-email-jasowang@redhat.com>
From: Zhang Chen <zhangchen.fnst@cn.fujitsu.com>
Improve efficiency of TCP packet comparison.
Signed-off-by: Zhang Chen <zhangchen.fnst@cn.fujitsu.com>
Signed-off-by: Li Zhijian <lizhijian@cn.fujitsu.com>
Signed-off-by: Jason Wang <jasowang@redhat.com>
---
net/colo-compare.c | 19 +++++++++++++++++++
1 file changed, 19 insertions(+)
diff --git a/net/colo-compare.c b/net/colo-compare.c
index 4962976..162fd6a 100644
--- a/net/colo-compare.c
+++ b/net/colo-compare.c
@@ -101,6 +101,15 @@ static int compare_chr_send(CharBackend *out,
const uint8_t *buf,
uint32_t size);
+static gint seq_sorter(Packet *a, Packet *b, gpointer data)
+{
+ struct tcphdr *atcp, *btcp;
+
+ atcp = (struct tcphdr *)(a->transport_header);
+ btcp = (struct tcphdr *)(b->transport_header);
+ return ntohl(atcp->th_seq) - ntohl(btcp->th_seq);
+}
+
/*
* Return 0 on success, if return -1 means the pkt
* is unsupported(arp and ipv6) and will be sent later
@@ -137,6 +146,11 @@ static int packet_enqueue(CompareState *s, int mode)
if (g_queue_get_length(&conn->primary_list) <=
MAX_QUEUE_SIZE) {
g_queue_push_tail(&conn->primary_list, pkt);
+ if (conn->ip_proto == IPPROTO_TCP) {
+ g_queue_sort(&conn->primary_list,
+ (GCompareDataFunc)seq_sorter,
+ NULL);
+ }
} else {
error_report("colo compare primary queue size too big,"
"drop packet");
@@ -145,6 +159,11 @@ static int packet_enqueue(CompareState *s, int mode)
if (g_queue_get_length(&conn->secondary_list) <=
MAX_QUEUE_SIZE) {
g_queue_push_tail(&conn->secondary_list, pkt);
+ if (conn->ip_proto == IPPROTO_TCP) {
+ g_queue_sort(&conn->secondary_list,
+ (GCompareDataFunc)seq_sorter,
+ NULL);
+ }
} else {
error_report("colo compare secondary queue size too big,"
"drop packet");
--
2.7.4
next prev parent reply other threads:[~2017-02-15 3:53 UTC|newest]
Thread overview: 7+ messages / expand[flat|nested] mbox.gz Atom feed top
2017-02-15 3:53 [Qemu-devel] [PULL 0/5] Net patches Jason Wang
2017-02-15 3:53 ` [Qemu-devel] [PULL 1/5] net: Mark 'vlan' parameter as deprecated Jason Wang
2017-02-15 3:53 ` [Qemu-devel] [PULL 2/5] net: e1000e: fix dead code in e1000e_write_packet_to_guest Jason Wang
2017-02-15 3:53 ` Jason Wang [this message]
2017-02-15 3:53 ` [Qemu-devel] [PULL 4/5] net: imx: limit buffer descriptor count Jason Wang
2017-02-15 3:53 ` [Qemu-devel] [PULL 5/5] net: e1000e: fix an infinite loop issue Jason Wang
2017-02-16 14:23 ` [Qemu-devel] [PULL 0/5] Net patches Peter Maydell
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=1487130802-27953-4-git-send-email-jasowang@redhat.com \
--to=jasowang@redhat.com \
--cc=lizhijian@cn.fujitsu.com \
--cc=peter.maydell@linaro.org \
--cc=qemu-devel@nongnu.org \
--cc=zhangchen.fnst@cn.fujitsu.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).