From: Jason Wang <jasowang@redhat.com>
To: peter.maydell@linaro.org, qemu-devel@nongnu.org
Cc: Zhang Chen <zhangchen.fnst@cn.fujitsu.com>,
Jason Wang <jasowang@redhat.com>
Subject: [Qemu-devel] [PULL 7/8] COLO-compare: Optimize tcp compare for option field
Date: Mon, 24 Apr 2017 13:16:05 +0800 [thread overview]
Message-ID: <1493010966-22976-8-git-send-email-jasowang@redhat.com> (raw)
In-Reply-To: <1493010966-22976-1-git-send-email-jasowang@redhat.com>
From: Zhang Chen <zhangchen.fnst@cn.fujitsu.com>
In this patch we support packet that have tcp options field.
Add tcp options field check, If the packet have options
field we just skip it and compare tcp payload,
Avoid unnecessary checkpoint, optimize performance.
Signed-off-by: Zhang Chen <zhangchen.fnst@cn.fujitsu.com>
Signed-off-by: Jason Wang <jasowang@redhat.com>
---
net/colo-compare.c | 27 ++++++++++++++++++++++++++-
1 file changed, 26 insertions(+), 1 deletion(-)
diff --git a/net/colo-compare.c b/net/colo-compare.c
index 9b09cfc..4ab80b1 100644
--- a/net/colo-compare.c
+++ b/net/colo-compare.c
@@ -233,7 +233,32 @@ static int colo_packet_compare_tcp(Packet *spkt, Packet *ppkt)
spkt->ip->ip_sum = ppkt->ip->ip_sum;
}
- if (ptcp->th_sum == stcp->th_sum) {
+ /*
+ * Check tcp header length for tcp option field.
+ * th_off > 5 means this tcp packet have options field.
+ * The tcp options maybe always different.
+ * for example:
+ * From RFC 7323.
+ * TCP Timestamps option (TSopt):
+ * Kind: 8
+ *
+ * Length: 10 bytes
+ *
+ * +-------+-------+---------------------+---------------------+
+ * |Kind=8 | 10 | TS Value (TSval) |TS Echo Reply (TSecr)|
+ * +-------+-------+---------------------+---------------------+
+ * 1 1 4 4
+ *
+ * In this case the primary guest's timestamp always different with
+ * the secondary guest's timestamp. COLO just focus on payload,
+ * so we just need skip this field.
+ */
+ if (ptcp->th_off > 5) {
+ ptrdiff_t tcp_offset;
+ tcp_offset = ppkt->transport_header - (uint8_t *)ppkt->data
+ + (ptcp->th_off * 4);
+ res = colo_packet_compare_common(ppkt, spkt, tcp_offset);
+ } else if (ptcp->th_sum == stcp->th_sum) {
res = colo_packet_compare_common(ppkt, spkt, ETH_HLEN);
} else {
res = -1;
--
2.7.4
next prev parent reply other threads:[~2017-04-24 5:16 UTC|newest]
Thread overview: 13+ messages / expand[flat|nested] mbox.gz Atom feed top
2017-04-24 5:15 [Qemu-devel] [PULL 0/8] Net patches Jason Wang
2017-04-24 5:15 ` [Qemu-devel] [PULL 1/8] colo-compare: Fix old packet check bug Jason Wang
2017-04-24 5:16 ` [Qemu-devel] [PULL 2/8] hw/net: add MII definitions Jason Wang
2017-04-24 5:16 ` [Qemu-devel] [PULL 3/8] net: add FTGMAC100 support Jason Wang
2017-04-24 5:16 ` [Qemu-devel] [PULL 4/8] net/ftgmac100: add a 'aspeed' property Jason Wang
2017-04-24 5:16 ` [Qemu-devel] [PULL 5/8] aspeed: add a FTGMAC100 nic Jason Wang
2017-04-24 5:16 ` [Qemu-devel] [PULL 6/8] slirp: add a fake NC-SI backend Jason Wang
2017-04-24 5:16 ` Jason Wang [this message]
2017-04-24 5:16 ` [Qemu-devel] [PULL 8/8] COLO-compare: Optimize tcp compare trace event Jason Wang
2017-04-24 13:49 ` [Qemu-devel] [PULL 0/8] Net patches Peter Maydell
2017-04-24 16:02 ` Cédric Le Goater
2017-04-25 3:57 ` Jason Wang
2017-04-25 6:18 ` Cédric Le Goater
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=1493010966-22976-8-git-send-email-jasowang@redhat.com \
--to=jasowang@redhat.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).