DPDK patches and discussions
 help / color / mirror / Atom feed
From: 钢锁0310 <liw@dtdream.com>
To: "Zhou, Tianlin" <tianlin.zhou@tekcomms.com>,
	"dev@dpdk.org" <dev@dpdk.org>
Subject: [dpdk-dev] 答复： Poor Virtio PMD TX Performance
Date: Fri, 05 Jun 2015 18:06:36 +0800	[thread overview]
Message-ID: <----P3------meVv3$6f37f46b-28f3-4f72-b428-a494101b4857@dtdream.com> (raw)
In-Reply-To: 7D6C3D7847A9FE4E8EB311EAC72727A04EB1447D@US-BV-EXM02-P.global.tektronix.net

[-- Warning: decoded text below may be mangled, UTF-8 assumed --]
[-- Attachment #1: Type: text/plain; charset="UTF-8", Size: 1521 bytes --]

There is same problem by using ovs-dpdk
Maybe that is because recv of VM is poor,so no free tx descriptors,ovs-dpdk drop the pkts********************RTFSC*********************------------------------------------------------------------------发件人：Zhou, Tianlin <tianlin.zhou@tekcomms.com>发送时间：2015年6月5日(星期五) 17:23收件人：dev@dpdk.org <dev@dpdk.org>主　题：[dpdk-dev] Poor Virtio PMD TX PerformanceHi there,We tested TX performance of Virtio PMD by DPDK l2fwd, but found even at 60KPPS (720B packet length) TX rate, there is 1/1000 packet dropping rate.The log shows "No free tx descriptors to transmit" in Virtio PMD.Increasing TX queues by modifying DPDK l2fwd can decreases packet dropping rate, but can't ensure no packet dropping unless retransmitting packets that can't be sent successfully.Oppositely, RX rate can be 600KPPS without packet dropping.Test Env- Host CPU: 4 cores, 2127.770MHz- Host Memory: 8G- Host OS: Linux dw-2 3.13.0-24-generic #46-Ubuntu SMP Thu Apr 10 19:11:08 UTC 2014 x86_64 x86_64 x86_64 GNU/Linux- Guest CPU: 4 cores, 2127.770MHz- Guest Memory: 4G- Guest OS: fedora20Anybody here face the same problem?-Tianlin
\x16º&n»œz¸œ…ªÝ²‰âž×¥r‰…®"nŸvۍ9ÛMyEën®sÚ¶\x16ë¹Ç«‰ÈZ­Û(ž)ízW(™\x17œz+Þuúèšh\x1aÓX§µé\¢i kMbž×¥r‰µ÷nyço<o'ivJ+€ú,µø±Â+a\x11#\x13>'@Û®Äà\x0e·~ŠÝz÷ivJ+€Zâ䛧ÛMy×m¸ÓŸ´ÛM\x02\x11$ÑyÇ¢½ç_®‰¨®É kM7ø§µé\¢mtïm=Û¶ò~k&­tÕù¢ž×¥r‰°ŠØDHÄÏÓ’nŸm5çMöãN4ïM\x17\x13^[K¢ŠuÕr+¢sè®Ð\x15

             reply	other threads:[~2015-06-05 10:06 UTC|newest]

Thread overview: 6+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2015-06-05 10:06 钢锁0310 [this message]
  -- strict thread matches above, loose matches on Subject: below --
2015-06-05  9:23 [dpdk-dev] " Zhou, Tianlin
     [not found] ` <F52918179C57134FAEC9EA62FA2F962511B84FEE@shsmsx102.ccr.corp.intel.com>
2015-06-12  9:35   ` Zhou, Tianlin
2015-06-12  9:45     ` Jason Wang
2015-06-15  7:04       ` Zhou, Tianlin
2015-06-12 15:46     ` Ouyang, Changchun

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='----P3------meVv3$6f37f46b-28f3-4f72-b428-a494101b4857@dtdream.com' \
    --to=liw@dtdream.com \
    --cc=dev@dpdk.org \
    --cc=tianlin.zhou@tekcomms.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).