From: "Yang, Zhiyong" <zhiyong.yang@intel.com>
To: Panu Matilainen <pmatilai@redhat.com>, "dev@dpdk.org" <dev@dpdk.org>
Cc: "Yang, Zhiyong" <zhiyong.yang@intel.com>
Subject: Re: [dpdk-dev] [PATCH] vhost: add pmd xstats
Date: Tue, 23 Aug 2016 08:04:17 +0000 [thread overview]
Message-ID: <E182254E98A5DA4EB1E657AC7CB9BD2A08B3BEE0@BGSMSX101.gar.corp.intel.com> (raw)
In-Reply-To: <08c5733b-6758-2d98-df4a-a2261ecf43e4@redhat.com>
Hi, Panu:
> -----Original Message-----
> From: Panu Matilainen [mailto:pmatilai@redhat.com]
> Sent: Monday, August 22, 2016 3:53 PM
> To: Yang, Zhiyong <zhiyong.yang@intel.com>; dev@dpdk.org
> Subject: Re: [dpdk-dev] [PATCH] vhost: add pmd xstats
>
> On 08/19/2016 03:16 PM, Zhiyong Yang wrote:
> > This feature adds vhost pmd extended statistics from per queue
> > perspective for the application such as OVS etc.
> >
> > The statistics counters are based on RFC 2819 and 2863 as follows:
> >
> > rx/tx_good_packets
> > rx/tx_total_bytes
> > rx/tx_dropped_pkts
> > rx/tx_broadcast_packets
> > rx/tx_multicast_packets
> > rx/tx_ucast_packets
> > rx/tx_undersize_errors
> > rx/tx_size_64_packets
> > rx/tx_size_65_to_127_packets;
> > rx/tx_size_128_to_255_packets;
> > rx/tx_size_256_to_511_packets;
> > rx/tx_size_512_to_1023_packets;
> > rx/tx_size_1024_to_1522_packets;
> > rx/tx_1523_to_max_packets;
> > rx/tx_errors
> > rx_fragmented_errors
> > rx_jabber_errors
> > rx_unknown_protos_packets;
> >
> > No API is changed or added.
> > rte_eth_xstats_get_names() to retrieve what kinds of vhost xstats are
> > supported,
> > rte_eth_xstats_get() to retrieve vhost extended statistics,
> > rte_eth_xstats_reset() to reset vhost extended statistics.
> >
> > Since collecting data of vhost_update_packet_xstats will have some
> > effect on RX/TX performance, so, Setting compiling switch
> > CONFIG_RTE_LIBRTE_PMD_VHOST_UPDATE_XSTATS=n by default in the
> file
> > config/common_base, if needing xstats data, you can enable it(y).
>
> NAK, such things need to be switchable at run-time.
>
> - Panu -
Considering the following reasons using the compiler switch, not
command-line at run-time.
1.Similar xstats update functions are always collecting stats data in the
background when rx/tx are running, such as the physical NIC or virtio,
which have no switch. Compiler switch for vhost pmd xstats is added
as a option when performance is viewed as critical factor.
2. No data structure and API in any layer support the xstats update switch
at run-time. Common data structure (struct rte_eth_dev_data) has no
device-specific data member, if implementing enable/disable of vhost_update
_packet_xstats at run-time, must define a flag(device-specific) in it,
because the definition of struct vhost_queue in the driver code
(eth_vhost_rx/eth_vhost_tx processing)is not visible from device perspective.
3. I tested RX/TX with v1 patch (y) as reference based on Intel(R)
Xeon(R) CPU E5-2699 v3 @ 2.30GHz, for 64byts packets in burst mode, 32 packets
in one RX/TX processing. Overhead of vhost_update_packet_xstats is less than
3% for the rx/tx processing. It looks that vhost_update_packet_xstats has a
limited effect on performance drop.
-zhiyong-
next prev parent reply other threads:[~2016-08-23 8:04 UTC|newest]
Thread overview: 57+ messages / expand[flat|nested] mbox.gz Atom feed top
2016-08-19 12:16 Zhiyong Yang
2016-08-22 7:52 ` Panu Matilainen
2016-08-23 8:04 ` Yang, Zhiyong [this message]
2016-08-23 9:45 ` Panu Matilainen
2016-08-24 5:46 ` Yuanhan Liu
2016-08-24 8:44 ` Thomas Monjalon
2016-08-24 12:37 ` Panu Matilainen
2016-08-25 9:21 ` Yang, Zhiyong
2016-08-30 2:45 ` Yao, Lei A
2016-08-30 3:03 ` Xu, Qian Q
2016-08-30 3:21 ` Yao, Lei A
2016-08-31 7:18 ` Yang, Zhiyong
2016-09-01 6:37 ` Yang, Zhiyong
2016-09-09 8:15 ` [dpdk-dev] [PATCH v2] net/vhost: " Zhiyong Yang
2016-09-09 8:40 ` Van Haaren, Harry
2016-09-09 8:54 ` Yang, Zhiyong
2016-09-14 6:20 ` Yuanhan Liu
2016-09-14 7:43 ` Yang, Zhiyong
2016-09-18 13:16 ` Yuanhan Liu
2016-09-19 2:48 ` Yang, Zhiyong
2016-09-14 8:30 ` Yang, Zhiyong
2016-09-20 9:36 ` [dpdk-dev] [PATCH v3 0/2] net/vhost: add pmd xstats support Zhiyong Yang
2016-09-20 9:36 ` [dpdk-dev] [PATCH v3 1/2] net/vhost: add a new stats struct Zhiyong Yang
2016-09-20 10:44 ` Yuanhan Liu
2016-09-21 5:12 ` Yang, Zhiyong
2016-09-21 10:05 ` [dpdk-dev] [PATCH v4 0/2] net/vhost: add pmd xstats support Zhiyong Yang
2016-09-21 10:05 ` Zhiyong Yang
2016-09-21 10:05 ` [dpdk-dev] [PATCH v4 2/2] net/vhost: add pmd xstats Zhiyong Yang
2016-09-21 10:57 ` Yuanhan Liu
2016-09-22 1:42 ` Yang, Zhiyong
2016-09-22 2:09 ` Yuanhan Liu
2016-09-21 10:13 ` [dpdk-dev] [PATCH v4 1/2] net/vhost: add a new defined stats struct Zhiyong Yang
2016-09-22 8:19 ` [dpdk-dev] [PATCH v5 0/2] net/vhost: add pmd xstats support Zhiyong Yang
2016-09-22 8:19 ` [dpdk-dev] [PATCH v5 1/2] net/vhost: add a new defined stats struct Zhiyong Yang
2016-09-28 8:33 ` [dpdk-dev] [PATCH v6 0/2] net/vhost: add pmd xstats support Zhiyong Yang
2016-09-28 8:33 ` [dpdk-dev] [PATCH v6 1/2] net/vhost: add a new defined stats struct Zhiyong Yang
2016-09-28 13:26 ` [dpdk-dev] [PATCH v7 0/2] net/vhost: add pmd xstats support Zhiyong Yang
2016-09-28 13:26 ` [dpdk-dev] [PATCH v7 1/2] net/vhost: add a new defined stats struct Zhiyong Yang
2016-09-29 1:55 ` Yuanhan Liu
2016-09-29 12:35 ` [dpdk-dev] [PATCH v8 0/2] net/vhost: add pmd xstats support Zhiyong Yang
2016-09-29 12:35 ` [dpdk-dev] [PATCH v8 1/2] net/vhost: add a new defined stats struct Zhiyong Yang
2016-09-29 12:35 ` [dpdk-dev] [PATCH v8 2/2] net/vhost: add pmd xstats Zhiyong Yang
2016-09-29 13:04 ` Yuanhan Liu
2016-09-29 13:50 ` Yang, Zhiyong
2016-09-28 13:26 ` [dpdk-dev] [PATCH v7 " Zhiyong Yang
2016-09-29 8:48 ` Loftus, Ciara
2016-09-29 12:02 ` Yuanhan Liu
2016-09-29 12:22 ` Yang, Zhiyong
2016-09-28 8:33 ` [dpdk-dev] [PATCH v6 " Zhiyong Yang
2016-09-22 8:19 ` [dpdk-dev] [PATCH v5 " Zhiyong Yang
2016-09-23 3:56 ` [dpdk-dev] [PATCH v5 0/2] net/vhost: add pmd xstats support Yuanhan Liu
2016-09-28 2:35 ` Yuanhan Liu
2016-09-20 9:36 ` [dpdk-dev] [PATCH v3 2/2] net/vhost: add pmd xstats Zhiyong Yang
2016-09-20 10:56 ` Yuanhan Liu
2016-09-21 7:22 ` Yang, Zhiyong
2016-09-20 11:50 ` Yuanhan Liu
2016-09-21 6:15 ` Yang, Zhiyong
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=E182254E98A5DA4EB1E657AC7CB9BD2A08B3BEE0@BGSMSX101.gar.corp.intel.com \
--to=zhiyong.yang@intel.com \
--cc=dev@dpdk.org \
--cc=pmatilai@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).