All of lore.kernel.org
 help / color / mirror / Atom feed
From: Thadeu Lima de Souza Cascardo <cascardo@linux.vnet.ibm.com>
To: Or Gerlitz <or.gerlitz@gmail.com>
Cc: Rick Jones <rick.jones2@hp.com>,
	"davem@davemloft.net" <davem@davemloft.net>,
	"netdev@vger.kernel.org" <netdev@vger.kernel.org>,
	"yevgenyp@mellanox.co.il" <yevgenyp@mellanox.co.il>,
	"ogerlitz@mellanox.com" <ogerlitz@mellanox.com>,
	"amirv@mellanox.com" <amirv@mellanox.com>,
	"brking@linux.vnet.ibm.com" <brking@linux.vnet.ibm.com>,
	"leitao@linux.vnet.ibm.com" <leitao@linux.vnet.ibm.com>,
	"klebers@linux.vnet.ibm.com" <klebers@linux.vnet.ibm.com>,
	"linuxppc-dev@lists.ozlabs.org" <linuxppc-dev@lists.ozlabs.org>,
	"anton@samba.org" <anton@samba.org>
Subject: Re: [PATCH] mlx4_en: map entire pages to increase throughput
Date: Mon, 16 Jul 2012 17:57:08 -0300	[thread overview]
Message-ID: <20120716205708.GB16137@oc1711230544.ibm.com> (raw)
In-Reply-To: <CAJZOPZL3F+xdHSFfhg7v9A6DDjT6CPK=kgwyzcE6c0pGYFyupg@mail.gmail.com>

On Mon, Jul 16, 2012 at 11:43:33PM +0300, Or Gerlitz wrote:
> On Mon, Jul 16, 2012 at 10:42 PM, Rick Jones <rick.jones2@hp.com> wrote:
> 
> > I was thinking more along the lines of an additional comparison,
> > explicitly using netperf TCP_RR or something like it, not just the packets
> > per second from a bulk transfer test.
> 
> 
> TCP_STREAM from this setup before the patch would be good to know as well
> 

Hi, Or.

Does the stream test that I did with uperf using messages of 64000 bytes
fit?

TCP_NODELAY does not make a difference in this case. I get something
around 3Gbps before the patch and something around 9Gbps after the
patch.

Before the patch:

# ./uperf-1.0.3-beta/src/uperf -m tcp.xml
Starting 16 threads running profile:tcp_stream ...   0.00 seconds
Txn1          0 /1.00(s) =            0          16op/s
Txn2    20.81GB /59.26(s) =     3.02Gb/s        5914op/s
Txn3          0 /0.00(s) =            0      128295op/s
-------------------------------------------------------------------------------------------------------------------------------
Total   20.81GB /61.37(s) =     2.91Gb/s        5712op/s

Netstat statistics for this run
-------------------------------------------------------------------------------------------------------------------------------
Nic       opkts/s     ipkts/s     obits/s     ibits/s
eth6       252459       31694   3.06Gb/s  16.74Mb/s
eth0            2          18   3.87Kb/s  14.28Kb/s
-------------------------------------------------------------------------------------------------------------------------------

Run Statistics
Hostname           Time        Data   Throughput   Operations
Errors
-------------------------------------------------------------------------------------------------------------------------------
10.0.0.2         61.47s     20.81GB     2.91Gb/s       350528
0.00
master           61.37s     20.81GB     2.91Gb/s       350528
0.00
-------------------------------------------------------------------------------------------------------------------------------
Difference(%)     -0.16%      0.00%        0.16%        0.00%
0.00%


After the patch:

# ./uperf-1.0.3-beta/src/uperf -m tcp.xml
Starting 16 threads running profile:tcp_stream ...   0.00 seconds
Txn1          0 /1.00(s) =            0          16op/s
Txn2    64.50GB /60.27(s) =     9.19Gb/s       17975op/s
Txn3          0 /0.00(s) =            0
-------------------------------------------------------------------------------------------------------------------------------
Total   64.50GB /62.27(s) =     8.90Gb/s       17397op/s

Netstat statistics for this run
-------------------------------------------------------------------------------------------------------------------------------
Nic       opkts/s     ipkts/s     obits/s     ibits/s
eth6       769428       96018   9.31Gb/s  50.72Mb/s
eth0            1          15   2.48Kb/s  13.59Kb/s
-------------------------------------------------------------------------------------------------------------------------------

Run Statistics
Hostname           Time        Data   Throughput   Operations
Errors
-------------------------------------------------------------------------------------------------------------------------------
10.0.0.2         62.27s     64.36GB     8.88Gb/s      1081096
0.00
master           62.27s     64.50GB     8.90Gb/s      1083325
0.00
-------------------------------------------------------------------------------------------------------------------------------
Difference(%)     -0.00%      0.21%        0.21%        0.21%
0.00%


Profile tcp.xml:

<?xml version="1.0"?>
<profile name="TCP_STREAM">
  <group nthreads="16">
        <transaction iterations="1">
            <flowop type="connect" options="remotehost=10.0.0.2 protocol=tcp tcp_nodelay"/>
        </transaction>
        <transaction duration="60">
            <flowop type="write" options="count=160 size=64000"/>
        </transaction>
        <transaction iterations="1">
            <flowop type="disconnect" />
        </transaction>
  </group>
</profile>

WARNING: multiple messages have this Message-ID (diff)
From: Thadeu Lima de Souza Cascardo <cascardo@linux.vnet.ibm.com>
To: Or Gerlitz <or.gerlitz@gmail.com>
Cc: "netdev@vger.kernel.org" <netdev@vger.kernel.org>,
	"leitao@linux.vnet.ibm.com" <leitao@linux.vnet.ibm.com>,
	Rick Jones <rick.jones2@hp.com>,
	"amirv@mellanox.com" <amirv@mellanox.com>,
	"yevgenyp@mellanox.co.il" <yevgenyp@mellanox.co.il>,
	"klebers@linux.vnet.ibm.com" <klebers@linux.vnet.ibm.com>,
	"anton@samba.org" <anton@samba.org>,
	"brking@linux.vnet.ibm.com" <brking@linux.vnet.ibm.com>,
	"ogerlitz@mellanox.com" <ogerlitz@mellanox.com>,
	"linuxppc-dev@lists.ozlabs.org" <linuxppc-dev@lists.ozlabs.org>,
	"davem@davemloft.net" <davem@davemloft.net>
Subject: Re: [PATCH] mlx4_en: map entire pages to increase throughput
Date: Mon, 16 Jul 2012 17:57:08 -0300	[thread overview]
Message-ID: <20120716205708.GB16137@oc1711230544.ibm.com> (raw)
In-Reply-To: <CAJZOPZL3F+xdHSFfhg7v9A6DDjT6CPK=kgwyzcE6c0pGYFyupg@mail.gmail.com>

On Mon, Jul 16, 2012 at 11:43:33PM +0300, Or Gerlitz wrote:
> On Mon, Jul 16, 2012 at 10:42 PM, Rick Jones <rick.jones2@hp.com> wrote:
> 
> > I was thinking more along the lines of an additional comparison,
> > explicitly using netperf TCP_RR or something like it, not just the packets
> > per second from a bulk transfer test.
> 
> 
> TCP_STREAM from this setup before the patch would be good to know as well
> 

Hi, Or.

Does the stream test that I did with uperf using messages of 64000 bytes
fit?

TCP_NODELAY does not make a difference in this case. I get something
around 3Gbps before the patch and something around 9Gbps after the
patch.

Before the patch:

# ./uperf-1.0.3-beta/src/uperf -m tcp.xml
Starting 16 threads running profile:tcp_stream ...   0.00 seconds
Txn1          0 /1.00(s) =            0          16op/s
Txn2    20.81GB /59.26(s) =     3.02Gb/s        5914op/s
Txn3          0 /0.00(s) =            0      128295op/s
-------------------------------------------------------------------------------------------------------------------------------
Total   20.81GB /61.37(s) =     2.91Gb/s        5712op/s

Netstat statistics for this run
-------------------------------------------------------------------------------------------------------------------------------
Nic       opkts/s     ipkts/s     obits/s     ibits/s
eth6       252459       31694   3.06Gb/s  16.74Mb/s
eth0            2          18   3.87Kb/s  14.28Kb/s
-------------------------------------------------------------------------------------------------------------------------------

Run Statistics
Hostname           Time        Data   Throughput   Operations
Errors
-------------------------------------------------------------------------------------------------------------------------------
10.0.0.2         61.47s     20.81GB     2.91Gb/s       350528
0.00
master           61.37s     20.81GB     2.91Gb/s       350528
0.00
-------------------------------------------------------------------------------------------------------------------------------
Difference(%)     -0.16%      0.00%        0.16%        0.00%
0.00%


After the patch:

# ./uperf-1.0.3-beta/src/uperf -m tcp.xml
Starting 16 threads running profile:tcp_stream ...   0.00 seconds
Txn1          0 /1.00(s) =            0          16op/s
Txn2    64.50GB /60.27(s) =     9.19Gb/s       17975op/s
Txn3          0 /0.00(s) =            0
-------------------------------------------------------------------------------------------------------------------------------
Total   64.50GB /62.27(s) =     8.90Gb/s       17397op/s

Netstat statistics for this run
-------------------------------------------------------------------------------------------------------------------------------
Nic       opkts/s     ipkts/s     obits/s     ibits/s
eth6       769428       96018   9.31Gb/s  50.72Mb/s
eth0            1          15   2.48Kb/s  13.59Kb/s
-------------------------------------------------------------------------------------------------------------------------------

Run Statistics
Hostname           Time        Data   Throughput   Operations
Errors
-------------------------------------------------------------------------------------------------------------------------------
10.0.0.2         62.27s     64.36GB     8.88Gb/s      1081096
0.00
master           62.27s     64.50GB     8.90Gb/s      1083325
0.00
-------------------------------------------------------------------------------------------------------------------------------
Difference(%)     -0.00%      0.21%        0.21%        0.21%
0.00%


Profile tcp.xml:

<?xml version="1.0"?>
<profile name="TCP_STREAM">
  <group nthreads="16">
        <transaction iterations="1">
            <flowop type="connect" options="remotehost=10.0.0.2 protocol=tcp tcp_nodelay"/>
        </transaction>
        <transaction duration="60">
            <flowop type="write" options="count=160 size=64000"/>
        </transaction>
        <transaction iterations="1">
            <flowop type="disconnect" />
        </transaction>
  </group>
</profile>

  reply	other threads:[~2012-07-16 20:57 UTC|newest]

Thread overview: 28+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2012-07-16 17:01 [PATCH] mlx4_en: map entire pages to increase throughput Thadeu Lima de Souza Cascardo
2012-07-16 17:27 ` Rick Jones
2012-07-16 19:06   ` Thadeu Lima de Souza Cascardo
2012-07-16 19:06     ` Thadeu Lima de Souza Cascardo
2012-07-16 19:42     ` Rick Jones
2012-07-16 19:42       ` Rick Jones
2012-07-16 20:36       ` Or Gerlitz
2012-07-16 20:36         ` Or Gerlitz
2012-07-16 20:43       ` Or Gerlitz
2012-07-16 20:43         ` Or Gerlitz
2012-07-16 20:57         ` Thadeu Lima de Souza Cascardo [this message]
2012-07-16 20:57           ` Thadeu Lima de Souza Cascardo
2012-07-18 14:59           ` Or Gerlitz
2012-07-18 14:59             ` Or Gerlitz
2012-07-16 20:47       ` Thadeu Lima de Souza Cascardo
2012-07-16 20:47         ` Thadeu Lima de Souza Cascardo
2012-07-16 21:08         ` Rick Jones
2012-07-16 21:08           ` Rick Jones
2012-07-17  5:29   ` David Miller
2012-07-17 12:42     ` David Laight
2012-07-17 12:50       ` David Miller
2012-07-17 13:36         ` David Laight
2012-07-17 13:46           ` David Miller
2012-07-17 13:50         ` Eric Dumazet
2012-07-17 18:17     ` Rick Jones
2012-07-17 20:10       ` Brian King
2012-07-17 20:20         ` David Miller
2012-07-19 17:53 ` David Miller

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=20120716205708.GB16137@oc1711230544.ibm.com \
    --to=cascardo@linux.vnet.ibm.com \
    --cc=amirv@mellanox.com \
    --cc=anton@samba.org \
    --cc=brking@linux.vnet.ibm.com \
    --cc=davem@davemloft.net \
    --cc=klebers@linux.vnet.ibm.com \
    --cc=leitao@linux.vnet.ibm.com \
    --cc=linuxppc-dev@lists.ozlabs.org \
    --cc=netdev@vger.kernel.org \
    --cc=ogerlitz@mellanox.com \
    --cc=or.gerlitz@gmail.com \
    --cc=rick.jones2@hp.com \
    --cc=yevgenyp@mellanox.co.il \
    /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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.