Virtex TEMAC ping -s 10000 host, is it working?

DISCUSSION alex_snippet 2 participants 4 messages Nov 15, 2007 – Nov 20, 2007

Share & tools

alex_snippet

author

2007-11-15 15:07 UTC #0 lore raw

Hi All!

On Virtex 4FX board with TEMAC core, Linux ping working fine, but if s - parameter set to big values it freezes for ever...

Colleagues please share your experience with ping -s 10000 host.

Do you know what parameters in core or in Linux kernel must be changed to improve it.

My customer is too hypercritical, he likes to ping :(

I tried to increase LX/TX buffers in core, it increased dead line but there is no desirable result.

Signature · 2 lines

View this message in context: http://www.nabble.com/Virtex-TEMAC-ping--s-10000-host%2C-is-it-working--tf4812989.html#a13770288
Sent from the linuxppc-embedded mailing list archive at Nabble.com.

Lorenz Kolb

2007-11-16 10:30 UTC #1 lore raw

Quoted 8 lines · alex_snippet

Hi All!
On Virtex 4FX board with TEMAC core, Linux ping working fine, but if s - parameter set to big values it freezes for ever...
Colleagues please share your experience with ping -s 10000 host.

Quoted 10 lines

Do you know what parameters in core or in Linux kernel must be changed to improve it.
My customer is too hypercritical, he likes to ping :(
I tried to increase LX/TX buffers in core, it increased dead line but there is no desirable result.

Hey, I can understand that customer, I like pinging as well. And it works for me. Our design is based on ML403. We use PLB_TEMAC (with minimum Fifos (4kB each)) and HardTEMAC

Quoted 8 lines

.
.
.
10008 bytes from 192.168.0.206: icmp_seq=733 ttl=64 time=2.42 ms 10008 bytes from 192.168.0.206: icmp_seq=734 ttl=64 time=2.50 ms 10008 bytes from 192.168.0.206: icmp_seq=735 ttl=64 time=2.43 ms 10008 bytes from 192.168.0.206: icmp_seq=736 ttl=64 time=2.43 ms 10008 bytes from 192.168.0.206: icmp_seq=737 ttl=64 time=2.44 ms

Quoted 9 lines

10008 bytes from 192.168.0.206: icmp_seq=738 ttl=64 time=2.42 ms 10008 bytes from 192.168.0.206: icmp_seq=739 ttl=64 time=2.51 ms 10008 bytes from 192.168.0.206: icmp_seq=740 ttl=64 time=2.42 ms 10008 bytes from 192.168.0.206: icmp_seq=741 ttl=64 time=2.50 ms 10008 bytes from 192.168.0.206: icmp_seq=742 ttl=64 time=2.43 ms .
.
.

And so on...

Quoted 4 lines

--- 192.168.0.206 ping statistics ---
850 packets transmitted, 850 received, 0% packet loss, time 849010ms rtt min/avg/max/mdev = 2.399/11.623/1001.859/92.782 ms, pipe 3

Signature · 2 lines

View this message in context: http://www.nabble.com/Virtex-TEMAC-ping--s-10000-host%2C-is-it-working--tf4812989.html#a13790720
Sent from the linuxppc-embedded mailing list archive at Nabble.com.

alex_snippet

author

2007-11-19 09:03 UTC #2 lore raw

Hi Lorenz Kolb,

Thank you for answering.

It's interesting to see some info from your design files, PLB_TEMAC & HardTEMAC description from mhs,
and kernel .config network section.

The biggest problem that i actually do not understand what kind of problem is it, hardware or software or configuration.

Quoted 55 lines · Lorenz Kolb

Quoted 8 lines · alex_snippet
Hi All!
On Virtex 4FX board with TEMAC core, Linux ping working fine, but if s - parameter set to big values it freezes for ever...
Colleagues please share your experience with ping -s 10000 host.
Quoted 10 lines
Do you know what parameters in core or in Linux kernel must be changed to improve it.
My customer is too hypercritical, he likes to ping :(
I tried to increase LX/TX buffers in core, it increased dead line but there is no desirable result.
Hey, I can understand that customer, I like pinging as well. And it works for me. Our design is based on ML403. We use PLB_TEMAC (with minimum Fifos (4kB each)) and HardTEMAC
Quoted 8 lines
.
.
.
10008 bytes from 192.168.0.206: icmp_seq=733 ttl=64 time=2.42 ms 10008 bytes from 192.168.0.206: icmp_seq=734 ttl=64 time=2.50 ms 10008 bytes from 192.168.0.206: icmp_seq=735 ttl=64 time=2.43 ms 10008 bytes from 192.168.0.206: icmp_seq=736 ttl=64 time=2.43 ms 10008 bytes from 192.168.0.206: icmp_seq=737 ttl=64 time=2.44 ms
Quoted 9 lines
10008 bytes from 192.168.0.206: icmp_seq=738 ttl=64 time=2.42 ms 10008 bytes from 192.168.0.206: icmp_seq=739 ttl=64 time=2.51 ms 10008 bytes from 192.168.0.206: icmp_seq=740 ttl=64 time=2.42 ms 10008 bytes from 192.168.0.206: icmp_seq=741 ttl=64 time=2.50 ms 10008 bytes from 192.168.0.206: icmp_seq=742 ttl=64 time=2.43 ms .
.
.
And so on...
Quoted 4 lines
--- 192.168.0.206 ping statistics ---
850 packets transmitted, 850 received, 0% packet loss, time 849010ms rtt min/avg/max/mdev = 2.399/11.623/1001.859/92.782 ms, pipe 3

Signature · 2 lines

View this message in context: http://www.nabble.com/Virtex-TEMAC-ping--s-10000-host%2C-is-it-working--tf4812989.html#a13830023
Sent from the linuxppc-embedded mailing list archive at Nabble.com.

Lorenz Kolb

2007-11-20 07:45 UTC #3 lore raw

Quoted 6 lines · alex_snippet

It's interesting to see some info from your design files, PLB_TEMAC & HardTEMAC description from mhs,
and kernel .config network section.

.mhs

Quoted 30 lines

<snip>
BEGIN hard_temac
PARAMETER INSTANCE = hard_temac_0
PARAMETER HW_VER = 3.00.a
BUS_INTERFACE V4EMACDST0 = plb_temac_0_V4EMACSRC PORT MII_TX_CLK_0 = fpga_0_Hard_Temac_0_MII_TX_CLK_0 PORT GMII_TXD_0 = fpga_0_Hard_Temac_0_GMII_TXD_0 PORT GMII_TX_EN_0 = fpga_0_Hard_Temac_0_GMII_TX_EN_0 PORT GMII_TX_ER_0 = fpga_0_Hard_Temac_0_GMII_TX_ER_0 PORT GMII_TX_CLK_0 = fpga_0_Hard_Temac_0_GMII_TX_CLK_0 PORT GMII_RXD_0 = fpga_0_Hard_Temac_0_GMII_RXD_0 PORT GMII_RX_DV_0 = fpga_0_Hard_Temac_0_GMII_RX_DV_0 PORT GMII_RX_ER_0 = fpga_0_Hard_Temac_0_GMII_RX_ER_0 PORT GMII_RX_CLK_0 = fpga_0_Hard_Temac_0_GMII_RX_CLK_0 PORT MDC_0 = fpga_0_Hard_Temac_0_MDC_0
PORT MDIO_0 = fpga_0_Hard_Temac_0_MDIO_0
PORT RESET = Emac_Reset_s
PORT GTX_CLK_0 = temac_0_clk_s
PORT REFCLK = sys_clk
END
BEGIN plb_temac
PARAMETER INSTANCE = plb_temac_0
PARAMETER HW_VER = 3.00.a
PARAMETER C_MAC_FIFO_DEPTH = 64
PARAMETER C_RX_DRE_TYPE = 0
PARAMETER C_TX_DRE_TYPE = 0
PARAMETER C_DMA_TYPE = 1
PARAMETER C_PLB_CLK_PERIOD_PS = 10000
PARAMETER C_BASEADDR = 0x40000000

Quoted 9 lines

PARAMETER C_HIGHADDR = 0x4000FFFF BUS_INTERFACE V4EMACSRC = plb_temac_0_V4EMACSRC BUS_INTERFACE MSPLB = plb_v34_0
PORT Emac_Reset = Emac_Reset_s
PORT PhyResetN = fpga_0_TriMode_MAC_GMII_PhyResetN PORT IP2INTC_Irpt = plb_temac_0_IP2INTC_Irpt
END
<snap>

.config

Quoted 6 lines

<snip>
#
# Networking
#
CONFIG_NET=y

Quoted 12 lines

#
# Networking options
#
CONFIG_PACKET=y
CONFIG_PACKET_MMAP=y
CONFIG_UNIX=y
CONFIG_INET=y
CONFIG_IP_FIB_HASH=y
CONFIG_TCP_CONG_CUBIC=y
CONFIG_DEFAULT_TCP_CONG="cubic"
<snap>

We use the Temac driver from Grant's tree.
Nevertheless we changed the auto-negotiation code, as we had problem with the default code when using the same code in U-Boot.
I have attached our auto-negotiation patch (nevertheless the old auto-negotiation worked fine with the linux kernel, the main reason we patched that is to hold the code base to maintain minimal).
http://www.nabble.com/file/p13852281/0018-TEMAC-changed-renegotiation-function-to-ESIC-U-Boo.patch
0018-TEMAC-changed-renegotiation-function-to-ESIC-U-Boo.patch

Quoted 4 lines · alex_snippet

The biggest problem that i actually do not understand what kind of problem is it, hardware or software or configuration.

Regards,

--
Lorenz Kolb
Embedded specialist
ESIC Solutions
San Jose, CA
Neu-Ulm, Germany

Signature · 2 lines

View this message in context: http://www.nabble.com/Virtex-TEMAC-ping--s-10000-host%2C-is-it-working--tf4812989.html#a13852281
Sent from the linuxppc-embedded mailing list archive at Nabble.com.