thr3ads.net - freebsd stable - When will the new BCE driver in HEAD be incorporated into RELENG

If this information is useful, please help other people find it:
Share via:

Conrad Burger

2006-Oct-18 02:58 UTC

When will the new BCE driver in HEAD be incorporated into RELENG_6?

Hi

It looks like there is a "new"  version of the bce driver in HEAD.
When will it be incorporated into  Releng_6?

We are currently having some  performance problems with a java
application on our Dell 1950s.

And it looks like it has something  to do with the speed with which
network I/Os are  performed.

We have Dell 2850s running FreeBSD  5.4/i386 SMP. With Intel nics (em)
and they are performing quite well.

With 34000 tcp sockets open the  maximum time it takes to perform a
single network I/O is about 100ms.

The Dell 1950s running FreeBSD  6.2-Prerelease/i386 SMP with Broadcom
nics (bce), the same application and 34000  tcp connections open.

The maximum time it takes to  perform a single network I/O is about 7000ms.

Most of the packets the systems  send/receive are rather small.

We are not quite sure what could  cause this behavior.

If anyone has any ideas of what we  could do to decrease the time it
takes to perform network I/O it would be much  appreciated.

Regards
Conrad

Some  information:
dev.bce.0.%desc: Broadcom  NetXtreme II BCM5708 1000Base-T (B1), v0.9.6
dev.bce.0.%driver:  bce
dev.bce.0.%location: slot=0  function=0
dev.bce.0.%pnpinfo: vendor=0x14e4  device=0x164c subvendor=0x1028
subdevice=0x01b3  class=0x020000
dev.bce.0.%parent:  pci9
dev.bce.0.driver_version:  v0.9.6
dev.bce.0.stat_IfHcInOctets:  2346165
dev.bce.0.stat_IfHCInBadOctets:  1877825702
dev.bce.0.stat_IfHCOutOctets:  2751390538
dev.bce.0.stat_IfHCOutBadOctets:  0
dev.bce.0.stat_IfHCInUcastPkts:  360078711
dev.bce.0.stat_IfHCInMulticastPkts:  18339
dev.bce.0.stat_IfHCInBroadcastPkts:  270544
dev.bce.0.stat_IfHCOutUcastPkts:  323261730
dev.bce.0.stat_IfHCOutMulticastPkts:  147410
dev.bce.0.stat_IfHCOutBroadcastPkts:  985
dev.bce.0.stat_emac_tx_stat_dot3statsinternalmactransmiterrors:  0
dev.bce.0.stat_Dot3StatsCarrierSenseErrors:  0
dev.bce.0.stat_Dot3StatsFCSErrors:  0
dev.bce.0.stat_Dot3StatsAlignmentErrors:  0
dev.bce.0.stat_Dot3StatsSingleCollisionFraes:  0
dev.bce.0.stat_Dot3StatsMultipleCollisionFrames:  0
dev.bce.0.stat_Dot3StatsDeferredTransmissions:  0
dev.bce.0.stat_Dot3StatsExcessiveCollisions:  0
dev.bce.0.stat_Dot3StatsLateCollisions:  0
dev.bce.0.stat_EtherStatsCollisions:  0
dev.bce.0.stat_EtherStatsFragments:  0
dev.bce.0.stat_EtherStatsJabbers:  0
dev.bce.0.stat_EtherStatsUndersizePkts:  0
dev.bce.0.stat_EtherStatsOverrsizePkts:  0
dev.bce.0.stat_EtherStatsPktsRx64Octets:  44671171
dev.bce.0.stat_EtherStatsPktsRx65Octetsto127Octets:  166377250
dev.bce.0.stat_EtherStatsPktsRx128Octetsto255Octets:  125306581
dev.bce.0.stat_EtherStatsPktsRx256Octetsto511Octets:  11502851
dev.bce.0.stat_EtherStatsPktsRx512Octetsto1023Octets:  3372657
dev.bce.0.stat_EtherStatsPktsRx1024Octetsto1522Octets:  9137084
dev.bce.0.stat_EtherStatsPktsRx1523Octetsto9022Octets:  0
dev.bce.0.stat_EtherStatsPktsTx64Octets:  12605056
dev.bce.0.stat_EtherStatsPktsTx65Octetsto127Octets:  208798776
dev.bce.0.stat_EtherStatsPktsTx128Octetsto255Octets:  82452517
dev.bce.0.stat_EtherStatsPktsTx256Octetsto511Octets:  8532515
dev.bce.0.stat_EtherStatsPktsTx512Octetsto1023Octets:  3204492
dev.bce.0.stat_EtherStatsPktsTx1024Octetsto1522Octets:  7816769
dev.bce.0.stat_EtherStatsPktsTx1523Octetsto9022Octets:  0
dev.bce.0.stat_XonPauseFramesReceived:  0
dev.bce.0.stat_XoffPauseFramesReceived:  0
dev.bce.0.stat_OutXonSent:  0
dev.bce.0.stat_OutXoffSent:  0
dev.bce.0.stat_FlowControlDone:  0
dev.bce.0.stat_MacControlFramesReceived:  0
dev.bce.0.stat_XoffStateEntered:  0
dev.bce.0.stat_IfInFramesL2FilterDiscards:  4933702
dev.bce.0.stat_IfInRuleCheckerDiscards:  0
dev.bce.0.stat_IfInFTQDiscards:  0
dev.bce.0.stat_IfInMBUFDiscards:  0
dev.bce.0.stat_IfInRuleCheckerP4Hit:  0
dev.bce.0.stat_CatchupInRuleCheckerDiscards:  0
dev.bce.0.stat_CatchupInFTQDiscards:  0
dev.bce.0.stat_CatchupInMBUFDiscards:  0
dev.bce.0.stat_CatchupInRuleCheckerP4Hit:  0

# vmstat  -i
interrupt                           total       rate
irq14:  ata0                           47          0
irq16: bce0 bce1                548968755       1086
irq21: uhci0  uhci+                     5          0
irq78: mfi0                        343548          0
cpu0: timer                     998576924       1976
cpu1: timer                    1008301350       1995
cpu3: timer                    1008469139       1995
cpu2: timer                     995126109       1969
Total                          4559785877       9023

 # uname  -a
FreeBSD niobium.mxit.co.za  6.2-PRERELEASE FreeBSD 6.2-PRERELEASE #1:
Tue Oct 10 13:28:54 SAST 2006
toor@krypton.mxit.co.za:/usr/obj/usr/src/sys/MXIT-SMP-I386   i386

Kevin Kramer

2006-Oct-18 06:31 UTC

head link

When will the new BCE driver in HEAD be incorporated into RELENG_6?

and will it support the BCM5754 in the Precision 390?

------------------------------

Kevin Kramer
Sr. Systems Administrator
512.418.5725
Centaur Technology, Inc.
www.centtech.com



Conrad Burger wrote the following on 10/18/06 04:58:> Hi
>
> It looks like there is a "new"  version of the bce driver in
HEAD.
> When will it be incorporated into  Releng_6?
>
> We are currently having some  performance problems with a java
> application on our Dell 1950s.
>
> And it looks like it has something  to do with the speed with which
> network I/Os are  performed.
>
> We have Dell 2850s running FreeBSD  5.4/i386 SMP. With Intel nics (em)
> and they are performing quite well.
>
> With 34000 tcp sockets open the  maximum time it takes to perform a
> single network I/O is about 100ms.
>
> The Dell 1950s running FreeBSD  6.2-Prerelease/i386 SMP with Broadcom
> nics (bce), the same application and 34000  tcp connections open.
>
> The maximum time it takes to  perform a single network I/O is about 
> 7000ms.
>
> Most of the packets the systems  send/receive are rather small.
>
> We are not quite sure what could  cause this behavior.
>
> If anyone has any ideas of what we  could do to decrease the time it
> takes to perform network I/O it would be much  appreciated.
>
> Regards
> Conrad
>
> Some  information:
> dev.bce.0.%desc: Broadcom  NetXtreme II BCM5708 1000Base-T (B1), v0.9.6
> dev.bce.0.%driver:  bce
> dev.bce.0.%location: slot=0  function=0
> dev.bce.0.%pnpinfo: vendor=0x14e4  device=0x164c subvendor=0x1028
> subdevice=0x01b3  class=0x020000
> dev.bce.0.%parent:  pci9
> dev.bce.0.driver_version:  v0.9.6
> dev.bce.0.stat_IfHcInOctets:  2346165
> dev.bce.0.stat_IfHCInBadOctets:  1877825702
> dev.bce.0.stat_IfHCOutOctets:  2751390538
> dev.bce.0.stat_IfHCOutBadOctets:  0
> dev.bce.0.stat_IfHCInUcastPkts:  360078711
> dev.bce.0.stat_IfHCInMulticastPkts:  18339
> dev.bce.0.stat_IfHCInBroadcastPkts:  270544
> dev.bce.0.stat_IfHCOutUcastPkts:  323261730
> dev.bce.0.stat_IfHCOutMulticastPkts:  147410
> dev.bce.0.stat_IfHCOutBroadcastPkts:  985
> dev.bce.0.stat_emac_tx_stat_dot3statsinternalmactransmiterrors:  0
> dev.bce.0.stat_Dot3StatsCarrierSenseErrors:  0
> dev.bce.0.stat_Dot3StatsFCSErrors:  0
> dev.bce.0.stat_Dot3StatsAlignmentErrors:  0
> dev.bce.0.stat_Dot3StatsSingleCollisionFraes:  0
> dev.bce.0.stat_Dot3StatsMultipleCollisionFrames:  0
> dev.bce.0.stat_Dot3StatsDeferredTransmissions:  0
> dev.bce.0.stat_Dot3StatsExcessiveCollisions:  0
> dev.bce.0.stat_Dot3StatsLateCollisions:  0
> dev.bce.0.stat_EtherStatsCollisions:  0
> dev.bce.0.stat_EtherStatsFragments:  0
> dev.bce.0.stat_EtherStatsJabbers:  0
> dev.bce.0.stat_EtherStatsUndersizePkts:  0
> dev.bce.0.stat_EtherStatsOverrsizePkts:  0
> dev.bce.0.stat_EtherStatsPktsRx64Octets:  44671171
> dev.bce.0.stat_EtherStatsPktsRx65Octetsto127Octets:  166377250
> dev.bce.0.stat_EtherStatsPktsRx128Octetsto255Octets:  125306581
> dev.bce.0.stat_EtherStatsPktsRx256Octetsto511Octets:  11502851
> dev.bce.0.stat_EtherStatsPktsRx512Octetsto1023Octets:  3372657
> dev.bce.0.stat_EtherStatsPktsRx1024Octetsto1522Octets:  9137084
> dev.bce.0.stat_EtherStatsPktsRx1523Octetsto9022Octets:  0
> dev.bce.0.stat_EtherStatsPktsTx64Octets:  12605056
> dev.bce.0.stat_EtherStatsPktsTx65Octetsto127Octets:  208798776
> dev.bce.0.stat_EtherStatsPktsTx128Octetsto255Octets:  82452517
> dev.bce.0.stat_EtherStatsPktsTx256Octetsto511Octets:  8532515
> dev.bce.0.stat_EtherStatsPktsTx512Octetsto1023Octets:  3204492
> dev.bce.0.stat_EtherStatsPktsTx1024Octetsto1522Octets:  7816769
> dev.bce.0.stat_EtherStatsPktsTx1523Octetsto9022Octets:  0
> dev.bce.0.stat_XonPauseFramesReceived:  0
> dev.bce.0.stat_XoffPauseFramesReceived:  0
> dev.bce.0.stat_OutXonSent:  0
> dev.bce.0.stat_OutXoffSent:  0
> dev.bce.0.stat_FlowControlDone:  0
> dev.bce.0.stat_MacControlFramesReceived:  0
> dev.bce.0.stat_XoffStateEntered:  0
> dev.bce.0.stat_IfInFramesL2FilterDiscards:  4933702
> dev.bce.0.stat_IfInRuleCheckerDiscards:  0
> dev.bce.0.stat_IfInFTQDiscards:  0
> dev.bce.0.stat_IfInMBUFDiscards:  0
> dev.bce.0.stat_IfInRuleCheckerP4Hit:  0
> dev.bce.0.stat_CatchupInRuleCheckerDiscards:  0
> dev.bce.0.stat_CatchupInFTQDiscards:  0
> dev.bce.0.stat_CatchupInMBUFDiscards:  0
> dev.bce.0.stat_CatchupInRuleCheckerP4Hit:  0
>
> # vmstat  -i
> interrupt                           total       rate
> irq14:  ata0                           47          0
> irq16: bce0 bce1                548968755       1086
> irq21: uhci0  uhci+                     5          0
> irq78: mfi0                        343548          0
> cpu0: timer                     998576924       1976
> cpu1: timer                    1008301350       1995
> cpu3: timer                    1008469139       1995
> cpu2: timer                     995126109       1969
> Total                          4559785877       9023
>
> # uname  -a
> FreeBSD niobium.mxit.co.za  6.2-PRERELEASE FreeBSD 6.2-PRERELEASE #1:
> Tue Oct 10 13:28:54 SAST 2006
> toor@krypton.mxit.co.za:/usr/obj/usr/src/sys/MXIT-SMP-I386   i386
> _______________________________________________
> freebsd-stable@freebsd.org mailing list
> http://lists.freebsd.org/mailman/listinfo/freebsd-stable
> To unsubscribe, send any mail to
"freebsd-stable-unsubscribe@freebsd.org"

Scott Long

2006-Oct-18 08:26 UTC

head link

When will the new BCE driver in HEAD be incorporated into RELENG_6?

Conrad Burger wrote:> Hi
> 
> It looks like there is a "new"  version of the bce driver in
HEAD.
> When will it be incorporated into  Releng_6?
It will be merged when someone, preferably 2-3 people, tell me that
the changes in HEAD work for them.  So far, no one has.

Scott

Scott Long

2006-Oct-18 08:26 UTC

head link

When will the new BCE driver in HEAD be incorporated into RELENG_6?

Kevin Kramer wrote:> and will it support the BCM5754 in the Precision 390?
> 
No idea, ask the vendor.

Scott

Brian A. Seklecki

2006-Oct-23 09:19 UTC

head link

When will the new BCE driver in HEAD be incorporated RELE6?

Kevin:

Maybe you can get a punter on linux-poweredge@ lists to do "scanpci
-v" or
"lspci" or whatever to get the IDs.

~BAS

On Wed, 18 Oct 2006, Scott Long wrote:
> Kevin Kramer wrote:
>> and will it support the BCM5754 in the Precision 390?
>> 
>
> No idea, ask the vendor.
>
> Scott
> _______________________________________________
> freebsd-stable@freebsd.org mailing list
> http://lists.freebsd.org/mailman/listinfo/freebsd-stable
> To unsubscribe, send any mail to
"freebsd-stable-unsubscribe@freebsd.org"
>
l8*
 	-lava (Brian A. Seklecki - Pittsburgh, PA, USA)
 	       http://www.spiritual-machines.org/

"...from back in the heady days when "helpdesk" meant nothing,
"diskquota"
meant everything, and lives could be bought and sold for a couple of pages
of laser printout - and frequently were."

Kevin Kramer

2006-Oct-23 10:35 UTC

head link

When will the new BCE driver in HEAD be incorporated RELE6?

I have booted it into FC3 using 2.6.18 kernel. here is the dmesg and 
scanpci -v output

tg3.c:v3.65 (August 07, 2006)
ACPI: PCI Interrupt 0000:04:00.0[A] -> GSI 17 (level, low) -> IRQ 177
PCI: Setting latency timer of device 0000:04:00.0 to 64
eth0: Tigon3 [partno(BCM95754) rev b002 PHY(5787)] (PCI Express) 
10/100/1000Base
T Ethernet 00:13:72:25:67:ec
eth0: RXcsums[1] LinkChgREG[1] MIirq[1] ASF[0] Split[0] WireSpeed[1] 
TSOcap[1]
eth0: dma_rwctrl[76180000] dma_mask[64-bit]


pci bus 0x0004 cardnum 0x00 function 0x00: vendor 0x14e4 device 0x167a
 Broadcom Corporation  Device unknown
 CardVendor 0x1028 card 0x01de (Card unknown)
  STATUS    0x0010  COMMAND 0x0006
  CLASS     0x02 0x00 0x00  REVISION 0x02
  BIST      0x00  HEADER 0x00  LATENCY 0x00  CACHE 0x10
  BASE0     0x00000000eddf0004  addr 0x00000000eddf0000  MEM 64BIT
  MAX_LAT   0x00  MIN_GNT 0x00  INT_PIN 0x01  INT_LINE 0x0a

------------------------------

Kevin Kramer
Sr. Systems Administrator
512.418.5725
Centaur Technology, Inc.
www.centtech.com



Brian A. Seklecki wrote the following on 10/23/06 11:18:>
>
> Kevin:
>
> Maybe you can get a punter on linux-poweredge@ lists to do "scanpci 
> -v" or "lspci" or whatever to get the IDs.
>
> ~BAS
>
> On Wed, 18 Oct 2006, Scott Long wrote:
>
>> Kevin Kramer wrote:
>>> and will it support the BCM5754 in the Precision 390?
>>>
>>
>> No idea, ask the vendor.
>>
>> Scott
>> _______________________________________________
>> freebsd-stable@freebsd.org mailing list
>> http://lists.freebsd.org/mailman/listinfo/freebsd-stable
>> To unsubscribe, send any mail to 
>> "freebsd-stable-unsubscribe@freebsd.org"
>>
>
> l8*
>     -lava (Brian A. Seklecki - Pittsburgh, PA, USA)
>            http://www.spiritual-machines.org/
>
> "...from back in the heady days when "helpdesk" meant
nothing,
> "diskquota"
> meant everything, and lives could be bought and sold for a couple of 
> pages
> of laser printout - and frequently were."

freebsd stable - Oct 2006 - When will the new BCE driver in HEAD be incorporated into RELENG_6?

When will the new BCE driver in HEAD be incorporated into RELENG_6?

When will the new BCE driver in HEAD be incorporated into RELENG_6?

When will the new BCE driver in HEAD be incorporated into RELENG_6?

When will the new BCE driver in HEAD be incorporated into RELENG_6?

When will the new BCE driver in HEAD be incorporated RELE6?

When will the new BCE driver in HEAD be incorporated RELE6?