* RE: 82540EM very slow on 2.6.0-test[45]
@ 2003-09-11 1:14 rwhron
0 siblings, 0 replies; 7+ messages in thread
From: rwhron @ 2003-09-11 1:14 UTC (permalink / raw)
To: scott.feldman; +Cc: netdev
>> ftp'ing a multi-megabyte file gives about 16-20k/second
>> throughput. The destination machine was running Solaris 8.
> Linux -> Solaris
Linux doing an ftp put on Solaris.
>> This is a dual boot Dell P4. XP is about 1000x faster for
>> an ftp xfer, so the network seems okay.
> Is this Linux -> XP or XP -> Solaris? Trying to eliminate one player.
Linux ftp put to Solaris is slow. When booted into XP, ftp put to
Solaris is fast. Solaris -> Solaris is fast too.
> What about Linux -> Linux? Is that slow?
I will try that and some other combinations.
>> dmesg shows "e1000: eth0 NIC Link is Up 100 Mbps Full Duplex".
> This feels like a duplex mis-match.
Could well be. On our LAN, Solaris often has to be forced full-duplex
because auto-negotiate to the switches gives half-duplex. The ftp server
is full duplex. The client and server are on different segments.
I'll check if the PC is using correct duplex/speed for it's segment.
> Are you using the same cable for the different tests?
Yes. Same cable, same PC. I swapped CAT5 cables, but that didn't
change throughput.
Thanks for the suggestions!
--
Randy Hron
http://home.earthlink.net/~rwhron/kernel/bigbox.html
^ permalink raw reply [flat|nested] 7+ messages in thread
* RE: 82540EM very slow on 2.6.0-test[45]
@ 2003-09-11 21:40 Feldman, Scott
2003-09-11 22:19 ` Ben Greear
0 siblings, 1 reply; 7+ messages in thread
From: Feldman, Scott @ 2003-09-11 21:40 UTC (permalink / raw)
To: rwhron; +Cc: netdev
> I tried 4 Solaris servers. 2 had forced full duplex
> and 100 Mbps. Those are slow. 2 other Solaris servers
> on the same LAN as the "slow" Solaris servers are fast.
> These "fast" servers are using default settings (which
> should also be 100 Mbps full-duplex).
Maybe someone else on the list has some suggestions? I think we're
troubleshooting your network now.
Is it just ftp that's slow? What's in the path between the Linux and
the "slow" Solaris server? Can you shorten the path? What happens if
you don't force 100/full on the "slow" Solaris server?
-scott
^ permalink raw reply [flat|nested] 7+ messages in thread
* Re: 82540EM very slow on 2.6.0-test[45]
2003-09-11 21:40 Feldman, Scott
@ 2003-09-11 22:19 ` Ben Greear
0 siblings, 0 replies; 7+ messages in thread
From: Ben Greear @ 2003-09-11 22:19 UTC (permalink / raw)
To: Feldman, Scott; +Cc: rwhron, netdev
Feldman, Scott wrote:
>>I tried 4 Solaris servers. 2 had forced full duplex
>>and 100 Mbps. Those are slow. 2 other Solaris servers
>>on the same LAN as the "slow" Solaris servers are fast.
>>These "fast" servers are using default settings (which
>>should also be 100 Mbps full-duplex).
>
>
> Maybe someone else on the list has some suggestions? I think we're
> troubleshooting your network now.
>
> Is it just ftp that's slow? What's in the path between the Linux and
> the "slow" Solaris server? Can you shorten the path? What happens if
> you don't force 100/full on the "slow" Solaris server?
I know that Becker always yells and folks that force duplex. It is
evidently not a good thing to do.
Also, I've seen linux ftp get very poor results when there is any
latency in the link. That latency could include the solaris machine
reading from it's HD, etc.
Try saving the file locally to /dev/null, that takes at least one HD
out of the picture. Also try using some network transfer tool that
does not read or write to disk. I think ttcp might be good for that.
>
> -scott
>
--
Ben Greear <greearb@candelatech.com>
Candela Technologies Inc http://www.candelatech.com
^ permalink raw reply [flat|nested] 7+ messages in thread
* RE: 82540EM very slow on 2.6.0-test[45]
@ 2003-09-11 21:06 rwhron
0 siblings, 0 replies; 7+ messages in thread
From: rwhron @ 2003-09-11 21:06 UTC (permalink / raw)
To: scott.feldman; +Cc: netdev
> Is this Linux -> XP or XP -> Solaris? Trying to eliminate one player.
The destination Solaris machine has an impact. There are two
Solaris servers on the same subnet. For one of the servers:
Solaris ftp put to linux is fast
Solaris ftp get from linux is slow
Linux ftp put to solaris is slow
Linux ftp get from solaris is slow
For the another Solaris 8 server on the same subnet,
all ftp xfer's with Linux machine are fast. When the
machine is booted into XP, ftp is fast to either server.
>> dmesg shows "e1000: eth0 NIC Link is Up 100 Mbps Full Duplex".
> This feels like a duplex mis-match.
The Solaris server that is slow for most Linux ftp xfers has
100 MBPs full-duplex forced.
The Solaris server that Linux talks to fast doesn't have
any duplex/capabilities forced.
I tried 4 Solaris servers. 2 had forced full duplex
and 100 Mbps. Those are slow. 2 other Solaris servers
on the same LAN as the "slow" Solaris servers are fast.
These "fast" servers are using default settings (which
should also be 100 Mbps full-duplex).
The odd part is that XP will talk to all four Solaris
servers fast.
--
Randy Hron
http://home.earthlink.net/~rwhron/kernel/bigbox.html
^ permalink raw reply [flat|nested] 7+ messages in thread
* RE: 82540EM very slow on 2.6.0-test[45]
@ 2003-09-11 0:28 Feldman, Scott
0 siblings, 0 replies; 7+ messages in thread
From: Feldman, Scott @ 2003-09-11 0:28 UTC (permalink / raw)
To: rwhron, netdev
> ftp'ing a multi-megabyte file gives about 16-20k/second
> throughput. I first noticed this on 2.6.0-test4, but
> the slowness may have existed longer. The destination
> machine was running Solaris 8.
Linux -> Solaris
> This is a dual boot Dell P4. XP is about 1000x faster for
> an ftp xfer, so the network seems okay.
Is this Linux -> XP or XP -> Solaris? Trying to eliminate one player.
What about Linux -> Linux? Is that slow?
> dmesg shows "e1000: eth0 NIC Link is Up 100 Mbps Full
> Duplex". Here is the full dmesg log:
This feels like a duplex mis-match. Do you have good cat 5 cables? Are
you using the same cable for the different tests?
-scott
^ permalink raw reply [flat|nested] 7+ messages in thread
* 82540EM very slow on 2.6.0-test[45]
@ 2003-09-10 23:35 rwhron
2003-09-14 17:23 ` Florian Zwoch
0 siblings, 1 reply; 7+ messages in thread
From: rwhron @ 2003-09-10 23:35 UTC (permalink / raw)
To: netdev; +Cc: scott.feldman
ftp'ing a multi-megabyte file gives about 16-20k/second
throughput. I first noticed this on 2.6.0-test4, but
the slowness may have existed longer. The destination
machine was running Solaris 8.
This is a dual boot Dell P4. XP is about 1000x faster for
an ftp xfer, so the network seems okay.
I tried the 11 patches in
http://marc.theaimsgroup.com/?l=linux-netdev&m=106307597016664&w=2
but that didn't make a noticeable difference in ftp xfer throughput.
The e1000 driver is non-module with default settings.
ifconfig doesn't show any dropped packets.
eth0 Link encap:Ethernet HWaddr 00:08:74:EA:C8:9E
inet addr:146.126.194.254 Bcast:146.126.194.255 Mask:255.255.255.128
UP BROADCAST RUNNING MULTICAST MTU:1500 Metric:1
RX packets:14198 errors:0 dropped:0 overruns:0 frame:0
TX packets:6195 errors:0 dropped:0 overruns:0 carrier:0
collisions:0 txqueuelen:100
RX bytes:3531096 (3.3 Mb) TX bytes:8602840 (8.2 Mb)
Interrupt:10 Base address:0xecc0 Memory:ff8e0000-ff900000
netstat during the ftp xfer shows a large send-Q:
Active Internet connections (servers and established)
Proto Recv-Q Send-Q Local Address Foreign Address State PID/Program name
tcp 0 0 0.0.0.0:6000 0.0.0.0:* LISTEN 1036/X
tcp 0 0 0.0.0.0:22 0.0.0.0:* LISTEN 921/sshd
tcp 0 66608 146.126.194.254:32804 146.126.60.140:50182 ESTABLISHED 1686/ftp
tcp 0 0 146.126.194.254:32805 146.126.88.210:443 ESTABLISHED 1594/mozilla-bin
tcp 0 0 146.126.194.254:32803 146.126.60.140:21 ESTABLISHED 1686/ftp
iptables is on the system. I ran "/etc/init.d/iptables stop"
and re-tried ftp, but that didn't make a difference.
Here is grep ^C /usr/src/linux/.config
CONFIG_X86=y
CONFIG_MMU=y
CONFIG_UID16=y
CONFIG_GENERIC_ISA_DMA=y
CONFIG_EXPERIMENTAL=y
CONFIG_CLEAN_COMPILE=y
CONFIG_STANDALONE=y
CONFIG_BROKEN_ON_SMP=y
CONFIG_SWAP=y
CONFIG_SYSVIPC=y
CONFIG_SYSCTL=y
CONFIG_LOG_BUF_SHIFT=14
CONFIG_EMBEDDED=y
CONFIG_KALLSYMS=y
CONFIG_FUTEX=y
CONFIG_EPOLL=y
CONFIG_IOSCHED_AS=y
CONFIG_IOSCHED_DEADLINE=y
CONFIG_X86_PC=y
CONFIG_MPENTIUM4=y
CONFIG_X86_CMPXCHG=y
CONFIG_X86_XADD=y
CONFIG_X86_L1_CACHE_SHIFT=7
CONFIG_RWSEM_XCHGADD_ALGORITHM=y
CONFIG_X86_WP_WORKS_OK=y
CONFIG_X86_INVLPG=y
CONFIG_X86_BSWAP=y
CONFIG_X86_POPAD_OK=y
CONFIG_X86_GOOD_APIC=y
CONFIG_X86_INTEL_USERCOPY=y
CONFIG_X86_USE_PPRO_CHECKSUM=y
CONFIG_X86_TSC=y
CONFIG_X86_MCE=y
CONFIG_NOHIGHMEM=y
CONFIG_MTRR=y
CONFIG_PM=y
CONFIG_PCI=y
CONFIG_PCI_GOANY=y
CONFIG_PCI_BIOS=y
CONFIG_PCI_DIRECT=y
CONFIG_PCI_NAMES=y
CONFIG_BINFMT_ELF=y
CONFIG_PNP=y
CONFIG_BLK_DEV_FD=y
CONFIG_BLK_DEV_RAM=y
CONFIG_BLK_DEV_RAM_SIZE=4096
CONFIG_IDE=y
CONFIG_BLK_DEV_IDE=y
CONFIG_BLK_DEV_IDEDISK=y
CONFIG_IDEDISK_MULTI_MODE=y
CONFIG_BLK_DEV_IDECD=y
CONFIG_BLK_DEV_IDEFLOPPY=y
CONFIG_BLK_DEV_IDEPCI=y
CONFIG_IDEPCI_SHARE_IRQ=y
CONFIG_BLK_DEV_GENERIC=y
CONFIG_BLK_DEV_IDEDMA_PCI=y
CONFIG_IDEDMA_PCI_AUTO=y
CONFIG_BLK_DEV_ADMA=y
CONFIG_BLK_DEV_PIIX=y
CONFIG_BLK_DEV_IDEDMA=y
CONFIG_IDEDMA_AUTO=y
CONFIG_NET=y
CONFIG_PACKET=y
CONFIG_PACKET_MMAP=y
CONFIG_UNIX=y
CONFIG_NET_KEY=y
CONFIG_INET=y
CONFIG_NETFILTER=y
CONFIG_IP_NF_CONNTRACK=y
CONFIG_IP_NF_FTP=y
CONFIG_IP_NF_IPTABLES=y
CONFIG_IP_NF_MATCH_LIMIT=y
CONFIG_IP_NF_MATCH_PKTTYPE=y
CONFIG_IP_NF_MATCH_MARK=y
CONFIG_IP_NF_MATCH_MULTIPORT=y
CONFIG_IP_NF_MATCH_TOS=y
CONFIG_IP_NF_MATCH_ECN=y
CONFIG_IP_NF_MATCH_DSCP=y
CONFIG_IP_NF_MATCH_STATE=y
CONFIG_IP_NF_MATCH_CONNTRACK=y
CONFIG_IP_NF_FILTER=y
CONFIG_IP_NF_TARGET_REJECT=y
CONFIG_IP_NF_MANGLE=y
CONFIG_IP_NF_TARGET_LOG=y
CONFIG_XFRM=y
CONFIG_IPV6_SCTP__=y
CONFIG_NETDEVICES=y
CONFIG_NET_ETHERNET=y
CONFIG_NET_PCI=y
CONFIG_EEPRO100=y
CONFIG_E1000=y
CONFIG_E1000_NAPI=y
CONFIG_INPUT=y
CONFIG_INPUT_MOUSEDEV=y
CONFIG_INPUT_MOUSEDEV_PSAUX=y
CONFIG_INPUT_MOUSEDEV_SCREEN_X=1024
CONFIG_INPUT_MOUSEDEV_SCREEN_Y=768
CONFIG_SOUND_GAMEPORT=y
CONFIG_SERIO=y
CONFIG_SERIO_I8042=y
CONFIG_SERIO_SERPORT=y
CONFIG_INPUT_KEYBOARD=y
CONFIG_KEYBOARD_ATKBD=y
CONFIG_INPUT_MOUSE=y
CONFIG_MOUSE_PS2=y
CONFIG_VT=y
CONFIG_VT_CONSOLE=y
CONFIG_HW_CONSOLE=y
CONFIG_UNIX98_PTYS=y
CONFIG_UNIX98_PTY_COUNT=128
CONFIG_RTC=y
CONFIG_AGP=y
CONFIG_AGP_INTEL=y
CONFIG_DRM=y
CONFIG_DRM_I810=y
CONFIG_EXT2_FS=y
CONFIG_EXT3_FS=y
CONFIG_JBD=y
CONFIG_ISO9660_FS=y
CONFIG_JOLIET=y
CONFIG_FAT_FS=y
CONFIG_MSDOS_FS=y
CONFIG_PROC_FS=y
CONFIG_DEVPTS_FS=y
CONFIG_TMPFS=y
CONFIG_RAMFS=y
CONFIG_SMB_FS=y
CONFIG_MSDOS_PARTITION=y
CONFIG_SMB_NLS=y
CONFIG_NLS=y
CONFIG_NLS_DEFAULT="iso8859-1"
CONFIG_NLS_CODEPAGE_437=y
CONFIG_FB=y
CONFIG_FB_VGA16=y
CONFIG_FB_VESA=y
CONFIG_VIDEO_SELECT=y
CONFIG_VGA_CONSOLE=y
CONFIG_DUMMY_CONSOLE=y
CONFIG_FRAMEBUFFER_CONSOLE=y
CONFIG_PCI_CONSOLE=y
CONFIG_FONT_8x8=y
CONFIG_FONT_8x16=y
CONFIG_SOUND=y
CONFIG_SOUND_PRIME=y
CONFIG_SOUND_ICH=y
CONFIG_DEBUG_KERNEL=y
CONFIG_MAGIC_SYSRQ=y
CONFIG_X86_BIOS_REBOOT=y
dmesg shows "e1000: eth0 NIC Link is Up 100 Mbps Full Duplex".
Here is the full dmesg log:
Linux version 2.6.0-test5 (root@hilltop) (gcc version 3.2.2 20030222 (Red Hat Linux 3.2.2-5)) #3 Wed Sep 10 10:07:45 EDT 2003
Video mode to be used for restore is f00
BIOS-provided physical RAM map:
BIOS-e820: 0000000000000000 - 00000000000a0000 (usable)
BIOS-e820: 00000000000f0000 - 0000000000100000 (reserved)
BIOS-e820: 0000000000100000 - 000000001fe71000 (usable)
BIOS-e820: 000000001fe71000 - 000000001fe73000 (ACPI NVS)
BIOS-e820: 000000001fe73000 - 000000001fe94000 (ACPI data)
BIOS-e820: 000000001fe94000 - 000000001ff00000 (reserved)
BIOS-e820: 00000000fec00000 - 00000000fec10000 (reserved)
BIOS-e820: 00000000fee00000 - 00000000fee10000 (reserved)
BIOS-e820: 00000000ffb00000 - 0000000100000000 (reserved)
510MB LOWMEM available.
On node 0 totalpages: 130673
DMA zone: 4096 pages, LIFO batch:1
Normal zone: 126577 pages, LIFO batch:16
HighMem zone: 0 pages, LIFO batch:1
DMI 2.3 present.
Building zonelist for node : 0
Kernel command line: ro nousb profile=2
kernel profiling enabled
Initializing CPU#0
PID hash table entries: 2048 (order 11: 16384 bytes)
Detected 1793.494 MHz processor.
Console: colour VGA+ 80x25
Memory: 512536k/522692k available (1601k kernel code, 9376k reserved, 468k data, 300k init, 0k highmem)
Calibrating delay loop... 3538.94 BogoMIPS
Dentry cache hash table entries: 65536 (order: 6, 262144 bytes)
Inode-cache hash table entries: 32768 (order: 5, 131072 bytes)
Mount-cache hash table entries: 512 (order: 0, 4096 bytes)
-> /dev
-> /dev/console
-> /root
CPU: After generic identify, caps: bfebfbff 00000000 00000000 00000000
CPU: After vendor identify, caps: bfebfbff 00000000 00000000 00000000
CPU: Trace cache: 12K uops, L1 D cache: 8K
CPU: L2 cache: 512K
CPU: After all inits, caps: bfebfbff 00000000 00000000 00000080
Intel machine check architecture supported.
Intel machine check reporting enabled on CPU#0.
CPU#0: Intel P4/Xeon Extended MCE MSRs (12) available
CPU: Intel(R) Pentium(R) 4 CPU 1.80GHz stepping 07
Enabling fast FPU save and restore... done.
Enabling unmasked SIMD FPU exception support... done.
Checking 'hlt' instruction... OK.
POSIX conformance testing by UNIFIX
NET: Registered protocol family 16
PCI: PCI BIOS revision 2.10 entry at 0xfbdf8, last bus=1
PCI: Using configuration type 1
mtrr: v2.0 (20020519)
Linux Plug and Play Support v0.97 (c) Adam Belay
PCI: Probing PCI hardware
PCI: Probing PCI hardware (bus 00)
PCI: Ignoring BAR0-3 of IDE controller 0000:00:1f.1
Transparent bridge - 0000:00:1e.0
PCI: Using IRQ router PIIX [8086/24c0] at 0000:00:1f.0
PCI: IRQ 0 for device 0000:00:1f.1 doesn't match PIRQ mask - try pci=usepirqmask
PCI: Found IRQ 10 for device 0000:00:1f.1
PCI: Sharing IRQ 10 with 0000:00:1d.2
PCI: Sharing IRQ 10 with 0000:01:0c.0
vga16fb: initializing
vga16fb: mapped to 0xc00a0000
fb0: VGA16 VGA frame buffer device
Console: switching to colour frame buffer device 80x30
pty: 256 Unix98 ptys configured
SBF: Simple Boot Flag extension found and enabled.
SBF: Simple boot flag value 0x87 read from CMOS RAM was invalid
SBF: Setting boot flags 0x1
Real Time Clock Driver v1.12
Linux agpgart interface v0.100 (c) Dave Jones
agpgart: Detected an Intel 845G Chipset.
agpgart: Maximum main memory to use for agp memory: 438M
agpgart: Detected 892K stolen memory.
agpgart: AGP aperture is 128M @ 0xe8000000
[drm] Initialized i810 1.4.0 20030605 on minor 0
Using anticipatory scheduling io scheduler
Floppy drive(s): fd0 is 1.44M
FDC 0 is a post-1991 82077
RAMDISK driver initialized: 16 RAM disks of 4096K size 1024 blocksize
Intel(R) PRO/1000 Network Driver - version 5.2.16-k1
Copyright (c) 1999-2003 Intel Corporation.
PCI: Found IRQ 10 for device 0000:01:0c.0
PCI: Sharing IRQ 10 with 0000:00:1d.2
PCI: Sharing IRQ 10 with 0000:00:1f.1
eth0: Intel(R) PRO/1000 Network Connection
Uniform Multi-Platform E-IDE driver Revision: 7.00alpha2
ide: Assuming 33MHz system bus speed for PIO modes; override with idebus=xx
ICH4: IDE controller at PCI slot 0000:00:1f.1
PCI: Enabling device 0000:00:1f.1 (0005 -> 0007)
PCI: Found IRQ 10 for device 0000:00:1f.1
PCI: Sharing IRQ 10 with 0000:00:1d.2
PCI: Sharing IRQ 10 with 0000:01:0c.0
ICH4: chipset revision 1
ICH4: not 100% native mode: will probe irqs later
ide0: BM-DMA at 0xffa0-0xffa7, BIOS settings: hda:DMA, hdb:pio
ide1: BM-DMA at 0xffa8-0xffaf, BIOS settings: hdc:DMA, hdd:pio
hda: ST340016A, ATA DISK drive
ide0 at 0x1f0-0x1f7,0x3f6 on irq 14
hdc: SAMSUNG DVD-ROM SD-616T, ATAPI CD/DVD-ROM drive
ide1 at 0x170-0x177,0x376 on irq 15
hda: max request size: 128KiB
hda: 78165360 sectors (40020 MB) w/2048KiB Cache, CHS=65535/16/63, UDMA(100)
hda: hda1 hda2 hda3 hda4 < hda5 >
hdc: ATAPI 48X DVD-ROM drive, 512kB Cache, UDMA(33)
Uniform CD-ROM driver Revision: 3.12
ide-floppy driver 0.99.newide
Console: switching to colour frame buffer device 80x30
mice: PS/2 mouse device common for all mice
input: ImPS/2 Generic Wheel Mouse on isa0060/serio1
serio: i8042 AUX port at 0x60,0x64 irq 12
input: AT Set 2 keyboard on isa0060/serio0
serio: i8042 KBD port at 0x60,0x64 irq 1
Intel 810 + AC97 Audio, version 0.24, 17:13:46 Sep 8 2003
PCI: Found IRQ 11 for device 0000:00:1f.5
PCI: Sharing IRQ 11 with 0000:00:1f.3
PCI: Setting latency timer of device 0000:00:1f.5 to 64
i810: Intel ICH4 found at IO 0xdc40 and 0xd800, MEM 0xffa00400 and 0xffa00000, IRQ 11
i810: Intel ICH4 mmio at 0xe08ca400 and 0xe08cc000
i810_audio: Primary codec has ID 0
i810_audio: Audio Controller supports 6 channels.
i810_audio: Defaulting to base 2 channel mode.
i810_audio: Resetting connection 0
i810_audio: Connection 0 with codec id 0
ac97_codec: AC97 Audio codec, id: ADS116 (Unknown)
i810_audio: AC'97 codec 0 supports AMAP, total channels = 2
i810_audio: setting clocking to 48648
NET: Registered protocol family 2
IP: routing cache hash table of 4096 buckets, 32Kbytes
TCP: Hash tables configured (established 32768 bind 65536)
ip_conntrack version 2.1 (4083 buckets, 32664 max) - 160 bytes per conntrack
ip_tables: (C) 2000-2002 Netfilter core team
NET: Registered protocol family 1
NET: Registered protocol family 17
NET: Registered protocol family 15
kjournald starting. Commit interval 5 seconds
EXT3-fs: mounted filesystem with ordered data mode.
VFS: Mounted root (ext3 filesystem) readonly.
Freeing unused kernel memory: 300k freed
EXT3 FS on hda2, internal journal
Adding 514072k swap on /dev/hda3. Priority:-1 extents:1
kjournald starting. Commit interval 5 seconds
EXT3 FS on hda5, internal journal
EXT3-fs: mounted filesystem with ordered data mode.
blk: queue dfcdea00, I/O limit 4095Mb (mask 0xffffffff)
e1000: eth0 NIC Link is Up 100 Mbps Full Duplex
spurious 8259A interrupt: IRQ7.
Here is a short snippet of "tcpdump -s 1500 host $remotehost"
14:22:44.181589 tcmsgpc.southernco.com.50182 > sixgp06w.southernco.com.32804: . ack 3236331158 win 24616 <nop,nop,timestamp 497026209 13941233> (DF)
14:22:44.488916 sixgp06w.southernco.com.32804 > tcmsgpc.southernco.com.50182: . 1:1449(1448) ack 0 win 5840 <nop,nop,timestamp 13941661 497026209> (DF) [tos 0x8]
14:22:44.601516 tcmsgpc.southernco.com.50182 > sixgp06w.southernco.com.32804: . ack 1449 win 24616 <nop,nop,timestamp 497026251 13941661> (DF)
14:22:44.601551 sixgp06w.southernco.com.32804 > tcmsgpc.southernco.com.50182: . 1449:2897(1448) ack 0 win 5840 <nop,nop,timestamp 13941773 497026251> (DF) [tos 0x8]
14:22:44.601560 sixgp06w.southernco.com.32804 > tcmsgpc.southernco.com.50182: . 2897:4345(1448) ack 0 win 5840 <nop,nop,timestamp 13941773 497026251> (DF) [tos 0x8]
14:22:44.602592 tcmsgpc.southernco.com.50182 > sixgp06w.southernco.com.32804: . ack 4345 win 24616 <nop,nop,timestamp 497026251 13941773> (DF)
14:22:44.602607 sixgp06w.southernco.com.32804 > tcmsgpc.southernco.com.50182: . 4345:5793(1448) ack 0 win 5840 <nop,nop,timestamp 13941774 497026251> (DF) [tos 0x8]
14:22:44.602614 sixgp06w.southernco.com.32804 > tcmsgpc.southernco.com.50182: . 5793:7241(1448) ack 0 win 5840 <nop,nop,timestamp 13941774 497026251> (DF) [tos 0x8]
14:22:44.603513 tcmsgpc.southernco.com.50182 > sixgp06w.southernco.com.32804: . ack 7241 win 24616 <nop,nop,timestamp 497026251 13941774> (DF)
14:22:44.603526 sixgp06w.southernco.com.32804 > tcmsgpc.southernco.com.50182: . 7241:8689(1448) ack 0 win 5840 <nop,nop,timestamp 13941775 497026251> (DF) [tos 0x8]
14:22:44.603533 sixgp06w.southernco.com.32804 > tcmsgpc.southernco.com.50182: P 8689:10137(1448) ack 0 win 5840 <nop,nop,timestamp 13941775 497026251> (DF) [tos 0x8]
14:22:44.604437 tcmsgpc.southernco.com.50182 > sixgp06w.southernco.com.32804: . ack 10137 win 24616 <nop,nop,timestamp 497026251 13941775> (DF)
14:22:44.604451 sixgp06w.southernco.com.32804 > tcmsgpc.southernco.com.50182: . 10137:10085(4294967244) ack 0 win 5840 <nop,nop,timestamp 13941776 497026251> (DF) [tos 0x8]
14:22:44.721478 tcmsgpc.southernco.com.50182 > sixgp06w.southernco.com.32804: . ack 11585 win 24616 <nop,nop,timestamp 497026263 13941776> (DF)
14:22:44.721497 sixgp06w.southernco.com.32804 > tcmsgpc.southernco.com.50182: . 11585:13033(1448) ack 0 win 5840 <nop,nop,timestamp 13941893 497026263> (DF) [tos 0x8]
14:22:44.841444 tcmsgpc.southernco.com.50182 > sixgp06w.southernco.com.32804: . ack 13033 win 24616 <nop,nop,timestamp 497026275 13941893> (DF)
14:22:44.841505 sixgp06w.southernco.com.32804 > tcmsgpc.southernco.com.50182: . 13033:14481(1448) ack 0 win 5840 <nop,nop,timestamp 13942013 497026275> (DF) [tos 0x8]
14:22:44.961555 tcmsgpc.southernco.com.50182 > sixgp06w.southernco.com.32804: . ack 14481 win 24616 <nop,nop,timestamp 497026287 13942013> (DF)
14:22:44.961575 sixgp06w.southernco.com.32804 > tcmsgpc.southernco.com.50182: . 14481:15929(1448) ack 0 win 5840 <nop,nop,timestamp 13942133 497026287> (DF) [tos 0x8]
14:22:45.081516 tcmsgpc.southernco.com.50182 > sixgp06w.southernco.com.32804: . ack 15929 win 24616 <nop,nop,timestamp 497026299 13942133> (DF)
14:22:45.081535 sixgp06w.southernco.com.32804 > tcmsgpc.southernco.com.50182: . 15929:17377(1448) ack 0 win 5840 <nop,nop,timestamp 13942253 497026299> (DF) [tos 0x8]
14:22:45.201477 tcmsgpc.southernco.com.50182 > sixgp06w.southernco.com.32804: . ack 17377 win 24616 <nop,nop,timestamp 497026311 13942253> (DF)
14:22:45.201494 sixgp06w.southernco.com.32804 > tcmsgpc.southernco.com.50182: . 17377:18825(1448) ack 0 win 5840 <nop,nop,timestamp 13942373 497026311> (DF) [tos 0x8]
14:22:45.321599 tcmsgpc.southernco.com.50182 > sixgp06w.southernco.com.32804: . ack 18825 win 24616 <nop,nop,timestamp 497026323 13942373> (DF)
14:22:45.321670 sixgp06w.southernco.com.32804 > tcmsgpc.southernco.com.50182: . 18825:20273(1448) ack 0 win 5840 <nop,nop,timestamp 13942493 497026323> (DF) [tos 0x8]
14:22:45.441416 tcmsgpc.southernco.com.50182 > sixgp06w.southernco.com.32804: . ack 20273 win 24616 <nop,nop,timestamp 497026335 13942493> (DF)
14:22:45.441511 sixgp06w.southernco.com.32804 > tcmsgpc.southernco.com.50182: . 20273:21721(1448) ack 0 win 5840 <nop,nop,timestamp 13942613 497026335> (DF) [tos 0x8]
14:22:45.561525 tcmsgpc.southernco.com.50182 > sixgp06w.southernco.com.32804: . ack 21721 win 24616 <nop,nop,timestamp 497026347 13942613> (DF)
14:22:45.561610 sixgp06w.southernco.com.32804 > tcmsgpc.southernco.com.50182: . 21721:21669(4294967244) ack 0 win 5840 <nop,nop,timestamp 13942733 497026347> (DF) [tos 0x8]
14:22:45.681540 tcmsgpc.southernco.com.50182 > sixgp06w.southernco.com.32804: . ack 23169 win 24616 <nop,nop,timestamp 497026359 13942733> (DF)
14:22:45.988697 sixgp06w.southernco.com.32804 > tcmsgpc.southernco.com.50182: . 23169:24617(1448) ack 0 win 5840 <nop,nop,timestamp 13943161 497026359> (DF) [tos 0x8]
14:22:46.101407 tcmsgpc.southernco.com.50182 > sixgp06w.southernco.com.32804: . ack 24617 win 24616 <nop,nop,timestamp 497026401 13943161> (DF)
14:22:46.101478 sixgp06w.southernco.com.32804 > tcmsgpc.southernco.com.50182: . 24617:26065(1448) ack 0 win 5840 <nop,nop,timestamp 13943273 497026401> (DF) [tos 0x8]
14:22:46.101492 sixgp06w.southernco.com.32804 > tcmsgpc.southernco.com.50182: . 26065:27513(1448) ack 0 win 5840 <nop,nop,timestamp 13943273 497026401> (DF) [tos 0x8]
14:22:46.102601 tcmsgpc.southernco.com.50182 > sixgp06w.southernco.com.32804: . ack 27513 win 24616 <nop,nop,timestamp 497026401 13943273> (DF)
14:22:46.102616 sixgp06w.southernco.com.32804 > tcmsgpc.southernco.com.50182: . 27513:28961(1448) ack 0 win 5840 <nop,nop,timestamp 13943274 497026401> (DF) [tos 0x8]
14:22:46.102622 sixgp06w.southernco.com.32804 > tcmsgpc.southernco.com.50182: . 28961:30409(1448) ack 0 win 5840 <nop,nop,timestamp 13943274 497026401> (DF) [tos 0x8]
14:22:46.103601 tcmsgpc.southernco.com.50182 > sixgp06w.southernco.com.32804: . ack 30409 win 24616 <nop,nop,timestamp 497026401 13943274> (DF)
14:22:46.103614 sixgp06w.southernco.com.32804 > tcmsgpc.southernco.com.50182: . 30409:31857(1448) ack 0 win 5840 <nop,nop,timestamp 13943275 497026401> (DF) [tos 0x8]
14:22:46.103621 sixgp06w.southernco.com.32804 > tcmsgpc.southernco.com.50182: . 31857:33305(1448) ack 0 win 5840 <nop,nop,timestamp 13943275 497026401> (DF) [tos 0x8]
14:22:46.104600 tcmsgpc.southernco.com.50182 > sixgp06w.southernco.com.32804: . ack 33305 win 24616 <nop,nop,timestamp 497026401 13943275> (DF)
14:22:46.104613 sixgp06w.southernco.com.32804 > tcmsgpc.southernco.com.50182: . 33305:33253(4294967244) ack 0 win 5840 <nop,nop,timestamp 13943276 497026401> (DF) [tos 0x8]
Here is lspci:
00:00.0 Host bridge: Intel Corp. 82845G/GL [Brookdale-G] Chipset Host Bridge (rev 01)
00:02.0 VGA compatible controller: Intel Corp. 82845G/GL [Brookdale-G] Chipset Integrated Graphics Device (rev 01)
00:1d.0 USB Controller: Intel Corp. 82801DB USB (Hub #1) (rev 01)
00:1d.1 USB Controller: Intel Corp. 82801DB USB (Hub #2) (rev 01)
00:1d.2 USB Controller: Intel Corp. 82801DB USB (Hub #3) (rev 01)
00:1d.7 USB Controller: Intel Corp. 82801DB USB EHCI Controller (rev 01)
00:1e.0 PCI bridge: Intel Corp. 82801BA/CA/DB PCI Bridge (rev 81)
00:1f.0 ISA bridge: Intel Corp. 82801DB ISA Bridge (LPC) (rev 01)
00:1f.1 IDE interface: Intel Corp. 82801DB ICH4 IDE (rev 01)
00:1f.3 SMBus: Intel Corp. 82801DB SMBus (rev 01)
00:1f.5 Multimedia audio controller: Intel Corp. 82801DB AC'97 Audio (rev 01)
01:0c.0 Ethernet controller: Intel Corp. 82540EM Gigabit Ethernet Controller (rev 02)
Is anyone getting decent throughput from an Intel 82540EM
Gigabit Ethernet Controller with 2.6.0-test? Suggestions
are welcome.
--
Randy Hron
http://home.earthlink.net/~rwhron/kernel/bigbox.html
^ permalink raw reply [flat|nested] 7+ messages in thread* Re: 82540EM very slow on 2.6.0-test[45]
2003-09-10 23:35 rwhron
@ 2003-09-14 17:23 ` Florian Zwoch
0 siblings, 0 replies; 7+ messages in thread
From: Florian Zwoch @ 2003-09-14 17:23 UTC (permalink / raw)
To: netdev
rwhron@earthlink.net wrote:
> ftp'ing a multi-megabyte file gives about 16-20k/second
> throughput. I first noticed this on 2.6.0-test4, but
> the slowness may have existed longer. The destination
> machine was running Solaris 8.
>
same behaviour confimed here. test5 and test4 (can not confirm on
earlier). both suffer from real bad network send performance on the
82540EM Gigabit Ethernet Controller (rev 02).
i did not test ftp but scp suffers from exactly the same mentioned
above. scp from this device resulted in about 80k/s to a local linux
2.4.x machine. scp to this device gives about 4.5mb/s.
samba copy between the two machines is fast in both directions.
irc dcc protocol stalls down to about 1k/s (host specific?).
nothing has changed between a normal operating 2.4.20 kernel. i suppose
something is broken atm. i did not set up any specific duplex mode, but
it is detected as 100 mbps full duplex - as expected (like the 2.4 kernel).
maybe someone can look into this?
--
Florian Zwoch
^ permalink raw reply [flat|nested] 7+ messages in thread
end of thread, other threads:[~2003-09-14 17:23 UTC | newest]
Thread overview: 7+ messages (download: mbox.gz follow: Atom feed
-- links below jump to the message on this page --
2003-09-11 1:14 82540EM very slow on 2.6.0-test[45] rwhron
-- strict thread matches above, loose matches on Subject: below --
2003-09-11 21:40 Feldman, Scott
2003-09-11 22:19 ` Ben Greear
2003-09-11 21:06 rwhron
2003-09-11 0:28 Feldman, Scott
2003-09-10 23:35 rwhron
2003-09-14 17:23 ` Florian Zwoch
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).