Hi,
I've noticed that on a recent 8-STABLE/amd64, scp(1) appears to be
stalling very frequently. This is the output from a "scp -v -v"
of a 300Mb file from a local to a remote within an internal network:
[.. authentication negotiation ...]
debug2: channel 0: open confirm rwindow 0 rmax 32768
debug2: channel 0: rcvd adjust 131072
debug2: channel_input_status_confirm: type 99 id 0
debug2: exec request accepted on channel 0
Sending file modes: C0700 367085370 file1
file1 0% 192KB 140.0KB/s 42:39 ETAdebug2: channel 0: rcvd adjust
65593
file1 0% 256KB 78.2KB/s - stalled -debug2: channel 0: rcvd adjust
81920
file1 0% 336KB 41.6KB/s - stalled -debug2: channel 0: rcvd adjust
81920
file1 0% 416KB 26.9KB/s - stalled -debug2: channel 0: rcvd adjust
81920
file1 0% 496KB 17.1KB/s - stalled -debug2: channel 0: rcvd adjust
81920
file1 0% 576KB 12.4KB/s - stalled -debug2: channel 0: rcvd adjust
81920
file1 0% 656KB 11.3KB/s - stalled -debug2: channel 0: rcvd adjust
81920
file1 0% 736KB 9.7KB/s - stalled -debug2: channel 0: rcvd adjust
81920
file1 0% 816KB 9.9KB/s - stalled -debug2: channel 0: rcvd adjust
81920
file1 0% 896KB 9.0KB/s - stalled -debug2: channel 0: rcvd adjust
81920
file1 0% 976KB 9.5KB/s - stalled -debug2: channel 0: rcvd adjust
81920
/etc/ssh/ssh_config is untouched. Oddly enough a scp of a remote file
to the local machine is blindingly fast.
Does anyone know what's happening here? Any tips on how to track down
what the problem is? The network config appears to be fine - fetch(1) will
have downloads speeds of up to 300KB/s.
Cheers.
--
Jonathan Chen <jonc@chen.org.nz>
----------------------------------------------------------------------
"With sufficient thrust, pigs fly just fine. However, this is not
necessarily
a good idea. It is hard to be sure where they are going to land, and it
could be dangerous sitting under them as they fly overhead." -- RFC 1925
At 02:36 PM 2/2/2010, Jonathan Chen wrote:>Hi, > >I've noticed that on a recent 8-STABLE/amd64, scp(1) appears to be >stalling very frequently. This is the output from a "scp -v -v" >of a 300Mb file from a local to a remote within an internal network:Hi, Is it on the same ethernet segment, or does it go through a router(s) and is the path asymmetric? I noticed similar symptoms on a jailed box where the round trip was asymmetric and an intermediary router was generating a lot of ICMP redirects that were ignored by the sending host. ---Mike -------------------------------------------------------------------- Mike Tancsa, tel +1 519 651 3400 Sentex Communications, mike@sentex.net Providing Internet since 1994 www.sentex.net Cambridge, Ontario Canada www.sentex.net/mike
Jonathan Chen
2010-Feb-03 22:53 UTC
if_bge upload stalls repeatedly (Was: 8-STABLE outgoing scp stalling frequently)
On Tue, Feb 02, 2010 at 11:20:29PM +0200, Nikos Ntarmos wrote:> On Wed, Feb 03, 2010 at 08:36:16AM +1300, Jonathan Chen wrote: > > Hi, > > > > I've noticed that on a recent 8-STABLE/amd64, scp(1) appears to be > > stalling very frequently. This is the output from a "scp -v -v" > > of a 300Mb file from a local to a remote within an internal network:[...]> > Does anyone know what's happening here? Any tips on how to track down > > what the problem is? The network config appears to be fine - fetch(1) will > > have downloads speeds of up to 300KB/s. > > But how about upload speeds? It seems that's where scp is suffering as > well.This is the obvious test that I should have done; and you're hit the nail on the head. bge(4) on 8-STABLE (csup'd 4-Feb-2010) has a very bad upload speed. I've just tried using ftp to transfer some files: Upload speed: starts at 63 KB/s, falls rapidly before stalling. Download speeds: starts at 9 MB/s, increasing slightly before completing. Device from dmesg: bge0: <Broadcom NetXtreme Gigabit Ethernet Controller, ASIC rev. 0x00a002> mem 0xf1bf0000-0xf1bfffff irq 17 at device 0.0 on pci9 -- Jonathan Chen <jonc@chen.org.nz> ---------------------------------------------------------------------- "I don't want to achive immortality through my works.. I want to achieve it through not dying" - Woody Allen
On Tue, Feb 2, 2010 at 8:36 PM, Jonathan Chen <jonc@chen.org.nz> wrote:> Hi, > > I've noticed that on a recent 8-STABLE/amd64, scp(1) appears to be > stalling very frequently.I've got the same problem since I've upgraded from 7.2 to 8-stable (32bit). My NIC is a vge(4), with txsum and rxsum disabled. dmesg: vge0: <VIA Networking Gigabit Ethernet> port 0xfc00-0xfcff mem 0xfdfff000-0xfdfff0ff irq 18 at device 14.0 on pci0 I can't SCP big file too because my transferts stall and abord. Regards, Olivier