Bug 4615
| Summary: | Modem connection stalls out. | ||
|---|---|---|---|
| Product: | Drivers | Reporter: | Alan Grimes (agrimes) |
| Component: | Serial | Assignee: | Russell King (rmk) |
| Status: | REJECTED UNREPRODUCIBLE | ||
| Severity: | high | ||
| Priority: | P2 | ||
| Hardware: | i386 | ||
| OS: | Linux | ||
| Kernel Version: | 2.6.0 through 2.6.12-rc5 (all inclusive) | Subsystem: | |
| Regression: | --- | Bisected commit-id: | |
| Attachments: | The boring DMESG output. | ||
The bug is reproducable in 2.6.12-rc5 The modem will stall out as soon as you put any non-trivial load on it, eg attempting to pull a medium-large sized package from CVS or visiting a webpage with many graphics... This bug is seriously diminishing my quality of life. I'm going to have to upgrade to Windows XP soon if this isn't fixed. The only other part of the system that exhibits a similar failure mode is OpenGL graphics via DRI... (I have an ATI R128 ) Games will stall out randomly for multiples of exactly ten seconds. It is possible that whatever kernel plumbing is shared between the serial port and the DRI infrastructure is the culprit. Rarely, the modem will hang from anywhere from 17 to 51 seconds as recorded by ping, using the terminal server at my ISP as the other end... (normal ping time is 0.1 seconds..) Please attach the entire kernel messages - preferably the output of dmesg after the problem has been noticed. Created attachment 5133 [details]
The boring DMESG output.
Earlier kernel versions, around 2.6.6 and earlier used to panic at the time of
the modem stall... Kernels 2.6.10 and later have been completely silent about
any issues.
The only reliable feedback I get from the bug, asside from its obvious symptoms,
is through ping...
Here is a typical output:
64 bytes from 10.65.28.26: icmp_seq=296 ttl=255 time=2552 ms
64 bytes from 10.65.28.26: icmp_seq=297 ttl=255 time=1561 ms
64 bytes from 10.65.28.26: icmp_seq=298 ttl=255 time=567 ms
64 bytes from 10.65.28.26: icmp_seq=299 ttl=255 time=137 ms
64 bytes from 10.65.28.26: icmp_seq=300 ttl=255 time=484 ms # Hmm, exactly 5
## minutes, though I've seen it quit after only 10 seconds...)
ping: sendmsg: No buffer space available
ping: sendmsg: No buffer space available
ping: sendmsg: No buffer space available
ping: sendmsg: No buffer space available
ping: sendmsg: No buffer space available
ping: sendmsg: No buffer space available
## It would have continued repeating this message indefinitely...
## Note: many more iterations have been removed from this report!!! =P
## Below is what happens when I manually disconnect the modem by sending
## the break signal to the dialer.
ping: sendmsg: Network is unreachable
ping: sendmsg: Network is unreachable
ping: sendmsg: Network is unreachable
ping: sendmsg: Network is unreachable
--- 10.65.28.26 ping statistics ---
337 packets transmitted, 300 received, 10% packet loss, time 35529
5ms
rtt min/avg/max/mdev = 122.973/687.037/6298.163/1093.624 ms, pipe
7
###################################
After power cycling the modem here's what the dialer does:
leenooks ~ # wvdial
--> WvDial: Internet dialer version 1.54.0
--> Initializing modem.
--> Sending: ATZ
--> Sending: ATQ0
--> Re-Sending: ATZ
### the dialer is hung and will report that the modem is not responding in a
### few seconds...
### At this point I could ctrl-break the dialer and try again,
### However, this would be entirely unproductive as I'd get the same mesage
### each and every time.
### Only by allowing it to complete its cycle, will it return the modem to
### functionality. I suspect that the dialer sends an IOCTL or something to the
### driver which clears the fault...
--> Modem not responding.
leenooks ~ # wvdial
--> WvDial: Internet dialer version 1.54.0
--> Initializing modem.
--> Sending: ATZ
ATZ
OK
--> Sending: AT&F&D2&C1X4V1Q0S7=70W2\N3&K3S11=60
AT&F&D2&C1X4V1Q0S7=70W2\N3&K3S11=60
OK
--> Modem initialized.
--> Sending: ATDT7038298111
--> Waiting for carrier.
ATDT7038298111
CONNECT 49333
--> Carrier detected. Waiting for prompt.
** Ascend TNT2.LNHVA.MD.RCN.NET Terminal Server **
Login:
--> Looks like a login prompt.
--> Sending: alangrimes
alangrimes
Password:
--> Looks like a password prompt.
--> Sending: (password)
Entering PPP Session.
IP address is 66.44.56.212
MTU is 1006.
--> Looks like a welcome message.
--> Starting pppd at Tue Jun 7 04:58:30 2005
--> pid of pppd: 19733
--> Using interface ppp0
--> local IP address 66.44.56.212
--> remote IP address 10.65.28.27
--> primary DNS address 207.172.3.10
--> secondary DNS address 207.172.3.11
Having been utterly fed up with Linux, I plugged the same modem into the back of my Athlon 800 running BeOS. THE DAMN THING WORKS LIKE A DREAM!!!! I can load three websites at once and download at the same time and the modem is ROCK SOLID!!! My fone line isn't perfect and it will drop on occasion (loss of carrier) but host--modem communication is not an issue at all. and oh god, is this 5 year old dialer program pure bliss!!! I don't have to muck about in /etc... I don't have to su to root. It connects with barely two clicks on my trackball.. It provides realtimes statistics in a pleasant, easy-to-read GUI... it connects IMMEDIATELY, on the first shot. If only I had a Javascript/CSS web-browser and I'd never need to go back... =P TBH I've no idea what's going on here. I don't think its a serial problem
though, since serial will not cause the sendmsg errors. I've asked the
networking folk to comment, and they've come back with:
> It's probably not running low of system memory. However, it might
> be running out of things such as routing cache entries.
>
> Check the dmesg output, it might have a clue on what went wrong.
Sorry.
In addition, I notice that you say older kernels paniced, though you don't say how. Do you really expect me to guess what the panic was? Bug author has lost interest in Linux. I just received a link to my earlier bug-report, # 1893. Of interest is the date it was submitted... =(((( I'm seeing a similar thing with 2.6.17-rc1 and a ppp connection over
ssh
.
Earlier kernels (at least linux-2.6.14-rc4) did not show this with the
exactly same
settings
How it
happens
:
- open up the ppp connection over
ssh.
- stress it a bit with
samba
- after a few minutes, pinging the remote end
gives
ping: sendmsg: No buffer space
available
and I have to re-establish the
connection
The ssh connection seems solid afaict. Also, with bare ssh connetion,
no
problems occur even under load. The ppp connection seems prone to
hang
especially with SMB traffic (don't know why
.)
In dmesg, there seems to be nothing relevant. /proc/slabinfo doesn't seem
to
to have anything alerting in
it.
The underlying connection is ADSL (8/1Mbit). The driver is eepro100. ppp
is
ppp-2.4.3-6.2.
1
.
ppp_deflate is in
use
:
ppp_deflate 5536
3
zlib_deflate 18360 1 ppp_
deflate
bsd_comp 5312
0
ppp_async 9664
2
crc_ccitt 1952 1 ppp_
async
ppp_generic 20468 11 ppp_deflate,bsd_comp,ppp_async
|
Distribution: Gentoo Hardware Environment: Dual K7. Software Environment: Wvdial/pppd Problem Description: My dialup internet connection will simply STALL.... If I ping the terminal server on the other end of the ppp connection, it will usually come in at around 103 msec, or no higher than 5,000 msec when I'm surfing the net. However, with no output to the xterm that is running the dialer, the connection will simply stop cold and Ping will report that it has no buffer space. The stalling is frequently associated with attempting to go to certain websites with no obvious pattern. In general, uploading any non-negilgable ammount of data tends to break it such as an e-mail over 8k or so. On one occasion it actually recovered from this state (it usually doesn't), and ping reported a time of a little over 51 seconds for the first return packets... This bug was reported earlier. I submitted a patch through bugzilla which I thought had solved the problem, well the problem is back. =( The patch does seem to reduce the frequency and severity of the problem somewhat but it's still there. As I mentioned when I closed the earlier bug report, I'd be back if it comes up again... The dialer program, Wvdial, behaves strangely too. ######################################### leenooks ~ # wvdial --> WvDial: Internet dialer version 1.54.0 --> Initializing modem. --> Sending: ATZ ATZ OK --> Sending: AT&F&D2&C1X4V1Q0S7=70W2\N3&K3S11=50 AT&F&D2&C1X4V1Q0S7=70W2\N3&K3S11=50 OK --> Modem initialized. --> Sending: ATDT7038298111 --> Waiting for carrier. ATDT7038298111 CONNECT 48000 --> Carrier detected. Waiting for prompt. ** Ascend TNT2.LNHVA.MD.RCN.NET Terminal Server ** Login: Login: --> Looks like a login prompt. --> Sending: alangrimes alangrimes Password: --> Looks like a password prompt. --> Sending: (password) Entering PPP Session. IP address is 66.44.57.81 MTU is 1006. --> Looks like a welcome message. --> Starting pppd at Wed May 11 14:16:50 2005 --> pid of pppd: 21778 --> Using interface ppp0 --> Disconnecting at Wed May 11 14:17:13 2005 --> The PPP daemon has died: A modem hung up the phone (exit code = 16) --> man pppd explains pppd error codes in more detail. --> Try again and look into /var/log/messages and the wvdial and pppd man pages for more information. --> Auto Reconnect will be attempted in 5 seconds --> Initializing modem. --> Sending: ATZ NO CARRIER --> Sending: ATQ0 ATQ0 OK --> Re-Sending: ATZ ATZ OK --> Initializing modem. --> Sending: ATZ ATZ OK --> Sending: AT&F&D2&C1X4V1Q0S7=70W2\N3&K3S11=50 AT&F&D2&C1X4V1Q0S7=70W2\N3&K3S11=50 OK --> Modem initialized. --> Initializing modem. --> Sending: ATZ ATZ OK --> Sending: AT&F&D2&C1X4V1Q0S7=70W2\N3&K3S11=50 AT&F&D2&C1X4V1Q0S7=70W2\N3&K3S11=50 OK --> Modem initialized. --> Sending: ATDT7038298111 --> Waiting for carrier. ATDT7038298111 CONNECT 49333 --> Carrier detected. Waiting for prompt. ** Ascend TNT3.LNHVA.MD.RCN.NET Terminal Server ** Login: --> Looks like a login prompt. --> Sending: alangrimes alangrimes Password: --> Looks like a password prompt. --> Sending: (password) Entering PPP Session. IP address is 66.44.58.13 MTU is 1006. --> Looks like a welcome message. --> Starting pppd at Wed May 11 14:17:48 2005 --> pid of pppd: 21786 --> Using interface ppp0 --> local IP address 66.44.58.13 --> remote IP address 10.65.28.28 --> primary DNS address 207.172.3.10 --> secondary DNS address 207.172.3.11 Caught signal #2! Attempting to exit gracefully... --> Terminating on signal 15 --> Connect time 0.8 minutes. ####################################### Ofcourse, the reason I sent it the break signal was because the connection had stalled... Ofcourse this could be a hardware problem but then linux offers utterly no tools that could possibly help me determine wheather that is actually the case. Steps to reproduce: Just try to use Linux version 2.6.x with an external serial modem. =\