The bt shows you are in cpu_idle but what is the full trace. If i had
to bet i would say that this is related to power management issue or
some another interrupt that the OS is waiting for that does not
arrive.
2011/3/19 Shachar Shemesh shac...@shemesh.biz:
In 2009 I won a SheevaPlug as part of
OK i lost the bet :)
2011/3/19 Shachar Shemesh shac...@shemesh.biz:
On 19/03/11 14:42, Shachar Shemesh wrote:
Now I'm stuck for idea as to what to try next. Anyone?
The problem turned out to be that the inittab was running everything it had
to do, and was done. It closed the serial line
Alex Hi,
Looks like in 2.4 your apps spent most of the time waiting for data
(select) - and in 2.6 they spend more time doing I/O (writev). I
assume this is network I/O - but it might be disk. If it's network,
check for things that might worsen network I/O: MTU / Csum offloads /
Net card driver +
Try to disable any daemons that might mess with interfaces/routing:
dhclient NetworkManager etc, try see if the problem goes away when
these daemons are down.
2010/1/3 Hetz Ben Hamo het...@gmail.com:
Hi,
Last time I asked about routing issue on a wifi connected machine.
Today I have noticed
Just out of curiousity: why do you care about the resulting assembly?
It's a strong indication that you are doing something wrong :)
I would try to set i to volatile or to an extern to trick the compiler
to drop the optimization (if the flags don't work).
--Aviv
2009/12/21 Shachar Shemesh
: c3 ret
looks like i was right!
On Mon, Dec 21, 2009 at 15:54, Shachar Shemesh shac...@shemesh.biz wrote:
Aviv Greenberg wrote:
Just out of curiousity: why do you care about the resulting assembly?
It's a strong indication that you are doing something wrong :)
First
Also, i tried grepping for loop and then negate all loop related params:
linux-gec2:~/projects/lu # gcc -c -O3 -fno-align-loops
-fno-move-loop-invariants -fno-peel-loops -fno-prefetch-loop-arrays
-fno-rerun-cse-after-loop -fno-reschedule-modulo-scheduled-loops
-fno-tree-loop-im
On Tue, Dec 1, 2009 at 18:12, Ilya A. Volynets-Evenbakh
i...@total-knowledge.com wrote:
Lev Olshvang wrote:
Something looks rather messed up, since your init function calls a
cleanup function.
Could it be some sort of stack corruption?
Not likely. Many times when an init function fails,
it seems that something failed while a module (lpg610) was
initializing, and cleanup was called. At some point during cleanup, an
access to invalid memory was attempted, cusing the oops. what is
lpg610, i searched using lxr got no results. Is this a standard
module?
On Tue, Dec 1, 2009 at 09:57,
Every incoming packet goes through input routing. The result of that
routing is either to receive the packet locally, drop, or forward it.
There is a hidden local routing table, that is used to do routing
for incoming packets. It is populated automatically (e.g when u add an
new local interface)
There are many services that does that. Just add the word api to
your google search. An example:
http://smart-ip.net/en/api/
The idea is not to scrape HTML but to query some web service and get a
parsable answer.
On 08/08/2009, diksbcseanbcsa sdbsd...@sdf.lonestar.org wrote:
Are there web
I think that the reason for installing PAE kernel as a default is
because the No Execute (aka NX bit) CPU feature is available only when
the CPU is configured to PAE mode. AFAIK the other OS from Redmond
also uses PAE by default (using the ntkrpamp image).
I don't know about performance
Hi Noam,
I recommend you contact Gilad Ben-Yosef (just google the name) - he is
a real pro, both on the technical side and on lecturing about Linux
Kerenl. I've been to some of his lectures, i really think he just
great - and on top he is a nice guy too.
I'm not affiliated to him on any level.
From what i understand - you have 3 network interfaces: one for media,
one for management and loopback.
Why don't you create 2 listeners (media+loopback) from the application
- such that only local connections or connections comming from the
media interface (but not the management) are received?
If you ping another destination during the hang - does it work?
If you ifdown and ifup the interfaces (wan + lan) on the router after
a hang - is it released?
an icmp packet is short so i don't think this is the case but: what is
the MTU on the lan/wan?
Also, use a tool like mtr
is wrong with the outgoing ping request packet.
Did you see any difference between a goog ping and bad ping packets?
On Wed, May 27, 2009 at 10:05, Erez D erez0...@gmail.com wrote:
On Wed, May 27, 2009 at 9:41 AM, Aviv Greenberg avivg...@gmail.com wrote:
If you ping another destination during
I totally agree! There is no shame of making a quick buck as long as
you're honest about it.
On Tue, May 12, 2009 at 12:56, Geoffrey Mendelson
geoffreymendel...@gmail.com wrote:
he said: please contact some...@activity
he didn't say: send your resume.
My experience with activity: if you tell
2009/3/16 Shachar Shemesh shac...@shemesh.biz:
Sorry, almost got it :-)
Didn't i say mind boggling routing rules? Told ya! :)
Shachar
--
Shachar Shemesh
Lingnu Open Source Consulting Ltd.
http://www.lingnu.com
___
Linux-il mailing list
My 2 cents: make sure that you have the latest BIOS installed. All pre
OS code relies on BIOS services to discover devices and read/write
data. funky BIOS is not something unheard of.
2009/3/16 Dvir Volk dvir...@gmail.com:
Can you try and boot from an image from:
Seems like you have a routing problem.
Say you have 1 box with 2 interfaces, having IP x and y.
When you try to ping or connect to either x or y, the routing table is
being consulted.
The answer of what is the route to x is Local - and it is treated
as loopback.
I don't think actual packets will
What is the server used for? What traffic is comming into the server
(small packets? full MTU?)? at what rate? How many RX descriptors is
your driver set for? Do you have 802.3X flow control enabled (both
ends)? Do you see any abnormal CPU usage when the packet drops occur?
But more
On Wed, Mar 11, 2009 at 13:49, Michael Green mishagr...@gmail.com wrote:
On Wed, Mar 11, 2009 at 11:36 AM, Aviv Greenberg avivg...@gmail.com wrote:
What is the server used for? What traffic is comming into the server
(small packets? full MTU?)? at what rate? How many RX descriptors is
your
How about google apps? It has secure pop+smtp+imap, has excellent web
interface, and can support many domain aliases. Ohh and it is free (up
to ~7Gb).
On Fri, Oct 10, 2008 at 23:05, Shlomi Fish [EMAIL PROTECTED] wrote:
Hi all!
Can anyone recommend email hosting (secure POP + SMTP) without an
On 16/07/2008, ronys [EMAIL PROTECTED] wrote:
Good question.
I may have something wrong when trying to install the module manually, since
putting in in /lib/modules/... and running depmod didn't work under reboot,
Verify the installation by trying to modprobe (instead of insmod) the
module.
Don't know about swik, but there is this site:
http://www.givemebackmygoogle.com/ - that is a google wrapper site
with many garbage searches removed.
On Wed, Aug 6, 2008 at 13:01, Erez D [EMAIL PROTECTED] wrote:
is there a way to make it permanent ? so i do not have to put -swik in every
search
Hi All,
I would like to share with you a great project called Satchmo
(http://www.satchmoproject.com/).
It's a shopping cart framework based on django / python. While my
forte is far far
from web development, i find this technology fascinating. so much that I helped
translate the project to
http://www.freesshd.com/
On 3/12/08, Gil Freund [EMAIL PROTECTED] wrote:
Hi,
I am looking for an SSHD implementation on Windows, prefreably one that
does not depend on an installation of cygwin or SFU, and will use
Windows authentication and command prompt.
Any ideas?
Thanks
Gil
I still fail to see how this is not an issue with IOAT - if you want to
DMA into the user buffer, you better have that pinned and locked doe the
duration of the DMA transfer.
I checked and you are right! there is pinning of the pages (
http://lxr.linux.no/linux/net/ipv4/tcp.c#L1158). But i
IOAT - its not a TCP offload engine. Intel's assumption is that the
CPU is wasting a lot of cycles to copy data (from kernel to user and
vv). IOAT is just a smart DMA engine that can move data (copy)
without wasting the main CPU cycles. There are more details (cpu
caching
Hello Ira,
You talked about many things
First off, Zero Copy I/O is enabled in Linux only using the sendfile
syscall. You also must have a network device that has Checksum Offload
(calculate ip/tcp csum and put it on the packet). The regular socket api
does not enable zero copy.
Interrupt
)
Aviv Greenberg
On 12/19/07, Dotan Shavit [EMAIL PROTECTED] wrote:
On Tuesday 18 December 2007, Oded Arbel wrote:
I can see that a lot of time is spent in the hard-IRQ region -
sometimes
more then all other regions together.
Lets look for more hints...
- Anything interesting in the logs
31 matches
Mail list logo