FAQ Search Today's Posts Mark Forums Read
» Video Reviews

» Linux Archive

Linux-archive is a website aiming to archive linux email lists and to make them easily accessible for linux users/developers.


» Sponsor

» Partners

» Sponsor

Go Back   Linux Archive > Redhat > Fedora User

 
 
LinkBack Thread Tools
 
Old 09-08-2012, 05:07 PM
JD
 
Default I/O or CPU bandwidth issue or wget issue or perhaps isp???

fc16 (latest updates) + wget-1.12-4.fc16.i686, and system load
negligible when I start wget.

CPU is Athlon64 3700+ (but I run i686 kernel/apps).

Sometimes, wget chokes


25% [+++++=====> ] 1,000,855,688 --.-K/s
eta 27m 57s


even though I can actually start another download in a a separate terminal)
of the same file from the same server with no delays, which in turn after
a while chokes as above. The download speeds fluctuate as low as a few
hundred
Kbytes/s to 2.70 Mbytes/s. It usually chokes when it reaches the high
end of

download speeds.

I have measured my disk i/o throughput using dd from one drive (on the
internal
eide bus) to the external eSATA drive connected to system via a dual
port eSATA cardbus.

The speed ranges from 20 to 27 megabytes/s.

The wget download goes to the external eSATA drive /dev/sdb, on
partition sdb5 (7200 rpm).


So, I am at a total loss with the reason why this is happening (and
frequently within the last few days).


Also, during wget runs, iostat -chm 5

avg-cpu: %user %nice %system %iowait %steal %idle
15.64 0.00 14.80 13.74 0.00 55.81

Device: tps MB_read/s MB_wrtn/s MB_read MB_wrtn
sdb 7.82 0.00 1.94 0 9
sdb1 0.63 0.00 0.01 0 0
sdb2 0.00 0.00 0.00 0 0
sdb3 2.54 0.00 0.04 0 0
sdb4 0.00 0.00 0.00 0 0
sdb5 4.65 0.00 1.89 0 8

shows no obvious bottlenecks during 2.2 mbyte/s download speed snap shot.

Does anyone have an idea what I should be monitoring in order to see
the event that is leading to this?
As I stated above, it does not seem to be the server because I can
immediately start another transfer of same file from same server without
seeing any delays.
By the way, I am not ruling out the ISP as the cause of the hickup.

Finally, ultimate reason I am posting this issue is because wget seems
to remain
in the chocked state and does not simply close the connection and
immediately open

a new one. Yesterday, it remained in the chocked state all night, until I
interrupted wget and restarted the download (with -c of course) in the
morning.




--
users mailing list
users@lists.fedoraproject.org
To unsubscribe or change subscription options:
https://admin.fedoraproject.org/mailman/listinfo/users
Guidelines: http://fedoraproject.org/wiki/Mailing_list_guidelines
Have a question? Ask away: http://ask.fedoraproject.org
 
Old 09-10-2012, 06:57 PM
Rick Stevens
 
Default I/O or CPU bandwidth issue or wget issue or perhaps isp???

On 09/08/2012 10:07 AM, JD uttered this comment:

fc16 (latest updates) + wget-1.12-4.fc16.i686, and system load
negligible when I start wget.
CPU is Athlon64 3700+ (but I run i686 kernel/apps).

Sometimes, wget chokes


25% [+++++=====> ] 1,000,855,688 --.-K/s
eta 27m 57s

even though I can actually start another download in a a separate terminal)
of the same file from the same server with no delays, which in turn after
a while chokes as above. The download speeds fluctuate as low as a few
hundred
Kbytes/s to 2.70 Mbytes/s. It usually chokes when it reaches the high
end of
download speeds.

I have measured my disk i/o throughput using dd from one drive (on the
internal
eide bus) to the external eSATA drive connected to system via a dual
port eSATA cardbus.
The speed ranges from 20 to 27 megabytes/s.

The wget download goes to the external eSATA drive /dev/sdb, on
partition sdb5 (7200 rpm).

So, I am at a total loss with the reason why this is happening (and
frequently within the last few days).

Also, during wget runs, iostat -chm 5

avg-cpu: %user %nice %system %iowait %steal %idle
15.64 0.00 14.80 13.74 0.00 55.81

Device: tps MB_read/s MB_wrtn/s MB_read MB_wrtn
sdb 7.82 0.00 1.94 0 9
sdb1 0.63 0.00 0.01 0 0
sdb2 0.00 0.00 0.00 0 0
sdb3 2.54 0.00 0.04 0 0
sdb4 0.00 0.00 0.00 0 0
sdb5 4.65 0.00 1.89 0 8

shows no obvious bottlenecks during 2.2 mbyte/s download speed snap shot.

Does anyone have an idea what I should be monitoring in order to see
the event that is leading to this?
As I stated above, it does not seem to be the server because I can
immediately start another transfer of same file from same server without
seeing any delays.
By the way, I am not ruling out the ISP as the cause of the hickup.

Finally, ultimate reason I am posting this issue is because wget seems
to remain
in the chocked state and does not simply close the connection and
immediately open
a new one. Yesterday, it remained in the chocked state all night, until I
interrupted wget and restarted the download (with -c of course) in the
morning.


I've run into a similar choke scenario when using iptables. I haven't
bothered sorting out which of my rules causes the issue. When it
happens, I shut down iptables (I'm behind a hardware firewall anyway),
complete the download and turn iptables back on. Might be worth a look.
----------------------------------------------------------------------
- Rick Stevens, Systems Engineer, AllDigital ricks@alldigital.com -
- AIM/Skype: therps2 ICQ: 22643734 Yahoo: origrps2 -
- -
- Fear is finding a ".vbs" script in your Inbox -
----------------------------------------------------------------------
--
users mailing list
users@lists.fedoraproject.org
To unsubscribe or change subscription options:
https://admin.fedoraproject.org/mailman/listinfo/users
Guidelines: http://fedoraproject.org/wiki/Mailing_list_guidelines
Have a question? Ask away: http://ask.fedoraproject.org
 

Thread Tools




All times are GMT. The time now is 12:02 AM.

VBulletin, Copyright ©2000 - 2014, Jelsoft Enterprises Ltd.
Content Relevant URLs by vBSEO ©2007, Crawlability, Inc.
Copyright 2007 - 2008, www.linux-archive.org