Blaisorblade wrote:
On Thursday 16 June 2005 02:27, Dan Lund wrote:
I'm having a problem that I need a little advice on.
I'm running a guest kernel 2.4.31 on a 2.6.11 host with the skas3v8
patch installed.
The host is a IBM xSeries 335 with a 2.8 Ghz dual processor, 4Gb of RAM
installed.
I'm running a tmpfs of 256mb, and a memlimit of 256mb on the instance.
Here's the situation, when I scp across to the machine a large number of
files "scp -r /root/* [EMAIL PROTECTED]:/root" it seems to hang for a little
bit... the console is totally unresponsive for 10 or so seconds at a
time. (sometimes 1 - 2 mins) and the scp transfer is stalled.
The thing that bothers me is that the bridge I've created has 397
overruns out of 157585 RX and 692311 TX packets.
I.e.? You mean the net is under-used?
Using synchronous UBD (CONFIG_BLK_DEV_UBD_SYNC)? That would generate the
slowdown.
Turning it off and replacing ubd0= with ubd0s= gives the same safety without
this big artificial slowdown (search for "bonnie++" in the archives to find a
deep discussion of this issue).
On my homepage, the recent -bs2 prereleases contain the backport of the fix I
included in 2.6.
Thank you,
I'll check that out tomorrow when I get in, and turn off synchronous
UBD. Would this pause the console itself, also?
-------------------------------------------------------
SF.Net email is sponsored by: Discover Easy Linux Migration Strategies
from IBM. Find simple to follow Roadmaps, straightforward articles,
informative Webcasts and more! Get everything you need to get up to
speed, fast. http://ads.osdn.com/?ad_id=7477&alloc_id=16492&op=click
_______________________________________________
User-mode-linux-user mailing list
User-mode-linux-user@lists.sourceforge.net
https://lists.sourceforge.net/lists/listinfo/user-mode-linux-user
