28 Jul
2006
28 Jul
'06
2:02 a.m.
der Mouse wrote:
Concidering that 1MB (Now, I assume you mean byte, or don't know what SI
means) is very close to the 10Mbit limit of 1.2Mbytes/s, that gives the
view that there'a approx 12.5% protocol overhead on network transmissions.
Please correct me if I am wrong, thx.
A
"300MB" file takes up how much space in memory,
If you load the whole thing? 300MB. Plus whatever overhead the OS
imposes (eg, page table entries to map the space).
and how much space on disk?
Assuming it's not sparse? 300MB. Plus whatever overhead the
filesystem imposes (eg, inode and indirect blocks).
Time to send it over a 100Mbit line? 25.165824 seconds, plus comm
overhead - probably more like 30 seconds. (This is where metric
measurement for line speeds versus binary measurement for aggregate
data storage needs care. Perhaps fortunately, you rarely get raw data
rate out of real protocols; my rule of thumb is to expect 1MB/sec out
of a nominally 10Mbit/sec line.)
/~\ The ASCII der Mouse
\ / Ribbon Campaign
X Against HTML mouse at rodents.montreal.qc.ca
/ \ Email! 7D C8 61 52 5D E7 2D 39 4E F1 31 3E E8 B3 27 4B
--
The real problem with C++ for kernel modules is: the language just sucks.
-- Linus Torvalds