lkml.org 
[lkml]   [1999]   [Sep]   [16]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
 
Messages in this thread
/
Date
From
SubjectRe: > 15,000 Simultaneous Connections
On Wed, 15 Sep 1999, Stephen C. Tweedie wrote:

> For sockets, look at sock_wake_async: it already does a first pass at
> eliminating redundant signals.

I'm obviously missing something but it looks like sock_wake_async
always queues/sends a signal if SO_WAITDATA isn't set and that is
only set if something blocks on the socket. Event driven code
wouldn't be blocking on the socket. Then looking at the tcp code
it seems to call wake_async for each packet. This is fine for
a traditional SIGIO but with queued signals you have a situation
where increasing load causes a needless increase in overhead.

Mike

--
Failure isn't an option - it's built in to Windows
.----------------------------------------------------------------------.
| Mike Jagdis | Internet: mailto:mike@roan.co.uk |
| Roan Technology Ltd. | |
| 2 Markham Mews, Broad Street | Telephone: +44 118 989 0403 |
| Wokingham ENGLAND | Fax: +44 118 989 1195 |
`----------------------------------------------------------------------'


-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.rutgers.edu
Please read the FAQ at http://www.tux.org/lkml/

\
 
 \ /
  Last update: 2005-03-22 13:54    [W:0.108 / U:0.044 seconds]
©2003-2020 Jasper Spaans|hosted at Digital Ocean and TransIP|Read the blog|Advertise on this site