uses readtcp() to gather data from the network; readtcp() uses select(),
with a timeout of 35 seconds. The problem with this is that if you
connect to a TCP server, send two bytes of data, then just pause, the
server will remain blocked in readtcp() for up to 35 seconds, which is
sort of a long time. If you keep doing this every 35 seconds, you can
keep the server occupied indefinitely.
To fix this, I modified readtcp() (and its cousin, readunix() in svc_unix.c)
to monitor all service transport handles instead of just the current socket.
This allows the server to keep handling new connections that arrive while
readtcp() is running. This prevents one client from potentially monopolizing
a server.
Also, while I was here, I fixed a bug in the timeout calculations. Someone
attempted to adjust the timeout so that if select() returned EINTR and the
loop was restarted, the timeout would be reduced so that rather than waiting
for another 35 seconds, you could never wait for more than 35 seconds total.
Unfortunately, the calculation was wrong, and the timeout could expire much
sooner than 35 seconds.
output for local users. FTP protocol RFC also says that 'ls' output is
not machine-readable. "always UTC" still possible with TZ= in ftpd
environment by price of having UTC in log files too.
Fix INTERNAL_LS to sense new /etc/localtime after chroot
available. The per-cpu variable ss_tpr has been replaced by ss_eflags.
This reduced the number of interrupts sent to the wrong CPU, due to
the cpu having the global lock being inside a critical region.
Remove some unneeded manipulation of tpr register in mplock.s.
Adjust code in mplock.s to be aware of variables on the stack being
destroyed by MPgetlock if GRAB_LOPRIO is defined.
update of cpu usage as shown by top when one process is cpu bound
(no system calls) while the system is otherwise idle (except for top).
Don't attempt to switch to the BSP in boot(). If the system was idle when
an interrupt caused a panic, this won't work. Instead, switch to the BSP
in cpu_reset.
Remove some spurious forward_statclock/forward_hardclock warnings.
syndrome avoidance. The combination of SWS avoidance and ack-every-other
causes low throughput if the block size divided by the MSS is odd (which
is true with the default block size and MSS).
Turning on TCP_NODELAY disables the Nagle algorithm and sender SWS avoidance.
The rdump request/response protocol can not invoke Nagle and cannot cause
SWS, so this has no negative effects.
Tor Egge
Brian Somers
Bill Paul
Guido van Rooij
Wolfram Schneider
Peter Dufault
Dmitrij Tejblum
Joseph Koshy
Philippe Charnier
Julian Elischer
John Birrell
Andrey A. Chernov
Jonathan M. Bresler
Justin T. Gibbs
Bruce Evans
Poul-Henning Kamp
Søren Schmidt
Bill Fenner
John Dyson