Messages in this thread |  | | Date | Sat, 4 Nov 2000 12:11:11 -0800 (PST) | From | dean gaudet <> | Subject | Re: [PATCH] Re: Negative scalability by removal of lock_kernel()?(Was:Strange performance behavior of 2.4.0-test9) |
| |
On Sat, 4 Nov 2000, Andrew Morton wrote:
> Dean, > > neither flock() nor fcntl() serialisation are effective > on linux 2.2 or linux 2.4.
i have to admit the last time i timed any of the methods on linux was in 2.0.x days. thanks for the updated data!
> For kernel 2.2 I recommend that Apache consider using > sysv semaphores for serialisation. They use wake-one.
sysv semaphores have a very unfortunate negative feature -- if the admin kill -9's the server (impatient admins do this all the time) then you end up leaving a semaphore lying around. sysvsem don't have the usual unix unlink semantics. actually flock has the same problem... which is why i generally preferred fcntl whenever it was a performance wash, as it was back in 2.0.x days.
however given the vast performance difference i think it warrants the change. i'll include your results with the commit.
> For kernel 2.4 I recommend that Apache use unserialised > accept.
per linus' request i'll unserialise 2.2 as well.
i'll leave 2.0.x settings alone.
(oh yeah, and compile-time only detection.)
-dean
- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.kernel.org Please read the FAQ at http://www.tux.org/lkml/
|  |