Messages in this thread | | | Date | Fri, 19 Nov 1999 16:01:56 +0100 | From | Manfred Spraul <> | Subject | Re: [Patch] shm bug introduced with pagecache in 2.3.11 |
| |
Richard Guenther wrote: > > We are implementing a real-time audio-processing tool which will > support tree-like filter-chains, each filter beeing a thread > and mmaping parts of a global swap-file (the filters passing > data (as pointers to a mmapped area) via sockets). > is your application really disk I/O bound? I would guess that - most of that global swap-file is always swapped in. - "real-time filtering" sounds like the application could be CPU bound?
My test app is disk-io bound, I defeat the cache with a completely random IO pattern , and I use > 60 threads/processes.
With 16 threads/processes, the difference is only 15%.
-- Manfred
- 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/
| |