Messages in this thread | | | Date | Thu, 29 Jul 1999 11:22:58 -0700 (PDT) | From | Gerald Aigner <> | Subject | Re: (disk/cpu) kernel performance problem |
| |
On Thu, 29 Jul 1999, Stephen C. Tweedie wrote:
> Hi, > > On Wed, 28 Jul 1999 16:12:59 -0700 (PDT), Gerald Aigner > <aigner@stanford.edu> said: > > > I just profiled the 2.3.11 kernel and around 37% of the time was spend in > > file_read_actor. By looking at the function I discovered that this > > function is responsible for copying data from the kernel to the user > > space. > > > Here the basic performance of this function: > > data transfered: 1.8 GB > > total execution time of the function: 23 seconds > > --------------------------------------------------- > > throughput per second: 78 MB/sec > > > This means that the Linux memory copy function used for copying > > disk data achieves a memory bandwidth of approximately 156 MB/sec > > on a system with a 66 MHz system bus. > > Remember that you are doing disk IO here too so there is also 78MB/sec > of bus traffic going between the scsi controller and main memory. > That's also going to reduce the available bandwidth. Try doing a copy > purely out of cache to see what the real memory bandwidth available via > the filesystem is. > The total execution time of a cached loading is 20 seconds.
This brings the throughput to 90 MB/second and therefore the memory bandwidth to 180 MB/second (the kernel is 2.3.11, and the reading is done in 10 MB chunks, in two threads).
-Gerald
- 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/
| |