[seL4] Re: seL4 vs QNX and Linux benchmarks

19 Apr 2024


      On 4/19/24 02:45, Gernot Heiser via Devel wrote:
...
On 19 Apr 2024, at 14:00, Andrew Warkentin  wrote:
...
Somehow I said Send()/Recv()/Reply() when I meant Call()/Recv()/Send()
(MCS of course doesn't even have a distinct Reply() function).
the correct syscall to use is ReplyWait():
Recv(…);
while (1) {
  ReplyWait(…);
}
Es per my blog: Send() and Recv() should only ever be used in initialisation and exception handling.
...
The QNX/Linux equivalent is:
int main()
{
   char buf[100];
   int f = open("/dev/null", O_WRONLY);
   int i;
   for (i = 0; i < 10; i++) {
       uint64_t start = __rdtsc();
       uint64_t end;
       int j;
       for (j = 0; j < 10000; j++){
           if (write(f, buf, 100) != 100){
               printf("cannot write\n");
               exit(1);
           }
       }
       end = __rdtsc();
       printf("cycles: %u\n", end - start);
   }
}
so you’re using standard I/O to /dev/null
My Posix is a bit rusty, but this should be buffered in the library (i.e. most calls will *not* result in a system call).
Not true on any *nix I am familiar with.  The buffered version is fwrite().
write() always results in a real system call.

That said, I know nothing about QNX other than it being based on a microkernel.
It might be that QNX _does_ implement userspace buffering for write() and avoid
the system call overhead in this benchmark.
-- 
Sincerely,
Demi Marie Obenour (she/her/hers)