Neil Brown posted a patch couple days ago for this! http://thread.gmane.org/gmane.linux.nfs/58473 Regards, Malahal. Quentin Barnes [qbarnes@xxxxxxxxx] wrote: > If two (or more) processes are doing nothing more than writing to > the memory addresses of an mmapped shared file on an NFS mounted > file system, it results in the kernel scribbling WRITEs to the > server as fast as it can (1000s per second) even while no syscalls > are going on. > > The problems happens on NFS clients mounting NFSv3 or NFSv4. I've > reproduced this on the 3.11 kernel, and it happens as far back as > RHEL6 (2.6.32 based), however, it is not a problem on RHEL5 (2.6.18 > based). (All x86_64 systems.) I didn't try anything in between. > > I've created a self-contained program below that will demonstrate > the problem (call it "t1"). Assuming /mnt has an NFS file system: > > $ t1 /mnt/mynfsfile 1 # Fork 1 writer, kernel behaves normally > $ t1 /mnt/mynfsfile 2 # Fork 2 writers, kernel goes crazy WRITEing > > Just run "watch -d nfsstat" in another window while running the two > writer test and watch the WRITE count explode. > > I don't see anything particularly wrong with what the example code > is doing with its use of mmap. Is there anything undefined about > the code that would explain this behavior, or is this a NFS bug > that's really lived this long? > > Quentin > > > > #include <sys/stat.h> > #include <sys/mman.h> > #include <sys/stat.h> > #include <sys/wait.h> > #include <errno.h> > #include <fcntl.h> > #include <stdio.h> > #include <stdlib.h> > #include <signal.h> > #include <string.h> > #include <unistd.h> > > int > kill_children() > { > int cnt = 0; > siginfo_t infop; > > signal(SIGINT, SIG_IGN); > kill(0, SIGINT); > while (waitid(P_ALL, 0, &infop, WEXITED) != -1) ++cnt; > > return cnt; > } > > void > sighandler(int sig) > { > printf("Cleaning up all children.\n"); > int cnt = kill_children(); > printf("Cleaned up %d child%s.\n", cnt, cnt == 1 ? "" : "ren"); > > exit(0); > } > > int > do_child(volatile int *iaddr) > { > while (1) *iaddr = 1; > } > > int > main(int argc, char **argv) > { > const char *path; > int fd; > ssize_t wlen; > int *ip; > int fork_count = 1; > > if (argc == 1) { > fprintf(stderr, "Usage: %s {filename} [fork_count].\n", > argv[0]); > return 1; > } > > path = argv[1]; > > if (argc > 2) { > int fc = atoi(argv[2]); > if (fc >= 0) > fork_count = fc; > } > > fd = open(path, O_CREAT|O_TRUNC|O_RDWR|O_APPEND, S_IRUSR|S_IWUSR); > if (fd < 0) { > fprintf(stderr, "Open of '%s' failed: %s (%d)\n", > path, strerror(errno), errno); > return 1; > } > > wlen = write(fd, &(int){0}, sizeof(int)); > if (wlen != sizeof(int)) { > if (wlen < 0) > fprintf(stderr, "Write of '%s' failed: %s (%d)\n", > path, strerror(errno), errno); > else > fprintf(stderr, "Short write to '%s'\n", path); > return 1; > } > > ip = (int *)mmap(NULL, sizeof(int), PROT_READ|PROT_WRITE, > MAP_SHARED, fd, 0); > if (ip == MAP_FAILED) { > fprintf(stderr, "Mmap of '%s' failed: %s (%d)\n", > path, strerror(errno), errno); > return 1; > } > > signal(SIGINT, sighandler); > > while (fork_count-- > 0) { > switch(fork()) { > case -1: > fprintf(stderr, "Fork failed: %s (%d)\n", > strerror(errno), errno); > kill_children(); > return 1; > case 0: /* child */ > signal(SIGINT, SIG_DFL); > do_child(ip); > break; > default: /* parent */ > break; > } > } > > printf("Press ^C to terminate test.\n"); > pause(); > > return 0; > } > -- > To unsubscribe from this list: send the line "unsubscribe linux-nfs" in > the body of a message to majordomo@xxxxxxxxxxxxxxx > More majordomo info at http://vger.kernel.org/majordomo-info.html > -- To unsubscribe from this list: send the line "unsubscribe linux-nfs" in the body of a message to majordomo@xxxxxxxxxxxxxxx More majordomo info at http://vger.kernel.org/majordomo-info.html
