[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

[Xen-devel] weird memory access problem running on dom0

hi all,

    recently we met an unbelievable weird memory problem running on dom0, test case is very simple, code is as following:

#define BUF_SIZE        4096
#define IO_PATTERN      0xab

int main(int argc, char *argv[])
        void *buf;
        char cmp_buf[BUF_SIZE];
        int err = 0;

        buf = malloc(BUF_SIZE);
        if (!buf) {
                fprintf(stderr, "error %s during %s\n",
                return 1;
        memset(buf, IO_PATTERN, BUF_SIZE);
        memset(cmp_buf, IO_PATTERN, BUF_SIZE);

        if (memcmp(buf, cmp_buf, BUF_SIZE)) {
                unsigned long long *ubuf = (unsigned long long *)buf;
                int i;

                for (i = 0; i < BUF_SIZE / sizeof(unsigned long long); i++)
                        printf("%d: 0x%llx\n", i, ubuf[i]);
                return 2;

        return 0;

    memcmp failure occurs while the case is running on 500 machines with Xen, each for billion times. 
    error log has two results, one is 0x0, it shows buf is zero,  the other one is 0xabababa...ababa,  it shows cmp_buf isn't 0xabab..ab

    both of error log shows either buf or cmp_buf is all incorrect.

    However, this case pass when we run on native linux kernel(2.6.32) without Xen.

    we suspect maybe it's relevent to pvops behavior of dom0.

    we're not sure whether it's a bug fixed in newer version of kernel and xen, so we have tried diffrent version of Xen and dom0 including Xen4.0.1+kernel2.6.32/3.0/3.11 and Xen4.2 + kernel2.6.32, unfortunately, all of these failed.

    we found PAT behaves differenly between linux and xen, so we try to add nopat into command line of kernel 3.11, and it also failed.

    now we're blocked, realy need some help.

    any advice will be appreciated

    thanks in advance


Xen-devel mailing list



Lists.xenproject.org is hosted with RackSpace, monitoring our
servers 24x7x365 and backed by RackSpace's Fanatical Support®.