Add rmb() to tsc_read_##x to enforce serialization of rdtsc captures.

Intel Architecture Manual specifies that rdtsc instruction is not serialized,
so without this change, TSC synchronization test would periodically fail,
resulting in use of HPET timecounter instead of TSC-low.  This caused
severe performance degradation (40-50%) when running high IO/s workloads due to
HPET MMIO reads and GEOM stat collection.

Tests on Xeon E5-2600 (Sandy Bridge) 8C systems were seeing TSC synchronization
fail approximately 20% of the time.

Sponsored by: Intel
Reviewed by: kib
MFC after: 3 days
This commit is contained in:
Jim Harris 2012-07-24 22:10:11 +00:00
parent b18b53bad0
commit 3f6e7b9b11
Notes: svn2git 2020-12-20 02:59:44 +00:00
svn path=/head/; revision=238755

View File

@ -328,6 +328,7 @@ init_TSC(void)
#ifdef SMP
/* rmb is required here because rdtsc is not a serializing instruction. */
#define TSC_READ(x) \
static void \
tsc_read_##x(void *arg) \
@ -335,6 +336,7 @@ tsc_read_##x(void *arg) \
uint32_t *tsc = arg; \
u_int cpu = PCPU_GET(cpuid); \
\
rmb(); \
tsc[cpu * 3 + x] = rdtsc32(); \
}
TSC_READ(0)