Fix MMP write frequency for large pools

When a single pool contains more vdevs than the CONFIG_HZ for for the kernel the mmp thread will not delay properly. Switch to using cv_timedwait_sig_hires() to handle higher resolution delays. This issue was reported on Arch Linux where HZ defaults to only 100 and this could be fairly easily reproduced with a reasonably large pool. Most distribution kernels set CONFIG_HZ=250 or CONFIG_HZ=1000 and thus are unlikely to be impacted. Reviewed-by: George Melikov <[email protected]> Reviewed-by: Giuseppe Di Natale <[email protected]> Reviewed-by: Olaf Faaland <[email protected]> Reviewed-by: Tony Hutter <[email protected]> Signed-off-by: Brian Behlendorf <[email protected]> Closes openzfs#7205 Closes openzfs#7289
tonyhutter · Mar 8, 2018 · 88f792c · 88f792c
1 parent 20a503a
commit 88f792c
Show file tree

Hide file tree

Showing 2 changed files with 7 additions and 3 deletions.
diff --git a/lib/libspl/include/sys/time.h b/lib/libspl/include/sys/time.h
@@ -58,6 +58,10 @@
 #define	NSEC2MSEC(n)    ((n) / (NANOSEC / MILLISEC))
 #endif
 
+#ifndef USEC2NSEC
+#define USEC2NSEC(m)    ((hrtime_t)(m) * (NANOSEC / MICROSEC))
+#endif
+
 #ifndef	NSEC2SEC
 #define	NSEC2SEC(n)	((n) / (NANOSEC / SEC))
 #endif

diff --git a/module/zfs/mmp.c b/module/zfs/mmp.c
@@ -462,9 +462,9 @@ mmp_thread(spa_t *spa)
 			mmp_write_uberblock(spa);
 
 		CALLB_CPR_SAFE_BEGIN(&cpr);
-		(void) cv_timedwait_sig(&mmp->mmp_thread_cv,
-		    &mmp->mmp_thread_lock, ddi_get_lbolt() +
-		    ((next_time - gethrtime()) / (NANOSEC / hz)));
+		(void) cv_timedwait_sig_hires(&mmp->mmp_thread_cv,
+		    &mmp->mmp_thread_lock, next_time, USEC2NSEC(1),
+		    CALLOUT_FLAG_ABSOLUTE);
 		CALLB_CPR_SAFE_END(&cpr, &mmp->mmp_thread_lock);
 	}