You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
I ran into a situation where issuing a request to drop caches never returned. The command:
# echo 3 > /proc/sys/vm/drop_caches
I ended up crashing the node with sysrq, and I'll list some info from the crash dump below along with the "interesting" threads that I see in the resulting crash dump:
It has been observed that it's possible to get in a state where
shrink_slabs() will spin repeated invoking the generic kmem cache
shrinker. It fails to detect it's not making forward progress
reclaiming from the cache and doesn't give up. To ensure this
never occurs we unconditionally return -1 after reclaiming what
we can.
Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov>
Issue openzfs/zfs#1276
Issue openzfs/zfs#1598
It has been observed that it's possible to get in a state where
shrink_slabs() will spin repeated invoking the generic kmem cache
shrinker. It fails to detect it's not making forward progress
reclaiming from the cache and doesn't give up. To ensure this
never occurs we unconditionally return -1 after reclaiming what
we can.
Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov>
Issue openzfs/zfs#1276
Issue openzfs/zfs#1598
It has been observed that it's possible to get in a state where
shrink_slabs() will spin repeated invoking the generic kmem cache
shrinker. It fails to detect it's not making forward progress
reclaiming from the cache and doesn't give up. To ensure this
never occurs we unconditionally return -1 after reclaiming what
we can.
Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov>
Issue openzfs/zfs#1276
Issue openzfs/zfs#1598
I ran into a situation where issuing a request to drop caches never returned. The command:
I ended up crashing the node with sysrq, and I'll list some info from the crash dump below along with the "interesting" threads that I see in the resulting crash dump:
System information:
Running processes:
Stacks of "interesting" threads, along with some gdb source info:
The text was updated successfully, but these errors were encountered: