On 5/5/20 9:31 AM, Eric Dumazet wrote:
On 5/5/20 9:25 AM, Eric Dumazet wrote:
On 5/5/20 9:13 AM, SeongJae Park wrote:
On Tue, 5 May 2020 09:00:44 -0700 Eric Dumazet edumazet@google.com wrote:
On Tue, May 5, 2020 at 8:47 AM SeongJae Park sjpark@amazon.com wrote:
On Tue, 5 May 2020 08:20:50 -0700 Eric Dumazet eric.dumazet@gmail.com wrote:
On 5/5/20 8:07 AM, SeongJae Park wrote: > On Tue, 5 May 2020 07:53:39 -0700 Eric Dumazet edumazet@google.com wrote: >
>> Why do we have 10,000,000 objects around ? Could this be because of >> some RCU problem ? > > Mainly because of a long RCU grace period, as you guess. I have no idea how > the grace period became so long in this case. > > As my test machine was a virtual machine instance, I guess RCU readers > preemption[1] like problem might affected this. > > [1] https://www.usenix.org/system/files/conference/atc17/atc17-prasad.pdf > >> >> Once Al patches reverted, do you have 10,000,000 sock_alloc around ? > > Yes, both the old kernel that prior to Al's patches and the recent kernel > reverting the Al's patches didn't reproduce the problem. >
I repeat my question : Do you have 10,000,000 (smaller) objects kept in slab caches ?
TCP sockets use the (very complex, error prone) SLAB_TYPESAFE_BY_RCU, but not the struct socket_wq object that was allocated in sock_alloc_inode() before Al patches.
These objects should be visible in kmalloc-64 kmem cache.
Not exactly the 10,000,000, as it is only the possible highest number, but I was able to observe clear exponential increase of the number of the objects using slabtop. Before the start of the problematic workload, the number of objects of 'kmalloc-64' was 5760, but I was able to observe the number increase to 1,136,576.
OBJS ACTIVE USE OBJ SIZE SLABS OBJ/SLAB CACHE SIZE NAMEbefore: 5760 5088 88% 0.06K 90 64 360K kmalloc-64 after: 1136576 1136576 100% 0.06K 17759 64 71036K kmalloc-64
Great, thanks.
How recent is the kernel you are running for your experiment ?
It's based on 5.4.35.
Let's make sure the bug is not in RCU.
One thing I can currently say is that the grace period passes at last. I modified the benchmark to repeat not 10,000 times but only 5,000 times to run the test without OOM but easily observable memory pressure. As soon as the benchmark finishes, the memory were freed.
If you need more tests, please let me know.
I would ask Paul opinion on this issue, because we have many objects being freed after RCU grace periods.
If RCU subsystem can not keep-up, I guess other workloads will also suffer.
Sure, we can revert patches there and there trying to work around the issue, but for objects allocated from process context, we should not have these problems.
I wonder if simply adjusting rcu_divisor to 6 or 5 would help
diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c index d9a49cd6065a20936edbda1b334136ab597cde52..fde833bac0f9f81e8536211b4dad6e7575c1219a 100644 --- a/kernel/rcu/tree.c +++ b/kernel/rcu/tree.c @@ -427,7 +427,7 @@ module_param(qovld, long, 0444); static ulong jiffies_till_first_fqs = ULONG_MAX; static ulong jiffies_till_next_fqs = ULONG_MAX; static bool rcu_kick_kthreads; -static int rcu_divisor = 7; +static int rcu_divisor = 6; module_param(rcu_divisor, int, 0644); /* Force an exit from rcu_do_batch() after 3 milliseconds. */
To be clear, you can adjust the value without building a new kernel.
echo 6 >/sys/module/rcutree/parameters/rcu_divisor