On Tue, Jun 04, 2024 at 07:25:16PM +0900, Byungchul Park wrote: > On Tue, Jun 04, 2024 at 06:12:22PM +0900, Byungchul Park wrote: > > On Tue, Jun 04, 2024 at 04:57:17PM +0800, Huang, Ying wrote: > > > Byungchul Park <byungchul@xxxxxx> writes: > > > > > > > On Tue, Jun 04, 2024 at 03:57:54PM +0800, Huang, Ying wrote: > > > >> Byungchul Park <byungchul@xxxxxx> writes: > > > >> > > > >> > Changes from v1: > > > >> > 1. Don't allow to resume kswapd if the system is under memory > > > >> > pressure that might affect direct reclaim by any chance, like > > > >> > if NR_FREE_PAGES is less than (low wmark + min wmark)/2. > > > >> > > > > >> > --->8--- > > > >> > From 6c73fc16b75907f5da9e6b33aff86bf7d7c9dd64 Mon Sep 17 00:00:00 2001 > > > >> > From: Byungchul Park <byungchul@xxxxxx> > > > >> > Date: Tue, 4 Jun 2024 15:27:56 +0900 > > > >> > Subject: [PATCH v2] mm: let kswapd work again for node that used to be hopeless but may not now > > > >> > > > > >> > A system should run with kswapd running in background when under memory > > > >> > pressure, such as when the available memory level is below the low water > > > >> > mark and there are reclaimable folios. > > > >> > > > > >> > However, the current code let the system run with kswapd stopped if > > > >> > kswapd has been stopped due to more than MAX_RECLAIM_RETRIES failures > > > >> > until direct reclaim will do for that, even if there are reclaimable > > > >> > folios that can be reclaimed by kswapd. This case was observed in the > > > >> > following scenario: > > > >> > > > > >> > CONFIG_NUMA_BALANCING enabled > > > >> > sysctl_numa_balancing_mode set to NUMA_BALANCING_MEMORY_TIERING > > > >> > numa node0 (500GB local DRAM, 128 CPUs) > > > >> > numa node1 (100GB CXL memory, no CPUs) > > > >> > swap off > > > >> > > > > >> > 1) Run a workload with big anon pages e.g. mmap(200GB). > > > >> > 2) Continue adding the same workload to the system. > > > >> > 3) The anon pages are placed in node0 by promotion/demotion. > > > >> > 4) kswapd0 stops because of the unreclaimable anon pages in node0. > > > >> > 5) Kill the memory hoggers to restore the system. > > > >> > > > > >> > After restoring the system at 5), the system starts to run without > > > >> > kswapd. Even worse, tiering mechanism is no longer able to work since > > > >> > the mechanism relies on kswapd for demotion. > > > >> > > > >> We have run into the situation that kswapd is kept in failure state for > > > >> long in a multiple tiers system. I think that your solution is too > > > > > > > > My solution just gives a chance for kswapd to work again even if > > > > kswapd_failures >= MAX_RECLAIM_RETRIES, if there are potential > > > > reclaimable folios. That's it. > > > > > > > >> limited, because OOM killing may not happen, while the access pattern of > > > > > > > > I don't get this. OOM will happen as is, through direct reclaim. > > > > > > A system that fails to reclaim via kswapd may succeed to reclaim via > > > direct reclaim, because more CPUs are used to scanning the page tables. > > > > > > In a system with NUMA balancing based page promotion and page demotion > > > enabled, page promotion will wake up kswapd, but kswapd may fail in some > > > situations. But page promotion will no trigger direct reclaim or OOM. > > > > > > >> the workloads may change. We have a preliminary and simple solution for > > > >> this as follows, > > > >> > > > >> https://git.kernel.org/pub/scm/linux/kernel/git/vishal/tiering.git/commit/?h=tiering-0.8&id=17a24a354e12d4d4675d78481b358f668d5a6866 > > > > > > > > Whether tiering is involved or not, the same problem can arise if > > > > kswapd gets stopped due to kswapd_failures >= MAX_RECLAIM_RETRIES. > > > > > > Your description is about tiering too. Can you describe a situation > > > > I mentioned "tiering" while I described how to reproduce because I ran > > into the situation while testing with tiering system but I don't think > > it's the necessary condition. > > > > Let me ask you back, why the logic to stop kswapd was considered in the > > first place? That's because the problem was already observed anyway > > To be clear.. > > The problem, kswapd_failures >= MAX_RECLAIM_RETRIES, can happen whether > tiering is involved not not. Once kswapd stops, the system should run > without kswapd even after recovered e.g. by killing the hoggers. *Even > worse*, tiering mechanism doesn't work in this situation. But like Ying said, in other situations it's direct reclaim that kicks in and clears the flag. The failure-sleep and direct reclaim triggered recovery have been in place since 2017. Both parties who observed an issue with it recently did so in tiering scenarios. IMO a tiering-specific solution makes the most sense.
