Re: [PATCH v5] mm, vmscan: retry kswapd's priority loop with cache_trim_mode off on failure

[Huang, Ying]

Byungchul Park <byungchul@xxxxxx> writes:

> Sorry for noise. I should've applied v5's change in v4.
>
> Changes from v4:
> 	1. Make other scans start with may_cache_trim_mode = 1.
>
> Changes from v3:
> 	1. Update the test result in the commit message with v4.
> 	2. Retry the whole priority loop with cache_trim_mode off again,
> 	   rather than forcing the mode off at the highest priority,
> 	   when the mode doesn't work. (feedbacked by Johannes Weiner)
>
> Changes from v2:
> 	1. Change the condition to stop cache_trim_mode.
>
> 	   From - Stop it if it's at high scan priorities, 0 or 1.
> 	   To   - Stop it if it's at high scan priorities, 0 or 1, and
> 	          the mode didn't work in the previous turn.
>
> 	   (feedbacked by Huang Ying)
>
> 	2. Change the test result in the commit message after testing
> 	   with the new logic.
>
> Changes from v1:
> 	1. Add a comment describing why this change is necessary in code
> 	   and rewrite the commit message with how to reproduce and what
> 	   the result is using vmstat. (feedbacked by Andrew Morton and
> 	   Yu Zhao)
> 	2. Change the condition to avoid cache_trim_mode from
> 	   'sc->priority != 1' to 'sc->priority > 1' to reflect cases
> 	   where the priority goes to zero all the way. (feedbacked by
> 	   Yu Zhao)
> --->8---
> From 58f1a0e41b9feea72d7fd4bd7bed1ace592e6e4c Mon Sep 17 00:00:00 2001
> From: Byungchul Park <byungchul@xxxxxx>
> Date: Mon, 4 Mar 2024 11:24:40 +0900
> Subject: [PATCH v5] mm, vmscan: retry kswapd's priority loop with cache_trim_mode off on failure
>
> With cache_trim_mode on, reclaim logic doesn't bother reclaiming anon
> pages.  However, it should be more careful to use the mode because it's
> going to prevent anon pages from being reclaimed even if there are a
> huge number of anon pages that are cold and should be reclaimed.  Even
> worse, that leads kswapd_failures to reach MAX_RECLAIM_RETRIES and
> stopping kswapd from functioning until direct reclaim eventually works
> to resume kswapd.
>
> So kswapd needs to retry its scan priority loop with cache_trim_mode
> off again if the mode doesn't work for reclaim.
>
> The problematic behavior can be reproduced by:
>
>    CONFIG_NUMA_BALANCING enabled
>    sysctl_numa_balancing_mode set to NUMA_BALANCING_MEMORY_TIERING
>    numa node0 (8GB local memory, 16 CPUs)
>    numa node1 (8GB slow tier memory, no CPUs)
>
>    Sequence:
>
>    1) echo 3 > /proc/sys/vm/drop_caches
>    2) To emulate the system with full of cold memory in local DRAM, run
>       the following dummy program and never touch the region:
>
>          mmap(0, 8 * 1024 * 1024 * 1024, PROT_READ | PROT_WRITE,
>               MAP_ANONYMOUS | MAP_PRIVATE | MAP_POPULATE, -1, 0);
>
>    3) Run any memory intensive work e.g. XSBench.
>    4) Check if numa balancing is working e.i. promotion/demotion.
>    5) Iterate 1) ~ 4) until numa balancing stops.
>
> With this, you could see that promotion/demotion are not working because
> kswapd has stopped due to ->kswapd_failures >= MAX_RECLAIM_RETRIES.
>
> Interesting vmstat delta's differences between before and after are like:
>
>    +-----------------------+-------------------------------+
>    | interesting vmstat    | before        | after         |
>    +-----------------------+-------------------------------+
>    | nr_inactive_anon      | 321935        | 1646193       |
>    | nr_active_anon        | 1780700       | 456388        |
>    | nr_inactive_file      | 30425         | 27836         |
>    | nr_active_file        | 14961         | 1217          |
>    | pgpromote_success     | 356           | 1310120       |
>    | pgpromote_candidate   | 21953245      | 1736872       |
>    | pgactivate            | 1844523       | 3292443       |
>    | pgdeactivate          | 50634         | 1526701       |
>    | pgfault               | 31100294      | 6715375       |
>    | pgdemote_kswapd       | 30856         | 1954199       |
>    | pgscan_kswapd         | 1861981       | 7100099       |
>    | pgscan_anon           | 1822930       | 7061135       |
>    | pgscan_file           | 39051         | 38964         |
>    | pgsteal_anon          | 386           | 1925214       |
>    | pgsteal_file          | 30470         | 28985         |
>    | pageoutrun            | 30            | 500           |
>    | numa_hint_faults      | 27418279      | 3090773       |
>    | numa_pages_migrated   | 356           | 1310120       |
>    +-----------------------+-------------------------------+
>
> Signed-off-by: Byungchul Park <byungchul@xxxxxx>
> ---
>  mm/vmscan.c | 23 +++++++++++++++++++++--
>  1 file changed, 21 insertions(+), 2 deletions(-)
>
> diff --git a/mm/vmscan.c b/mm/vmscan.c
> index bba207f41b14..77948b0f8b5b 100644
> --- a/mm/vmscan.c
> +++ b/mm/vmscan.c
> @@ -108,6 +108,9 @@ struct scan_control {
>  	/* Can folios be swapped as part of reclaim? */
>  	unsigned int may_swap:1;
>  
> +	/* Can cache_trim_mode be turned on as part of reclaim? */
> +	unsigned int may_cache_trim_mode:1;
> +

Although it's generally not good to use negative logic, I think that
it's better to name the flag as something like "no_cache_trim_mode" to
make it easier to initialize the flag to its default value ("0").

>  	/* Proactive reclaim invoked by userspace through memory.reclaim */
>  	unsigned int proactive:1;
>  
> @@ -1500,6 +1503,7 @@ unsigned int reclaim_clean_pages_from_list(struct zone *zone,
>  	struct scan_control sc = {
>  		.gfp_mask = GFP_KERNEL,
>  		.may_unmap = 1,
> +		.may_cache_trim_mode = 1,
>  	};
>  	struct reclaim_stat stat;
>  	unsigned int nr_reclaimed;
> @@ -2094,6 +2098,7 @@ static unsigned int reclaim_folio_list(struct list_head *folio_list,
>  		.may_writepage = 1,
>  		.may_unmap = 1,
>  		.may_swap = 1,
> +		.may_cache_trim_mode = 1,
>  		.no_demotion = 1,
>  	};
>  
> @@ -2268,7 +2273,8 @@ static void prepare_scan_control(pg_data_t *pgdat, struct scan_control *sc)
>  	 * anonymous pages.
>  	 */
>  	file = lruvec_page_state(target_lruvec, NR_INACTIVE_FILE);
> -	if (file >> sc->priority && !(sc->may_deactivate & DEACTIVATE_FILE))
> +	if (file >> sc->priority && !(sc->may_deactivate & DEACTIVATE_FILE) &&
> +	    sc->may_cache_trim_mode)
>  		sc->cache_trim_mode = 1;
>  	else
>  		sc->cache_trim_mode = 0;
> @@ -5435,6 +5441,7 @@ static ssize_t lru_gen_seq_write(struct file *file, const char __user *src,
>  		.may_writepage = true,
>  		.may_unmap = true,
>  		.may_swap = true,
> +		.may_cache_trim_mode = 1,
>  		.reclaim_idx = MAX_NR_ZONES - 1,
>  		.gfp_mask = GFP_KERNEL,
>  	};
> @@ -6394,6 +6401,7 @@ unsigned long try_to_free_pages(struct zonelist *zonelist, int order,
>  		.may_writepage = !laptop_mode,
>  		.may_unmap = 1,
>  		.may_swap = 1,
> +		.may_cache_trim_mode = 1,
>  	};
>  
>  	/*
> @@ -6439,6 +6447,7 @@ unsigned long mem_cgroup_shrink_node(struct mem_cgroup *memcg,
>  		.may_unmap = 1,
>  		.reclaim_idx = MAX_NR_ZONES - 1,
>  		.may_swap = !noswap,
> +		.may_cache_trim_mode = 1,
>  	};
>  
>  	WARN_ON_ONCE(!current->reclaim_state);
> @@ -6482,6 +6491,7 @@ unsigned long try_to_free_mem_cgroup_pages(struct mem_cgroup *memcg,
>  		.may_writepage = !laptop_mode,
>  		.may_unmap = 1,
>  		.may_swap = !!(reclaim_options & MEMCG_RECLAIM_MAY_SWAP),
> +		.may_cache_trim_mode = 1,
>  		.proactive = !!(reclaim_options & MEMCG_RECLAIM_PROACTIVE),
>  	};
>  	/*
> @@ -6744,6 +6754,7 @@ static int balance_pgdat(pg_data_t *pgdat, int order, int highest_zoneidx)
>  		.gfp_mask = GFP_KERNEL,
>  		.order = order,
>  		.may_unmap = 1,
> +		.may_cache_trim_mode = 1,
>  	};
>  
>  	set_task_reclaim_state(current, &sc.reclaim_state);
> @@ -6898,8 +6909,14 @@ static int balance_pgdat(pg_data_t *pgdat, int order, int highest_zoneidx)
>  			sc.priority--;
>  	} while (sc.priority >= 1);
>  
> -	if (!sc.nr_reclaimed)
> +	if (!sc.nr_reclaimed) {
> +		if (sc.may_cache_trim_mode) {

sc.may_cache_trim_mode && cache_trim_mode ?

> +			sc.may_cache_trim_mode = 0;
> +			goto restart;
> +		}
> +
>  		pgdat->kswapd_failures++;
> +	}
>  
>  out:
>  	clear_reclaim_active(pgdat, highest_zoneidx);
> @@ -7202,6 +7219,7 @@ unsigned long shrink_all_memory(unsigned long nr_to_reclaim)
>  		.may_writepage = 1,
>  		.may_unmap = 1,
>  		.may_swap = 1,
> +		.may_cache_trim_mode = 1,
>  		.hibernation_mode = 1,
>  	};
>  	struct zonelist *zonelist = node_zonelist(numa_node_id(), sc.gfp_mask);
> @@ -7360,6 +7378,7 @@ static int __node_reclaim(struct pglist_data *pgdat, gfp_t gfp_mask, unsigned in
>  		.may_writepage = !!(node_reclaim_mode & RECLAIM_WRITE),
>  		.may_unmap = !!(node_reclaim_mode & RECLAIM_UNMAP),
>  		.may_swap = 1,
> +		.may_cache_trim_mode = 1,
>  		.reclaim_idx = gfp_zone(gfp_mask),
>  	};
>  	unsigned long pflags;

--
Best Regards,
Huang, Ying