From 872cd437e7b5a15c928e094710a7022184ab0217 Mon Sep 17 00:00:00 2001 From: Chris Webb Date: Sat, 9 Dec 2023 12:50:31 +0000 Subject: [PATCH] bcachefs-tools: Avoid glibc-specific mallinfo() in shrinker Before 326d7c1, the shrinker used freeram and totalram from a struct sysinfo (constructed from /proc/meminfo) to target 25% free physical memory. As well as the slowness of repeatedly reading /proc/meminfo, this was a problem as freeram rises when the system starts to swap. We don't want swapping to reduce our estimate of memory pressure. To work around this, in 326d7c1 the shrinker started to use the total allocated heap from a glibc-specific interface mallinfo2(), aiming to shrink such that our heap is less than 80% of physical memory, unless overall free memory is less than 6% so that becomes the determining factor. Unfortunately, a sign error in the calculation means this heuristic never worked. It would shrink aggressively when the process was small, and not at all when the process grew beyond 80% of physical RAM. Only the fallback test ensuring the free physical RAM doesn't fall below 6% would actually kick in under memory pressure. It also breaks portability to anything other than recent glibc. Later, in 2440469 the mallinfo2() was replaced with the older mallinfo() to improve compatibility with older glibc. This is even more problematic: it's still not portable but also struct mallinfo has (signed) int fields which overflow for large processes on 32-bit machines with a 3G/1G split. Rather than trying to use libc-specific debug interfaces and our own heap to inform the shrinker, use the information about free and total swap we already have from sysinfo(2) to explicitly compensate for swapping in our estimate of free physical memory. Target free memory of 6% of physical RAM adjusted for zero swap use when calculating the pressure on the shrinker, based on the effective behaviour of 326d7c1 in practice given the sign error. As well as fixing portability to non-glibc systems, this loosens the assumption that we are the only process using significant memory when setting the shrinker target. It wouldn't be unreasonable to run two fsck jobs against independent devices on a large RAM machine and want to balance physical RAM between them. Signed-off-by: Chris Webb Signed-off-by: Kent Overstreet --- linux/shrinker.c | 16 +++++----------- 1 file changed, 5 insertions(+), 11 deletions(-) diff --git a/linux/shrinker.c b/linux/shrinker.c index 7658fb7..8a24565 100644 --- a/linux/shrinker.c +++ b/linux/shrinker.c @@ -54,7 +54,6 @@ void run_shrinkers(gfp_t gfp_mask, bool allocation_failed) { struct shrinker *shrinker; struct sysinfo info; - struct mallinfo malloc_info = mallinfo(); s64 want_shrink; if (!(gfp_mask & GFP_KERNEL)) @@ -71,16 +70,11 @@ void run_shrinkers(gfp_t gfp_mask, bool allocation_failed) si_meminfo(&info); - if (info.totalram && info.totalram >> 4 < info.freeram) { - /* freeram goes up when system swaps, use malloced data instead */ - want_shrink = -malloc_info.arena + (info.totalram / 10 * 8); - - if (want_shrink <= 0) - return; - } else { - /* We want to play nice with other apps keep 6% avaliable, free 3% */ - want_shrink = (info.totalram >> 5); - } + /* Aim for 6% of physical RAM free without anything in swap */ + want_shrink = (info.totalram << 4) - info.freeram + + info.totalswap - info.freeswap; + if (want_shrink <= 0) + return; mutex_lock(&shrinker_lock); list_for_each_entry(shrinker, &shrinker_list, list) { -- 2.39.2