BACKPORT: UPSTREAM: mm: fs: invalidate bh_lrus for only cold path
kernel test robot reported the regression of fio.write_iops[1] with [2]. Since lru_add_drain is called frequently, invalidate bh_lrus there could increase bh_lrus cache miss ratio, which needs more IO in the end. This patch moves the bh_lrus invalidation from the hot path( e.g., zap_page_range, pagevec_release) to cold path(i.e., lru_add_drain_all, lru_cache_disable). "Xing, Zhengjun" confirmed : I test the patch, the regression reduced to -2.9%. [1] https://lore.kernel.org/lkml/20210520083144.GD14190@xsang-OptiPlex-9020/ [2] 8cc621d2f45d, mm: fs: invalidate BH LRU during page migration Bug: 194673488 Link: https://lkml.kernel.org/r/20210907212347.1977686-1-minchan@kernel.org (cherry picked from commit 243418e3925d5b5b0657ae54c322d43035e97eed) [Chris: resolved conflicts due to Minchan's AOSP LRU commits] Signed-off-by: Minchan Kim <minchan@kernel.org> Reported-by: kernel test robot <oliver.sang@intel.com> Reviewed-by: Chris Goldsworthy <cgoldswo@codeaurora.org> Tested-by: "Xing, Zhengjun" <zhengjun.xing@intel.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Chris Goldsworthy <quic_cgoldswo@quicinc.com> Change-Id: Icc5e456b058df516480b4378853464d6d7b43505
This commit is contained in:

committed by
Chris Goldsworthy

parent
49af2e35d5
commit
a9ac6ae90e
@@ -1454,12 +1454,16 @@ void invalidate_bh_lrus(void)
|
||||
}
|
||||
EXPORT_SYMBOL_GPL(invalidate_bh_lrus);
|
||||
|
||||
void invalidate_bh_lrus_cpu(int cpu)
|
||||
/*
|
||||
* It's called from workqueue context so we need a bh_lru_lock to close
|
||||
* the race with preemption/irq.
|
||||
*/
|
||||
void invalidate_bh_lrus_cpu(void)
|
||||
{
|
||||
struct bh_lru *b;
|
||||
|
||||
bh_lru_lock();
|
||||
b = per_cpu_ptr(&bh_lrus, cpu);
|
||||
b = this_cpu_ptr(&bh_lrus);
|
||||
__invalidate_bh_lrus(b);
|
||||
bh_lru_unlock();
|
||||
}
|
||||
|
@@ -194,7 +194,7 @@ void __breadahead_gfp(struct block_device *, sector_t block, unsigned int size,
|
||||
struct buffer_head *__bread_gfp(struct block_device *,
|
||||
sector_t block, unsigned size, gfp_t gfp);
|
||||
void invalidate_bh_lrus(void);
|
||||
void invalidate_bh_lrus_cpu(int cpu);
|
||||
void invalidate_bh_lrus_cpu(void);
|
||||
bool has_bh_in_lru(int cpu, void *dummy);
|
||||
struct buffer_head *alloc_buffer_head(gfp_t gfp_flags);
|
||||
void free_buffer_head(struct buffer_head * bh);
|
||||
@@ -408,7 +408,7 @@ static inline int inode_has_buffers(struct inode *inode) { return 0; }
|
||||
static inline void invalidate_inode_buffers(struct inode *inode) {}
|
||||
static inline int remove_inode_buffers(struct inode *inode) { return 1; }
|
||||
static inline int sync_mapping_buffers(struct address_space *mapping) { return 0; }
|
||||
static inline void invalidate_bh_lrus_cpu(int cpu) {}
|
||||
static inline void invalidate_bh_lrus_cpu(void) {}
|
||||
static inline bool has_bh_in_lru(int cpu, void *dummy) { return 0; }
|
||||
#define buffer_heads_over_limit 0
|
||||
|
||||
|
19
mm/swap.c
19
mm/swap.c
@@ -691,7 +691,6 @@ void lru_add_drain_cpu(int cpu)
|
||||
pagevec_lru_move_fn(pvec, lru_lazyfree_movetail_fn, NULL);
|
||||
|
||||
activate_page_drain(cpu);
|
||||
invalidate_bh_lrus_cpu(cpu);
|
||||
}
|
||||
|
||||
/**
|
||||
@@ -797,6 +796,20 @@ void lru_add_drain(void)
|
||||
local_unlock(&lru_pvecs.lock);
|
||||
}
|
||||
|
||||
/*
|
||||
* It's called from per-cpu workqueue context in SMP case so
|
||||
* lru_add_drain_cpu and invalidate_bh_lrus_cpu should run on
|
||||
* the same cpu. It shouldn't be a problem in !SMP case since
|
||||
* the core is only one and the locks will disable preemption.
|
||||
*/
|
||||
static void lru_add_and_bh_lrus_drain(void)
|
||||
{
|
||||
local_lock(&lru_pvecs.lock);
|
||||
lru_add_drain_cpu(smp_processor_id());
|
||||
local_unlock(&lru_pvecs.lock);
|
||||
invalidate_bh_lrus_cpu();
|
||||
}
|
||||
|
||||
void lru_add_drain_cpu_zone(struct zone *zone)
|
||||
{
|
||||
local_lock(&lru_pvecs.lock);
|
||||
@@ -811,7 +824,7 @@ static DEFINE_PER_CPU(struct work_struct, lru_add_drain_work);
|
||||
|
||||
static void lru_add_drain_per_cpu(struct work_struct *dummy)
|
||||
{
|
||||
lru_add_drain();
|
||||
lru_add_and_bh_lrus_drain();
|
||||
}
|
||||
|
||||
/*
|
||||
@@ -969,7 +982,7 @@ void lru_cache_disable(void)
|
||||
*/
|
||||
__lru_add_drain_all(true);
|
||||
#else
|
||||
lru_add_drain();
|
||||
lru_add_and_bh_lrus_drain();
|
||||
#endif
|
||||
atomic_inc(&lru_disable_count);
|
||||
}
|
||||
|
Reference in New Issue
Block a user