Re: [LKP] [mm] 3484b2de949: -46.2% aim7.jobs-per-min

From: Huang Ying
Date: Sat Feb 28 2015 - 02:57:32 EST


On Fri, 2015-02-27 at 11:53 +0000, Mel Gorman wrote:
> On Fri, Feb 27, 2015 at 03:21:36PM +0800, Huang Ying wrote:
> > FYI, we noticed the below changes on
> >
> > git://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git master
> > commit 3484b2de9499df23c4604a513b36f96326ae81ad ("mm: rearrange zone fields into read-only, page alloc, statistics and page reclaim lines")
> >
> > The perf cpu-cycles for spinlock (zone->lock) increased a lot. I suspect there are some cache ping-pong or false sharing.
> >
>
> Annoying because this is pretty much the opposite of what I found during
> testing. What is the kernel config? Similar to the kernel config, can you
> post "pahole -C zone vmlinux" for the kernel you built? I should get the same
> result if I use the same kernel config but no harm in being sure. Thanks.

The output of pahole -C zone vmlinux for the kernels are as below.

Best Regards,
Huang, Ying

3484b2de94
-------------------------------------------------------
struct zone {
long unsigned int watermark[3]; /* 0 24 */
long int lowmem_reserve[4]; /* 24 32 */
int node; /* 56 4 */
unsigned int inactive_ratio; /* 60 4 */
/* --- cacheline 1 boundary (64 bytes) --- */
struct pglist_data * zone_pgdat; /* 64 8 */
struct per_cpu_pageset * pageset; /* 72 8 */
long unsigned int dirty_balance_reserve; /* 80 8 */
long unsigned int min_unmapped_pages; /* 88 8 */
long unsigned int min_slab_pages; /* 96 8 */
long unsigned int zone_start_pfn; /* 104 8 */
long unsigned int managed_pages; /* 112 8 */
long unsigned int spanned_pages; /* 120 8 */
/* --- cacheline 2 boundary (128 bytes) --- */
long unsigned int present_pages; /* 128 8 */
const char * name; /* 136 8 */
int nr_migrate_reserve_block; /* 144 4 */
seqlock_t span_seqlock; /* 148 8 */

/* XXX 4 bytes hole, try to pack */

wait_queue_head_t * wait_table; /* 160 8 */
long unsigned int wait_table_hash_nr_entries; /* 168 8 */
long unsigned int wait_table_bits; /* 176 8 */

/* XXX 8 bytes hole, try to pack */

/* --- cacheline 3 boundary (192 bytes) --- */
struct zone_padding _pad1_; /* 192 0 */
spinlock_t lock; /* 192 4 */

/* XXX 4 bytes hole, try to pack */

struct free_area free_area[11]; /* 200 968 */
/* --- cacheline 18 boundary (1152 bytes) was 16 bytes ago --- */
long unsigned int flags; /* 1168 8 */

/* XXX 40 bytes hole, try to pack */

/* --- cacheline 19 boundary (1216 bytes) --- */
struct zone_padding _pad2_; /* 1216 0 */
spinlock_t lru_lock; /* 1216 4 */

/* XXX 4 bytes hole, try to pack */

long unsigned int pages_scanned; /* 1224 8 */
struct lruvec lruvec; /* 1232 120 */
/* --- cacheline 21 boundary (1344 bytes) was 8 bytes ago --- */
atomic_long_t inactive_age; /* 1352 8 */
long unsigned int percpu_drift_mark; /* 1360 8 */
long unsigned int compact_cached_free_pfn; /* 1368 8 */
long unsigned int compact_cached_migrate_pfn[2]; /* 1376 16 */
unsigned int compact_considered; /* 1392 4 */
unsigned int compact_defer_shift; /* 1396 4 */
int compact_order_failed; /* 1400 4 */
bool compact_blockskip_flush; /* 1404 1 */

/* XXX 3 bytes hole, try to pack */

/* --- cacheline 22 boundary (1408 bytes) --- */
struct zone_padding _pad3_; /* 1408 0 */
atomic_long_t vm_stat[38]; /* 1408 304 */
/* --- cacheline 26 boundary (1664 bytes) was 48 bytes ago --- */

/* size: 1728, cachelines: 27, members: 37 */
/* sum members: 1649, holes: 6, sum holes: 63 */
/* padding: 16 */
};

24b7e5819a
---------------------------------------------------------------
struct zone {
long unsigned int watermark[3]; /* 0 24 */
long unsigned int percpu_drift_mark; /* 24 8 */
long unsigned int lowmem_reserve[4]; /* 32 32 */
/* --- cacheline 1 boundary (64 bytes) --- */
long unsigned int dirty_balance_reserve; /* 64 8 */
int node; /* 72 4 */

/* XXX 4 bytes hole, try to pack */

long unsigned int min_unmapped_pages; /* 80 8 */
long unsigned int min_slab_pages; /* 88 8 */
struct per_cpu_pageset * pageset; /* 96 8 */
spinlock_t lock; /* 104 4 */
bool compact_blockskip_flush; /* 108 1 */

/* XXX 3 bytes hole, try to pack */

long unsigned int compact_cached_free_pfn; /* 112 8 */
long unsigned int compact_cached_migrate_pfn[2]; /* 120 16 */
/* --- cacheline 2 boundary (128 bytes) was 8 bytes ago --- */
seqlock_t span_seqlock; /* 136 8 */
struct free_area free_area[11]; /* 144 968 */
/* --- cacheline 17 boundary (1088 bytes) was 24 bytes ago --- */
unsigned int compact_considered; /* 1112 4 */
unsigned int compact_defer_shift; /* 1116 4 */
int compact_order_failed; /* 1120 4 */

/* XXX 28 bytes hole, try to pack */

/* --- cacheline 18 boundary (1152 bytes) --- */
struct zone_padding _pad1_; /* 1152 0 */
spinlock_t lru_lock; /* 1152 4 */

/* XXX 4 bytes hole, try to pack */

struct lruvec lruvec; /* 1160 120 */
/* --- cacheline 20 boundary (1280 bytes) --- */
atomic_long_t inactive_age; /* 1280 8 */
long unsigned int pages_scanned; /* 1288 8 */
long unsigned int flags; /* 1296 8 */
atomic_long_t vm_stat[38]; /* 1304 304 */
/* --- cacheline 25 boundary (1600 bytes) was 8 bytes ago --- */
unsigned int inactive_ratio; /* 1608 4 */

/* XXX 52 bytes hole, try to pack */

/* --- cacheline 26 boundary (1664 bytes) --- */
struct zone_padding _pad2_; /* 1664 0 */
wait_queue_head_t * wait_table; /* 1664 8 */
long unsigned int wait_table_hash_nr_entries; /* 1672 8 */
long unsigned int wait_table_bits; /* 1680 8 */
struct pglist_data * zone_pgdat; /* 1688 8 */
long unsigned int zone_start_pfn; /* 1696 8 */
long unsigned int spanned_pages; /* 1704 8 */
long unsigned int present_pages; /* 1712 8 */
long unsigned int managed_pages; /* 1720 8 */
/* --- cacheline 27 boundary (1728 bytes) --- */
int nr_migrate_reserve_block; /* 1728 4 */

/* XXX 4 bytes hole, try to pack */

const char * name; /* 1736 8 */

/* size: 1792, cachelines: 28, members: 36 */
/* sum members: 1649, holes: 6, sum holes: 95 */
/* padding: 48 */
};


--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/