From: root@programming.kicks-ass.net
To: linux-mm@kvack.org, linux-kernel@vger.kernel.org
Cc: miklos@szeredi.hu, akpm@linux-foundation.org, neilb@suse.de,
dgc@sgi.com, tomoki.sekiyama.qu@hitachi.com,
a.p.zijlstra@chello.nl, nikita@clusterfs.com
Subject: [PATCH 02/12] mm: scalable bdi statistics counters.
Date: Thu, 05 Apr 2007 19:42:11 +0200 [thread overview]
Message-ID: <20070405174317.854739299@programming.kicks-ass.net> (raw)
In-Reply-To: <20070405174209.498059336@programming.kicks-ass.net>
[-- Attachment #1: bdi_stat.patch --]
[-- Type: text/plain, Size: 10066 bytes --]
Provide scalable per backing_dev_info statistics counters modeled on the ZVC
code.
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
---
block/ll_rw_blk.c | 1
drivers/block/rd.c | 2
drivers/char/mem.c | 2
fs/char_dev.c | 1
fs/fuse/inode.c | 1
fs/nfs/client.c | 1
include/linux/backing-dev.h | 98 +++++++++++++++++++++++++++++++++++++++++
mm/backing-dev.c | 103 ++++++++++++++++++++++++++++++++++++++++++++
8 files changed, 209 insertions(+)
Index: linux-2.6-mm/block/ll_rw_blk.c
===================================================================
--- linux-2.6-mm.orig/block/ll_rw_blk.c 2007-04-05 16:39:56.000000000 +0200
+++ linux-2.6-mm/block/ll_rw_blk.c 2007-04-05 16:40:45.000000000 +0200
@@ -208,6 +208,7 @@ void blk_queue_make_request(request_queu
blk_queue_max_phys_segments(q, MAX_PHYS_SEGMENTS);
blk_queue_max_hw_segments(q, MAX_HW_SEGMENTS);
q->make_request_fn = mfn;
+ bdi_init(&q->backing_dev_info);
blk_queue_max_sectors(q, SAFE_MAX_SECTORS);
blk_queue_hardsect_size(q, 512);
blk_queue_dma_alignment(q, 511);
Index: linux-2.6-mm/include/linux/backing-dev.h
===================================================================
--- linux-2.6-mm.orig/include/linux/backing-dev.h 2007-04-05 16:40:41.000000000 +0200
+++ linux-2.6-mm/include/linux/backing-dev.h 2007-04-05 16:40:45.000000000 +0200
@@ -8,6 +8,7 @@
#ifndef _LINUX_BACKING_DEV_H
#define _LINUX_BACKING_DEV_H
+#include <linux/spinlock.h>
#include <asm/atomic.h>
struct page;
@@ -22,6 +23,17 @@ enum bdi_state {
BDI_unused, /* Available bits start here */
};
+enum bdi_stat_item {
+ NR_BDI_STAT_ITEMS
+};
+
+#ifdef CONFIG_SMP
+struct bdi_per_cpu_data {
+ s8 stat_threshold;
+ s8 bdi_stat_diff[NR_BDI_STAT_ITEMS];
+} ____cacheline_aligned_in_smp;
+#endif
+
typedef int (congested_fn)(void *, int);
struct backing_dev_info {
@@ -34,8 +46,94 @@ struct backing_dev_info {
void *congested_data; /* Pointer to aux data for congested func */
void (*unplug_io_fn)(struct backing_dev_info *, struct page *);
void *unplug_io_data;
+
+ atomic_long_t bdi_stats[NR_BDI_STAT_ITEMS];
+#ifdef CONFIG_SMP
+ struct bdi_per_cpu_data pcd[NR_CPUS];
+#endif
};
+extern atomic_long_t bdi_stats[NR_BDI_STAT_ITEMS];
+
+static inline void bdi_stat_add(long x, struct backing_dev_info *bdi,
+ enum bdi_stat_item item)
+{
+ atomic_long_add(x, &bdi->bdi_stats[item]);
+ atomic_long_add(x, &bdi_stats[item]);
+}
+
+static inline unsigned long __global_bdi_stat(enum bdi_stat_item item)
+{
+ return atomic_long_read(&bdi_stats[item]);
+}
+
+static inline unsigned long __bdi_stat(struct backing_dev_info *bdi,
+ enum bdi_stat_item item)
+{
+ return atomic_long_read(&bdi->bdi_stats[item]);
+}
+
+/*
+ * cannot be unsigned long and clip on 0.
+ */
+static inline unsigned long global_bdi_stat(enum bdi_stat_item item)
+{
+ long x = atomic_long_read(&bdi_stats[item]);
+#ifdef CONFIG_SMP
+ if (x < 0)
+ x = 0;
+#endif
+ return x;
+}
+
+static inline unsigned long bdi_stat(struct backing_dev_info *bdi,
+ enum bdi_stat_item item)
+{
+ long x = atomic_long_read(&bdi->bdi_stats[item]);
+#ifdef CONFIG_SMP
+ if (x < 0)
+ x = 0;
+#endif
+ return x;
+}
+
+#ifdef CONFIG_SMP
+void __mod_bdi_stat(struct backing_dev_info *bdi, enum bdi_stat_item item, int delta);
+void __inc_bdi_stat(struct backing_dev_info *bdi, enum bdi_stat_item item);
+void __dec_bdi_stat(struct backing_dev_info *bdi, enum bdi_stat_item item);
+
+void mod_bdi_stat(struct backing_dev_info *bdi, enum bdi_stat_item item, int delta);
+void inc_bdi_stat(struct backing_dev_info *bdi, enum bdi_stat_item item);
+void dec_bdi_stat(struct backing_dev_info *bdi, enum bdi_stat_item item);
+
+#else /* CONFIG_SMP */
+
+static inline void __mod_bdi_stat(struct backing_dev_info *bdi,
+ enum bdi_stat_item item, int delta)
+{
+ bdi_stat_add(delta, bdi, item);
+}
+
+static inline void __inc_bdi_stat(struct backing_dev_info *bdi,
+ enum bdi_stat_item item)
+{
+ atomic_long_inc(&bdi->bdi_stats[item]);
+ atomic_long_inc(&bdi_stats[item]);
+}
+
+static inline void __dec_bdi_stat(struct backing_dev_info *bdi,
+ enum bdi_stat_item item)
+{
+ atomic_long_dec(&bdi->bdi_stats[item]);
+ atomic_long_dec(&bdi_stats[item]);
+}
+
+#define mod_bdi_stat __mod_bdi_stat
+#define inc_bdi_stat __inc_bdi_stat
+#define dec_bdi_stat __dec_bdi_stat
+#endif
+
+void bdi_init(struct backing_dev_info *bdi);
/*
* Flags in backing_dev_info::capability
Index: linux-2.6-mm/mm/backing-dev.c
===================================================================
--- linux-2.6-mm.orig/mm/backing-dev.c 2007-04-05 16:40:41.000000000 +0200
+++ linux-2.6-mm/mm/backing-dev.c 2007-04-05 16:42:37.000000000 +0200
@@ -70,3 +70,106 @@ long congestion_wait_interruptible(int r
return ret;
}
EXPORT_SYMBOL(congestion_wait_interruptible);
+
+atomic_long_t bdi_stats[NR_BDI_STAT_ITEMS];
+EXPORT_SYMBOL(bdi_stats);
+
+void bdi_init(struct backing_dev_info *bdi)
+{
+ int i;
+
+ for (i = 0; i < NR_BDI_STAT_ITEMS; i++)
+ atomic_long_set(&bdi->bdi_stats[i], 0);
+
+#ifdef CONFIG_SMP
+ for (i = 0; i < NR_CPUS; i++) {
+ int j;
+ for (j = 0; j < NR_BDI_STAT_ITEMS; j++)
+ bdi->pcd[i].bdi_stat_diff[j] = 0;
+ bdi->pcd[i].stat_threshold = 8 * ilog2(num_online_cpus());
+ }
+#endif
+}
+EXPORT_SYMBOL(bdi_init);
+
+#ifdef CONFIG_SMP
+void __mod_bdi_stat(struct backing_dev_info *bdi,
+ enum bdi_stat_item item, int delta)
+{
+ struct bdi_per_cpu_data *pcd = &bdi->pcd[smp_processor_id()];
+ s8 *p = pcd->bdi_stat_diff + item;
+ long x;
+
+ x = delta + *p;
+
+ if (unlikely(x > pcd->stat_threshold || x < -pcd->stat_threshold)) {
+ bdi_stat_add(x, bdi, item);
+ x = 0;
+ }
+ *p = x;
+}
+EXPORT_SYMBOL(__mod_bdi_stat);
+
+void mod_bdi_stat(struct backing_dev_info *bdi,
+ enum bdi_stat_item item, int delta)
+{
+ unsigned long flags;
+
+ local_irq_save(flags);
+ __mod_bdi_stat(bdi, item, delta);
+ local_irq_restore(flags);
+}
+EXPORT_SYMBOL(mod_bdi_stat);
+
+void __inc_bdi_stat(struct backing_dev_info *bdi, enum bdi_stat_item item)
+{
+ struct bdi_per_cpu_data *pcd = &bdi->pcd[smp_processor_id()];
+ s8 *p = pcd->bdi_stat_diff + item;
+
+ (*p)++;
+
+ if (unlikely(*p > pcd->stat_threshold)) {
+ int overstep = pcd->stat_threshold / 2;
+
+ bdi_stat_add(*p + overstep, bdi, item);
+ *p = -overstep;
+ }
+}
+EXPORT_SYMBOL(__inc_bdi_stat);
+
+void inc_bdi_stat(struct backing_dev_info *bdi, enum bdi_stat_item item)
+{
+ unsigned long flags;
+
+ local_irq_save(flags);
+ __inc_bdi_stat(bdi, item);
+ local_irq_restore(flags);
+}
+EXPORT_SYMBOL(inc_bdi_stat);
+
+void __dec_bdi_stat(struct backing_dev_info *bdi, enum bdi_stat_item item)
+{
+ struct bdi_per_cpu_data *pcd = &bdi->pcd[smp_processor_id()];
+ s8 *p = pcd->bdi_stat_diff + item;
+
+ (*p)--;
+
+ if (unlikely(*p < -pcd->stat_threshold)) {
+ int overstep = pcd->stat_threshold / 2;
+
+ bdi_stat_add(*p - overstep, bdi, item);
+ *p = overstep;
+ }
+}
+EXPORT_SYMBOL(__dec_bdi_stat);
+
+void dec_bdi_stat(struct backing_dev_info *bdi, enum bdi_stat_item item)
+{
+ unsigned long flags;
+
+ local_irq_save(flags);
+ __dec_bdi_stat(bdi, item);
+ local_irq_restore(flags);
+}
+EXPORT_SYMBOL(dec_bdi_stat);
+#endif
Index: linux-2.6-mm/drivers/block/rd.c
===================================================================
--- linux-2.6-mm.orig/drivers/block/rd.c 2007-04-05 16:39:56.000000000 +0200
+++ linux-2.6-mm/drivers/block/rd.c 2007-04-05 16:40:45.000000000 +0200
@@ -421,6 +421,8 @@ static int __init rd_init(void)
int i;
int err = -ENOMEM;
+ bdi_init(&rd_file_backing_dev_info);
+
if (rd_blocksize > PAGE_SIZE || rd_blocksize < 512 ||
(rd_blocksize & (rd_blocksize-1))) {
printk("RAMDISK: wrong blocksize %d, reverting to defaults\n",
Index: linux-2.6-mm/drivers/char/mem.c
===================================================================
--- linux-2.6-mm.orig/drivers/char/mem.c 2007-04-05 16:39:56.000000000 +0200
+++ linux-2.6-mm/drivers/char/mem.c 2007-04-05 16:40:45.000000000 +0200
@@ -987,6 +987,8 @@ static int __init chr_dev_init(void)
MKDEV(MEM_MAJOR, devlist[i].minor),
devlist[i].name);
+ bdi_init(&zero_bdi);
+
return 0;
}
Index: linux-2.6-mm/fs/char_dev.c
===================================================================
--- linux-2.6-mm.orig/fs/char_dev.c 2007-04-05 16:39:56.000000000 +0200
+++ linux-2.6-mm/fs/char_dev.c 2007-04-05 16:40:45.000000000 +0200
@@ -548,6 +548,7 @@ static struct kobject *base_probe(dev_t
void __init chrdev_init(void)
{
cdev_map = kobj_map_init(base_probe, &chrdevs_lock);
+ bdi_init(&directly_mappable_cdev_bdi);
}
Index: linux-2.6-mm/fs/fuse/inode.c
===================================================================
--- linux-2.6-mm.orig/fs/fuse/inode.c 2007-04-05 16:39:56.000000000 +0200
+++ linux-2.6-mm/fs/fuse/inode.c 2007-04-05 16:40:45.000000000 +0200
@@ -413,6 +413,7 @@ static struct fuse_conn *new_conn(void)
atomic_set(&fc->num_waiting, 0);
fc->bdi.ra_pages = (VM_MAX_READAHEAD * 1024) / PAGE_CACHE_SIZE;
fc->bdi.unplug_io_fn = default_unplug_io_fn;
+ bdi_init(&fc->bdi);
fc->reqctr = 0;
fc->blocked = 1;
get_random_bytes(&fc->scramble_key, sizeof(fc->scramble_key));
Index: linux-2.6-mm/fs/nfs/client.c
===================================================================
--- linux-2.6-mm.orig/fs/nfs/client.c 2007-04-05 16:39:56.000000000 +0200
+++ linux-2.6-mm/fs/nfs/client.c 2007-04-05 16:40:45.000000000 +0200
@@ -661,6 +661,7 @@ static void nfs_server_set_fsinfo(struct
server->backing_dev_info.ra_pages0 = min_t(unsigned, server->rpages,
VM_MIN_READAHEAD >> (PAGE_CACHE_SHIFT - 10));
server->backing_dev_info.ra_thrash_bytes = server->rsize * NFS_MAX_READAHEAD;
+ bdi_init(&server->backing_dev_info);
if (server->wsize > max_rpc_payload)
server->wsize = max_rpc_payload;
--
--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>
next prev parent reply other threads:[~2007-04-05 17:42 UTC|newest]
Thread overview: 27+ messages / expand[flat|nested] mbox.gz Atom feed top
2007-04-05 17:42 [PATCH 00/12] per device dirty throttling -v3 root
2007-04-05 17:42 ` [PATCH 01/12] nfs: remove congestion_end() root
2007-04-05 17:42 ` root [this message]
2007-04-05 22:37 ` [PATCH 02/12] mm: scalable bdi statistics counters Andrew Morton
2007-04-06 7:22 ` Peter Zijlstra
2007-04-05 17:42 ` [PATCH 03/12] mm: count dirty pages per BDI root
2007-04-05 17:42 ` [PATCH 04/12] mm: count writeback " root
2007-04-05 17:42 ` [PATCH 05/12] mm: count unstable " root
2007-04-05 17:42 ` [PATCH 06/12] mm: expose BDI statistics in sysfs root
2007-04-05 17:42 ` [PATCH 07/12] mm: per device dirty threshold root
2007-04-05 17:42 ` [PATCH 08/12] mm: fixup possible deadlock root
2007-04-05 22:43 ` Andrew Morton
2007-04-05 17:42 ` [PATCH 09/12] mm: remove throttle_vm_writeback root
2007-04-05 22:44 ` Andrew Morton
2007-09-26 20:42 ` Peter Zijlstra
2007-04-05 17:42 ` [PATCH 10/12] mm: page_alloc_wait root
2007-04-05 22:57 ` Andrew Morton
2007-04-06 6:37 ` Peter Zijlstra
2007-04-05 17:42 ` [PATCH 11/12] mm: accurate pageout congestion wait root
2007-04-05 23:17 ` Andrew Morton
2007-04-06 6:51 ` Peter Zijlstra
2007-04-05 17:42 ` [PATCH 12/12] mm: per BDI congestion feedback root
2007-04-05 23:24 ` Andrew Morton
2007-04-06 7:01 ` Peter Zijlstra
2007-04-06 11:00 ` Andrew Morton
2007-04-06 11:10 ` Miklos Szeredi
2007-04-05 17:47 ` [PATCH 00/12] per device dirty throttling -v3 Peter Zijlstra
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20070405174317.854739299@programming.kicks-ass.net \
--to=root@programming.kicks-ass.net \
--cc=a.p.zijlstra@chello.nl \
--cc=akpm@linux-foundation.org \
--cc=dgc@sgi.com \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=miklos@szeredi.hu \
--cc=neilb@suse.de \
--cc=nikita@clusterfs.com \
--cc=tomoki.sekiyama.qu@hitachi.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox