mirror of
https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git
synced 2024-08-26 02:39:48 +00:00
![Darrick J. Wong](/assets/img/avatar_default.png)
This patchset ("stable page writes, part 2") makes some key modifications to the original 'stable page writes' patchset. First, it provides creators (devices and filesystems) of a backing_dev_info a flag that declares whether or not it is necessary to ensure that page contents cannot change during writeout. It is no longer assumed that this is true of all devices (which was never true anyway). Second, the flag is used to relaxed the wait_on_page_writeback calls so that wait only occurs if the device needs it. Third, it fixes up the remaining disk-backed filesystems to use this improved conditional-wait logic to provide stable page writes on those filesystems. It is hoped that (for people not using checksumming devices, anyway) this patchset will give back unnecessary performance decreases since the original stable page write patchset went into 3.0. Sorry about not fixing it sooner. Complaints were registered by several people about the long write latencies introduced by the original stable page write patchset. Generally speaking, the kernel ought to allocate as little extra memory as possible to facilitate writeout, but for people who simply cannot wait, a second page stability strategy is (re)introduced: snapshotting page contents. The waiting behavior is still the default strategy; to enable page snapshotting, a superblock flag (MS_SNAP_STABLE) must be set. This flag is used to bandaid^Henable stable page writeback on ext3[1], and is not used anywhere else. Given that there are already a few storage devices and network FSes that have rolled their own page stability wait/page snapshot code, it would be nice to move towards consolidating all of these. It seems possible that iscsi and raid5 may wish to use the new stable page write support to enable zero-copy writeout. Thank you to Jan Kara for helping fix a couple more filesystems. Per Andrew Morton's request, here are the result of using dbench to measure latencies on ext2: 3.8.0-rc3: Operation Count AvgLat MaxLat ---------------------------------------- WriteX 109347 0.028 59.817 ReadX 347180 0.004 3.391 Flush 15514 29.828 287.283 Throughput 57.429 MB/sec 4 clients 4 procs max_latency=287.290 ms 3.8.0-rc3 + patches: WriteX 105556 0.029 4.273 ReadX 335004 0.005 4.112 Flush 14982 30.540 298.634 Throughput 55.4496 MB/sec 4 clients 4 procs max_latency=298.650 ms As you can see, for ext2 the maximum write latency decreases from ~60ms on a laptop hard disk to ~4ms. I'm not sure why the flush latencies increase, though I suspect that being able to dirty pages faster gives the flusher more work to do. On ext4, the average write latency decreases as well as all the maximum latencies: 3.8.0-rc3: WriteX 85624 0.152 33.078 ReadX 272090 0.010 61.210 Flush 12129 36.219 168.260 Throughput 44.8618 MB/sec 4 clients 4 procs max_latency=168.276 ms 3.8.0-rc3 + patches: WriteX 86082 0.141 30.928 ReadX 273358 0.010 36.124 Flush 12214 34.800 165.689 Throughput 44.9941 MB/sec 4 clients 4 procs max_latency=165.722 ms XFS seems to exhibit similar latency improvements as ext2: 3.8.0-rc3: WriteX 125739 0.028 104.343 ReadX 399070 0.005 4.115 Flush 17851 25.004 131.390 Throughput 66.0024 MB/sec 4 clients 4 procs max_latency=131.406 ms 3.8.0-rc3 + patches: WriteX 123529 0.028 6.299 ReadX 392434 0.005 4.287 Flush 17549 25.120 188.687 Throughput 64.9113 MB/sec 4 clients 4 procs max_latency=188.704 ms ...and btrfs, just to round things out, also shows some latency decreases: 3.8.0-rc3: WriteX 67122 0.083 82.355 ReadX 212719 0.005 2.828 Flush 9547 47.561 147.418 Throughput 35.3391 MB/sec 4 clients 4 procs max_latency=147.433 ms 3.8.0-rc3 + patches: WriteX 64898 0.101 71.631 ReadX 206673 0.005 7.123 Flush 9190 47.963 219.034 Throughput 34.0795 MB/sec 4 clients 4 procs max_latency=219.044 ms Before this patchset, all filesystems would block, regardless of whether or not it was necessary. ext3 would wait, but still generate occasional checksum errors. The network filesystems were left to do their own thing, so they'd wait too. After this patchset, all the disk filesystems except ext3 and btrfs will wait only if the hardware requires it. ext3 (if necessary) snapshots pages instead of blocking, and btrfs provides its own bdi so the mm will never wait. Network filesystems haven't been touched, so either they provide their own wait code, or they don't block at all. The blocking behavior is back to what it was before 3.0 if you don't have a disk requiring stable page writes. This patchset has been tested on 3.8.0-rc3 on x64 with ext3, ext4, and xfs. I've spot-checked 3.8.0-rc4 and seem to be getting the same results as -rc3. [1] The alternative fixes to ext3 include fixing the locking order and page bit handling like we did for ext4 (but then why not just use ext4?), or setting PG_writeback so early that ext3 becomes extremely slow. I tried that, but the number of write()s I could initiate dropped by nearly an order of magnitude. That was a bit much even for the author of the stable page series! :) This patch: Creates a per-backing-device flag that tracks whether or not pages must be held immutable during writeout. Eventually it will be used to waive wait_for_page_writeback() if nothing requires stable pages. Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com> Reviewed-by: Jan Kara <jack@suse.cz> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Andy Lutomirski <luto@amacapital.net> Cc: Artem Bityutskiy <dedekind1@gmail.com> Cc: Joel Becker <jlbec@evilplan.org> Cc: Mark Fasheh <mfasheh@suse.com> Cc: Steven Whitehouse <swhiteho@redhat.com> Cc: Jens Axboe <axboe@kernel.dk> Cc: Eric Van Hensbergen <ericvh@gmail.com> Cc: Ron Minnich <rminnich@sandia.gov> Cc: Latchesar Ionkov <lucho@ionkov.net> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
452 lines
12 KiB
C
452 lines
12 KiB
C
/*
|
|
* blk-integrity.c - Block layer data integrity extensions
|
|
*
|
|
* Copyright (C) 2007, 2008 Oracle Corporation
|
|
* Written by: Martin K. Petersen <martin.petersen@oracle.com>
|
|
*
|
|
* This program is free software; you can redistribute it and/or
|
|
* modify it under the terms of the GNU General Public License version
|
|
* 2 as published by the Free Software Foundation.
|
|
*
|
|
* This program is distributed in the hope that it will be useful, but
|
|
* WITHOUT ANY WARRANTY; without even the implied warranty of
|
|
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
|
|
* General Public License for more details.
|
|
*
|
|
* You should have received a copy of the GNU General Public License
|
|
* along with this program; see the file COPYING. If not, write to
|
|
* the Free Software Foundation, 675 Mass Ave, Cambridge, MA 02139,
|
|
* USA.
|
|
*
|
|
*/
|
|
|
|
#include <linux/blkdev.h>
|
|
#include <linux/mempool.h>
|
|
#include <linux/bio.h>
|
|
#include <linux/scatterlist.h>
|
|
#include <linux/export.h>
|
|
#include <linux/slab.h>
|
|
|
|
#include "blk.h"
|
|
|
|
static struct kmem_cache *integrity_cachep;
|
|
|
|
static const char *bi_unsupported_name = "unsupported";
|
|
|
|
/**
|
|
* blk_rq_count_integrity_sg - Count number of integrity scatterlist elements
|
|
* @q: request queue
|
|
* @bio: bio with integrity metadata attached
|
|
*
|
|
* Description: Returns the number of elements required in a
|
|
* scatterlist corresponding to the integrity metadata in a bio.
|
|
*/
|
|
int blk_rq_count_integrity_sg(struct request_queue *q, struct bio *bio)
|
|
{
|
|
struct bio_vec *iv, *ivprv = NULL;
|
|
unsigned int segments = 0;
|
|
unsigned int seg_size = 0;
|
|
unsigned int i = 0;
|
|
|
|
bio_for_each_integrity_vec(iv, bio, i) {
|
|
|
|
if (ivprv) {
|
|
if (!BIOVEC_PHYS_MERGEABLE(ivprv, iv))
|
|
goto new_segment;
|
|
|
|
if (!BIOVEC_SEG_BOUNDARY(q, ivprv, iv))
|
|
goto new_segment;
|
|
|
|
if (seg_size + iv->bv_len > queue_max_segment_size(q))
|
|
goto new_segment;
|
|
|
|
seg_size += iv->bv_len;
|
|
} else {
|
|
new_segment:
|
|
segments++;
|
|
seg_size = iv->bv_len;
|
|
}
|
|
|
|
ivprv = iv;
|
|
}
|
|
|
|
return segments;
|
|
}
|
|
EXPORT_SYMBOL(blk_rq_count_integrity_sg);
|
|
|
|
/**
|
|
* blk_rq_map_integrity_sg - Map integrity metadata into a scatterlist
|
|
* @q: request queue
|
|
* @bio: bio with integrity metadata attached
|
|
* @sglist: target scatterlist
|
|
*
|
|
* Description: Map the integrity vectors in request into a
|
|
* scatterlist. The scatterlist must be big enough to hold all
|
|
* elements. I.e. sized using blk_rq_count_integrity_sg().
|
|
*/
|
|
int blk_rq_map_integrity_sg(struct request_queue *q, struct bio *bio,
|
|
struct scatterlist *sglist)
|
|
{
|
|
struct bio_vec *iv, *ivprv = NULL;
|
|
struct scatterlist *sg = NULL;
|
|
unsigned int segments = 0;
|
|
unsigned int i = 0;
|
|
|
|
bio_for_each_integrity_vec(iv, bio, i) {
|
|
|
|
if (ivprv) {
|
|
if (!BIOVEC_PHYS_MERGEABLE(ivprv, iv))
|
|
goto new_segment;
|
|
|
|
if (!BIOVEC_SEG_BOUNDARY(q, ivprv, iv))
|
|
goto new_segment;
|
|
|
|
if (sg->length + iv->bv_len > queue_max_segment_size(q))
|
|
goto new_segment;
|
|
|
|
sg->length += iv->bv_len;
|
|
} else {
|
|
new_segment:
|
|
if (!sg)
|
|
sg = sglist;
|
|
else {
|
|
sg->page_link &= ~0x02;
|
|
sg = sg_next(sg);
|
|
}
|
|
|
|
sg_set_page(sg, iv->bv_page, iv->bv_len, iv->bv_offset);
|
|
segments++;
|
|
}
|
|
|
|
ivprv = iv;
|
|
}
|
|
|
|
if (sg)
|
|
sg_mark_end(sg);
|
|
|
|
return segments;
|
|
}
|
|
EXPORT_SYMBOL(blk_rq_map_integrity_sg);
|
|
|
|
/**
|
|
* blk_integrity_compare - Compare integrity profile of two disks
|
|
* @gd1: Disk to compare
|
|
* @gd2: Disk to compare
|
|
*
|
|
* Description: Meta-devices like DM and MD need to verify that all
|
|
* sub-devices use the same integrity format before advertising to
|
|
* upper layers that they can send/receive integrity metadata. This
|
|
* function can be used to check whether two gendisk devices have
|
|
* compatible integrity formats.
|
|
*/
|
|
int blk_integrity_compare(struct gendisk *gd1, struct gendisk *gd2)
|
|
{
|
|
struct blk_integrity *b1 = gd1->integrity;
|
|
struct blk_integrity *b2 = gd2->integrity;
|
|
|
|
if (!b1 && !b2)
|
|
return 0;
|
|
|
|
if (!b1 || !b2)
|
|
return -1;
|
|
|
|
if (b1->sector_size != b2->sector_size) {
|
|
printk(KERN_ERR "%s: %s/%s sector sz %u != %u\n", __func__,
|
|
gd1->disk_name, gd2->disk_name,
|
|
b1->sector_size, b2->sector_size);
|
|
return -1;
|
|
}
|
|
|
|
if (b1->tuple_size != b2->tuple_size) {
|
|
printk(KERN_ERR "%s: %s/%s tuple sz %u != %u\n", __func__,
|
|
gd1->disk_name, gd2->disk_name,
|
|
b1->tuple_size, b2->tuple_size);
|
|
return -1;
|
|
}
|
|
|
|
if (b1->tag_size && b2->tag_size && (b1->tag_size != b2->tag_size)) {
|
|
printk(KERN_ERR "%s: %s/%s tag sz %u != %u\n", __func__,
|
|
gd1->disk_name, gd2->disk_name,
|
|
b1->tag_size, b2->tag_size);
|
|
return -1;
|
|
}
|
|
|
|
if (strcmp(b1->name, b2->name)) {
|
|
printk(KERN_ERR "%s: %s/%s type %s != %s\n", __func__,
|
|
gd1->disk_name, gd2->disk_name,
|
|
b1->name, b2->name);
|
|
return -1;
|
|
}
|
|
|
|
return 0;
|
|
}
|
|
EXPORT_SYMBOL(blk_integrity_compare);
|
|
|
|
int blk_integrity_merge_rq(struct request_queue *q, struct request *req,
|
|
struct request *next)
|
|
{
|
|
if (blk_integrity_rq(req) != blk_integrity_rq(next))
|
|
return -1;
|
|
|
|
if (req->nr_integrity_segments + next->nr_integrity_segments >
|
|
q->limits.max_integrity_segments)
|
|
return -1;
|
|
|
|
return 0;
|
|
}
|
|
EXPORT_SYMBOL(blk_integrity_merge_rq);
|
|
|
|
int blk_integrity_merge_bio(struct request_queue *q, struct request *req,
|
|
struct bio *bio)
|
|
{
|
|
int nr_integrity_segs;
|
|
struct bio *next = bio->bi_next;
|
|
|
|
bio->bi_next = NULL;
|
|
nr_integrity_segs = blk_rq_count_integrity_sg(q, bio);
|
|
bio->bi_next = next;
|
|
|
|
if (req->nr_integrity_segments + nr_integrity_segs >
|
|
q->limits.max_integrity_segments)
|
|
return -1;
|
|
|
|
req->nr_integrity_segments += nr_integrity_segs;
|
|
|
|
return 0;
|
|
}
|
|
EXPORT_SYMBOL(blk_integrity_merge_bio);
|
|
|
|
struct integrity_sysfs_entry {
|
|
struct attribute attr;
|
|
ssize_t (*show)(struct blk_integrity *, char *);
|
|
ssize_t (*store)(struct blk_integrity *, const char *, size_t);
|
|
};
|
|
|
|
static ssize_t integrity_attr_show(struct kobject *kobj, struct attribute *attr,
|
|
char *page)
|
|
{
|
|
struct blk_integrity *bi =
|
|
container_of(kobj, struct blk_integrity, kobj);
|
|
struct integrity_sysfs_entry *entry =
|
|
container_of(attr, struct integrity_sysfs_entry, attr);
|
|
|
|
return entry->show(bi, page);
|
|
}
|
|
|
|
static ssize_t integrity_attr_store(struct kobject *kobj,
|
|
struct attribute *attr, const char *page,
|
|
size_t count)
|
|
{
|
|
struct blk_integrity *bi =
|
|
container_of(kobj, struct blk_integrity, kobj);
|
|
struct integrity_sysfs_entry *entry =
|
|
container_of(attr, struct integrity_sysfs_entry, attr);
|
|
ssize_t ret = 0;
|
|
|
|
if (entry->store)
|
|
ret = entry->store(bi, page, count);
|
|
|
|
return ret;
|
|
}
|
|
|
|
static ssize_t integrity_format_show(struct blk_integrity *bi, char *page)
|
|
{
|
|
if (bi != NULL && bi->name != NULL)
|
|
return sprintf(page, "%s\n", bi->name);
|
|
else
|
|
return sprintf(page, "none\n");
|
|
}
|
|
|
|
static ssize_t integrity_tag_size_show(struct blk_integrity *bi, char *page)
|
|
{
|
|
if (bi != NULL)
|
|
return sprintf(page, "%u\n", bi->tag_size);
|
|
else
|
|
return sprintf(page, "0\n");
|
|
}
|
|
|
|
static ssize_t integrity_read_store(struct blk_integrity *bi,
|
|
const char *page, size_t count)
|
|
{
|
|
char *p = (char *) page;
|
|
unsigned long val = simple_strtoul(p, &p, 10);
|
|
|
|
if (val)
|
|
bi->flags |= INTEGRITY_FLAG_READ;
|
|
else
|
|
bi->flags &= ~INTEGRITY_FLAG_READ;
|
|
|
|
return count;
|
|
}
|
|
|
|
static ssize_t integrity_read_show(struct blk_integrity *bi, char *page)
|
|
{
|
|
return sprintf(page, "%d\n", (bi->flags & INTEGRITY_FLAG_READ) != 0);
|
|
}
|
|
|
|
static ssize_t integrity_write_store(struct blk_integrity *bi,
|
|
const char *page, size_t count)
|
|
{
|
|
char *p = (char *) page;
|
|
unsigned long val = simple_strtoul(p, &p, 10);
|
|
|
|
if (val)
|
|
bi->flags |= INTEGRITY_FLAG_WRITE;
|
|
else
|
|
bi->flags &= ~INTEGRITY_FLAG_WRITE;
|
|
|
|
return count;
|
|
}
|
|
|
|
static ssize_t integrity_write_show(struct blk_integrity *bi, char *page)
|
|
{
|
|
return sprintf(page, "%d\n", (bi->flags & INTEGRITY_FLAG_WRITE) != 0);
|
|
}
|
|
|
|
static struct integrity_sysfs_entry integrity_format_entry = {
|
|
.attr = { .name = "format", .mode = S_IRUGO },
|
|
.show = integrity_format_show,
|
|
};
|
|
|
|
static struct integrity_sysfs_entry integrity_tag_size_entry = {
|
|
.attr = { .name = "tag_size", .mode = S_IRUGO },
|
|
.show = integrity_tag_size_show,
|
|
};
|
|
|
|
static struct integrity_sysfs_entry integrity_read_entry = {
|
|
.attr = { .name = "read_verify", .mode = S_IRUGO | S_IWUSR },
|
|
.show = integrity_read_show,
|
|
.store = integrity_read_store,
|
|
};
|
|
|
|
static struct integrity_sysfs_entry integrity_write_entry = {
|
|
.attr = { .name = "write_generate", .mode = S_IRUGO | S_IWUSR },
|
|
.show = integrity_write_show,
|
|
.store = integrity_write_store,
|
|
};
|
|
|
|
static struct attribute *integrity_attrs[] = {
|
|
&integrity_format_entry.attr,
|
|
&integrity_tag_size_entry.attr,
|
|
&integrity_read_entry.attr,
|
|
&integrity_write_entry.attr,
|
|
NULL,
|
|
};
|
|
|
|
static const struct sysfs_ops integrity_ops = {
|
|
.show = &integrity_attr_show,
|
|
.store = &integrity_attr_store,
|
|
};
|
|
|
|
static int __init blk_dev_integrity_init(void)
|
|
{
|
|
integrity_cachep = kmem_cache_create("blkdev_integrity",
|
|
sizeof(struct blk_integrity),
|
|
0, SLAB_PANIC, NULL);
|
|
return 0;
|
|
}
|
|
subsys_initcall(blk_dev_integrity_init);
|
|
|
|
static void blk_integrity_release(struct kobject *kobj)
|
|
{
|
|
struct blk_integrity *bi =
|
|
container_of(kobj, struct blk_integrity, kobj);
|
|
|
|
kmem_cache_free(integrity_cachep, bi);
|
|
}
|
|
|
|
static struct kobj_type integrity_ktype = {
|
|
.default_attrs = integrity_attrs,
|
|
.sysfs_ops = &integrity_ops,
|
|
.release = blk_integrity_release,
|
|
};
|
|
|
|
bool blk_integrity_is_initialized(struct gendisk *disk)
|
|
{
|
|
struct blk_integrity *bi = blk_get_integrity(disk);
|
|
|
|
return (bi && bi->name && strcmp(bi->name, bi_unsupported_name) != 0);
|
|
}
|
|
EXPORT_SYMBOL(blk_integrity_is_initialized);
|
|
|
|
/**
|
|
* blk_integrity_register - Register a gendisk as being integrity-capable
|
|
* @disk: struct gendisk pointer to make integrity-aware
|
|
* @template: optional integrity profile to register
|
|
*
|
|
* Description: When a device needs to advertise itself as being able
|
|
* to send/receive integrity metadata it must use this function to
|
|
* register the capability with the block layer. The template is a
|
|
* blk_integrity struct with values appropriate for the underlying
|
|
* hardware. If template is NULL the new profile is allocated but
|
|
* not filled out. See Documentation/block/data-integrity.txt.
|
|
*/
|
|
int blk_integrity_register(struct gendisk *disk, struct blk_integrity *template)
|
|
{
|
|
struct blk_integrity *bi;
|
|
|
|
BUG_ON(disk == NULL);
|
|
|
|
if (disk->integrity == NULL) {
|
|
bi = kmem_cache_alloc(integrity_cachep,
|
|
GFP_KERNEL | __GFP_ZERO);
|
|
if (!bi)
|
|
return -1;
|
|
|
|
if (kobject_init_and_add(&bi->kobj, &integrity_ktype,
|
|
&disk_to_dev(disk)->kobj,
|
|
"%s", "integrity")) {
|
|
kmem_cache_free(integrity_cachep, bi);
|
|
return -1;
|
|
}
|
|
|
|
kobject_uevent(&bi->kobj, KOBJ_ADD);
|
|
|
|
bi->flags |= INTEGRITY_FLAG_READ | INTEGRITY_FLAG_WRITE;
|
|
bi->sector_size = queue_logical_block_size(disk->queue);
|
|
disk->integrity = bi;
|
|
} else
|
|
bi = disk->integrity;
|
|
|
|
/* Use the provided profile as template */
|
|
if (template != NULL) {
|
|
bi->name = template->name;
|
|
bi->generate_fn = template->generate_fn;
|
|
bi->verify_fn = template->verify_fn;
|
|
bi->tuple_size = template->tuple_size;
|
|
bi->set_tag_fn = template->set_tag_fn;
|
|
bi->get_tag_fn = template->get_tag_fn;
|
|
bi->tag_size = template->tag_size;
|
|
} else
|
|
bi->name = bi_unsupported_name;
|
|
|
|
disk->queue->backing_dev_info.capabilities |= BDI_CAP_STABLE_WRITES;
|
|
|
|
return 0;
|
|
}
|
|
EXPORT_SYMBOL(blk_integrity_register);
|
|
|
|
/**
|
|
* blk_integrity_unregister - Remove block integrity profile
|
|
* @disk: disk whose integrity profile to deallocate
|
|
*
|
|
* Description: This function frees all memory used by the block
|
|
* integrity profile. To be called at device teardown.
|
|
*/
|
|
void blk_integrity_unregister(struct gendisk *disk)
|
|
{
|
|
struct blk_integrity *bi;
|
|
|
|
if (!disk || !disk->integrity)
|
|
return;
|
|
|
|
disk->queue->backing_dev_info.capabilities &= ~BDI_CAP_STABLE_WRITES;
|
|
|
|
bi = disk->integrity;
|
|
|
|
kobject_uevent(&bi->kobj, KOBJ_REMOVE);
|
|
kobject_del(&bi->kobj);
|
|
kobject_put(&bi->kobj);
|
|
disk->integrity = NULL;
|
|
}
|
|
EXPORT_SYMBOL(blk_integrity_unregister);
|