From: Boaz Harrosh <bharrosh@panasas.com>
To: Jeff Garzik <jeff@garzik.org>,
James Bottomley <James.Bottomley@HansenPartnership.com>,
Jens Axboe <jens.axboe@oracle.com>,
FUJITA Tomonori <fujita.tomonori@lab.ntt.co.jp>,
linux-scs
Subject: [RFC C 4/5] exofs: No bio for you
Date: Thu, 19 Mar 2009 16:37:14 +0200 [thread overview]
Message-ID: <49C2589A.2080103@panasas.com> (raw)
In-Reply-To: <49C254FD.7020202@panasas.com>
bio based API to osd_initiator is depreciated. Move to
a page array API when writing/reading pages.
Signed-off-by: Boaz Harrosh <bharrosh@panasas.com>
---
fs/exofs/common.h | 4 --
fs/exofs/inode.c | 108 +++++++++++++++++++++++++++--------------------------
2 files changed, 55 insertions(+), 57 deletions(-)
diff --git a/fs/exofs/common.h b/fs/exofs/common.h
index f02cb4c..8a56338 100644
--- a/fs/exofs/common.h
+++ b/fs/exofs/common.h
@@ -44,10 +44,6 @@
#include <scsi/osd_initiator.h>
#include <scsi/osd_sec.h>
-/* FIXME: Temporarly until exofs tree syncs with scsi-misc's osd_initiator */
-#define osd_req_write osd_req_write_old
-#define osd_req_read osd_req_read_old
-
/****************************************************************************
* Object ID related defines
* NOTE: inode# = object ID - EXOFS_OBJ_OFF
diff --git a/fs/exofs/inode.c b/fs/exofs/inode.c
index 0f52e76..31cfd6d 100644
--- a/fs/exofs/inode.c
+++ b/fs/exofs/inode.c
@@ -49,9 +49,8 @@ struct page_collect {
struct inode *inode;
unsigned expected_pages;
- struct bio *bio;
- unsigned nr_pages;
- unsigned long length;
+ struct osd_pages_array opa;
+ unsigned pg_alloc_count;
long pg_first;
};
@@ -66,9 +65,8 @@ void _pcol_init(struct page_collect *pcol, unsigned expected_pages,
pcol->inode = inode;
pcol->expected_pages = expected_pages;
- pcol->bio = NULL;
- pcol->nr_pages = 0;
- pcol->length = 0;
+ memset(&pcol->opa, 0, sizeof(pcol->opa));
+ pcol->pg_alloc_count = 0;
pcol->pg_first = -1;
EXOFS_DBGMSG("_pcol_init ino=0x%lx expected_pages=%u\n", inode->i_ino,
@@ -77,11 +75,10 @@ void _pcol_init(struct page_collect *pcol, unsigned expected_pages,
void _pcol_reset(struct page_collect *pcol)
{
- pcol->expected_pages -= min(pcol->nr_pages, pcol->expected_pages);
+ pcol->expected_pages -= min(pcol->opa.nr_pages, pcol->expected_pages);
- pcol->bio = NULL;
- pcol->nr_pages = 0;
- pcol->length = 0;
+ memset(&pcol->opa, 0, sizeof(pcol->opa));
+ pcol->pg_alloc_count = 0;
pcol->pg_first = -1;
EXOFS_DBGMSG("_pcol_reset ino=0x%lx expected_pages=%u\n",
pcol->inode->i_ino, pcol->expected_pages);
@@ -98,9 +95,12 @@ int pcol_try_alloc(struct page_collect *pcol)
int pages = min_t(unsigned, pcol->expected_pages, BIO_MAX_PAGES);
for (; pages; pages >>= 1) {
- pcol->bio = bio_alloc(GFP_KERNEL, pages);
- if (likely(pcol->bio))
+ pcol->opa.pages = kcalloc(pages, sizeof(struct page *),
+ GFP_KERNEL);
+ if (likely(pcol->opa.pages)) {
+ pcol->pg_alloc_count = pages;
return 0;
+ }
}
EXOFS_ERR("Failed to kcalloc expected_pages=%d\n",
@@ -110,21 +110,25 @@ int pcol_try_alloc(struct page_collect *pcol)
void pcol_free(struct page_collect *pcol)
{
- bio_put(pcol->bio);
- pcol->bio = NULL;
+ kfree(pcol->opa.pages);
+ pcol->opa.pages = NULL;
+ pcol->pg_alloc_count = 0;
}
-int pcol_add_page(struct page_collect *pcol, struct page *page, unsigned len)
+int pcol_add_page(struct page_collect *pcol, struct page *page, int len)
{
- int added_len = bio_add_pc_page(pcol->req_q, pcol->bio, page, len, 0);
- if (unlikely(len != added_len))
+ if (pcol->opa.nr_pages >= pcol->pg_alloc_count)
return -ENOMEM;
- ++pcol->nr_pages;
- pcol->length += len;
+ pcol->opa.pages[pcol->opa.nr_pages++] = page;
+ pcol->opa.length += len;
return 0;
}
+#define __pcol_for_each_segment(page, pcol, i, s) \
+ for (page = pcol->opa.pages[s], i = s; i < pcol->opa.nr_pages; \
+ page = pcol->opa.pages[++(i)])
+
static int update_read_page(struct page *page, int ret)
{
if (ret == 0) {
@@ -164,7 +168,7 @@ static int _readpage(struct page *page, bool is_sync);
static int __readpages_done(struct osd_request *or, struct page_collect *pcol,
bool do_unlock)
{
- struct bio_vec *bvec;
+ struct page *page;
int i;
u64 resid;
u64 good_bytes;
@@ -174,19 +178,18 @@ static int __readpages_done(struct osd_request *or, struct page_collect *pcol,
osd_end_request(or);
if (!ret)
- good_bytes = pcol->length;
+ good_bytes = pcol->opa.length;
else if (ret && !resid)
good_bytes = 0;
else
- good_bytes = pcol->length - resid;
+ good_bytes = pcol->opa.length - resid;
EXOFS_DBGMSG("readpages_done(%ld) good_bytes=%llx"
" length=%zx nr_pages=%u\n",
- pcol->inode->i_ino, _LLU(good_bytes), pcol->length,
- pcol->nr_pages);
+ pcol->inode->i_ino, _LLU(good_bytes), pcol->opa.length,
+ pcol->opa.nr_pages);
- __bio_for_each_segment(bvec, pcol->bio, i, 0) {
- struct page *page = bvec->bv_page;
+ __pcol_for_each_segment(page, pcol, i, 0) {
struct inode *inode = page->mapping->host;
if (inode != pcol->inode)
@@ -210,7 +213,8 @@ static int __readpages_done(struct osd_request *or, struct page_collect *pcol,
_readpage(page, false);
}
- length += bvec->bv_len;
+ length += min_t(u64,
+ pcol->opa.length - length, PAGE_CACHE_SIZE);
}
pcol_free(pcol);
@@ -229,12 +233,10 @@ static void readpages_done(struct osd_request *or, void *p)
void _unlock_pcol_pages(struct page_collect *pcol, int ret, int rw)
{
- struct bio_vec *bvec;
+ struct page *page;
int i;
- __bio_for_each_segment(bvec, pcol->bio, i, 0) {
- struct page *page = bvec->bv_page;
-
+ __pcol_for_each_segment(page, pcol, i, 0) {
if (rw == READ)
update_read_page(page, ret);
else
@@ -255,11 +257,11 @@ int read_exec(struct page_collect *pcol, bool is_sync)
loff_t i_start = pcol->pg_first << PAGE_CACHE_SHIFT;
int ret;
- if (!pcol->bio)
+ if (!pcol->opa.pages)
return 0;
/* see comment in _readpage() about sync reads */
- WARN_ON(is_sync && (pcol->nr_pages != 1));
+ WARN_ON(is_sync && (pcol->opa.nr_pages != 1));
or = osd_start_request(pcol->sbi->s_dev, GFP_KERNEL);
if (unlikely(!or)) {
@@ -267,7 +269,7 @@ int read_exec(struct page_collect *pcol, bool is_sync)
goto err;
}
- osd_req_read(or, &obj, pcol->bio, i_start);
+ osd_req_read(or, &obj, &pcol->opa, i_start);
if (is_sync) {
exofs_sync_op(or, pcol->sbi->s_timeout, oi->i_cred);
@@ -288,7 +290,7 @@ int read_exec(struct page_collect *pcol, bool is_sync)
atomic_inc(&pcol->sbi->s_curr_pending);
EXOFS_DBGMSG("read_exec obj=%llx start=%llx length=%zx\n",
- obj.id, _LLU(i_start), pcol->length);
+ obj.id, _LLU(i_start), pcol->opa.length);
/* pages ownership was passed to pcol_copy */
_pcol_reset(pcol);
@@ -346,7 +348,7 @@ try_again:
if (unlikely(pcol->pg_first == -1)) {
pcol->pg_first = page->index;
- } else if (unlikely((pcol->pg_first + pcol->nr_pages) !=
+ } else if (unlikely((pcol->pg_first + pcol->opa.nr_pages) !=
page->index)) {
/* Discontinuity detected, split the request */
ret = read_exec(pcol, false);
@@ -355,7 +357,7 @@ try_again:
goto try_again;
}
- if (!pcol->bio) {
+ if (!pcol->opa.pages) {
ret = pcol_try_alloc(pcol);
if (unlikely(ret))
goto fail;
@@ -371,7 +373,7 @@ try_again:
if (ret) {
EXOFS_DBGMSG("Failed pcol_add_page pages[i]=%p "
"len=%zx nr_pages=%u length=%zx\n",
- page, len, pcol->nr_pages, pcol->length);
+ page, len, pcol->opa.nr_pages, pcol->opa.length);
/* split the request, and start again with current page */
ret = read_exec(pcol, false);
@@ -439,31 +441,30 @@ static int exofs_writepage(struct page *page, struct writeback_control *wbc2);
static void writepages_done(struct osd_request *or, void *p)
{
struct page_collect *pcol = p;
- struct bio_vec *bvec;
+ struct page *page;
int i;
u64 resid;
u64 good_bytes;
u64 length = 0;
-
+
int ret = exofs_check_ok_resid(or, NULL, &resid);
osd_end_request(or);
atomic_dec(&pcol->sbi->s_curr_pending);
if (likely(!ret))
- good_bytes = pcol->length;
+ good_bytes = pcol->opa.length;
else if (ret && !resid)
good_bytes = 0;
else
- good_bytes = pcol->length - resid;
+ good_bytes = pcol->opa.length - resid;
EXOFS_DBGMSG("writepages_done(%lx) good_bytes=%llx"
" length=%zx nr_pages=%u\n",
- pcol->inode->i_ino, _LLU(good_bytes), pcol->length,
- pcol->nr_pages);
+ pcol->inode->i_ino, _LLU(good_bytes), pcol->opa.length,
+ pcol->opa.nr_pages);
- __bio_for_each_segment(bvec, pcol->bio, i, 0) {
- struct page *page = bvec->bv_page;
+ __pcol_for_each_segment(page, pcol, i, 0) {
struct inode *inode = page->mapping->host;
if (inode != pcol->inode)
@@ -485,7 +486,8 @@ static void writepages_done(struct osd_request *or, void *p)
exofs_writepage(page, NULL);
}
- length += bvec->bv_len;
+ length += min_t(u64,
+ pcol->opa.length - length, PAGE_CACHE_SIZE);
}
pcol_free(pcol);
@@ -503,7 +505,7 @@ int write_exec(struct page_collect *pcol)
loff_t i_start = pcol->pg_first << PAGE_CACHE_SHIFT;
int ret;
- if (!pcol->bio)
+ if (!pcol->opa.pages)
return 0;
or = osd_start_request(pcol->sbi->s_dev, GFP_KERNEL);
@@ -522,7 +524,7 @@ int write_exec(struct page_collect *pcol)
*pcol_copy = *pcol;
- osd_req_write(or, &obj, pcol_copy->bio, i_start);
+ osd_req_write(or, &obj, &pcol_copy->opa, i_start);
ret = exofs_async_op(or, writepages_done, pcol_copy, oi->i_cred);
if (unlikely(ret)) {
EXOFS_ERR("write_exec: exofs_async_op() Faild\n");
@@ -532,7 +534,7 @@ int write_exec(struct page_collect *pcol)
atomic_inc(&pcol->sbi->s_curr_pending);
EXOFS_DBGMSG("write_exec(%lx, %lx) start=%llx length=%zx\n",
pcol->inode->i_ino, pcol->pg_first, _LLU(i_start),
- pcol->length);
+ pcol->opa.length);
/* pages ownership was passed to pcol_copy */
_pcol_reset(pcol);
return 0;
@@ -586,7 +588,7 @@ try_again:
if (unlikely(pcol->pg_first == -1)) {
pcol->pg_first = page->index;
- } else if (unlikely((pcol->pg_first + pcol->nr_pages) !=
+ } else if (unlikely((pcol->pg_first + pcol->opa.nr_pages) !=
page->index)) {
/* Discontinuity detected, split the request */
ret = write_exec(pcol);
@@ -595,7 +597,7 @@ try_again:
goto try_again;
}
- if (!pcol->bio) {
+ if (!pcol->opa.pages) {
ret = pcol_try_alloc(pcol);
if (unlikely(ret))
goto fail;
@@ -608,7 +610,7 @@ try_again:
if (unlikely(ret)) {
EXOFS_DBGMSG("Failed pcol_add_page "
"nr_pages=%u total_length=%zx\n",
- pcol->nr_pages, pcol->length);
+ pcol->opa.nr_pages, pcol->opa.length);
/* split the request, next loop will start again */
ret = write_exec(pcol);
--
1.6.2.1
next prev parent reply other threads:[~2009-03-19 14:38 UTC|newest]
Thread overview: 10+ messages / expand[flat|nested] mbox.gz Atom feed top
2009-03-19 14:21 [RFD] [PATCHSETS 0/2 0/2 0/5] Remove of blk_rq_append_bio usage Boaz Harrosh
2009-03-19 14:24 ` [PATCH A 1/2] allow blk_rq_map_kern to append to requests Boaz Harrosh
2009-03-19 14:27 ` [PATCH A 2/2] libosd: Use new blk_rq_map_kern Boaz Harrosh
2009-03-19 14:30 ` [RFC B 1/2] Export new blk_make_request() which takes bio and returns request Boaz Harrosh
2009-03-19 14:31 ` [RFC B 2/2] libosd: Use of new blk_make_request Boaz Harrosh
2009-03-19 14:33 ` [RFC C 1/5] blk_rq_map_pages() new API Boaz Harrosh
2009-03-19 14:34 ` [RFC C 2/5] libosd: Rename osd_req_write/read to osd_req_write/read_old Boaz Harrosh
2009-03-19 14:35 ` [RFC C 3/5] libosd: No bio for you Boaz Harrosh
2009-03-19 14:37 ` Boaz Harrosh [this message]
2009-03-19 14:38 ` [RFC C 5/5] libosd: Remove deprecated bio based API Boaz Harrosh
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=49C2589A.2080103@panasas.com \
--to=bharrosh@panasas.com \
--cc=James.Bottomley@HansenPartnership.com \
--cc=fujita.tomonori@lab.ntt.co.jp \
--cc=jeff@garzik.org \
--cc=jens.axboe@oracle.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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.