*
* You should have received a copy of the GNU General Public License
* version 2 along with this program; If not, see
- * http://www.sun.com/software/products/lustre/docs/GPLv2.pdf
- *
- * Please contact Sun Microsystems, Inc., 4150 Network Circle, Santa Clara,
- * CA 95054 USA or visit www.sun.com if you need additional information or
- * have any questions.
+ * http://www.gnu.org/licenses/gpl-2.0.html
*
* GPL HEADER END
*/
* Copyright (c) 2008, 2010, Oracle and/or its affiliates. All rights reserved.
* Use is subject to license terms.
*
- * Copyright (c) 2011, 2014, Intel Corporation.
+ * Copyright (c) 2011, 2017, Intel Corporation.
*/
/*
* This file is part of Lustre, http://www.lustre.org/
#define DEBUG_SUBSYSTEM S_OSC
-#include "osc_cl_internal.h"
+#include <lustre_obdo.h>
+#include <lustre_osc.h>
+#include <linux/pagevec.h>
+#include <linux/falloc.h>
-/** \addtogroup osc
- * @{
- */
+#include "osc_internal.h"
-/*****************************************************************************
- *
- * Type conversions.
- *
+/** \addtogroup osc
+ * @{
*/
-static struct osc_req *cl2osc_req(const struct cl_req_slice *slice)
-{
- LINVRNT(slice->crs_dev->cd_lu_dev.ld_type == &osc_device_type);
- return container_of0(slice, struct osc_req, or_cl);
-}
-
-static struct osc_io *cl2osc_io(const struct lu_env *env,
- const struct cl_io_slice *slice)
-{
- struct osc_io *oio = container_of0(slice, struct osc_io, oi_cl);
- LINVRNT(oio == osc_env_io(env));
- return oio;
-}
-
-static struct osc_page *osc_cl_page_osc(struct cl_page *page,
- struct osc_object *osc)
-{
- const struct cl_page_slice *slice;
-
- if (osc != NULL)
- slice = cl_object_page_slice(&osc->oo_cl, page);
- else
- slice = cl_page_at(page, &osc_device_type);
- LASSERT(slice != NULL);
-
- return cl2osc_page(slice);
-}
-
-
/*****************************************************************************
*
* io operations.
{
}
-static void osc_read_ahead_release(const struct lu_env *env,
- void *cbdata)
+void osc_read_ahead_release(const struct lu_env *env, void *cbdata)
{
struct ldlm_lock *dlmlock = cbdata;
struct lustre_handle lockh;
ldlm_lock_decref(&lockh, LCK_PR);
LDLM_LOCK_PUT(dlmlock);
}
+EXPORT_SYMBOL(osc_read_ahead_release);
static int osc_io_read_ahead(const struct lu_env *env,
const struct cl_io_slice *ios,
dlmlock = osc_dlmlock_at_pgoff(env, osc, start, 0);
if (dlmlock != NULL) {
+ LASSERT(dlmlock->l_ast_data == osc);
if (dlmlock->l_req_mode != LCK_PR) {
struct lustre_handle lockh;
ldlm_lock2handle(dlmlock, &lockh);
ldlm_lock_decref(&lockh, dlmlock->l_req_mode);
}
- ra->cra_end = cl_index(osc2cl(osc),
- dlmlock->l_policy_data.l_extent.end);
+ ra->cra_rpc_pages = osc_cli(osc)->cl_max_pages_per_rpc;
+ ra->cra_end_idx = cl_index(osc2cl(osc),
+ dlmlock->l_policy_data.l_extent.end);
ra->cra_release = osc_read_ahead_release;
ra->cra_cbdata = dlmlock;
+ if (ra->cra_end_idx != CL_PAGE_EOF)
+ ra->cra_contention = true;
result = 0;
}
* or, if page is already submitted, changes osc flags through
* osc_set_async_flags().
*/
-static int osc_io_submit(const struct lu_env *env,
- const struct cl_io_slice *ios,
- enum cl_req_type crt, struct cl_2queue *queue)
+int osc_io_submit(const struct lu_env *env, const struct cl_io_slice *ios,
+ enum cl_req_type crt, struct cl_2queue *queue)
{
struct cl_page *page;
struct cl_page *tmp;
struct osc_object *osc = NULL; /* to keep gcc happy */
struct osc_page *opg;
struct cl_io *io;
- struct list_head list = LIST_HEAD_INIT(list);
+ LIST_HEAD(list);
struct cl_page_list *qin = &queue->c2_qin;
struct cl_page_list *qout = &queue->c2_qout;
unsigned int queued = 0;
int result = 0;
- int cmd;
int brw_flags;
unsigned int max_pages;
+ unsigned int ppc_bits; /* pages per chunk bits */
+ unsigned int ppc;
+ bool sync_queue = false;
LASSERT(qin->pl_nr > 0);
- CDEBUG(D_CACHE, "%d %d\n", qin->pl_nr, crt);
+ CDEBUG(D_CACHE|D_READA, "%d %d\n", qin->pl_nr, crt);
osc = cl2osc(ios->cis_obj);
cli = osc_cli(osc);
max_pages = cli->cl_max_pages_per_rpc;
+ ppc_bits = cli->cl_chunkbits - PAGE_SHIFT;
+ ppc = 1 << ppc_bits;
- cmd = crt == CRT_WRITE ? OBD_BRW_WRITE : OBD_BRW_READ;
brw_flags = osc_io_srvlock(cl2osc_io(env, ios)) ? OBD_BRW_SRVLOCK : 0;
+ brw_flags |= crt == CRT_WRITE ? OBD_BRW_WRITE : OBD_BRW_READ;
+ if (crt == CRT_READ && ios->cis_io->ci_ndelay)
+ brw_flags |= OBD_BRW_NDELAY;
+
+ page = cl_page_list_first(qin);
+ if (page->cp_type == CPT_TRANSIENT)
+ brw_flags |= OBD_BRW_NOCACHE;
/*
* NOTE: here @page is a top-level page. This is done to avoid
else /* async IO */
cl_page_list_del(env, qin, page);
- if (++queued == max_pages) {
- queued = 0;
- result = osc_queue_sync_pages(env, osc, &list, cmd,
+ queued++;
+ if (queued == max_pages) {
+ sync_queue = true;
+ } else if (crt == CRT_WRITE) {
+ unsigned int chunks;
+ unsigned int next_chunks;
+
+ chunks = (queued + ppc - 1) >> ppc_bits;
+ /* chunk number if add another page */
+ next_chunks = (queued + ppc) >> ppc_bits;
+
+ /* next page will excceed write chunk limit */
+ if (chunks == osc_max_write_chunks(cli) &&
+ next_chunks > chunks)
+ sync_queue = true;
+ }
+
+ if (sync_queue) {
+ result = osc_queue_sync_pages(env, io, osc, &list,
brw_flags);
if (result < 0)
break;
+ queued = 0;
+ sync_queue = false;
}
}
if (queued > 0)
- result = osc_queue_sync_pages(env, osc, &list, cmd, brw_flags);
+ result = osc_queue_sync_pages(env, io, osc, &list, brw_flags);
+
+ /* Update c/mtime for sync write. LU-7310 */
+ if (crt == CRT_WRITE && qout->pl_nr > 0 && result == 0) {
+ struct cl_object *obj = ios->cis_obj;
+ struct cl_attr *attr = &osc_env_info(env)->oti_attr;
+
+ cl_object_attr_lock(obj);
+ attr->cat_mtime = attr->cat_ctime = ktime_get_real_seconds();
+ cl_object_attr_update(env, obj, attr, CAT_MTIME | CAT_CTIME);
+ cl_object_attr_unlock(obj);
+ }
CDEBUG(D_INFO, "%d/%d %d\n", qin->pl_nr, qout->pl_nr, result);
return qout->pl_nr > 0 ? 0 : result;
}
+EXPORT_SYMBOL(osc_io_submit);
/**
- * This is called when a page is accessed within file in a way that creates
- * new page, if one were missing (i.e., if there were a hole at that place in
- * the file, or accessed page is beyond the current file size).
+ * This is called to update the attributes when modifying a specific page,
+ * both when making new pages and when doing updates to existing cached pages.
*
* Expand stripe KMS if necessary.
*/
-static void osc_page_touch_at(const struct lu_env *env,
- struct cl_object *obj, pgoff_t idx, size_t to)
+void osc_page_touch_at(const struct lu_env *env, struct cl_object *obj,
+ pgoff_t idx, size_t to)
{
- struct lov_oinfo *loi = cl2osc(obj)->oo_oinfo;
- struct cl_attr *attr = &osc_env_info(env)->oti_attr;
- int valid;
- __u64 kms;
+ struct lov_oinfo *loi = cl2osc(obj)->oo_oinfo;
+ struct cl_attr *attr = &osc_env_info(env)->oti_attr;
+ int valid;
+ __u64 kms;
+
+ ENTRY;
- /* offset within stripe */
- kms = cl_offset(obj, idx) + to;
+ /* offset within stripe */
+ kms = cl_offset(obj, idx) + to;
- cl_object_attr_lock(obj);
- /*
- * XXX old code used
- *
- * ll_inode_size_lock(inode, 0); lov_stripe_lock(lsm);
- *
- * here
- */
- CDEBUG(D_INODE, "stripe KMS %sincreasing "LPU64"->"LPU64" "LPU64"\n",
- kms > loi->loi_kms ? "" : "not ", loi->loi_kms, kms,
- loi->loi_lvb.lvb_size);
+ cl_object_attr_lock(obj);
+ CDEBUG(D_INODE, "stripe KMS %sincreasing %llu->%llu %llu\n",
+ kms > loi->loi_kms ? "" : "not ", loi->loi_kms, kms,
+ loi->loi_lvb.lvb_size);
- attr->cat_mtime = attr->cat_ctime = LTIME_S(CFS_CURRENT_TIME);
+ attr->cat_mtime = attr->cat_ctime = ktime_get_real_seconds();
valid = CAT_MTIME | CAT_CTIME;
if (kms > loi->loi_kms) {
attr->cat_kms = kms;
}
cl_object_attr_update(env, obj, attr, valid);
cl_object_attr_unlock(obj);
+
+ EXIT;
}
-static int osc_io_commit_async(const struct lu_env *env,
- const struct cl_io_slice *ios,
- struct cl_page_list *qin, int from, int to,
- cl_commit_cbt cb)
+int osc_io_commit_async(const struct lu_env *env,
+ const struct cl_io_slice *ios,
+ struct cl_page_list *qin, int from, int to,
+ cl_commit_cbt cb)
{
struct cl_io *io = ios->cis_io;
struct osc_io *oio = cl2osc_io(env, ios);
struct cl_page *page;
struct cl_page *last_page;
struct osc_page *opg;
+ struct pagevec *pvec = &osc_env_info(env)->oti_pagevec;
int result = 0;
ENTRY;
}
}
+ ll_pagevec_init(pvec, 0);
+
while (qin->pl_nr > 0) {
struct osc_async_page *oap;
opg = osc_cl_page_osc(page, osc);
oap = &opg->ops_oap;
+ LASSERTF(osc == oap->oap_obj,
+ "obj mismatch: %p / %p\n", osc, oap->oap_obj);
+
if (!list_empty(&oap->oap_rpc_item)) {
CDEBUG(D_CACHE, "Busy oap %p page %p for submit.\n",
oap, opg);
/* The page may be already in dirty cache. */
if (list_empty(&oap->oap_pending_item)) {
- result = osc_page_cache_add(env, &opg->ops_cl, io);
+ result = osc_page_cache_add(env, opg, io, cb);
if (result != 0)
break;
}
cl_page_list_del(env, qin, page);
- (*cb)(env, io, page);
- /* Can't access page any more. Page can be in transfer and
- * complete at any time. */
+ /* if there are no more slots, do the callback & reinit */
+ if (pagevec_add(pvec, page->cp_vmpage) == 0) {
+ (*cb)(env, io, pvec);
+ pagevec_reinit(pvec);
+ }
}
+ /* Clean up any partially full pagevecs */
+ if (pagevec_count(pvec) != 0)
+ (*cb)(env, io, pvec);
+
+ /* Can't access these pages any more. Page can be in transfer and
+ * complete at any time. */
+
/* for sync write, kernel will wait for this page to be flushed before
* osc_io_end() is called, so release it earlier.
* for mkwrite(), it's known there is no further pages. */
CDEBUG(D_INFO, "%d %d\n", qin->pl_nr, result);
RETURN(result);
}
+EXPORT_SYMBOL(osc_io_commit_async);
-static int osc_io_rw_iter_init(const struct lu_env *env,
- const struct cl_io_slice *ios)
+static bool osc_import_not_healthy(struct obd_import *imp)
+{
+ return imp->imp_invalid || imp->imp_deactive ||
+ !(imp->imp_state == LUSTRE_IMP_FULL ||
+ imp->imp_state == LUSTRE_IMP_IDLE);
+}
+
+int osc_io_iter_init(const struct lu_env *env, const struct cl_io_slice *ios)
+{
+ struct osc_object *osc = cl2osc(ios->cis_obj);
+ struct obd_import *imp = osc_cli(osc)->cl_import;
+ struct osc_io *oio = osc_env_io(env);
+ int rc = -EIO;
+ ENTRY;
+
+ spin_lock(&imp->imp_lock);
+ /**
+ * check whether this OSC device is available for non-delay read,
+ * fast switching mirror if we haven't tried all mirrors.
+ */
+ if (ios->cis_io->ci_type == CIT_READ && ios->cis_io->ci_ndelay &&
+ !ios->cis_io->ci_tried_all_mirrors && osc_import_not_healthy(imp)) {
+ rc = -EWOULDBLOCK;
+ } else if (likely(!imp->imp_invalid)) {
+ atomic_inc(&osc->oo_nr_ios);
+ oio->oi_is_active = 1;
+ rc = 0;
+ }
+ spin_unlock(&imp->imp_lock);
+
+ if (cfs_capable(CFS_CAP_SYS_RESOURCE))
+ oio->oi_cap_sys_resource = 1;
+
+ RETURN(rc);
+}
+EXPORT_SYMBOL(osc_io_iter_init);
+
+int osc_io_rw_iter_init(const struct lu_env *env,
+ const struct cl_io_slice *ios)
{
struct cl_io *io = ios->cis_io;
struct osc_io *oio = osc_env_io(env);
struct osc_object *osc = cl2osc(ios->cis_obj);
- struct client_obd *cli = osc_cli(osc);
- unsigned long c;
unsigned long npages;
- unsigned long max_pages;
ENTRY;
if (cl_io_is_append(io))
- RETURN(0);
+ RETURN(osc_io_iter_init(env, ios));
- npages = io->u.ci_rw.crw_count >> PAGE_CACHE_SHIFT;
+ npages = io->u.ci_rw.crw_count >> PAGE_SHIFT;
if (io->u.ci_rw.crw_pos & ~PAGE_MASK)
++npages;
- max_pages = cli->cl_max_pages_per_rpc * cli->cl_max_rpcs_in_flight;
- if (npages > max_pages)
- npages = max_pages;
+ oio->oi_lru_reserved = osc_lru_reserve(osc_cli(osc), npages);
- c = atomic_long_read(cli->cl_lru_left);
- if (c < npages && osc_lru_reclaim(cli) > 0)
- c = atomic_long_read(cli->cl_lru_left);
- while (c >= npages) {
- if (c == atomic_long_cmpxchg(cli->cl_lru_left, c, c - npages)) {
- oio->oi_lru_reserved = npages;
- break;
- }
- c = atomic_long_read(cli->cl_lru_left);
- }
+ RETURN(osc_io_iter_init(env, ios));
+}
+EXPORT_SYMBOL(osc_io_rw_iter_init);
- RETURN(0);
+void osc_io_iter_fini(const struct lu_env *env,
+ const struct cl_io_slice *ios)
+{
+ struct osc_io *oio = osc_env_io(env);
+
+ if (oio->oi_is_active) {
+ struct osc_object *osc = cl2osc(ios->cis_obj);
+
+ oio->oi_is_active = 0;
+ LASSERT(atomic_read(&osc->oo_nr_ios) > 0);
+ if (atomic_dec_and_test(&osc->oo_nr_ios))
+ wake_up_all(&osc->oo_io_waitq);
+ }
}
+EXPORT_SYMBOL(osc_io_iter_fini);
-static void osc_io_rw_iter_fini(const struct lu_env *env,
- const struct cl_io_slice *ios)
+void osc_io_rw_iter_fini(const struct lu_env *env,
+ const struct cl_io_slice *ios)
{
struct osc_io *oio = osc_env_io(env);
struct osc_object *osc = cl2osc(ios->cis_obj);
- struct client_obd *cli = osc_cli(osc);
if (oio->oi_lru_reserved > 0) {
- atomic_long_add(oio->oi_lru_reserved, cli->cl_lru_left);
+ osc_lru_unreserve(osc_cli(osc), oio->oi_lru_reserved);
oio->oi_lru_reserved = 0;
}
oio->oi_write_osclock = NULL;
+
+ osc_io_iter_fini(env, ios);
}
+EXPORT_SYMBOL(osc_io_rw_iter_fini);
-static int osc_io_fault_start(const struct lu_env *env,
- const struct cl_io_slice *ios)
+int osc_io_fault_start(const struct lu_env *env, const struct cl_io_slice *ios)
{
struct cl_io *io;
struct cl_fault_io *fio;
fio->ft_index, fio->ft_nob);
RETURN(0);
}
+EXPORT_SYMBOL(osc_io_fault_start);
+
static int osc_async_upcall(void *a, int rc)
{
/**
* Checks that there are no pages being written in the extent being truncated.
*/
-static int trunc_check_cb(const struct lu_env *env, struct cl_io *io,
+static bool trunc_check_cb(const struct lu_env *env, struct cl_io *io,
struct osc_page *ops , void *cbdata)
{
struct cl_page *page = ops->ops_cl.cpl_page;
oap = &ops->ops_oap;
if (oap->oap_cmd & OBD_BRW_WRITE &&
!list_empty(&oap->oap_pending_item))
- CL_PAGE_DEBUG(D_ERROR, env, page, "exists " LPU64 "/%s.\n",
+ CL_PAGE_DEBUG(D_ERROR, env, page, "exists %llu/%s.\n",
start, current->comm);
if (PageLocked(page->cp_vmpage))
CDEBUG(D_CACHE, "page %p index %lu locked for %d.\n",
ops, osc_index(ops), oap->oap_cmd & OBD_BRW_RWMASK);
- return CLP_GANG_OKAY;
+ return true;
}
static void osc_trunc_check(const struct lu_env *env, struct cl_io *io,
static int osc_io_setattr_start(const struct lu_env *env,
const struct cl_io_slice *slice)
{
- struct cl_io *io = slice->cis_io;
- struct osc_io *oio = cl2osc_io(env, slice);
- struct cl_object *obj = slice->cis_obj;
- struct lov_oinfo *loi = cl2osc(obj)->oo_oinfo;
- struct cl_attr *attr = &osc_env_info(env)->oti_attr;
- struct obdo *oa = &oio->oi_oa;
+ struct cl_io *io = slice->cis_io;
+ struct osc_io *oio = cl2osc_io(env, slice);
+ struct cl_object *obj = slice->cis_obj;
+ struct lov_oinfo *loi = cl2osc(obj)->oo_oinfo;
+ struct cl_attr *attr = &osc_env_info(env)->oti_attr;
+ struct obdo *oa = &oio->oi_oa;
struct osc_async_cbargs *cbargs = &oio->oi_cbarg;
- __u64 size = io->u.ci_setattr.sa_attr.lvb_size;
- unsigned int ia_valid = io->u.ci_setattr.sa_valid;
- int result = 0;
+ unsigned int ia_avalid = io->u.ci_setattr.sa_avalid;
+ enum op_xvalid ia_xvalid = io->u.ci_setattr.sa_xvalid;
+ int result = 0;
+ __u64 size = io->u.ci_setattr.sa_attr.lvb_size;
+ __u64 end = OBD_OBJECT_EOF;
+ bool io_is_falloc = false;
+ ENTRY;
/* truncate cache dirty pages first */
- if (cl_io_is_trunc(io))
- result = osc_cache_truncate_start(env, oio, cl2osc(obj), size);
+ if (cl_io_is_trunc(io)) {
+ result = osc_cache_truncate_start(env, cl2osc(obj), size,
+ &oio->oi_trunc);
+ } else if (cl_io_is_fallocate(io)) {
+ io_is_falloc = true;
+ size = io->u.ci_setattr.sa_falloc_offset;
+ end = io->u.ci_setattr.sa_falloc_end;
+ }
if (result == 0 && oio->oi_lockless == 0) {
cl_object_attr_lock(obj);
struct ost_lvb *lvb = &io->u.ci_setattr.sa_attr;
unsigned int cl_valid = 0;
- if (ia_valid & ATTR_SIZE) {
- attr->cat_size = attr->cat_kms = size;
+ if (ia_avalid & ATTR_SIZE) {
+ attr->cat_size = size;
+ attr->cat_kms = size;
cl_valid = (CAT_SIZE | CAT_KMS);
}
- if (ia_valid & ATTR_MTIME_SET) {
+ if (ia_avalid & ATTR_MTIME_SET) {
attr->cat_mtime = lvb->lvb_mtime;
cl_valid |= CAT_MTIME;
}
- if (ia_valid & ATTR_ATIME_SET) {
+ if (ia_avalid & ATTR_ATIME_SET) {
attr->cat_atime = lvb->lvb_atime;
cl_valid |= CAT_ATIME;
}
- if (ia_valid & ATTR_CTIME_SET) {
+ if (ia_xvalid & OP_XVALID_CTIME_SET) {
attr->cat_ctime = lvb->lvb_ctime;
cl_valid |= CAT_CTIME;
}
oa->o_oi = loi->loi_oi;
obdo_set_parent_fid(oa, io->u.ci_setattr.sa_parent_fid);
oa->o_stripe_idx = io->u.ci_setattr.sa_stripe_index;
- oa->o_valid |= OBD_MD_FLID | OBD_MD_FLGROUP;
- if (ia_valid & ATTR_CTIME) {
+ oa->o_layout = io->u.ci_setattr.sa_layout;
+ oa->o_valid |= OBD_MD_FLID | OBD_MD_FLGROUP |
+ OBD_MD_FLOSTLAYOUT;
+ if (ia_avalid & ATTR_CTIME) {
oa->o_valid |= OBD_MD_FLCTIME;
oa->o_ctime = attr->cat_ctime;
}
- if (ia_valid & ATTR_ATIME) {
+ if (ia_avalid & ATTR_ATIME) {
oa->o_valid |= OBD_MD_FLATIME;
oa->o_atime = attr->cat_atime;
}
- if (ia_valid & ATTR_MTIME) {
+ if (ia_avalid & ATTR_MTIME) {
oa->o_valid |= OBD_MD_FLMTIME;
oa->o_mtime = attr->cat_mtime;
}
- if (ia_valid & ATTR_SIZE) {
- oa->o_size = size;
- oa->o_blocks = OBD_OBJECT_EOF;
- oa->o_valid |= OBD_MD_FLSIZE | OBD_MD_FLBLOCKS;
-
- if (oio->oi_lockless) {
- oa->o_flags = OBD_FL_SRVLOCK;
- oa->o_valid |= OBD_MD_FLFLAGS;
- }
- } else {
- LASSERT(oio->oi_lockless == 0);
- }
+ if (ia_avalid & ATTR_SIZE) {
+ if (io_is_falloc) {
+ oa->o_size = size;
+ oa->o_blocks = end;
+ oa->o_valid |= OBD_MD_FLSIZE | OBD_MD_FLBLOCKS;
+ } else {
+ oa->o_size = size;
+ oa->o_blocks = OBD_OBJECT_EOF;
+ oa->o_valid |= OBD_MD_FLSIZE | OBD_MD_FLBLOCKS;
+ }
+
+ if (oio->oi_lockless) {
+ oa->o_flags = OBD_FL_SRVLOCK;
+ oa->o_valid |= OBD_MD_FLFLAGS;
+ }
+
+ if (io->ci_layout_version > 0) {
+ /* verify layout version */
+ oa->o_valid |= OBD_MD_LAYOUT_VERSION;
+ oa->o_layout_version = io->ci_layout_version;
+ }
+ } else {
+ LASSERT(oio->oi_lockless == 0);
+ }
- if (ia_valid & ATTR_ATTR_FLAG) {
+ if (ia_xvalid & OP_XVALID_FLAGS) {
oa->o_flags = io->u.ci_setattr.sa_attr_flags;
oa->o_valid |= OBD_MD_FLFLAGS;
}
init_completion(&cbargs->opc_sync);
- if (ia_valid & ATTR_SIZE)
- result = osc_punch_base(osc_export(cl2osc(obj)),
- oa, osc_async_upcall,
- cbargs, PTLRPCD_SET);
- else
+ if (io_is_falloc) {
+ int falloc_mode = io->u.ci_setattr.sa_falloc_mode;
+
+ result = osc_fallocate_base(osc_export(cl2osc(obj)),
+ oa, osc_async_upcall,
+ cbargs, falloc_mode);
+ } else if (ia_avalid & ATTR_SIZE) {
+ result = osc_punch_send(osc_export(cl2osc(obj)),
+ oa, osc_async_upcall, cbargs);
+ } else {
result = osc_setattr_async(osc_export(cl2osc(obj)),
oa, osc_async_upcall,
cbargs, PTLRPCD_SET);
-
+ }
cbargs->opc_rpc_sent = result == 0;
}
- return result;
+ RETURN(result);
}
-static void osc_io_setattr_end(const struct lu_env *env,
- const struct cl_io_slice *slice)
+void osc_io_setattr_end(const struct lu_env *env,
+ const struct cl_io_slice *slice)
{
struct cl_io *io = slice->cis_io;
struct osc_io *oio = cl2osc_io(env, slice);
struct cl_object *obj = slice->cis_obj;
struct osc_async_cbargs *cbargs = &oio->oi_cbarg;
- int result = 0;
+ struct cl_attr *attr = &osc_env_info(env)->oti_attr;
+ struct obdo *oa = &oio->oi_oa;
+ unsigned int cl_valid = 0;
+ int result = 0;
if (cbargs->opc_rpc_sent) {
wait_for_completion(&cbargs->opc_sync);
result = io->ci_result = cbargs->opc_rc;
}
- if (result == 0) {
- if (oio->oi_lockless) {
- /* lockless truncate */
- struct osc_device *osd = lu2osc_dev(obj->co_lu.lo_dev);
- LASSERT(cl_io_is_trunc(io));
- /* XXX: Need a lock. */
- osd->od_stats.os_lockless_truncates++;
- }
- }
+ if (result == 0) {
+ if (oio->oi_lockless) {
+ /* lockless truncate */
+ struct osc_device *osd = lu2osc_dev(obj->co_lu.lo_dev);
+
+ LASSERT(cl_io_is_trunc(io));
+ LASSERT(cl_io_is_trunc(io) || cl_io_is_fallocate(io));
+ /* XXX: Need a lock. */
+ osd->od_stats.os_lockless_truncates++;
+ }
+ }
if (cl_io_is_trunc(io)) {
__u64 size = io->u.ci_setattr.sa_attr.lvb_size;
+
+ if (result == 0) {
+ cl_object_attr_lock(obj);
+ if (oa->o_valid & OBD_MD_FLBLOCKS) {
+ attr->cat_blocks = oa->o_blocks;
+ cl_valid |= CAT_BLOCKS;
+ }
+
+ cl_object_attr_update(env, obj, attr, cl_valid);
+ cl_object_attr_unlock(obj);
+ }
osc_trunc_check(env, io, oio, size);
- if (oio->oi_trunc != NULL) {
- osc_cache_truncate_end(env, oio, cl2osc(obj));
- oio->oi_trunc = NULL;
+ osc_cache_truncate_end(env, oio->oi_trunc);
+ oio->oi_trunc = NULL;
+ }
+
+ if (cl_io_is_fallocate(io)) {
+ cl_object_attr_lock(obj);
+
+ /* update blocks */
+ if (oa->o_valid & OBD_MD_FLBLOCKS) {
+ attr->cat_blocks = oa->o_blocks;
+ cl_valid |= CAT_BLOCKS;
}
+
+ /* update size */
+ if (oa->o_valid & OBD_MD_FLSIZE) {
+ attr->cat_size = oa->o_size;
+ cl_valid |= CAT_SIZE;
+ }
+
+ cl_object_attr_update(env, obj, attr, cl_valid);
+ cl_object_attr_unlock(obj);
}
}
+EXPORT_SYMBOL(osc_io_setattr_end);
struct osc_data_version_args {
struct osc_io *dva_oio;
static int
osc_data_version_interpret(const struct lu_env *env, struct ptlrpc_request *req,
- void *arg, int rc)
+ void *args, int rc)
{
- struct osc_data_version_args *dva = arg;
+ struct osc_data_version_args *dva = args;
struct osc_io *oio = dva->dva_oio;
const struct ost_body *body;
ptlrpc_request_set_replen(req);
req->rq_interpret_reply = osc_data_version_interpret;
- CLASSERT(sizeof(*dva) <= sizeof(req->rq_async_args));
- dva = ptlrpc_req_async_args(req);
+ dva = ptlrpc_req_async_args(dva, req);
dva->dva_oio = oio;
ptlrpcd_add_req(req);
if (cbargs->opc_rc != 0) {
slice->cis_io->ci_result = cbargs->opc_rc;
- } else if (!(oio->oi_oa.o_valid & OBD_MD_FLDATAVERSION)) {
- slice->cis_io->ci_result = -EOPNOTSUPP;
} else {
- dv->dv_data_version = oio->oi_oa.o_data_version;
slice->cis_io->ci_result = 0;
+ if (!(oio->oi_oa.o_valid &
+ (OBD_MD_LAYOUT_VERSION | OBD_MD_FLDATAVERSION)))
+ slice->cis_io->ci_result = -ENOTSUPP;
+
+ if (oio->oi_oa.o_valid & OBD_MD_LAYOUT_VERSION)
+ dv->dv_layout_version = oio->oi_oa.o_layout_version;
+ if (oio->oi_oa.o_valid & OBD_MD_FLDATAVERSION)
+ dv->dv_data_version = oio->oi_oa.o_data_version;
}
EXIT;
}
-static int osc_io_read_start(const struct lu_env *env,
- const struct cl_io_slice *slice)
+int osc_io_read_start(const struct lu_env *env,
+ const struct cl_io_slice *slice)
{
struct cl_object *obj = slice->cis_obj;
struct cl_attr *attr = &osc_env_info(env)->oti_attr;
if (!slice->cis_io->ci_noatime) {
cl_object_attr_lock(obj);
- attr->cat_atime = LTIME_S(CFS_CURRENT_TIME);
+ attr->cat_atime = ktime_get_real_seconds();
rc = cl_object_attr_update(env, obj, attr, CAT_ATIME);
cl_object_attr_unlock(obj);
}
RETURN(rc);
}
+EXPORT_SYMBOL(osc_io_read_start);
-static int osc_io_write_start(const struct lu_env *env,
- const struct cl_io_slice *slice)
+int osc_io_write_start(const struct lu_env *env,
+ const struct cl_io_slice *slice)
{
struct cl_object *obj = slice->cis_obj;
struct cl_attr *attr = &osc_env_info(env)->oti_attr;
OBD_FAIL_TIMEOUT(OBD_FAIL_OSC_DELAY_SETTIME, 1);
cl_object_attr_lock(obj);
- attr->cat_mtime = attr->cat_ctime = LTIME_S(CFS_CURRENT_TIME);
+ attr->cat_mtime = attr->cat_ctime = ktime_get_real_seconds();
rc = cl_object_attr_update(env, obj, attr, CAT_MTIME | CAT_CTIME);
cl_object_attr_unlock(obj);
RETURN(rc);
}
+EXPORT_SYMBOL(osc_io_write_start);
-static int osc_fsync_ost(const struct lu_env *env, struct osc_object *obj,
- struct cl_fsync_io *fio)
+int osc_fsync_ost(const struct lu_env *env, struct osc_object *obj,
+ struct cl_fsync_io *fio)
{
struct osc_io *oio = osc_env_io(env);
struct obdo *oa = &oio->oi_oa;
rc = osc_sync_base(obj, oa, osc_async_upcall, cbargs, PTLRPCD_SET);
RETURN(rc);
}
+EXPORT_SYMBOL(osc_fsync_ost);
-static int osc_io_fsync_start(const struct lu_env *env,
- const struct cl_io_slice *slice)
+int osc_io_fsync_start(const struct lu_env *env,
+ const struct cl_io_slice *slice)
{
struct cl_io *io = slice->cis_io;
struct cl_fsync_io *fio = &io->u.ci_fsync;
RETURN(result);
}
-static void osc_io_fsync_end(const struct lu_env *env,
- const struct cl_io_slice *slice)
+void osc_io_fsync_end(const struct lu_env *env,
+ const struct cl_io_slice *slice)
{
struct cl_fsync_io *fio = &slice->cis_io->u.ci_fsync;
struct cl_object *obj = slice->cis_obj;
}
slice->cis_io->ci_result = result;
}
+EXPORT_SYMBOL(osc_io_fsync_end);
-static void osc_io_end(const struct lu_env *env,
- const struct cl_io_slice *slice)
+static int osc_io_ladvise_start(const struct lu_env *env,
+ const struct cl_io_slice *slice)
+{
+ int result = 0;
+ struct cl_io *io = slice->cis_io;
+ struct osc_io *oio = cl2osc_io(env, slice);
+ struct cl_object *obj = slice->cis_obj;
+ struct lov_oinfo *loi = cl2osc(obj)->oo_oinfo;
+ struct cl_ladvise_io *lio = &io->u.ci_ladvise;
+ struct obdo *oa = &oio->oi_oa;
+ struct osc_async_cbargs *cbargs = &oio->oi_cbarg;
+ struct lu_ladvise *ladvise;
+ struct ladvise_hdr *ladvise_hdr;
+ int buf_size;
+ int num_advise = 1;
+ ENTRY;
+
+ /* TODO: add multiple ladvise support in CLIO */
+ buf_size = offsetof(typeof(*ladvise_hdr), lah_advise[num_advise]);
+ if (osc_env_info(env)->oti_ladvise_buf.lb_len < buf_size)
+ lu_buf_realloc(&osc_env_info(env)->oti_ladvise_buf, buf_size);
+
+ ladvise_hdr = osc_env_info(env)->oti_ladvise_buf.lb_buf;
+ if (ladvise_hdr == NULL)
+ RETURN(-ENOMEM);
+
+ memset(ladvise_hdr, 0, buf_size);
+ ladvise_hdr->lah_magic = LADVISE_MAGIC;
+ ladvise_hdr->lah_count = num_advise;
+ ladvise_hdr->lah_flags = lio->li_flags;
+
+ memset(oa, 0, sizeof(*oa));
+ oa->o_oi = loi->loi_oi;
+ oa->o_valid = OBD_MD_FLID;
+ obdo_set_parent_fid(oa, lio->li_fid);
+
+ ladvise = ladvise_hdr->lah_advise;
+ ladvise->lla_start = lio->li_start;
+ ladvise->lla_end = lio->li_end;
+ ladvise->lla_advice = lio->li_advice;
+
+ if (lio->li_flags & LF_ASYNC) {
+ result = osc_ladvise_base(osc_export(cl2osc(obj)), oa,
+ ladvise_hdr, NULL, NULL, NULL);
+ } else {
+ init_completion(&cbargs->opc_sync);
+ result = osc_ladvise_base(osc_export(cl2osc(obj)), oa,
+ ladvise_hdr, osc_async_upcall,
+ cbargs, PTLRPCD_SET);
+ cbargs->opc_rpc_sent = result == 0;
+ }
+ RETURN(result);
+}
+
+static void osc_io_ladvise_end(const struct lu_env *env,
+ const struct cl_io_slice *slice)
+{
+ struct cl_io *io = slice->cis_io;
+ struct osc_io *oio = cl2osc_io(env, slice);
+ struct osc_async_cbargs *cbargs = &oio->oi_cbarg;
+ int result = 0;
+ struct cl_ladvise_io *lio = &io->u.ci_ladvise;
+
+ if ((!(lio->li_flags & LF_ASYNC)) && cbargs->opc_rpc_sent) {
+ wait_for_completion(&cbargs->opc_sync);
+ result = cbargs->opc_rc;
+ }
+ slice->cis_io->ci_result = result;
+}
+
+void osc_io_end(const struct lu_env *env, const struct cl_io_slice *slice)
{
struct osc_io *oio = cl2osc_io(env, slice);
oio->oi_active = NULL;
}
}
+EXPORT_SYMBOL(osc_io_end);
+
+struct osc_lseek_args {
+ struct osc_io *lsa_oio;
+};
+
+static int osc_lseek_interpret(const struct lu_env *env,
+ struct ptlrpc_request *req,
+ void *arg, int rc)
+{
+ struct ost_body *reply;
+ struct osc_lseek_args *lsa = arg;
+ struct osc_io *oio = lsa->lsa_oio;
+ struct cl_io *io = oio->oi_cl.cis_io;
+ struct cl_lseek_io *lsio = &io->u.ci_lseek;
+
+ ENTRY;
+
+ if (rc != 0)
+ GOTO(out, rc);
+
+ reply = req_capsule_server_get(&req->rq_pill, &RMF_OST_BODY);
+ if (reply == NULL)
+ GOTO(out, rc = -EPROTO);
+
+ lsio->ls_result = reply->oa.o_size;
+out:
+ osc_async_upcall(&oio->oi_cbarg, rc);
+ RETURN(rc);
+}
+
+int osc_io_lseek_start(const struct lu_env *env,
+ const struct cl_io_slice *slice)
+{
+ struct cl_io *io = slice->cis_io;
+ struct osc_io *oio = cl2osc_io(env, slice);
+ struct cl_object *obj = slice->cis_obj;
+ struct lov_oinfo *loi = cl2osc(obj)->oo_oinfo;
+ struct cl_lseek_io *lsio = &io->u.ci_lseek;
+ struct obdo *oa = &oio->oi_oa;
+ struct osc_async_cbargs *cbargs = &oio->oi_cbarg;
+ struct obd_export *exp = osc_export(cl2osc(obj));
+ struct ptlrpc_request *req;
+ struct ost_body *body;
+ struct osc_lseek_args *lsa;
+ int rc = 0;
+
+ ENTRY;
+
+ /* No negative values at this point */
+ LASSERT(lsio->ls_start >= 0);
+ LASSERT(lsio->ls_whence == SEEK_HOLE || lsio->ls_whence == SEEK_DATA);
+
+ /* with IO lock taken we have object size in LVB and can check
+ * boundaries prior sending LSEEK RPC
+ */
+ if (lsio->ls_start >= loi->loi_lvb.lvb_size) {
+ /* consider area beyond end of object as hole */
+ if (lsio->ls_whence == SEEK_HOLE)
+ lsio->ls_result = lsio->ls_start;
+ else
+ lsio->ls_result = -ENXIO;
+ RETURN(0);
+ }
+
+ /* if LSEEK RPC is not supported by server, consider whole stripe
+ * object is data with hole after end of object
+ */
+ if (!exp_connect_lseek(exp)) {
+ if (lsio->ls_whence == SEEK_HOLE)
+ lsio->ls_result = loi->loi_lvb.lvb_size;
+ else
+ lsio->ls_result = lsio->ls_start;
+ RETURN(0);
+ }
+
+ memset(oa, 0, sizeof(*oa));
+ oa->o_oi = loi->loi_oi;
+ oa->o_valid = OBD_MD_FLID | OBD_MD_FLGROUP;
+ oa->o_size = lsio->ls_start;
+ oa->o_mode = lsio->ls_whence;
+ if (oio->oi_lockless) {
+ oa->o_flags = OBD_FL_SRVLOCK;
+ oa->o_valid |= OBD_MD_FLFLAGS;
+ }
+
+ init_completion(&cbargs->opc_sync);
+ req = ptlrpc_request_alloc(class_exp2cliimp(exp), &RQF_OST_SEEK);
+ if (req == NULL)
+ RETURN(-ENOMEM);
+
+ rc = ptlrpc_request_pack(req, LUSTRE_OST_VERSION, OST_SEEK);
+ if (rc < 0) {
+ ptlrpc_request_free(req);
+ RETURN(rc);
+ }
+
+ body = req_capsule_client_get(&req->rq_pill, &RMF_OST_BODY);
+ lustre_set_wire_obdo(&req->rq_import->imp_connect_data, &body->oa, oa);
+ ptlrpc_request_set_replen(req);
+ req->rq_interpret_reply = osc_lseek_interpret;
+ lsa = ptlrpc_req_async_args(lsa, req);
+ lsa->lsa_oio = oio;
+
+ ptlrpcd_add_req(req);
+ cbargs->opc_rpc_sent = 1;
+
+ RETURN(0);
+}
+EXPORT_SYMBOL(osc_io_lseek_start);
+
+void osc_io_lseek_end(const struct lu_env *env,
+ const struct cl_io_slice *slice)
+{
+ struct osc_io *oio = cl2osc_io(env, slice);
+ struct osc_async_cbargs *cbargs = &oio->oi_cbarg;
+ int rc = 0;
+
+ if (cbargs->opc_rpc_sent) {
+ wait_for_completion(&cbargs->opc_sync);
+ rc = cbargs->opc_rc;
+ }
+ slice->cis_io->ci_result = rc;
+}
+EXPORT_SYMBOL(osc_io_lseek_end);
static const struct cl_io_operations osc_io_ops = {
.op = {
[CIT_READ] = {
+ .cio_iter_init = osc_io_rw_iter_init,
+ .cio_iter_fini = osc_io_rw_iter_fini,
.cio_start = osc_io_read_start,
.cio_fini = osc_io_fini
},
.cio_fini = osc_io_fini
},
[CIT_SETATTR] = {
+ .cio_iter_init = osc_io_iter_init,
+ .cio_iter_fini = osc_io_iter_fini,
.cio_start = osc_io_setattr_start,
.cio_end = osc_io_setattr_end
},
.cio_end = osc_io_data_version_end,
},
[CIT_FAULT] = {
+ .cio_iter_init = osc_io_iter_init,
+ .cio_iter_fini = osc_io_iter_fini,
.cio_start = osc_io_fault_start,
.cio_end = osc_io_end,
.cio_fini = osc_io_fini
.cio_end = osc_io_fsync_end,
.cio_fini = osc_io_fini
},
+ [CIT_LADVISE] = {
+ .cio_start = osc_io_ladvise_start,
+ .cio_end = osc_io_ladvise_end,
+ .cio_fini = osc_io_fini
+ },
+ [CIT_LSEEK] = {
+ .cio_start = osc_io_lseek_start,
+ .cio_end = osc_io_lseek_end,
+ .cio_fini = osc_io_fini
+ },
[CIT_MISC] = {
.cio_fini = osc_io_fini
}
*
*/
-static int osc_req_prep(const struct lu_env *env,
- const struct cl_req_slice *slice)
-{
- return 0;
-}
-
-static void osc_req_completion(const struct lu_env *env,
- const struct cl_req_slice *slice, int ioret)
-{
- struct osc_req *or;
-
- or = cl2osc_req(slice);
- OBD_SLAB_FREE_PTR(or, osc_req_kmem);
-}
-
-/**
- * Implementation of struct cl_req_operations::cro_attr_set() for osc
- * layer. osc is responsible for struct obdo::o_id and struct obdo::o_seq
- * fields.
- */
-static void osc_req_attr_set(const struct lu_env *env,
- const struct cl_req_slice *slice,
- const struct cl_object *obj,
- struct cl_req_attr *attr, u64 flags)
-{
- struct lov_oinfo *oinfo;
- struct cl_req *clerq;
- struct cl_page *apage; /* _some_ page in @clerq */
- struct ldlm_lock *lock; /* _some_ lock protecting @apage */
- struct osc_page *opg;
- struct obdo *oa;
- struct ost_lvb *lvb;
-
- oinfo = cl2osc(obj)->oo_oinfo;
- lvb = &oinfo->loi_lvb;
- oa = attr->cra_oa;
-
- if ((flags & OBD_MD_FLMTIME) != 0) {
- oa->o_mtime = lvb->lvb_mtime;
- oa->o_valid |= OBD_MD_FLMTIME;
- }
- if ((flags & OBD_MD_FLATIME) != 0) {
- oa->o_atime = lvb->lvb_atime;
- oa->o_valid |= OBD_MD_FLATIME;
- }
- if ((flags & OBD_MD_FLCTIME) != 0) {
- oa->o_ctime = lvb->lvb_ctime;
- oa->o_valid |= OBD_MD_FLCTIME;
- }
- if (flags & OBD_MD_FLGROUP) {
- ostid_set_seq(&oa->o_oi, ostid_seq(&oinfo->loi_oi));
- oa->o_valid |= OBD_MD_FLGROUP;
- }
- if (flags & OBD_MD_FLID) {
- ostid_set_id(&oa->o_oi, ostid_id(&oinfo->loi_oi));
- oa->o_valid |= OBD_MD_FLID;
- }
- if (flags & OBD_MD_FLHANDLE) {
- clerq = slice->crs_req;
- LASSERT(!list_empty(&clerq->crq_pages));
- apage = container_of(clerq->crq_pages.next,
- struct cl_page, cp_flight);
- opg = osc_cl_page_osc(apage, NULL);
- lock = osc_dlmlock_at_pgoff(env, cl2osc(obj), osc_index(opg),
- OSC_DAP_FL_TEST_LOCK | OSC_DAP_FL_CANCELING);
- if (lock == NULL && !opg->ops_srvlock) {
- struct ldlm_resource *res;
- struct ldlm_res_id *resname;
-
- CL_PAGE_DEBUG(D_ERROR, env, apage, "uncovered page!\n");
-
- resname = &osc_env_info(env)->oti_resname;
- ostid_build_res_name(&oinfo->loi_oi, resname);
- res = ldlm_resource_get(
- osc_export(cl2osc(obj))->exp_obd->obd_namespace,
- NULL, resname, LDLM_EXTENT, 0);
- ldlm_resource_dump(D_ERROR, res);
-
- libcfs_debug_dumpstack(NULL);
- LBUG();
- }
-
- /* check for lockless io. */
- if (lock != NULL) {
- oa->o_handle = lock->l_remote_handle;
- oa->o_valid |= OBD_MD_FLHANDLE;
- LDLM_LOCK_PUT(lock);
- }
- }
-}
-
-static const struct cl_req_operations osc_req_ops = {
- .cro_prep = osc_req_prep,
- .cro_attr_set = osc_req_attr_set,
- .cro_completion = osc_req_completion
-};
-
-
int osc_io_init(const struct lu_env *env,
struct cl_object *obj, struct cl_io *io)
{
return 0;
}
-int osc_req_init(const struct lu_env *env, struct cl_device *dev,
- struct cl_req *req)
-{
- struct osc_req *or;
- int result;
-
- OBD_SLAB_ALLOC_PTR_GFP(or, osc_req_kmem, GFP_NOFS);
- if (or != NULL) {
- cl_req_slice_add(req, &or->or_cl, dev, &osc_req_ops);
- result = 0;
- } else
- result = -ENOMEM;
- return result;
-}
-
/** @} osc */
git://git.whamcloud.com / fs / lustre-release.git / blobdiff