* Copyright (c) 2008, 2010, Oracle and/or its affiliates. All rights reserved.
* Use is subject to license terms.
*
- * Copyright (c) 2012, 2016, Intel Corporation.
+ * Copyright (c) 2012, 2017, Intel Corporation.
*
*/
/*
if (ext->oe_sync && ext->oe_grants > 0)
GOTO(out, rc = 90);
- if (ext->oe_dlmlock != NULL && !ldlm_is_failed(ext->oe_dlmlock)) {
+ if (ext->oe_dlmlock != NULL &&
+ ext->oe_dlmlock->l_resource->lr_type == LDLM_EXTENT &&
+ !ldlm_is_failed(ext->oe_dlmlock)) {
struct ldlm_extent *extent;
extent = &ext->oe_dlmlock->l_policy_data.l_extent;
pgoff_t ext_chk_end = ext->oe_end >> ppc_bits;
LASSERT(sanity_check_nolock(ext) == 0);
- if (chunk > ext_chk_end + 1)
+ if (chunk > ext_chk_end + 1 || chunk < ext_chk_start)
break;
/* if covering by different locks, no chance to match */
struct client_obd *cli = osc_cli(obj);
struct osc_async_page *oap;
struct osc_async_page *tmp;
+ struct pagevec *pvec;
int pages_in_chunk = 0;
int ppc_bits = cli->cl_chunkbits -
PAGE_SHIFT;
if (IS_ERR(env))
RETURN(PTR_ERR(env));
- io = &osc_env_info(env)->oti_io;
+ io = osc_env_thread_io(env);
io->ci_obj = cl_object_top(osc2cl(obj));
io->ci_ignore_layout = 1;
+ pvec = &osc_env_info(env)->oti_pagevec;
+ ll_pagevec_init(pvec, 0);
rc = cl_io_init(env, io, CIT_MISC, io->ci_obj);
if (rc < 0)
GOTO(out, rc);
}
lu_ref_del(&page->cp_reference, "truncate", current);
- cl_page_put(env, page);
+ cl_pagevec_put(env, page, pvec);
--ext->oe_nr_pages;
++nr_pages;
}
+ pagevec_release(pvec);
+
EASSERTF(ergo(ext->oe_start >= trunc_index + !!partial,
ext->oe_nr_pages == 0),
ext, "trunc_index %lu, partial %d\n", trunc_index, partial);
ENTRY;
result = cl_page_make_ready(env, page, CRT_WRITE);
if (result == 0)
- opg->ops_submit_time = cfs_time_current();
+ opg->ops_submit_time = ktime_get();
RETURN(result);
}
pgoff_t index = osc_index(oap2osc(oap));
struct cl_object *obj;
struct cl_attr *attr = &osc_env_info(env)->oti_attr;
-
int result;
loff_t kms;
/* Clear opg->ops_transfer_pinned before VM lock is released. */
opg->ops_transfer_pinned = 0;
- opg->ops_submit_time = 0;
+ opg->ops_submit_time = ktime_set(0, 0);
srvlock = oap->oap_brw_flags & OBD_BRW_SRVLOCK;
/* statistic */
EXIT;
}
+EXPORT_SYMBOL(osc_wake_cache_waiters);
static int osc_max_rpc_in_flight(struct client_obd *cli, struct osc_object *osc)
{
if (tmp->oe_srvlock != ext->oe_srvlock ||
!tmp->oe_grants != !ext->oe_grants ||
+ tmp->oe_ndelay != ext->oe_ndelay ||
tmp->oe_no_merge || ext->oe_no_merge)
RETURN(0);
RETURN(1);
}
-static inline unsigned osc_max_write_chunks(const struct client_obd *cli)
-{
- /*
- * LU-8135:
- *
- * The maximum size of a single transaction is about 64MB in ZFS.
- * #define DMU_MAX_ACCESS (64 * 1024 * 1024)
- *
- * Since ZFS is a copy-on-write file system, a single dirty page in
- * a chunk will result in the rewrite of the whole chunk, therefore
- * an RPC shouldn't be allowed to contain too many chunks otherwise
- * it will make transaction size much bigger than 64MB, especially
- * with big block size for ZFS.
- *
- * This piece of code is to make sure that OSC won't send write RPCs
- * with too many chunks. The maximum chunk size that an RPC can cover
- * is set to PTLRPC_MAX_BRW_SIZE, which is defined to 16MB. Ideally
- * OST should tell the client what the biggest transaction size is,
- * but it's good enough for now.
- *
- * This limitation doesn't apply to ldiskfs, which allows as many
- * chunks in one RPC as we want. However, it won't have any benefits
- * to have too many discontiguous pages in one RPC.
- *
- * An osc_extent won't cover over a RPC size, so the chunks in an
- * osc_extent won't bigger than PTLRPC_MAX_BRW_SIZE >> chunkbits.
- */
- return PTLRPC_MAX_BRW_SIZE >> cli->cl_chunkbits;
-}
-
/**
* In order to prevent multiple ptlrpcd from breaking contiguous extents,
* get_write_extent() takes all appropriate extents in atomic.
oap, page, oap->oap_obj_off);
RETURN(0);
}
+EXPORT_SYMBOL(osc_prep_async_page);
int osc_queue_async_io(const struct lu_env *env, struct cl_io *io,
struct osc_page *ops)
++ext->oe_nr_pages;
list_add_tail(&oap->oap_pending_item, &ext->oe_pages);
osc_object_unlock(osc);
+
+ if (!ext->oe_layout_version)
+ ext->oe_layout_version = io->ci_layout_version;
}
+
RETURN(rc);
}
RETURN(rc);
}
-int osc_queue_sync_pages(const struct lu_env *env, struct osc_object *obj,
- struct list_head *list, int cmd, int brw_flags)
+int osc_queue_sync_pages(const struct lu_env *env, const struct cl_io *io,
+ struct osc_object *obj, struct list_head *list,
+ int brw_flags)
{
struct client_obd *cli = osc_cli(obj);
struct osc_extent *ext;
RETURN(-ENOMEM);
}
- ext->oe_rw = !!(cmd & OBD_BRW_READ);
+ ext->oe_rw = !!(brw_flags & OBD_BRW_READ);
ext->oe_sync = 1;
ext->oe_no_merge = !can_merge;
ext->oe_urgent = 1;
ext->oe_end = ext->oe_max_end = end;
ext->oe_obj = obj;
ext->oe_srvlock = !!(brw_flags & OBD_BRW_SRVLOCK);
+ ext->oe_ndelay = !!(brw_flags & OBD_BRW_NDELAY);
ext->oe_nr_pages = page_count;
ext->oe_mppr = mppr;
list_splice_init(list, &ext->oe_pages);
+ ext->oe_layout_version = io->ci_layout_version;
osc_object_lock(obj);
/* Reuse the initial refcount for RPC, don't drop it */
osc_extent_state_set(ext, OES_LOCK_DONE);
- if (cmd & OBD_BRW_WRITE) {
+ if (!ext->oe_rw) { /* write */
list_add_tail(&ext->oe_link, &obj->oo_urgent_exts);
osc_update_pending(obj, OBD_BRW_WRITE, page_count);
} else {
}
RETURN(result);
}
+EXPORT_SYMBOL(osc_cache_truncate_start);
/**
* Called after osc_io_setattr_end to add oio->oi_trunc back to cache.
OSC_IO_DEBUG(obj, "sync file range.\n");
RETURN(result);
}
+EXPORT_SYMBOL(osc_cache_wait_range);
/**
* Called to write out a range of osc object.
OSC_IO_DEBUG(obj, "pageout [%lu, %lu], %d.\n", start, end, result);
RETURN(result);
}
+EXPORT_SYMBOL(osc_cache_writeback_range);
/**
* Returns a list of pages by a given [start, end] of \a obj.
osc_page_gang_cbt cb, void *cbdata)
{
struct osc_page *ops;
+ struct pagevec *pagevec;
void **pvec;
pgoff_t idx;
unsigned int nr;
idx = start;
pvec = osc_env_info(env)->oti_pvec;
+ pagevec = &osc_env_info(env)->oti_pagevec;
+ ll_pagevec_init(pagevec, 0);
spin_lock(&osc->oo_tree_lock);
while ((nr = radix_tree_gang_lookup(&osc->oo_tree, pvec,
idx, OTI_PVEC_SIZE)) > 0) {
page = ops->ops_cl.cpl_page;
lu_ref_del(&page->cp_reference, "gang_lookup", current);
- cl_page_put(env, page);
+ cl_pagevec_put(env, page, pagevec);
}
+ pagevec_release(pagevec);
+
if (nr < OTI_PVEC_SIZE || end_of_region)
break;
spin_unlock(&osc->oo_tree_lock);
RETURN(res);
}
+EXPORT_SYMBOL(osc_page_gang_lookup);
/**
* Check if page @page is covered by an extra lock or discard it.
return CLP_GANG_OKAY;
}
-static int discard_cb(const struct lu_env *env, struct cl_io *io,
- struct osc_page *ops, void *cbdata)
+int osc_discard_cb(const struct lu_env *env, struct cl_io *io,
+ struct osc_page *ops, void *cbdata)
{
struct osc_thread_info *info = osc_env_info(env);
struct cl_page *page = ops->ops_cl.cpl_page;
return CLP_GANG_OKAY;
}
+EXPORT_SYMBOL(osc_discard_cb);
/**
* Discard pages protected by the given lock. This function traverses radix
pgoff_t start, pgoff_t end, bool discard)
{
struct osc_thread_info *info = osc_env_info(env);
- struct cl_io *io = &info->oti_io;
+ struct cl_io *io = osc_env_thread_io(env);
osc_page_gang_cbt cb;
int res;
int result;
if (result != 0)
GOTO(out, result);
- cb = discard ? discard_cb : check_and_discard_cb;
+ cb = discard ? osc_discard_cb : check_and_discard_cb;
info->oti_fn_index = info->oti_next_index = start;
do {
res = osc_page_gang_lookup(env, io, osc,
git://git.whamcloud.com / fs / lustre-release.git / blobdiff