dsl_pool.c revision c33e334fd3eb2b3d91c4b9667d7a465b6924e8d3
/*
* CDDL HEADER START
*
* The contents of this file are subject to the terms of the
* Common Development and Distribution License (the "License").
* You may not use this file except in compliance with the License.
*
* You can obtain a copy of the license at usr/src/OPENSOLARIS.LICENSE
* See the License for the specific language governing permissions
* and limitations under the License.
*
* When distributing Covered Code, include this CDDL HEADER in each
* file and include the License file at usr/src/OPENSOLARIS.LICENSE.
* If applicable, add the following below this CDDL HEADER, with the
* fields enclosed by brackets "[]" replaced with your own identifying
* information: Portions Copyright [yyyy] [name of copyright owner]
*
* CDDL HEADER END
*/
/*
* Copyright 2009 Sun Microsystems, Inc. All rights reserved.
* Use is subject to license terms.
*/
#include <sys/dsl_pool.h>
#include <sys/dsl_dataset.h>
#include <sys/dsl_synctask.h>
#include <sys/dmu_objset.h>
#include <sys/zfs_context.h>
#include <sys/zfs_znode.h>
#include <sys/spa_impl.h>
int zfs_no_write_throttle = 0;
static pgcnt_t old_physmem = 0;
static int
{
int err;
if (err)
return (err);
}
static dsl_pool_t *
{
dsl_pool_t *dp;
1, 4, 0);
return (dp);
}
int
{
int err;
&dp->dp_meta_objset);
if (err)
goto out;
&dp->dp_root_dir_obj);
if (err)
goto out;
if (err)
goto out;
if (err)
goto out;
if (err)
goto out;
if (err == 0) {
&dp->dp_origin_snap);
}
if (err)
goto out;
}
err = 0;
if (err)
goto out;
/* get scrub status */
&dp->dp_scrub_func);
if (err == 0) {
&dp->dp_scrub_queue_obj);
if (err)
goto out;
&dp->dp_scrub_min_txg);
if (err)
goto out;
&dp->dp_scrub_max_txg);
if (err)
goto out;
&dp->dp_scrub_bookmark);
if (err)
goto out;
&spa->spa_scrub_errors);
if (err)
goto out;
/*
* A new-type scrub was in progress on an old
* pool. Restart from the beginning, since the
* old software may have changed the pool in the
* meantime.
*/
}
} else {
/*
* It's OK if there is no scrub in progress (and if
* there was an I/O error, ignore it).
*/
err = 0;
}
out:
if (err)
else
return (err);
}
void
{
/* drop our references from dsl_pool_open() */
/*
* Since we held the origin_snap from "syncing" context (which
* includes pool-opening context), it actually only got a "ref"
* and not a hold, so just drop that here.
*/
if (dp->dp_origin_snap)
if (dp->dp_mos_dir)
if (dp->dp_root_dir)
/* undo the dmu_objset_open_impl(mos) from dsl_pool_open() */
if (dp->dp_meta_objset)
if (dp->dp_blkstats)
}
{
int err;
/* create and open the MOS (meta-objset) */
/* create the pool directory */
/* create and open the root dir */
/* create and open the meta-objset dir */
/* create the root dataset */
/* create the root objset */
#ifdef _KERNEL
#endif
return (dp);
}
void
{
int err;
dp->dp_read_overhead = 0;
/*
* We must not sync any non-MOS datasets twice, because
* we may have taken a snapshot of them. However, we
* may sync newly-created datasets on pass 2.
*/
}
/*
* Sync the datasets again to push out the changes due to
* userquota updates. This must be done before we process the
* sync tasks, because that could cause a snapshot of a dataset
* whose ds_bp will be rewritten when we do this 2nd sync.
*/
}
/*
* No more sync tasks should have been added while we
* were syncing.
*/
}
}
/*
* If the write limit max has not been explicitly set, set it
* to a fraction of available physical memory (default 1/8th).
* Note that we must inflate the limit because the spa
* inflates write sizes to account for data replication.
* Check this each sync phase to catch changing memory size.
*/
}
/*
* Attempt to keep the sync time consistent by adjusting the
* amount of write traffic allowed into each transaction group.
* Weight the throughput calculation towards the current value:
* thru = 3/4 old_thru + 1/4 new_thru
*/
ASSERT(zfs_write_limit_min > 0);
if (dp->dp_throughput)
else
}
}
void
{
}
}
/*
* TRUE if the current thread is the tx_sync_thread or if we
* are being called from SPA context during pool initialization.
*/
int
{
}
{
/*
* Reserve about 1.6% (1/64), or at least 32MB, for allocation
* efficiency.
* XXX The intent log is not accounted for, so it must fit
* within this slop.
*
* If we're trying to assess whether it's OK to do a free,
* cut the reservation in half to allow forward progress
* (e.g. make it possible to rm(1) files from a full pool).
*/
if (netfree)
resv >>= 1;
}
int
{
if (zfs_no_write_throttle) {
space);
return (0);
}
/*
* Check to see if we have exceeded the maximum allowed IO for
* this transaction group. We can do this without locks since
* a little slop here is ok. Note that we do the reserved check
* with only half the requested reserve: this is because the
* reserve requests are worst-case, and we really don't want to
* throttle based off of worst-case estimates.
*/
if (write_limit > 0) {
return (ERESTART);
}
/*
* If this transaction group is over 7/8ths capacity, delay
* the caller 1 clock tick. This will slow down the "fill"
* rate until the sync process can catch up with us.
*/
return (0);
}
void
{
}
void
{
uint64_t space_inuse = 0;
int i;
return;
for (i = 0; i < TXG_SIZE; i++) {
}
}
void
{
if (space > 0) {
}
}
/* ARGSUSED */
static int
{
int err;
if (err)
return (err);
if (err) {
return (err);
}
break;
}
/*
* The $ORIGIN can't have any data, or the accounting
* will be wrong.
*/
/* The origin doesn't get attached to itself */
return (0);
}
}
}
}
return (0);
}
void
{
tx, DS_FIND_CHILDREN));
}
void
{
/* create the origin dir, ds, & snap-ds */
}
taskq_t *
{
return (dp->dp_vnrele_taskq);
}
/*
* Walk through the pool-wide zap object of temporary snapshot user holds
* and release them.
*/
void
{
if (zapobj == 0)
return;
zap_cursor_advance(&zc)) {
char *htag;
*htag = '\0';
++htag;
}
}
/*
* Create the pool-wide zap object for storing temporary snapshot holds.
*/
void
{
DMU_OT_NONE, 0, tx);
}
static int
{
char *name;
int error;
/*
* If the pool was created prior to SPA_VERSION_USERREFS, the
* zap object for temporary holds might not exist yet.
*/
if (zapobj == 0) {
if (holding) {
} else {
return (ENOENT);
}
}
if (holding)
else
return (error);
}
/*
* Add a temporary hold for the given dataset object and tag.
*/
int
{
}
/*
* Release a temporary hold for the given dataset object and tag.
*/
int
{
}