linux/fs/xfs/xfs_trans_priv.h

146 lines
4.3 KiB
C
Raw Normal View History

/*
* Copyright (c) 2000,2002,2005 Silicon Graphics, Inc.
* All Rights Reserved.
*
* This program is free software; you can redistribute it and/or
* modify it under the terms of the GNU General Public License as
* published by the Free Software Foundation.
*
* This program is distributed in the hope that it would 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; if not, write the Free Software Foundation,
* Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA
*/
#ifndef __XFS_TRANS_PRIV_H__
#define __XFS_TRANS_PRIV_H__
struct xfs_log_item;
struct xfs_log_item_desc;
struct xfs_mount;
struct xfs_trans;
xfs: bulk AIL insertion during transaction commit When inserting items into the AIL from the transaction committed callbacks, we take the AIL lock for every single item that is to be inserted. For a CIL checkpoint commit, this can be tens of thousands of individual inserts, yet almost all of the items will be inserted at the same point in the AIL because they have the same index. To reduce the overhead and contention on the AIL lock for such operations, introduce a "bulk insert" operation which allows a list of log items with the same LSN to be inserted in a single operation via a list splice. To do this, we need to pre-sort the log items being committed into a temporary list for insertion. The complexity is that not every log item will end up with the same LSN, and not every item is actually inserted into the AIL. Items that don't match the commit LSN will be inserted and unpinned as per the current one-at-a-time method (relatively rare), while items that are not to be inserted will be unpinned and freed immediately. Items that are to be inserted at the given commit lsn are placed in a temporary array and inserted into the AIL in bulk each time the array fills up. As a result of this, we trade off AIL hold time for a significant reduction in traffic. lock_stat output shows that the worst case hold time is unchanged, but contention from AIL inserts drops by an order of magnitude and the number of lock traversal decreases significantly. Signed-off-by: Dave Chinner <dchinner@redhat.com> Reviewed-by: Christoph Hellwig <hch@lst.de>
2010-12-20 01:02:19 +00:00
struct xfs_ail;
struct xfs_log_vec;
void xfs_trans_add_item(struct xfs_trans *, struct xfs_log_item *);
void xfs_trans_del_item(struct xfs_log_item *);
void xfs_trans_free_items(struct xfs_trans *tp, xfs_lsn_t commit_lsn,
int flags);
xfs: Introduce delayed logging core code The delayed logging code only changes in-memory structures and as such can be enabled and disabled with a mount option. Add the mount option and emit a warning that this is an experimental feature that should not be used in production yet. We also need infrastructure to track committed items that have not yet been written to the log. This is what the Committed Item List (CIL) is for. The log item also needs to be extended to track the current log vector, the associated memory buffer and it's location in the Commit Item List. Extend the log item and log vector structures to enable this tracking. To maintain the current log format for transactions with delayed logging, we need to introduce a checkpoint transaction and a context for tracking each checkpoint from initiation to transaction completion. This includes adding a log ticket for tracking space log required/used by the context checkpoint. To track all the changes we need an io vector array per log item, rather than a single array for the entire transaction. Using the new log vector structure for this requires two passes - the first to allocate the log vector structures and chain them together, and the second to fill them out. This log vector chain can then be passed to the CIL for formatting, pinning and insertion into the CIL. Formatting of the log vector chain is relatively simple - it's just a loop over the iovecs on each log vector, but it is made slightly more complex because we re-write the iovec after the copy to point back at the memory buffer we just copied into. This code also needs to pin log items. If the log item is not already tracked in this checkpoint context, then it needs to be pinned. Otherwise it is already pinned and we don't need to pin it again. The only other complexity is calculating the amount of new log space the formatting has consumed. This needs to be accounted to the transaction in progress, and the accounting is made more complex becase we need also to steal space from it for log metadata in the checkpoint transaction. Calculate all this at insert time and update all the tickets, counters, etc correctly. Once we've formatted all the log items in the transaction, attach the busy extents to the checkpoint context so the busy extents live until checkpoint completion and can be processed at that point in time. Transactions can then be freed at this point in time. Now we need to issue checkpoints - we are tracking the amount of log space used by the items in the CIL, so we can trigger background checkpoints when the space usage gets to a certain threshold. Otherwise, checkpoints need ot be triggered when a log synchronisation point is reached - a log force event. Because the log write code already handles chained log vectors, writing the transaction is trivial, too. Construct a transaction header, add it to the head of the chain and write it into the log, then issue a commit record write. Then we can release the checkpoint log ticket and attach the context to the log buffer so it can be called during Io completion to complete the checkpoint. We also need to allow for synchronising multiple in-flight checkpoints. This is needed for two things - the first is to ensure that checkpoint commit records appear in the log in the correct sequence order (so they are replayed in the correct order). The second is so that xfs_log_force_lsn() operates correctly and only flushes and/or waits for the specific sequence it was provided with. To do this we need a wait variable and a list tracking the checkpoint commits in progress. We can walk this list and wait for the checkpoints to change state or complete easily, an this provides the necessary synchronisation for correct operation in both cases. Signed-off-by: Dave Chinner <dchinner@redhat.com> Reviewed-by: Christoph Hellwig <hch@lst.de> Signed-off-by: Alex Elder <aelder@sgi.com>
2010-05-21 04:37:18 +00:00
void xfs_trans_unreserve_and_mod_sb(struct xfs_trans *tp);
xfs: bulk AIL insertion during transaction commit When inserting items into the AIL from the transaction committed callbacks, we take the AIL lock for every single item that is to be inserted. For a CIL checkpoint commit, this can be tens of thousands of individual inserts, yet almost all of the items will be inserted at the same point in the AIL because they have the same index. To reduce the overhead and contention on the AIL lock for such operations, introduce a "bulk insert" operation which allows a list of log items with the same LSN to be inserted in a single operation via a list splice. To do this, we need to pre-sort the log items being committed into a temporary list for insertion. The complexity is that not every log item will end up with the same LSN, and not every item is actually inserted into the AIL. Items that don't match the commit LSN will be inserted and unpinned as per the current one-at-a-time method (relatively rare), while items that are not to be inserted will be unpinned and freed immediately. Items that are to be inserted at the given commit lsn are placed in a temporary array and inserted into the AIL in bulk each time the array fills up. As a result of this, we trade off AIL hold time for a significant reduction in traffic. lock_stat output shows that the worst case hold time is unchanged, but contention from AIL inserts drops by an order of magnitude and the number of lock traversal decreases significantly. Signed-off-by: Dave Chinner <dchinner@redhat.com> Reviewed-by: Christoph Hellwig <hch@lst.de>
2010-12-20 01:02:19 +00:00
void xfs_trans_committed_bulk(struct xfs_ail *ailp, struct xfs_log_vec *lv,
xfs_lsn_t commit_lsn, int aborted);
/*
* AIL traversal cursor.
*
* Rather than using a generation number for detecting changes in the ail, use
* a cursor that is protected by the ail lock. The aild cursor exists in the
* struct xfs_ail, but other traversals can declare it on the stack and link it
* to the ail list.
*
* When an object is deleted from or moved int the AIL, the cursor list is
* searched to see if the object is a designated cursor item. If it is, it is
* deleted from the cursor so that the next time the cursor is used traversal
* will return to the start.
*
* This means a traversal colliding with a removal will cause a restart of the
* list scan, rather than any insertion or deletion anywhere in the list. The
* low bit of the item pointer is set if the cursor has been invalidated so
* that we can tell the difference between invalidation and reaching the end
* of the list to trigger traversal restarts.
*/
struct xfs_ail_cursor {
struct xfs_ail_cursor *next;
struct xfs_log_item *item;
};
[XFS] Move AIL pushing into it's own thread When many hundreds to thousands of threads all try to do simultaneous transactions and the log is in a tail-pushing situation (i.e. full), we can get multiple threads walking the AIL list and contending on the AIL lock. The AIL push is, in effect, a simple I/O dispatch algorithm complicated by the ordering constraints placed on it by the transaction subsystem. It really does not need multiple threads to push on it - even when only a single CPU is pushing the AIL, it can push the I/O out far faster that pretty much any disk subsystem can handle. So, to avoid contention problems stemming from multiple list walkers, move the list walk off into another thread and simply provide a "target" to push to. When a thread requires a push, it sets the target and wakes the push thread, then goes to sleep waiting for the required amount of space to become available in the log. This mechanism should also be a lot fairer under heavy load as the waiters will queue in arrival order, rather than queuing in "who completed a push first" order. Also, by moving the pushing to a separate thread we can do more effectively overload detection and prevention as we can keep context from loop iteration to loop iteration. That is, we can push only part of the list each loop and not have to loop back to the start of the list every time we run. This should also help by reducing the number of items we try to lock and/or push items that we cannot move. Note that this patch is not intended to solve the inefficiencies in the AIL structure and the associated issues with extremely large list contents. That needs to be addresses separately; parallel access would cause problems to any new structure as well, so I'm only aiming to isolate the structure from unbounded parallelism here. SGI-PV: 972759 SGI-Modid: xfs-linux-melb:xfs-kern:30371a Signed-off-by: David Chinner <dgc@sgi.com> Signed-off-by: Lachlan McIlroy <lachlan@sgi.com>
2008-02-05 01:13:32 +00:00
/*
* Private AIL structures.
*
* Eventually we need to drive the locking in here as well.
[XFS] Move AIL pushing into it's own thread When many hundreds to thousands of threads all try to do simultaneous transactions and the log is in a tail-pushing situation (i.e. full), we can get multiple threads walking the AIL list and contending on the AIL lock. The AIL push is, in effect, a simple I/O dispatch algorithm complicated by the ordering constraints placed on it by the transaction subsystem. It really does not need multiple threads to push on it - even when only a single CPU is pushing the AIL, it can push the I/O out far faster that pretty much any disk subsystem can handle. So, to avoid contention problems stemming from multiple list walkers, move the list walk off into another thread and simply provide a "target" to push to. When a thread requires a push, it sets the target and wakes the push thread, then goes to sleep waiting for the required amount of space to become available in the log. This mechanism should also be a lot fairer under heavy load as the waiters will queue in arrival order, rather than queuing in "who completed a push first" order. Also, by moving the pushing to a separate thread we can do more effectively overload detection and prevention as we can keep context from loop iteration to loop iteration. That is, we can push only part of the list each loop and not have to loop back to the start of the list every time we run. This should also help by reducing the number of items we try to lock and/or push items that we cannot move. Note that this patch is not intended to solve the inefficiencies in the AIL structure and the associated issues with extremely large list contents. That needs to be addresses separately; parallel access would cause problems to any new structure as well, so I'm only aiming to isolate the structure from unbounded parallelism here. SGI-PV: 972759 SGI-Modid: xfs-linux-melb:xfs-kern:30371a Signed-off-by: David Chinner <dgc@sgi.com> Signed-off-by: Lachlan McIlroy <lachlan@sgi.com>
2008-02-05 01:13:32 +00:00
*/
struct xfs_ail {
struct xfs_mount *xa_mount;
struct list_head xa_ail;
xfs_lsn_t xa_target;
struct xfs_ail_cursor xa_cursors;
spinlock_t xa_lock;
struct delayed_work xa_work;
xfs_lsn_t xa_last_pushed_lsn;
unsigned long xa_flags;
};
#define XFS_AIL_PUSHING_BIT 0
/*
* From xfs_trans_ail.c
*/
extern struct workqueue_struct *xfs_ail_wq; /* AIL workqueue */
void xfs_trans_ail_update_bulk(struct xfs_ail *ailp,
struct xfs_log_item **log_items, int nr_items,
xfs_lsn_t lsn) __releases(ailp->xa_lock);
static inline void
xfs_trans_ail_update(
struct xfs_ail *ailp,
struct xfs_log_item *lip,
xfs_lsn_t lsn) __releases(ailp->xa_lock)
{
xfs_trans_ail_update_bulk(ailp, &lip, 1, lsn);
}
void xfs_trans_ail_delete_bulk(struct xfs_ail *ailp,
struct xfs_log_item **log_items, int nr_items)
__releases(ailp->xa_lock);
static inline void
xfs_trans_ail_delete(
struct xfs_ail *ailp,
xfs_log_item_t *lip) __releases(ailp->xa_lock)
{
xfs_trans_ail_delete_bulk(ailp, &lip, 1);
}
void xfs_ail_push(struct xfs_ail *, xfs_lsn_t);
void xfs_ail_push_all(struct xfs_ail *);
xfs_lsn_t xfs_ail_min_lsn(struct xfs_ail *ailp);
void xfs_trans_unlocked_item(struct xfs_ail *,
xfs_log_item_t *);
struct xfs_log_item *xfs_trans_ail_cursor_first(struct xfs_ail *ailp,
struct xfs_ail_cursor *cur,
xfs_lsn_t lsn);
struct xfs_log_item *xfs_trans_ail_cursor_next(struct xfs_ail *ailp,
struct xfs_ail_cursor *cur);
void xfs_trans_ail_cursor_done(struct xfs_ail *ailp,
struct xfs_ail_cursor *cur);
#if BITS_PER_LONG != 64
static inline void
xfs_trans_ail_copy_lsn(
struct xfs_ail *ailp,
xfs_lsn_t *dst,
xfs_lsn_t *src)
{
ASSERT(sizeof(xfs_lsn_t) == 8); /* don't lock if it shrinks */
spin_lock(&ailp->xa_lock);
*dst = *src;
spin_unlock(&ailp->xa_lock);
}
#else
static inline void
xfs_trans_ail_copy_lsn(
struct xfs_ail *ailp,
xfs_lsn_t *dst,
xfs_lsn_t *src)
{
ASSERT(sizeof(xfs_lsn_t) == 8);
*dst = *src;
}
#endif
#endif /* __XFS_TRANS_PRIV_H__ */