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>
diff --git a/fs/xfs/xfs_log.c b/fs/xfs/xfs_log.c
index 19d0c5f..027ebfe 100644
--- a/fs/xfs/xfs_log.c
+++ b/fs/xfs/xfs_log.c
@@ -54,9 +54,6 @@
STATIC int xlog_space_left(xlog_t *log, int cycle, int bytes);
STATIC int xlog_sync(xlog_t *log, xlog_in_core_t *iclog);
STATIC void xlog_dealloc_log(xlog_t *log);
-STATIC int xlog_write(struct log *log, struct xfs_log_vec *log_vector,
- struct xlog_ticket *tic, xfs_lsn_t *start_lsn,
- xlog_in_core_t **commit_iclog, uint flags);
/* local state machine functions */
STATIC void xlog_state_done_syncing(xlog_in_core_t *iclog, int);
@@ -86,12 +83,6 @@
STATIC void xlog_ungrant_log_space(xlog_t *log,
xlog_ticket_t *ticket);
-
-/* local ticket functions */
-STATIC xlog_ticket_t *xlog_ticket_alloc(xlog_t *log, int unit_bytes, int count,
- char clientid, uint flags,
- int alloc_flags);
-
#if defined(DEBUG)
STATIC void xlog_verify_dest_ptr(xlog_t *log, char *ptr);
STATIC void xlog_verify_grant_head(xlog_t *log, int equals);
@@ -460,6 +451,13 @@
/* Normal transactions can now occur */
mp->m_log->l_flags &= ~XLOG_ACTIVE_RECOVERY;
+ /*
+ * Now the log has been fully initialised and we know were our
+ * space grant counters are, we can initialise the permanent ticket
+ * needed for delayed logging to work.
+ */
+ xlog_cil_init_post_recovery(mp->m_log);
+
return 0;
out_destroy_ail:
@@ -666,6 +664,10 @@
item->li_ailp = mp->m_ail;
item->li_type = type;
item->li_ops = ops;
+ item->li_lv = NULL;
+
+ INIT_LIST_HEAD(&item->li_ail);
+ INIT_LIST_HEAD(&item->li_cil);
}
/*
@@ -1176,6 +1178,9 @@
*iclogp = log->l_iclog; /* complete ring */
log->l_iclog->ic_prev = prev_iclog; /* re-write 1st prev ptr */
+ error = xlog_cil_init(log);
+ if (error)
+ goto out_free_iclog;
return log;
out_free_iclog:
@@ -1502,6 +1507,8 @@
xlog_in_core_t *iclog, *next_iclog;
int i;
+ xlog_cil_destroy(log);
+
iclog = log->l_iclog;
for (i=0; i<log->l_iclog_bufs; i++) {
sv_destroy(&iclog->ic_force_wait);
@@ -1544,8 +1551,10 @@
* print out info relating to regions written which consume
* the reservation
*/
-STATIC void
-xlog_print_tic_res(xfs_mount_t *mp, xlog_ticket_t *ticket)
+void
+xlog_print_tic_res(
+ struct xfs_mount *mp,
+ struct xlog_ticket *ticket)
{
uint i;
uint ophdr_spc = ticket->t_res_num_ophdrs * (uint)sizeof(xlog_op_header_t);
@@ -1877,7 +1886,7 @@
* we don't update ic_offset until the end when we know exactly how many
* bytes have been written out.
*/
-STATIC int
+int
xlog_write(
struct log *log,
struct xfs_log_vec *log_vector,
@@ -1901,9 +1910,26 @@
*start_lsn = 0;
len = xlog_write_calc_vec_length(ticket, log_vector);
- if (ticket->t_curr_res < len)
+ if (log->l_cilp) {
+ /*
+ * Region headers and bytes are already accounted for.
+ * We only need to take into account start records and
+ * split regions in this function.
+ */
+ if (ticket->t_flags & XLOG_TIC_INITED)
+ ticket->t_curr_res -= sizeof(xlog_op_header_t);
+
+ /*
+ * Commit record headers need to be accounted for. These
+ * come in as separate writes so are easy to detect.
+ */
+ if (flags & (XLOG_COMMIT_TRANS | XLOG_UNMOUNT_TRANS))
+ ticket->t_curr_res -= sizeof(xlog_op_header_t);
+ } else
+ ticket->t_curr_res -= len;
+
+ if (ticket->t_curr_res < 0)
xlog_print_tic_res(log->l_mp, ticket);
- ticket->t_curr_res -= len;
index = 0;
lv = log_vector;
@@ -2999,6 +3025,8 @@
XFS_STATS_INC(xs_log_force);
+ xlog_cil_push(log, 1);
+
spin_lock(&log->l_icloglock);
iclog = log->l_iclog;
@@ -3148,6 +3176,12 @@
XFS_STATS_INC(xs_log_force);
+ if (log->l_cilp) {
+ lsn = xlog_cil_push_lsn(log, lsn);
+ if (lsn == NULLCOMMITLSN)
+ return 0;
+ }
+
try_again:
spin_lock(&log->l_icloglock);
iclog = log->l_iclog;
@@ -3322,7 +3356,7 @@
/*
* Allocate and initialise a new log ticket.
*/
-STATIC xlog_ticket_t *
+xlog_ticket_t *
xlog_ticket_alloc(
struct log *log,
int unit_bytes,