linux_dsm_epyc7002/fs/xfs/xfs_inode_item.c

784 lines
21 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
*/
#include "xfs.h"
#include "xfs_fs.h"
#include "xfs_format.h"
#include "xfs_log_format.h"
#include "xfs_trans_resv.h"
#include "xfs_mount.h"
#include "xfs_inode.h"
#include "xfs_trans.h"
#include "xfs_inode_item.h"
#include "xfs_error.h"
xfs: event tracing support Convert the old xfs tracing support that could only be used with the out of tree kdb and xfsidbg patches to use the generic event tracer. To use it make sure CONFIG_EVENT_TRACING is enabled and then enable all xfs trace channels by: echo 1 > /sys/kernel/debug/tracing/events/xfs/enable or alternatively enable single events by just doing the same in one event subdirectory, e.g. echo 1 > /sys/kernel/debug/tracing/events/xfs/xfs_ihold/enable or set more complex filters, etc. In Documentation/trace/events.txt all this is desctribed in more detail. To reads the events do a cat /sys/kernel/debug/tracing/trace Compared to the last posting this patch converts the tracing mostly to the one tracepoint per callsite model that other users of the new tracing facility also employ. This allows a very fine-grained control of the tracing, a cleaner output of the traces and also enables the perf tool to use each tracepoint as a virtual performance counter, allowing us to e.g. count how often certain workloads git various spots in XFS. Take a look at http://lwn.net/Articles/346470/ for some examples. Also the btree tracing isn't included at all yet, as it will require additional core tracing features not in mainline yet, I plan to deliver it later. And the really nice thing about this patch is that it actually removes many lines of code while adding this nice functionality: fs/xfs/Makefile | 8 fs/xfs/linux-2.6/xfs_acl.c | 1 fs/xfs/linux-2.6/xfs_aops.c | 52 - fs/xfs/linux-2.6/xfs_aops.h | 2 fs/xfs/linux-2.6/xfs_buf.c | 117 +-- fs/xfs/linux-2.6/xfs_buf.h | 33 fs/xfs/linux-2.6/xfs_fs_subr.c | 3 fs/xfs/linux-2.6/xfs_ioctl.c | 1 fs/xfs/linux-2.6/xfs_ioctl32.c | 1 fs/xfs/linux-2.6/xfs_iops.c | 1 fs/xfs/linux-2.6/xfs_linux.h | 1 fs/xfs/linux-2.6/xfs_lrw.c | 87 -- fs/xfs/linux-2.6/xfs_lrw.h | 45 - fs/xfs/linux-2.6/xfs_super.c | 104 --- fs/xfs/linux-2.6/xfs_super.h | 7 fs/xfs/linux-2.6/xfs_sync.c | 1 fs/xfs/linux-2.6/xfs_trace.c | 75 ++ fs/xfs/linux-2.6/xfs_trace.h | 1369 +++++++++++++++++++++++++++++++++++++++++ fs/xfs/linux-2.6/xfs_vnode.h | 4 fs/xfs/quota/xfs_dquot.c | 110 --- fs/xfs/quota/xfs_dquot.h | 21 fs/xfs/quota/xfs_qm.c | 40 - fs/xfs/quota/xfs_qm_syscalls.c | 4 fs/xfs/support/ktrace.c | 323 --------- fs/xfs/support/ktrace.h | 85 -- fs/xfs/xfs.h | 16 fs/xfs/xfs_ag.h | 14 fs/xfs/xfs_alloc.c | 230 +----- fs/xfs/xfs_alloc.h | 27 fs/xfs/xfs_alloc_btree.c | 1 fs/xfs/xfs_attr.c | 107 --- fs/xfs/xfs_attr.h | 10 fs/xfs/xfs_attr_leaf.c | 14 fs/xfs/xfs_attr_sf.h | 40 - fs/xfs/xfs_bmap.c | 507 +++------------ fs/xfs/xfs_bmap.h | 49 - fs/xfs/xfs_bmap_btree.c | 6 fs/xfs/xfs_btree.c | 5 fs/xfs/xfs_btree_trace.h | 17 fs/xfs/xfs_buf_item.c | 87 -- fs/xfs/xfs_buf_item.h | 20 fs/xfs/xfs_da_btree.c | 3 fs/xfs/xfs_da_btree.h | 7 fs/xfs/xfs_dfrag.c | 2 fs/xfs/xfs_dir2.c | 8 fs/xfs/xfs_dir2_block.c | 20 fs/xfs/xfs_dir2_leaf.c | 21 fs/xfs/xfs_dir2_node.c | 27 fs/xfs/xfs_dir2_sf.c | 26 fs/xfs/xfs_dir2_trace.c | 216 ------ fs/xfs/xfs_dir2_trace.h | 72 -- fs/xfs/xfs_filestream.c | 8 fs/xfs/xfs_fsops.c | 2 fs/xfs/xfs_iget.c | 111 --- fs/xfs/xfs_inode.c | 67 -- fs/xfs/xfs_inode.h | 76 -- fs/xfs/xfs_inode_item.c | 5 fs/xfs/xfs_iomap.c | 85 -- fs/xfs/xfs_iomap.h | 8 fs/xfs/xfs_log.c | 181 +---- fs/xfs/xfs_log_priv.h | 20 fs/xfs/xfs_log_recover.c | 1 fs/xfs/xfs_mount.c | 2 fs/xfs/xfs_quota.h | 8 fs/xfs/xfs_rename.c | 1 fs/xfs/xfs_rtalloc.c | 1 fs/xfs/xfs_rw.c | 3 fs/xfs/xfs_trans.h | 47 + fs/xfs/xfs_trans_buf.c | 62 - fs/xfs/xfs_vnodeops.c | 8 70 files changed, 2151 insertions(+), 2592 deletions(-) Signed-off-by: Christoph Hellwig <hch@lst.de> Signed-off-by: Alex Elder <aelder@sgi.com>
2009-12-15 06:14:59 +07:00
#include "xfs_trace.h"
#include "xfs_trans_priv.h"
#include "xfs_log.h"
kmem_zone_t *xfs_ili_zone; /* inode log item zone */
static inline struct xfs_inode_log_item *INODE_ITEM(struct xfs_log_item *lip)
{
return container_of(lip, struct xfs_inode_log_item, ili_item);
}
STATIC void
xfs_inode_item_data_fork_size(
struct xfs_inode_log_item *iip,
int *nvecs,
int *nbytes)
{
struct xfs_inode *ip = iip->ili_inode;
switch (ip->i_d.di_format) {
case XFS_DINODE_FMT_EXTENTS:
if ((iip->ili_fields & XFS_ILOG_DEXT) &&
ip->i_d.di_nextents > 0 &&
ip->i_df.if_bytes > 0) {
/* worst case, doesn't subtract delalloc extents */
*nbytes += XFS_IFORK_DSIZE(ip);
*nvecs += 1;
}
break;
case XFS_DINODE_FMT_BTREE:
if ((iip->ili_fields & XFS_ILOG_DBROOT) &&
ip->i_df.if_broot_bytes > 0) {
*nbytes += ip->i_df.if_broot_bytes;
*nvecs += 1;
}
break;
case XFS_DINODE_FMT_LOCAL:
if ((iip->ili_fields & XFS_ILOG_DDATA) &&
ip->i_df.if_bytes > 0) {
*nbytes += roundup(ip->i_df.if_bytes, 4);
*nvecs += 1;
}
break;
case XFS_DINODE_FMT_DEV:
case XFS_DINODE_FMT_UUID:
break;
default:
ASSERT(0);
break;
}
}
STATIC void
xfs_inode_item_attr_fork_size(
struct xfs_inode_log_item *iip,
int *nvecs,
int *nbytes)
{
struct xfs_inode *ip = iip->ili_inode;
switch (ip->i_d.di_aformat) {
case XFS_DINODE_FMT_EXTENTS:
if ((iip->ili_fields & XFS_ILOG_AEXT) &&
ip->i_d.di_anextents > 0 &&
ip->i_afp->if_bytes > 0) {
/* worst case, doesn't subtract unused space */
*nbytes += XFS_IFORK_ASIZE(ip);
*nvecs += 1;
}
break;
case XFS_DINODE_FMT_BTREE:
if ((iip->ili_fields & XFS_ILOG_ABROOT) &&
ip->i_afp->if_broot_bytes > 0) {
*nbytes += ip->i_afp->if_broot_bytes;
*nvecs += 1;
}
break;
case XFS_DINODE_FMT_LOCAL:
if ((iip->ili_fields & XFS_ILOG_ADATA) &&
ip->i_afp->if_bytes > 0) {
*nbytes += roundup(ip->i_afp->if_bytes, 4);
*nvecs += 1;
}
break;
default:
ASSERT(0);
break;
}
}
/*
* This returns the number of iovecs needed to log the given inode item.
*
* We need one iovec for the inode log format structure, one for the
* inode core, and possibly one for the inode data/extents/b-tree root
* and one for the inode attribute data/extents/b-tree root.
*/
STATIC void
xfs_inode_item_size(
struct xfs_log_item *lip,
int *nvecs,
int *nbytes)
{
struct xfs_inode_log_item *iip = INODE_ITEM(lip);
struct xfs_inode *ip = iip->ili_inode;
*nvecs += 2;
*nbytes += sizeof(struct xfs_inode_log_format) +
xfs_icdinode_size(ip->i_d.di_version);
xfs_inode_item_data_fork_size(iip, nvecs, nbytes);
if (XFS_IFORK_Q(ip))
xfs_inode_item_attr_fork_size(iip, nvecs, nbytes);
}
STATIC void
xfs_inode_item_format_data_fork(
struct xfs_inode_log_item *iip,
struct xfs_inode_log_format *ilf,
struct xfs_log_vec *lv,
struct xfs_log_iovec **vecp)
{
struct xfs_inode *ip = iip->ili_inode;
size_t data_bytes;
switch (ip->i_d.di_format) {
case XFS_DINODE_FMT_EXTENTS:
iip->ili_fields &=
~(XFS_ILOG_DDATA | XFS_ILOG_DBROOT |
XFS_ILOG_DEV | XFS_ILOG_UUID);
if ((iip->ili_fields & XFS_ILOG_DEXT) &&
ip->i_d.di_nextents > 0 &&
ip->i_df.if_bytes > 0) {
struct xfs_bmbt_rec *p;
ASSERT(ip->i_df.if_u1.if_extents != NULL);
ASSERT(ip->i_df.if_bytes / sizeof(xfs_bmbt_rec_t) > 0);
p = xlog_prepare_iovec(lv, vecp, XLOG_REG_TYPE_IEXT);
data_bytes = xfs_iextents_copy(ip, p, XFS_DATA_FORK);
xlog_finish_iovec(lv, *vecp, data_bytes);
ASSERT(data_bytes <= ip->i_df.if_bytes);
ilf->ilf_dsize = data_bytes;
ilf->ilf_size++;
} else {
iip->ili_fields &= ~XFS_ILOG_DEXT;
}
break;
case XFS_DINODE_FMT_BTREE:
iip->ili_fields &=
~(XFS_ILOG_DDATA | XFS_ILOG_DEXT |
XFS_ILOG_DEV | XFS_ILOG_UUID);
if ((iip->ili_fields & XFS_ILOG_DBROOT) &&
ip->i_df.if_broot_bytes > 0) {
ASSERT(ip->i_df.if_broot != NULL);
xlog_copy_iovec(lv, vecp, XLOG_REG_TYPE_IBROOT,
ip->i_df.if_broot,
ip->i_df.if_broot_bytes);
ilf->ilf_dsize = ip->i_df.if_broot_bytes;
ilf->ilf_size++;
} else {
ASSERT(!(iip->ili_fields &
XFS_ILOG_DBROOT));
iip->ili_fields &= ~XFS_ILOG_DBROOT;
}
break;
case XFS_DINODE_FMT_LOCAL:
iip->ili_fields &=
~(XFS_ILOG_DEXT | XFS_ILOG_DBROOT |
XFS_ILOG_DEV | XFS_ILOG_UUID);
if ((iip->ili_fields & XFS_ILOG_DDATA) &&
ip->i_df.if_bytes > 0) {
/*
* Round i_bytes up to a word boundary.
* The underlying memory is guaranteed to
* to be there by xfs_idata_realloc().
*/
data_bytes = roundup(ip->i_df.if_bytes, 4);
ASSERT(ip->i_df.if_real_bytes == 0 ||
ip->i_df.if_real_bytes == data_bytes);
ASSERT(ip->i_df.if_u1.if_data != NULL);
ASSERT(ip->i_d.di_size > 0);
xlog_copy_iovec(lv, vecp, XLOG_REG_TYPE_ILOCAL,
ip->i_df.if_u1.if_data, data_bytes);
ilf->ilf_dsize = (unsigned)data_bytes;
ilf->ilf_size++;
} else {
iip->ili_fields &= ~XFS_ILOG_DDATA;
}
break;
case XFS_DINODE_FMT_DEV:
iip->ili_fields &=
~(XFS_ILOG_DDATA | XFS_ILOG_DBROOT |
XFS_ILOG_DEXT | XFS_ILOG_UUID);
if (iip->ili_fields & XFS_ILOG_DEV)
ilf->ilf_u.ilfu_rdev = ip->i_df.if_u2.if_rdev;
break;
case XFS_DINODE_FMT_UUID:
iip->ili_fields &=
~(XFS_ILOG_DDATA | XFS_ILOG_DBROOT |
XFS_ILOG_DEXT | XFS_ILOG_DEV);
if (iip->ili_fields & XFS_ILOG_UUID)
ilf->ilf_u.ilfu_uuid = ip->i_df.if_u2.if_uuid;
break;
default:
ASSERT(0);
break;
}
}
STATIC void
xfs_inode_item_format_attr_fork(
struct xfs_inode_log_item *iip,
struct xfs_inode_log_format *ilf,
struct xfs_log_vec *lv,
struct xfs_log_iovec **vecp)
{
struct xfs_inode *ip = iip->ili_inode;
size_t data_bytes;
switch (ip->i_d.di_aformat) {
case XFS_DINODE_FMT_EXTENTS:
iip->ili_fields &=
~(XFS_ILOG_ADATA | XFS_ILOG_ABROOT);
if ((iip->ili_fields & XFS_ILOG_AEXT) &&
ip->i_d.di_anextents > 0 &&
ip->i_afp->if_bytes > 0) {
struct xfs_bmbt_rec *p;
ASSERT(ip->i_afp->if_bytes / sizeof(xfs_bmbt_rec_t) ==
ip->i_d.di_anextents);
ASSERT(ip->i_afp->if_u1.if_extents != NULL);
p = xlog_prepare_iovec(lv, vecp, XLOG_REG_TYPE_IATTR_EXT);
data_bytes = xfs_iextents_copy(ip, p, XFS_ATTR_FORK);
xlog_finish_iovec(lv, *vecp, data_bytes);
ilf->ilf_asize = data_bytes;
ilf->ilf_size++;
} else {
iip->ili_fields &= ~XFS_ILOG_AEXT;
}
break;
case XFS_DINODE_FMT_BTREE:
iip->ili_fields &=
~(XFS_ILOG_ADATA | XFS_ILOG_AEXT);
if ((iip->ili_fields & XFS_ILOG_ABROOT) &&
ip->i_afp->if_broot_bytes > 0) {
ASSERT(ip->i_afp->if_broot != NULL);
xlog_copy_iovec(lv, vecp, XLOG_REG_TYPE_IATTR_BROOT,
ip->i_afp->if_broot,
ip->i_afp->if_broot_bytes);
ilf->ilf_asize = ip->i_afp->if_broot_bytes;
ilf->ilf_size++;
} else {
iip->ili_fields &= ~XFS_ILOG_ABROOT;
}
break;
case XFS_DINODE_FMT_LOCAL:
iip->ili_fields &=
~(XFS_ILOG_AEXT | XFS_ILOG_ABROOT);
if ((iip->ili_fields & XFS_ILOG_ADATA) &&
ip->i_afp->if_bytes > 0) {
/*
* Round i_bytes up to a word boundary.
* The underlying memory is guaranteed to
* to be there by xfs_idata_realloc().
*/
data_bytes = roundup(ip->i_afp->if_bytes, 4);
ASSERT(ip->i_afp->if_real_bytes == 0 ||
ip->i_afp->if_real_bytes == data_bytes);
ASSERT(ip->i_afp->if_u1.if_data != NULL);
xlog_copy_iovec(lv, vecp, XLOG_REG_TYPE_IATTR_LOCAL,
ip->i_afp->if_u1.if_data,
data_bytes);
ilf->ilf_asize = (unsigned)data_bytes;
ilf->ilf_size++;
} else {
iip->ili_fields &= ~XFS_ILOG_ADATA;
}
break;
default:
ASSERT(0);
break;
}
}
/*
* This is called to fill in the vector of log iovecs for the given inode
* log item. It fills the first item with an inode log format structure,
* the second with the on-disk inode structure, and a possible third and/or
* fourth with the inode data/extents/b-tree root and inode attributes
* data/extents/b-tree root.
*/
STATIC void
xfs_inode_item_format(
struct xfs_log_item *lip,
struct xfs_log_vec *lv)
{
struct xfs_inode_log_item *iip = INODE_ITEM(lip);
struct xfs_inode *ip = iip->ili_inode;
struct xfs_inode_log_format *ilf;
struct xfs_log_iovec *vecp = NULL;
ASSERT(ip->i_d.di_version > 1);
ilf = xlog_prepare_iovec(lv, &vecp, XLOG_REG_TYPE_IFORMAT);
ilf->ilf_type = XFS_LI_INODE;
ilf->ilf_ino = ip->i_ino;
ilf->ilf_blkno = ip->i_imap.im_blkno;
ilf->ilf_len = ip->i_imap.im_len;
ilf->ilf_boffset = ip->i_imap.im_boffset;
ilf->ilf_fields = XFS_ILOG_CORE;
ilf->ilf_size = 2; /* format + core */
xlog_finish_iovec(lv, vecp, sizeof(struct xfs_inode_log_format));
xlog_copy_iovec(lv, &vecp, XLOG_REG_TYPE_ICORE,
&ip->i_d,
xfs_icdinode_size(ip->i_d.di_version));
xfs_inode_item_format_data_fork(iip, ilf, lv, &vecp);
if (XFS_IFORK_Q(ip)) {
xfs_inode_item_format_attr_fork(iip, ilf, lv, &vecp);
} else {
iip->ili_fields &=
~(XFS_ILOG_ADATA | XFS_ILOG_ABROOT | XFS_ILOG_AEXT);
}
/* update the format with the exact fields we actually logged */
ilf->ilf_fields |= (iip->ili_fields & ~XFS_ILOG_TIMESTAMP);
}
/*
* This is called to pin the inode associated with the inode log
* item in memory so it cannot be written out.
*/
STATIC void
xfs_inode_item_pin(
struct xfs_log_item *lip)
{
struct xfs_inode *ip = INODE_ITEM(lip)->ili_inode;
ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL));
trace_xfs_inode_pin(ip, _RET_IP_);
atomic_inc(&ip->i_pincount);
}
/*
* This is called to unpin the inode associated with the inode log
* item which was previously pinned with a call to xfs_inode_item_pin().
*
* Also wake up anyone in xfs_iunpin_wait() if the count goes to 0.
*/
STATIC void
xfs_inode_item_unpin(
struct xfs_log_item *lip,
int remove)
{
struct xfs_inode *ip = INODE_ITEM(lip)->ili_inode;
trace_xfs_inode_unpin(ip, _RET_IP_);
ASSERT(atomic_read(&ip->i_pincount) > 0);
if (atomic_dec_and_test(&ip->i_pincount))
wake_up_bit(&ip->i_flags, __XFS_IPINNED_BIT);
}
STATIC uint
xfs: on-stack delayed write buffer lists Queue delwri buffers on a local on-stack list instead of a per-buftarg one, and write back the buffers per-process instead of by waking up xfsbufd. This is now easily doable given that we have very few places left that write delwri buffers: - log recovery: Only done at mount time, and already forcing out the buffers synchronously using xfs_flush_buftarg - quotacheck: Same story. - dquot reclaim: Writes out dirty dquots on the LRU under memory pressure. We might want to look into doing more of this via xfsaild, but it's already more optimal than the synchronous inode reclaim that writes each buffer synchronously. - xfsaild: This is the main beneficiary of the change. By keeping a local list of buffers to write we reduce latency of writing out buffers, and more importably we can remove all the delwri list promotions which were hitting the buffer cache hard under sustained metadata loads. The implementation is very straight forward - xfs_buf_delwri_queue now gets a new list_head pointer that it adds the delwri buffers to, and all callers need to eventually submit the list using xfs_buf_delwi_submit or xfs_buf_delwi_submit_nowait. Buffers that already are on a delwri list are skipped in xfs_buf_delwri_queue, assuming they already are on another delwri list. The biggest change to pass down the buffer list was done to the AIL pushing. Now that we operate on buffers the trylock, push and pushbuf log item methods are merged into a single push routine, which tries to lock the item, and if possible add the buffer that needs writeback to the buffer list. This leads to much simpler code than the previous split but requires the individual IOP_PUSH instances to unlock and reacquire the AIL around calls to blocking routines. Given that xfsailds now also handle writing out buffers, the conditions for log forcing and the sleep times needed some small changes. The most important one is that we consider an AIL busy as long we still have buffers to push, and the other one is that we do increment the pushed LSN for buffers that are under flushing at this moment, but still count them towards the stuck items for restart purposes. Without this we could hammer on stuck items without ever forcing the log and not make progress under heavy random delete workloads on fast flash storage devices. [ Dave Chinner: - rebase on previous patches. - improved comments for XBF_DELWRI_Q handling - fix XBF_ASYNC handling in queue submission (test 106 failure) - rename delwri submit function buffer list parameters for clarity - xfs_efd_item_push() should return XFS_ITEM_PINNED ] Signed-off-by: Christoph Hellwig <hch@lst.de> Reviewed-by: Dave Chinner <dchinner@redhat.com> Reviewed-by: Mark Tinguely <tinguely@sgi.com> Signed-off-by: Ben Myers <bpm@sgi.com>
2012-04-23 12:58:39 +07:00
xfs_inode_item_push(
struct xfs_log_item *lip,
struct list_head *buffer_list)
{
struct xfs_inode_log_item *iip = INODE_ITEM(lip);
struct xfs_inode *ip = iip->ili_inode;
xfs: on-stack delayed write buffer lists Queue delwri buffers on a local on-stack list instead of a per-buftarg one, and write back the buffers per-process instead of by waking up xfsbufd. This is now easily doable given that we have very few places left that write delwri buffers: - log recovery: Only done at mount time, and already forcing out the buffers synchronously using xfs_flush_buftarg - quotacheck: Same story. - dquot reclaim: Writes out dirty dquots on the LRU under memory pressure. We might want to look into doing more of this via xfsaild, but it's already more optimal than the synchronous inode reclaim that writes each buffer synchronously. - xfsaild: This is the main beneficiary of the change. By keeping a local list of buffers to write we reduce latency of writing out buffers, and more importably we can remove all the delwri list promotions which were hitting the buffer cache hard under sustained metadata loads. The implementation is very straight forward - xfs_buf_delwri_queue now gets a new list_head pointer that it adds the delwri buffers to, and all callers need to eventually submit the list using xfs_buf_delwi_submit or xfs_buf_delwi_submit_nowait. Buffers that already are on a delwri list are skipped in xfs_buf_delwri_queue, assuming they already are on another delwri list. The biggest change to pass down the buffer list was done to the AIL pushing. Now that we operate on buffers the trylock, push and pushbuf log item methods are merged into a single push routine, which tries to lock the item, and if possible add the buffer that needs writeback to the buffer list. This leads to much simpler code than the previous split but requires the individual IOP_PUSH instances to unlock and reacquire the AIL around calls to blocking routines. Given that xfsailds now also handle writing out buffers, the conditions for log forcing and the sleep times needed some small changes. The most important one is that we consider an AIL busy as long we still have buffers to push, and the other one is that we do increment the pushed LSN for buffers that are under flushing at this moment, but still count them towards the stuck items for restart purposes. Without this we could hammer on stuck items without ever forcing the log and not make progress under heavy random delete workloads on fast flash storage devices. [ Dave Chinner: - rebase on previous patches. - improved comments for XBF_DELWRI_Q handling - fix XBF_ASYNC handling in queue submission (test 106 failure) - rename delwri submit function buffer list parameters for clarity - xfs_efd_item_push() should return XFS_ITEM_PINNED ] Signed-off-by: Christoph Hellwig <hch@lst.de> Reviewed-by: Dave Chinner <dchinner@redhat.com> Reviewed-by: Mark Tinguely <tinguely@sgi.com> Signed-off-by: Ben Myers <bpm@sgi.com>
2012-04-23 12:58:39 +07:00
struct xfs_buf *bp = NULL;
uint rval = XFS_ITEM_SUCCESS;
int error;
if (xfs_ipincount(ip) > 0)
return XFS_ITEM_PINNED;
if (!xfs_ilock_nowait(ip, XFS_ILOCK_SHARED))
return XFS_ITEM_LOCKED;
/*
* Re-check the pincount now that we stabilized the value by
* taking the ilock.
*/
if (xfs_ipincount(ip) > 0) {
xfs: on-stack delayed write buffer lists Queue delwri buffers on a local on-stack list instead of a per-buftarg one, and write back the buffers per-process instead of by waking up xfsbufd. This is now easily doable given that we have very few places left that write delwri buffers: - log recovery: Only done at mount time, and already forcing out the buffers synchronously using xfs_flush_buftarg - quotacheck: Same story. - dquot reclaim: Writes out dirty dquots on the LRU under memory pressure. We might want to look into doing more of this via xfsaild, but it's already more optimal than the synchronous inode reclaim that writes each buffer synchronously. - xfsaild: This is the main beneficiary of the change. By keeping a local list of buffers to write we reduce latency of writing out buffers, and more importably we can remove all the delwri list promotions which were hitting the buffer cache hard under sustained metadata loads. The implementation is very straight forward - xfs_buf_delwri_queue now gets a new list_head pointer that it adds the delwri buffers to, and all callers need to eventually submit the list using xfs_buf_delwi_submit or xfs_buf_delwi_submit_nowait. Buffers that already are on a delwri list are skipped in xfs_buf_delwri_queue, assuming they already are on another delwri list. The biggest change to pass down the buffer list was done to the AIL pushing. Now that we operate on buffers the trylock, push and pushbuf log item methods are merged into a single push routine, which tries to lock the item, and if possible add the buffer that needs writeback to the buffer list. This leads to much simpler code than the previous split but requires the individual IOP_PUSH instances to unlock and reacquire the AIL around calls to blocking routines. Given that xfsailds now also handle writing out buffers, the conditions for log forcing and the sleep times needed some small changes. The most important one is that we consider an AIL busy as long we still have buffers to push, and the other one is that we do increment the pushed LSN for buffers that are under flushing at this moment, but still count them towards the stuck items for restart purposes. Without this we could hammer on stuck items without ever forcing the log and not make progress under heavy random delete workloads on fast flash storage devices. [ Dave Chinner: - rebase on previous patches. - improved comments for XBF_DELWRI_Q handling - fix XBF_ASYNC handling in queue submission (test 106 failure) - rename delwri submit function buffer list parameters for clarity - xfs_efd_item_push() should return XFS_ITEM_PINNED ] Signed-off-by: Christoph Hellwig <hch@lst.de> Reviewed-by: Dave Chinner <dchinner@redhat.com> Reviewed-by: Mark Tinguely <tinguely@sgi.com> Signed-off-by: Ben Myers <bpm@sgi.com>
2012-04-23 12:58:39 +07:00
rval = XFS_ITEM_PINNED;
goto out_unlock;
}
/*
* Stale inode items should force out the iclog.
*/
if (ip->i_flags & XFS_ISTALE) {
rval = XFS_ITEM_PINNED;
goto out_unlock;
}
xfs: on-stack delayed write buffer lists Queue delwri buffers on a local on-stack list instead of a per-buftarg one, and write back the buffers per-process instead of by waking up xfsbufd. This is now easily doable given that we have very few places left that write delwri buffers: - log recovery: Only done at mount time, and already forcing out the buffers synchronously using xfs_flush_buftarg - quotacheck: Same story. - dquot reclaim: Writes out dirty dquots on the LRU under memory pressure. We might want to look into doing more of this via xfsaild, but it's already more optimal than the synchronous inode reclaim that writes each buffer synchronously. - xfsaild: This is the main beneficiary of the change. By keeping a local list of buffers to write we reduce latency of writing out buffers, and more importably we can remove all the delwri list promotions which were hitting the buffer cache hard under sustained metadata loads. The implementation is very straight forward - xfs_buf_delwri_queue now gets a new list_head pointer that it adds the delwri buffers to, and all callers need to eventually submit the list using xfs_buf_delwi_submit or xfs_buf_delwi_submit_nowait. Buffers that already are on a delwri list are skipped in xfs_buf_delwri_queue, assuming they already are on another delwri list. The biggest change to pass down the buffer list was done to the AIL pushing. Now that we operate on buffers the trylock, push and pushbuf log item methods are merged into a single push routine, which tries to lock the item, and if possible add the buffer that needs writeback to the buffer list. This leads to much simpler code than the previous split but requires the individual IOP_PUSH instances to unlock and reacquire the AIL around calls to blocking routines. Given that xfsailds now also handle writing out buffers, the conditions for log forcing and the sleep times needed some small changes. The most important one is that we consider an AIL busy as long we still have buffers to push, and the other one is that we do increment the pushed LSN for buffers that are under flushing at this moment, but still count them towards the stuck items for restart purposes. Without this we could hammer on stuck items without ever forcing the log and not make progress under heavy random delete workloads on fast flash storage devices. [ Dave Chinner: - rebase on previous patches. - improved comments for XBF_DELWRI_Q handling - fix XBF_ASYNC handling in queue submission (test 106 failure) - rename delwri submit function buffer list parameters for clarity - xfs_efd_item_push() should return XFS_ITEM_PINNED ] Signed-off-by: Christoph Hellwig <hch@lst.de> Reviewed-by: Dave Chinner <dchinner@redhat.com> Reviewed-by: Mark Tinguely <tinguely@sgi.com> Signed-off-by: Ben Myers <bpm@sgi.com>
2012-04-23 12:58:39 +07:00
/*
* Someone else is already flushing the inode. Nothing we can do
* here but wait for the flush to finish and remove the item from
* the AIL.
*/
if (!xfs_iflock_nowait(ip)) {
xfs: on-stack delayed write buffer lists Queue delwri buffers on a local on-stack list instead of a per-buftarg one, and write back the buffers per-process instead of by waking up xfsbufd. This is now easily doable given that we have very few places left that write delwri buffers: - log recovery: Only done at mount time, and already forcing out the buffers synchronously using xfs_flush_buftarg - quotacheck: Same story. - dquot reclaim: Writes out dirty dquots on the LRU under memory pressure. We might want to look into doing more of this via xfsaild, but it's already more optimal than the synchronous inode reclaim that writes each buffer synchronously. - xfsaild: This is the main beneficiary of the change. By keeping a local list of buffers to write we reduce latency of writing out buffers, and more importably we can remove all the delwri list promotions which were hitting the buffer cache hard under sustained metadata loads. The implementation is very straight forward - xfs_buf_delwri_queue now gets a new list_head pointer that it adds the delwri buffers to, and all callers need to eventually submit the list using xfs_buf_delwi_submit or xfs_buf_delwi_submit_nowait. Buffers that already are on a delwri list are skipped in xfs_buf_delwri_queue, assuming they already are on another delwri list. The biggest change to pass down the buffer list was done to the AIL pushing. Now that we operate on buffers the trylock, push and pushbuf log item methods are merged into a single push routine, which tries to lock the item, and if possible add the buffer that needs writeback to the buffer list. This leads to much simpler code than the previous split but requires the individual IOP_PUSH instances to unlock and reacquire the AIL around calls to blocking routines. Given that xfsailds now also handle writing out buffers, the conditions for log forcing and the sleep times needed some small changes. The most important one is that we consider an AIL busy as long we still have buffers to push, and the other one is that we do increment the pushed LSN for buffers that are under flushing at this moment, but still count them towards the stuck items for restart purposes. Without this we could hammer on stuck items without ever forcing the log and not make progress under heavy random delete workloads on fast flash storage devices. [ Dave Chinner: - rebase on previous patches. - improved comments for XBF_DELWRI_Q handling - fix XBF_ASYNC handling in queue submission (test 106 failure) - rename delwri submit function buffer list parameters for clarity - xfs_efd_item_push() should return XFS_ITEM_PINNED ] Signed-off-by: Christoph Hellwig <hch@lst.de> Reviewed-by: Dave Chinner <dchinner@redhat.com> Reviewed-by: Mark Tinguely <tinguely@sgi.com> Signed-off-by: Ben Myers <bpm@sgi.com>
2012-04-23 12:58:39 +07:00
rval = XFS_ITEM_FLUSHING;
goto out_unlock;
}
xfs: on-stack delayed write buffer lists Queue delwri buffers on a local on-stack list instead of a per-buftarg one, and write back the buffers per-process instead of by waking up xfsbufd. This is now easily doable given that we have very few places left that write delwri buffers: - log recovery: Only done at mount time, and already forcing out the buffers synchronously using xfs_flush_buftarg - quotacheck: Same story. - dquot reclaim: Writes out dirty dquots on the LRU under memory pressure. We might want to look into doing more of this via xfsaild, but it's already more optimal than the synchronous inode reclaim that writes each buffer synchronously. - xfsaild: This is the main beneficiary of the change. By keeping a local list of buffers to write we reduce latency of writing out buffers, and more importably we can remove all the delwri list promotions which were hitting the buffer cache hard under sustained metadata loads. The implementation is very straight forward - xfs_buf_delwri_queue now gets a new list_head pointer that it adds the delwri buffers to, and all callers need to eventually submit the list using xfs_buf_delwi_submit or xfs_buf_delwi_submit_nowait. Buffers that already are on a delwri list are skipped in xfs_buf_delwri_queue, assuming they already are on another delwri list. The biggest change to pass down the buffer list was done to the AIL pushing. Now that we operate on buffers the trylock, push and pushbuf log item methods are merged into a single push routine, which tries to lock the item, and if possible add the buffer that needs writeback to the buffer list. This leads to much simpler code than the previous split but requires the individual IOP_PUSH instances to unlock and reacquire the AIL around calls to blocking routines. Given that xfsailds now also handle writing out buffers, the conditions for log forcing and the sleep times needed some small changes. The most important one is that we consider an AIL busy as long we still have buffers to push, and the other one is that we do increment the pushed LSN for buffers that are under flushing at this moment, but still count them towards the stuck items for restart purposes. Without this we could hammer on stuck items without ever forcing the log and not make progress under heavy random delete workloads on fast flash storage devices. [ Dave Chinner: - rebase on previous patches. - improved comments for XBF_DELWRI_Q handling - fix XBF_ASYNC handling in queue submission (test 106 failure) - rename delwri submit function buffer list parameters for clarity - xfs_efd_item_push() should return XFS_ITEM_PINNED ] Signed-off-by: Christoph Hellwig <hch@lst.de> Reviewed-by: Dave Chinner <dchinner@redhat.com> Reviewed-by: Mark Tinguely <tinguely@sgi.com> Signed-off-by: Ben Myers <bpm@sgi.com>
2012-04-23 12:58:39 +07:00
ASSERT(iip->ili_fields != 0 || XFS_FORCED_SHUTDOWN(ip->i_mount));
ASSERT(iip->ili_logged == 0 || XFS_FORCED_SHUTDOWN(ip->i_mount));
spin_unlock(&lip->li_ailp->xa_lock);
error = xfs_iflush(ip, &bp);
if (!error) {
if (!xfs_buf_delwri_queue(bp, buffer_list))
rval = XFS_ITEM_FLUSHING;
xfs_buf_relse(bp);
}
xfs: on-stack delayed write buffer lists Queue delwri buffers on a local on-stack list instead of a per-buftarg one, and write back the buffers per-process instead of by waking up xfsbufd. This is now easily doable given that we have very few places left that write delwri buffers: - log recovery: Only done at mount time, and already forcing out the buffers synchronously using xfs_flush_buftarg - quotacheck: Same story. - dquot reclaim: Writes out dirty dquots on the LRU under memory pressure. We might want to look into doing more of this via xfsaild, but it's already more optimal than the synchronous inode reclaim that writes each buffer synchronously. - xfsaild: This is the main beneficiary of the change. By keeping a local list of buffers to write we reduce latency of writing out buffers, and more importably we can remove all the delwri list promotions which were hitting the buffer cache hard under sustained metadata loads. The implementation is very straight forward - xfs_buf_delwri_queue now gets a new list_head pointer that it adds the delwri buffers to, and all callers need to eventually submit the list using xfs_buf_delwi_submit or xfs_buf_delwi_submit_nowait. Buffers that already are on a delwri list are skipped in xfs_buf_delwri_queue, assuming they already are on another delwri list. The biggest change to pass down the buffer list was done to the AIL pushing. Now that we operate on buffers the trylock, push and pushbuf log item methods are merged into a single push routine, which tries to lock the item, and if possible add the buffer that needs writeback to the buffer list. This leads to much simpler code than the previous split but requires the individual IOP_PUSH instances to unlock and reacquire the AIL around calls to blocking routines. Given that xfsailds now also handle writing out buffers, the conditions for log forcing and the sleep times needed some small changes. The most important one is that we consider an AIL busy as long we still have buffers to push, and the other one is that we do increment the pushed LSN for buffers that are under flushing at this moment, but still count them towards the stuck items for restart purposes. Without this we could hammer on stuck items without ever forcing the log and not make progress under heavy random delete workloads on fast flash storage devices. [ Dave Chinner: - rebase on previous patches. - improved comments for XBF_DELWRI_Q handling - fix XBF_ASYNC handling in queue submission (test 106 failure) - rename delwri submit function buffer list parameters for clarity - xfs_efd_item_push() should return XFS_ITEM_PINNED ] Signed-off-by: Christoph Hellwig <hch@lst.de> Reviewed-by: Dave Chinner <dchinner@redhat.com> Reviewed-by: Mark Tinguely <tinguely@sgi.com> Signed-off-by: Ben Myers <bpm@sgi.com>
2012-04-23 12:58:39 +07:00
spin_lock(&lip->li_ailp->xa_lock);
out_unlock:
xfs_iunlock(ip, XFS_ILOCK_SHARED);
return rval;
}
/*
* Unlock the inode associated with the inode log item.
* Clear the fields of the inode and inode log item that
* are specific to the current transaction. If the
* hold flags is set, do not unlock the inode.
*/
STATIC void
xfs_inode_item_unlock(
struct xfs_log_item *lip)
{
struct xfs_inode_log_item *iip = INODE_ITEM(lip);
struct xfs_inode *ip = iip->ili_inode;
unsigned short lock_flags;
ASSERT(ip->i_itemp != NULL);
ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL));
lock_flags = iip->ili_lock_flags;
iip->ili_lock_flags = 0;
if (lock_flags)
xfs_iunlock(ip, lock_flags);
}
/*
* This is called to find out where the oldest active copy of the inode log
* item in the on disk log resides now that the last log write of it completed
* at the given lsn. Since we always re-log all dirty data in an inode, the
* latest copy in the on disk log is the only one that matters. Therefore,
* simply return the given lsn.
*
* If the inode has been marked stale because the cluster is being freed, we
* don't want to (re-)insert this inode into the AIL. There is a race condition
* where the cluster buffer may be unpinned before the inode is inserted into
* the AIL during transaction committed processing. If the buffer is unpinned
* before the inode item has been committed and inserted, then it is possible
xfs: unpin stale inodes directly in IOP_COMMITTED When inodes are marked stale in a transaction, they are treated specially when the inode log item is being inserted into the AIL. It tries to avoid moving the log item forward in the AIL due to a race condition with the writing the underlying buffer back to disk. The was "fixed" in commit de25c18 ("xfs: avoid moving stale inodes in the AIL"). To avoid moving the item forward, we return a LSN smaller than the commit_lsn of the completing transaction, thereby trying to trick the commit code into not moving the inode forward at all. I'm not sure this ever worked as intended - it assumes the inode is already in the AIL, but I don't think the returned LSN would have been small enough to prevent moving the inode. It appears that the reason it worked is that the lower LSN of the inodes meant they were inserted into the AIL and flushed before the inode buffer (which was moved to the commit_lsn of the transaction). The big problem is that with delayed logging, the returning of the different LSN means insertion takes the slow, non-bulk path. Worse yet is that insertion is to a position -before- the commit_lsn so it is doing a AIL traversal on every insertion, and has to walk over all the items that have already been inserted into the AIL. It's expensive. To compound the matter further, with delayed logging inodes are likely to go from clean to stale in a single checkpoint, which means they aren't even in the AIL at all when we come across them at AIL insertion time. Hence these were all getting inserted into the AIL when they simply do not need to be as inodes marked XFS_ISTALE are never written back. Transactional/recovery integrity is maintained in this case by the other items in the unlink transaction that were modified (e.g. the AGI btree blocks) and committed in the same checkpoint. So to fix this, simply unpin the stale inodes directly in xfs_inode_item_committed() and return -1 to indicate that the AIL insertion code does not need to do any further processing of these inodes. Signed-off-by: Dave Chinner <dchinner@redhat.com> Reviewed-by: Christoph Hellwig <hch@lst.de> Signed-off-by: Alex Elder <aelder@sgi.com>
2011-07-04 12:27:36 +07:00
* for the buffer to be written and IO completes before the inode is inserted
* into the AIL. In that case, we'd be inserting a clean, stale inode into the
* AIL which will never get removed. It will, however, get reclaimed which
* triggers an assert in xfs_inode_free() complaining about freein an inode
* still in the AIL.
*
xfs: unpin stale inodes directly in IOP_COMMITTED When inodes are marked stale in a transaction, they are treated specially when the inode log item is being inserted into the AIL. It tries to avoid moving the log item forward in the AIL due to a race condition with the writing the underlying buffer back to disk. The was "fixed" in commit de25c18 ("xfs: avoid moving stale inodes in the AIL"). To avoid moving the item forward, we return a LSN smaller than the commit_lsn of the completing transaction, thereby trying to trick the commit code into not moving the inode forward at all. I'm not sure this ever worked as intended - it assumes the inode is already in the AIL, but I don't think the returned LSN would have been small enough to prevent moving the inode. It appears that the reason it worked is that the lower LSN of the inodes meant they were inserted into the AIL and flushed before the inode buffer (which was moved to the commit_lsn of the transaction). The big problem is that with delayed logging, the returning of the different LSN means insertion takes the slow, non-bulk path. Worse yet is that insertion is to a position -before- the commit_lsn so it is doing a AIL traversal on every insertion, and has to walk over all the items that have already been inserted into the AIL. It's expensive. To compound the matter further, with delayed logging inodes are likely to go from clean to stale in a single checkpoint, which means they aren't even in the AIL at all when we come across them at AIL insertion time. Hence these were all getting inserted into the AIL when they simply do not need to be as inodes marked XFS_ISTALE are never written back. Transactional/recovery integrity is maintained in this case by the other items in the unlink transaction that were modified (e.g. the AGI btree blocks) and committed in the same checkpoint. So to fix this, simply unpin the stale inodes directly in xfs_inode_item_committed() and return -1 to indicate that the AIL insertion code does not need to do any further processing of these inodes. Signed-off-by: Dave Chinner <dchinner@redhat.com> Reviewed-by: Christoph Hellwig <hch@lst.de> Signed-off-by: Alex Elder <aelder@sgi.com>
2011-07-04 12:27:36 +07:00
* To avoid this, just unpin the inode directly and return a LSN of -1 so the
* transaction committed code knows that it does not need to do any further
* processing on the item.
*/
STATIC xfs_lsn_t
xfs_inode_item_committed(
struct xfs_log_item *lip,
xfs_lsn_t lsn)
{
struct xfs_inode_log_item *iip = INODE_ITEM(lip);
struct xfs_inode *ip = iip->ili_inode;
xfs: unpin stale inodes directly in IOP_COMMITTED When inodes are marked stale in a transaction, they are treated specially when the inode log item is being inserted into the AIL. It tries to avoid moving the log item forward in the AIL due to a race condition with the writing the underlying buffer back to disk. The was "fixed" in commit de25c18 ("xfs: avoid moving stale inodes in the AIL"). To avoid moving the item forward, we return a LSN smaller than the commit_lsn of the completing transaction, thereby trying to trick the commit code into not moving the inode forward at all. I'm not sure this ever worked as intended - it assumes the inode is already in the AIL, but I don't think the returned LSN would have been small enough to prevent moving the inode. It appears that the reason it worked is that the lower LSN of the inodes meant they were inserted into the AIL and flushed before the inode buffer (which was moved to the commit_lsn of the transaction). The big problem is that with delayed logging, the returning of the different LSN means insertion takes the slow, non-bulk path. Worse yet is that insertion is to a position -before- the commit_lsn so it is doing a AIL traversal on every insertion, and has to walk over all the items that have already been inserted into the AIL. It's expensive. To compound the matter further, with delayed logging inodes are likely to go from clean to stale in a single checkpoint, which means they aren't even in the AIL at all when we come across them at AIL insertion time. Hence these were all getting inserted into the AIL when they simply do not need to be as inodes marked XFS_ISTALE are never written back. Transactional/recovery integrity is maintained in this case by the other items in the unlink transaction that were modified (e.g. the AGI btree blocks) and committed in the same checkpoint. So to fix this, simply unpin the stale inodes directly in xfs_inode_item_committed() and return -1 to indicate that the AIL insertion code does not need to do any further processing of these inodes. Signed-off-by: Dave Chinner <dchinner@redhat.com> Reviewed-by: Christoph Hellwig <hch@lst.de> Signed-off-by: Alex Elder <aelder@sgi.com>
2011-07-04 12:27:36 +07:00
if (xfs_iflags_test(ip, XFS_ISTALE)) {
xfs_inode_item_unpin(lip, 0);
return -1;
}
return lsn;
}
/*
* XXX rcc - this one really has to do something. Probably needs
* to stamp in a new field in the incore inode.
*/
STATIC void
xfs_inode_item_committing(
struct xfs_log_item *lip,
xfs_lsn_t lsn)
{
INODE_ITEM(lip)->ili_last_lsn = lsn;
}
/*
* This is the ops vector shared by all buf log items.
*/
static const struct xfs_item_ops xfs_inode_item_ops = {
.iop_size = xfs_inode_item_size,
.iop_format = xfs_inode_item_format,
.iop_pin = xfs_inode_item_pin,
.iop_unpin = xfs_inode_item_unpin,
.iop_unlock = xfs_inode_item_unlock,
.iop_committed = xfs_inode_item_committed,
.iop_push = xfs_inode_item_push,
.iop_committing = xfs_inode_item_committing
};
/*
* Initialize the inode log item for a newly allocated (in-core) inode.
*/
void
xfs_inode_item_init(
struct xfs_inode *ip,
struct xfs_mount *mp)
{
struct xfs_inode_log_item *iip;
ASSERT(ip->i_itemp == NULL);
iip = ip->i_itemp = kmem_zone_zalloc(xfs_ili_zone, KM_SLEEP);
iip->ili_inode = ip;
xfs_log_item_init(mp, &iip->ili_item, XFS_LI_INODE,
&xfs_inode_item_ops);
}
/*
* Free the inode log item and any memory hanging off of it.
*/
void
xfs_inode_item_destroy(
xfs_inode_t *ip)
{
kmem_zone_free(xfs_ili_zone, ip->i_itemp);
}
/*
* This is the inode flushing I/O completion routine. It is called
* from interrupt level when the buffer containing the inode is
* flushed to disk. It is responsible for removing the inode item
* from the AIL if it has not been re-logged, and unlocking the inode's
* flush lock.
*
* To reduce AIL lock traffic as much as possible, we scan the buffer log item
* list for other inodes that will run this function. We remove them from the
* buffer list so we can process all the inode IO completions in one AIL lock
* traversal.
*/
void
xfs_iflush_done(
struct xfs_buf *bp,
struct xfs_log_item *lip)
{
struct xfs_inode_log_item *iip;
struct xfs_log_item *blip;
struct xfs_log_item *next;
struct xfs_log_item *prev;
struct xfs_ail *ailp = lip->li_ailp;
int need_ail = 0;
/*
* Scan the buffer IO completions for other inodes being completed and
* attach them to the current inode log item.
*/
blip = bp->b_fspriv;
prev = NULL;
while (blip != NULL) {
if (blip->li_cb != xfs_iflush_done) {
prev = blip;
blip = blip->li_bio_list;
continue;
}
/* remove from list */
next = blip->li_bio_list;
if (!prev) {
bp->b_fspriv = next;
} else {
prev->li_bio_list = next;
}
/* add to current list */
blip->li_bio_list = lip->li_bio_list;
lip->li_bio_list = blip;
/*
* while we have the item, do the unlocked check for needing
* the AIL lock.
*/
iip = INODE_ITEM(blip);
if (iip->ili_logged && blip->li_lsn == iip->ili_flush_lsn)
need_ail++;
blip = next;
}
/* make sure we capture the state of the initial inode. */
iip = INODE_ITEM(lip);
if (iip->ili_logged && lip->li_lsn == iip->ili_flush_lsn)
need_ail++;
/*
* We only want to pull the item from the AIL if it is
* actually there and its location in the log has not
* changed since we started the flush. Thus, we only bother
* if the ili_logged flag is set and the inode's lsn has not
* changed. First we check the lsn outside
* the lock since it's cheaper, and then we recheck while
* holding the lock before removing the inode from the AIL.
*/
if (need_ail) {
struct xfs_log_item *log_items[need_ail];
int i = 0;
spin_lock(&ailp->xa_lock);
for (blip = lip; blip; blip = blip->li_bio_list) {
iip = INODE_ITEM(blip);
if (iip->ili_logged &&
blip->li_lsn == iip->ili_flush_lsn) {
log_items[i++] = blip;
}
ASSERT(i <= need_ail);
}
/* xfs_trans_ail_delete_bulk() drops the AIL lock. */
xfs_trans_ail_delete_bulk(ailp, log_items, i,
SHUTDOWN_CORRUPT_INCORE);
}
/*
* clean up and unlock the flush lock now we are done. We can clear the
* ili_last_fields bits now that we know that the data corresponding to
* them is safely on disk.
*/
for (blip = lip; blip; blip = next) {
next = blip->li_bio_list;
blip->li_bio_list = NULL;
iip = INODE_ITEM(blip);
iip->ili_logged = 0;
iip->ili_last_fields = 0;
xfs_ifunlock(iip->ili_inode);
}
}
/*
* This is the inode flushing abort routine. It is called from xfs_iflush when
* the filesystem is shutting down to clean up the inode state. It is
* responsible for removing the inode item from the AIL if it has not been
* re-logged, and unlocking the inode's flush lock.
*/
void
xfs_iflush_abort(
xfs_inode_t *ip,
bool stale)
{
xfs_inode_log_item_t *iip = ip->i_itemp;
if (iip) {
if (iip->ili_item.li_flags & XFS_LI_IN_AIL) {
xfs_trans_ail_remove(&iip->ili_item,
stale ? SHUTDOWN_LOG_IO_ERROR :
SHUTDOWN_CORRUPT_INCORE);
}
iip->ili_logged = 0;
/*
* Clear the ili_last_fields bits now that we know that the
* data corresponding to them is safely on disk.
*/
iip->ili_last_fields = 0;
/*
* Clear the inode logging fields so no more flushes are
* attempted.
*/
iip->ili_fields = 0;
xfs: optimise away log forces on timestamp updates for fdatasync xfs: timestamp updates cause excessive fdatasync log traffic Sage Weil reported that a ceph test workload was writing to the log on every fdatasync during an overwrite workload. Event tracing showed that the only metadata modification being made was the timestamp updates during the write(2) syscall, but fdatasync(2) is supposed to ignore them. The key observation was that the transactions in the log all looked like this: INODE: #regs: 4 ino: 0x8b flags: 0x45 dsize: 32 And contained a flags field of 0x45 or 0x85, and had data and attribute forks following the inode core. This means that the timestamp updates were triggering dirty relogging of previously logged parts of the inode that hadn't yet been flushed back to disk. There are two parts to this problem. The first is that XFS relogs dirty regions in subsequent transactions, so it carries around the fields that have been dirtied since the last time the inode was written back to disk, not since the last time the inode was forced into the log. The second part is that on v5 filesystems, the inode change count update during inode dirtying also sets the XFS_ILOG_CORE flag, so on v5 filesystems this makes a timestamp update dirty the entire inode. As a result when fdatasync is run, it looks at the dirty fields in the inode, and sees more than just the timestamp flag, even though the only metadata change since the last fdatasync was just the timestamps. Hence we force the log on every subsequent fdatasync even though it is not needed. To fix this, add a new field to the inode log item that tracks changes since the last time fsync/fdatasync forced the log to flush the changes to the journal. This flag is updated when we dirty the inode, but we do it before updating the change count so it does not carry the "core dirty" flag from timestamp updates. The fields are zeroed when the inode is marked clean (due to writeback/freeing) or when an fsync/datasync forces the log. Hence if we only dirty the timestamps on the inode between fsync/fdatasync calls, the fdatasync will not trigger another log force. Over 100 runs of the test program: Ext4 baseline: runtime: 1.63s +/- 0.24s avg lat: 1.59ms +/- 0.24ms iops: ~2000 XFS, vanilla kernel: runtime: 2.45s +/- 0.18s avg lat: 2.39ms +/- 0.18ms log forces: ~400/s iops: ~1000 XFS, patched kernel: runtime: 1.49s +/- 0.26s avg lat: 1.46ms +/- 0.25ms log forces: ~30/s iops: ~1500 Reported-by: Sage Weil <sage@redhat.com> Signed-off-by: Dave Chinner <dchinner@redhat.com> Reviewed-by: Brian Foster <bfoster@redhat.com> Signed-off-by: Dave Chinner <david@fromorbit.com>
2015-11-03 09:14:59 +07:00
iip->ili_fsync_fields = 0;
}
/*
* Release the inode's flush lock since we're done with it.
*/
xfs_ifunlock(ip);
}
void
xfs_istale_done(
struct xfs_buf *bp,
struct xfs_log_item *lip)
{
xfs_iflush_abort(INODE_ITEM(lip)->ili_inode, true);
}
/*
* convert an xfs_inode_log_format struct from either 32 or 64 bit versions
* (which can have different field alignments) to the native version
*/
int
xfs_inode_item_format_convert(
xfs_log_iovec_t *buf,
xfs_inode_log_format_t *in_f)
{
if (buf->i_len == sizeof(xfs_inode_log_format_32_t)) {
xfs_inode_log_format_32_t *in_f32 = buf->i_addr;
in_f->ilf_type = in_f32->ilf_type;
in_f->ilf_size = in_f32->ilf_size;
in_f->ilf_fields = in_f32->ilf_fields;
in_f->ilf_asize = in_f32->ilf_asize;
in_f->ilf_dsize = in_f32->ilf_dsize;
in_f->ilf_ino = in_f32->ilf_ino;
/* copy biggest field of ilf_u */
memcpy(in_f->ilf_u.ilfu_uuid.__u_bits,
in_f32->ilf_u.ilfu_uuid.__u_bits,
sizeof(uuid_t));
in_f->ilf_blkno = in_f32->ilf_blkno;
in_f->ilf_len = in_f32->ilf_len;
in_f->ilf_boffset = in_f32->ilf_boffset;
return 0;
} else if (buf->i_len == sizeof(xfs_inode_log_format_64_t)){
xfs_inode_log_format_64_t *in_f64 = buf->i_addr;
in_f->ilf_type = in_f64->ilf_type;
in_f->ilf_size = in_f64->ilf_size;
in_f->ilf_fields = in_f64->ilf_fields;
in_f->ilf_asize = in_f64->ilf_asize;
in_f->ilf_dsize = in_f64->ilf_dsize;
in_f->ilf_ino = in_f64->ilf_ino;
/* copy biggest field of ilf_u */
memcpy(in_f->ilf_u.ilfu_uuid.__u_bits,
in_f64->ilf_u.ilfu_uuid.__u_bits,
sizeof(uuid_t));
in_f->ilf_blkno = in_f64->ilf_blkno;
in_f->ilf_len = in_f64->ilf_len;
in_f->ilf_boffset = in_f64->ilf_boffset;
return 0;
}
return -EFSCORRUPTED;
}