linux/fs/xfs/Makefile

176 lines
3.9 KiB
Makefile
Raw Normal View History

# SPDX-License-Identifier: GPL-2.0
#
# Copyright (c) 2000-2005 Silicon Graphics, Inc.
# All Rights Reserved.
#
ccflags-y += -I $(srctree)/$(src) # needed for trace events
ccflags-y += -I $(srctree)/$(src)/libxfs
obj-$(CONFIG_XFS_FS) += xfs.o
# this one should be compiled first, as the tracing macros can easily blow up
xfs-y += xfs_trace.o
# build the libxfs code first
xfs-y += $(addprefix libxfs/, \
xfs_ag.o \
xfs_alloc.o \
xfs_alloc_btree.o \
xfs_attr.o \
xfs_attr_leaf.o \
xfs_attr_remote.o \
xfs_bit.o \
xfs_bmap.o \
xfs_bmap_btree.o \
xfs_btree.o \
xfs_btree_staging.o \
xfs_da_btree.o \
xfs_defer.o \
xfs_dir2.o \
xfs_dir2_block.o \
xfs_dir2_data.o \
xfs_dir2_leaf.o \
xfs_dir2_node.o \
xfs_dir2_sf.o \
xfs_dquot_buf.o \
xfs_ialloc.o \
xfs_ialloc_btree.o \
xfs: use a b+tree for the in-core extent list Replace the current linear list and the indirection array for the in-core extent list with a b+tree to avoid the need for larger memory allocations for the indirection array when lots of extents are present. The current extent list implementations leads to heavy pressure on the memory allocator when modifying files with a high extent count, and can lead to high latencies because of that. The replacement is a b+tree with a few quirks. The leaf nodes directly store the extent record in two u64 values. The encoding is a little bit different from the existing in-core extent records so that the start offset and length which are required for lookups can be retreived with simple mask operations. The inner nodes store a 64-bit key containing the start offset in the first half of the node, and the pointers to the next lower level in the second half. In either case we walk the node from the beginninig to the end and do a linear search, as that is more efficient for the low number of cache lines touched during a search (2 for the inner nodes, 4 for the leaf nodes) than a binary search. We store termination markers (zero length for the leaf nodes, an otherwise impossible high bit for the inner nodes) to terminate the key list / records instead of storing a count to use the available cache lines as efficiently as possible. One quirk of the algorithm is that while we normally split a node half and half like usual btree implementations we just spill over entries added at the very end of the list to a new node on its own. This means we get a 100% fill grade for the common cases of bulk insertion when reading an inode into memory, and when only sequentially appending to a file. The downside is a slightly higher chance of splits on the first random insertions. Both insert and removal manually recurse into the lower levels, but the bulk deletion of the whole tree is still implemented as a recursive function call, although one limited by the overall depth and with very little stack usage in every iteration. For the first few extents we dynamically grow the list from a single extent to the next powers of two until we have a first full leaf block and that building the actual tree. The code started out based on the generic lib/btree.c code from Joern Engel based on earlier work from Peter Zijlstra, but has since been rewritten beyond recognition. Signed-off-by: Christoph Hellwig <hch@lst.de> Reviewed-by: Darrick J. Wong <darrick.wong@oracle.com> Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
2017-11-03 17:34:46 +00:00
xfs_iext_tree.o \
xfs_inode_fork.o \
xfs_inode_buf.o \
xfs_log_rlimit.o \
xfs: set up per-AG free space reservations One unfortunate quirk of the reference count and reverse mapping btrees -- they can expand in size when blocks are written to *other* allocation groups if, say, one large extent becomes a lot of tiny extents. Since we don't want to start throwing errors in the middle of CoWing, we need to reserve some blocks to handle future expansion. The transaction block reservation counters aren't sufficient here because we have to have a reserve of blocks in every AG, not just somewhere in the filesystem. Therefore, create two per-AG block reservation pools. One feeds the AGFL so that rmapbt expansion always succeeds, and the other feeds all other metadata so that refcountbt expansion never fails. Use the count of how many reserved blocks we need to have on hand to create a virtual reservation in the AG. Through selective clamping of the maximum length of allocation requests and of the length of the longest free extent, we can make it look like there's less free space in the AG unless the reservation owner is asking for blocks. In other words, play some accounting tricks in-core to make sure that we always have blocks available. On the plus side, there's nothing to clean up if we crash, which is contrast to the strategy that the rough draft used (actually removing extents from the freespace btrees). Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com> Reviewed-by: Dave Chinner <dchinner@redhat.com> Signed-off-by: Dave Chinner <david@fromorbit.com>
2016-09-19 00:30:52 +00:00
xfs_ag_resv.o \
xfs_rmap.o \
xfs_rmap_btree.o \
xfs_refcount.o \
xfs_refcount_btree.o \
xfs_sb.o \
xfs_symlink_remote.o \
xfs_trans_inode.o \
xfs_trans_resv.o \
xfs_types.o \
)
# xfs_rtbitmap is shared with libxfs
xfs-$(CONFIG_XFS_RT) += $(addprefix libxfs/, \
xfs_rtbitmap.o \
)
# highlevel code
xfs-y += xfs_aops.o \
xfs_attr_inactive.o \
xfs_attr_list.o \
xfs_bmap_util.o \
xfs_bio_io.o \
xfs_buf.o \
xfs_dir2_readdir.o \
xfs_discard.o \
xfs_error.o \
xfs_export.o \
xfs_extent_busy.o \
xfs_file.o \
xfs_filestream.o \
xfs_fsmap.o \
xfs_fsops.o \
xfs_globals.o \
xfs_health.o \
xfs_icache.o \
xfs_ioctl.o \
xfs_iomap.o \
xfs_iops.o \
xfs_inode.o \
xfs_itable.o \
xfs_iwalk.o \
xfs_message.o \
xfs_mount.o \
xfs_mru_cache.o \
xfs_pwork.o \
xfs_reflink.o \
xfs_stats.o \
xfs_super.o \
xfs_symlink.o \
xfs_sysfs.o \
xfs_trans.o \
xfs_xattr.o \
kmem.o
# low-level transaction/log code
xfs-y += xfs_log.o \
xfs_log_cil.o \
xfs_bmap_item.o \
xfs_buf_item.o \
xfs_buf_item_recover.o \
xfs_dquot_item_recover.o \
xfs_extfree_item.o \
xfs: Set up infrastructure for log attribute replay Currently attributes are modified directly across one or more transactions. But they are not logged or replayed in the event of an error. The goal of log attr replay is to enable logging and replaying of attribute operations using the existing delayed operations infrastructure. This will later enable the attributes to become part of larger multi part operations that also must first be recorded to the log. This is mostly of interest in the scheme of parent pointers which would need to maintain an attribute containing parent inode information any time an inode is moved, created, or removed. Parent pointers would then be of interest to any feature that would need to quickly derive an inode path from the mount point. Online scrub, nfs lookups and fs grow or shrink operations are all features that could take advantage of this. This patch adds two new log item types for setting or removing attributes as deferred operations. The xfs_attri_log_item will log an intent to set or remove an attribute. The corresponding xfs_attrd_log_item holds a reference to the xfs_attri_log_item and is freed once the transaction is done. Both log items use a generic xfs_attr_log_format structure that contains the attribute name, value, flags, inode, and an op_flag that indicates if the operations is a set or remove. [dchinner: added extra little bits needed for intent whiteouts] Signed-off-by: Allison Henderson <allison.henderson@oracle.com> Reviewed-by: Chandan Babu R <chandanrlinux@gmail.com> Reviewed-by: Darrick J. Wong <djwong@kernel.org> Signed-off-by: Dave Chinner <david@fromorbit.com>
2022-05-04 02:41:02 +00:00
xfs_attr_item.o \
xfs_icreate_item.o \
xfs_inode_item.o \
xfs_inode_item_recover.o \
xfs_iunlink_item.o \
xfs_refcount_item.o \
xfs_rmap_item.o \
xfs_log_recover.o \
xfs_trans_ail.o \
xfs_trans_buf.o
# optional features
xfs-$(CONFIG_XFS_QUOTA) += xfs_dquot.o \
xfs_dquot_item.o \
xfs_trans_dquot.o \
xfs_qm_syscalls.o \
xfs_qm_bhv.o \
xfs_qm.o \
xfs_quotaops.o
# xfs_rtbitmap is shared with libxfs
xfs-$(CONFIG_XFS_RT) += xfs_rtalloc.o
xfs-$(CONFIG_XFS_POSIX_ACL) += xfs_acl.o
xfs-$(CONFIG_SYSCTL) += xfs_sysctl.o
xfs-$(CONFIG_COMPAT) += xfs_ioctl32.o
xfs-$(CONFIG_EXPORTFS_BLOCK_OPS) += xfs_pnfs.o
# notify failure
ifeq ($(CONFIG_MEMORY_FAILURE),y)
xfs-$(CONFIG_FS_DAX) += xfs_notify_failure.o
endif
# online scrub/repair
ifeq ($(CONFIG_XFS_ONLINE_SCRUB),y)
# Tracepoints like to blow up, so build that before everything else
xfs-y += $(addprefix scrub/, \
trace.o \
agheader.o \
alloc.o \
attr.o \
bmap.o \
btree.o \
common.o \
dabtree.o \
dir.o \
fscounters.o \
health.o \
ialloc.o \
inode.o \
parent.o \
refcount.o \
rmap.o \
scrub.o \
symlink.o \
)
xfs-$(CONFIG_XFS_RT) += scrub/rtbitmap.o
xfs-$(CONFIG_XFS_QUOTA) += scrub/quota.o
# online repair
ifeq ($(CONFIG_XFS_ONLINE_REPAIR),y)
xfs-y += $(addprefix scrub/, \
agheader_repair.o \
bitmap.o \
repair.o \
)
endif
endif