Swap meta allocators with much more reserve.

We increase the reserve from 2x to 3x the minimum number of blocks needed for our reserve, and change the algorithm that determines when to swap them. The old algorithm swaps them if _avail is just larger than _freed. While the simplest algorithm, it suffers from the problem that in practice, when we hit ENOSPC conditions, it will almost always swap on every iteration when we hit our low water mark. In our testing, we regularly see failures because what is effectively happening is that we starve both allocators by slowly draining them block by block, trying to do work. The work of course requires us to drain more blocks to commit changes. This cycle doesn't end until both allocators are almost completely drained and not enough blocks remain to do any real work anymore. The new algorithm will not swap allocators unless _freed is 50% larger than _avail. The outcome is that, during meta space pressure, we're allowing _avail to slowly drain down to the same levels as before, effectively. However, we then swap to _freed which is now 1.5x larger. This results in us being able to do a whole chunk of work without needing to swap. While draining _avail for longer, we allow work to commit and recycle blocks back into _freed muich more effectively. Signed-off-by: Auke Kok <auke.kok@versity.com>
2026-04-30 09:56:55 +00:00 · 2025-02-11 17:04:28 -05:00
32 changed files with 335 additions and 1671 deletions
--- a/ReleaseNotes.md
+++ b/ReleaseNotes.md
@@ -1,43 +1,6 @@
 Versity ScoutFS Release Notes
 =============================

---
-v1.25
-\
-*Jun 3, 2025*
-
-Fix a bug that could cause indefinite retries of failed client commits.
-Under specific error conditions the client and server's understanding of
-the current client commit could get out of sync.  The client would retry
-commits indefinitely that could never succeed.  This manifested as
-infinite "critical transaction commit failure" messages in the kernel
-log on the client and matching "error <nr> committing client logs" on
-the server.
-
-Fix a bug in a specific case of server error handling that could result
-in sending references to unwritten blocks to the client.  The client
-would try to read blocks that hadn't been written and return spurious
-errors.  This was seen under low free space conditions on the server and
-resulted in error messages with error code 116 (The errno enum for
-ESTALE, the client's indication that it couldn't read the blocks that it
-expected.)
-
---
-v1.24
-\
-*Mar 14, 2025*
-
-Add support for coherent read and write mmap() mappings of regular file
-data between mounts.
-
-Fix a bug that was causing scoutfs utilities to parse and change some
-file names before passing them on to the kernel for processing.  This
-fixes spurious scoutfs command errors for files with the offending
-patterns in their names.
-
-Fix a bug where rename wasn't updating the ctime of the inode at the
-destination name if it existed.
-
 ---
 v1.23
 \
--- a/kmod/src/Makefile.kernelcompat
+++ b/kmod/src/Makefile.kernelcompat
@@ -6,6 +6,26 @@

 ccflags-y += -include $(src)/kernelcompat.h

+#
+# v3.10-rc6-21-gbb6f619b3a49
+#
+# _readdir changes from fop->readdir() to fop->iterate() and from
+# filldir(dirent) to dir_emit(ctx).
+#
+ifneq (,$(shell grep 'iterate.*dir_context' include/linux/fs.h))
+ccflags-y += -DKC_ITERATE_DIR_CONTEXT
+endif
+
+#
+# v3.10-rc6-23-g5f99f4e79abc
+#
+# Helpers including dir_emit_dots() are added in the process of
+# switching dcache_readdir() from fop->readdir() to fop->iterate()
+#
+ifneq (,$(shell grep 'dir_emit_dots' include/linux/fs.h))
+ccflags-y += -DKC_DIR_EMIT_DOTS
+endif
+
 #
 # v3.18-rc2-19-gb5ae6b15bd73
 # 
@@ -411,26 +431,3 @@ endif
 ifneq (,$(shell grep 'struct file.*bdev_file_open_by_path.const char.*path' include/linux/blkdev.h))
 ccflags-y += -DKC_BDEV_FILE_OPEN_BY_PATH
 endif
-
-# v4.0-rc7-1796-gfe0f07d08ee3
-#
-# direct-io changes modify inode_dio_done to now be called inode_dio_end
-ifneq (,$(shell grep 'void inode_dio_end.struct inode' include/linux/fs.h))
-ccflags-y += -DKC_INODE_DIO_END
-endif
-
-#
-# v5.0-6476-g3d3539018d2c
-#
-# page fault handlers return a bitmask vm_fault_t instead
-# Note: el8's header has a slightly modified prefix here
-ifneq (,$(shell grep 'typedef.*__bitwise unsigned.*int vm_fault_t' include/linux/mm_types.h))
-ccflags-y += -DKC_MM_VM_FAULT_T
-endif
-
-# v3.19-499-gd83a08db5ba6
-#
-# .remap pages becomes obsolete
-ifneq (,$(shell grep 'int ..remap_pages..struct vm_area_struct' include/linux/mm.h))
-ccflags-y += -DKC_MM_REMAP_PAGES
-endif
--- a/kmod/src/data.c
+++ b/kmod/src/data.c
@@ -560,7 +560,7 @@ static int scoutfs_get_block(struct inode *inode, sector_t iblock,
 	u64 offset;
 	int ret;

-	WARN_ON_ONCE(create && !rwsem_is_locked(&si->extent_sem));
+	WARN_ON_ONCE(create && !inode_is_locked(inode));

 	/* make sure caller holds a cluster lock */
 	lock = scoutfs_per_task_get(&si->pt_data_lock);
@@ -1515,93 +1515,6 @@ out:
 	return ret;
 }

-/*
- * Punch holes in offline extents.  This is a very specific tool that
- * only does one job: it converts extents from offline to sparse.  It
- * returns an error if it encounters an extent that isn't offline or has
- * a block mapping.  It ignores i_size completely; it does not test it,
- * and does not update it.
- *
- * The caller has the inode locked in the vfs and performed basic sanity
- * checks.  We manage transactions and the extent_sem which is ordered
- * inside the transaction.
- */
-int scoutfs_data_punch_offline(struct inode *inode, u64 iblock, u64 last, u64 data_version,
-			       struct scoutfs_lock *lock)
-{
-	struct scoutfs_inode_info *si = SCOUTFS_I(inode);
-	struct super_block *sb = inode->i_sb;
-	struct data_ext_args args = {
-		.ino = scoutfs_ino(inode),
-		.inode = inode,
-		.lock = lock,
-	};
-	struct scoutfs_extent ext;
-	LIST_HEAD(ind_locks);
-	int ret;
-	int i;
-
-	if (WARN_ON_ONCE(iblock > last)) {
-		ret = -EINVAL;
-		goto out;
-	}
-
-	/* idiomatic to call start,last with 0,~0, clamp last to last possible */
-	last = min(last, SCOUTFS_BLOCK_SM_MAX);
-
-	ret = 0;
-	while (iblock <= last) {
-		ret = scoutfs_inode_index_lock_hold(inode, &ind_locks, true, false) ?:
-		      scoutfs_dirty_inode_item(inode, lock);
-		if (ret < 0)
-			break;
-
-		down_write(&si->extent_sem);
-
-		for (i = 0; i < 32 && (iblock <= last); i++) {
-			ret = scoutfs_ext_next(sb, &data_ext_ops, &args, iblock, 1, &ext);
-			if (ret == -ENOENT || ext.start > iblock) {
-				iblock = last + 1;
-				ret = 0;
-				break;
-			}
-
-			if (ext.map) {
-				ret = -EINVAL;
-				break;
-			}
-
-			if (ext.flags & SEF_OFFLINE) {
-				if (iblock > ext.start) {
-					ext.len -= iblock - ext.start;
-					ext.start = iblock;
-				}
-				ext.len = min(ext.len, last - ext.start + 1);
-				ext.flags &= ~SEF_OFFLINE;
-
-				ret = scoutfs_ext_set(sb, &data_ext_ops, &args,
-						      ext.start, ext.len, ext.map, ext.flags);
-				if (ret < 0)
-					break;
-			}
-
-			iblock = ext.start + ext.len;
-		}
-
-		up_write(&si->extent_sem);
-
-		scoutfs_update_inode_item(inode, lock, &ind_locks);
-		scoutfs_release_trans(sb);
-		scoutfs_inode_index_unlock(sb, &ind_locks);
-
-		if (ret < 0)
-			break;
-	}
-
-out:
-	return ret;
-}
-
 /*
 * This copies to userspace :/
 */
@@ -1638,17 +1551,13 @@ int scoutfs_data_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
 	struct super_block *sb = inode->i_sb;
 	const u64 ino = scoutfs_ino(inode);
 	struct scoutfs_lock *lock = NULL;
-	struct scoutfs_extent *info = NULL;
-	struct page *page = NULL;
 	struct scoutfs_extent ext;
 	struct scoutfs_extent cur;
 	struct data_ext_args args;
 	u32 last_flags;
 	u64 iblock;
 	u64 last;
-	int entries = 0;
 	int ret;
-	int complete = 0;

 	if (len == 0) {
 		ret = 0;
@@ -1659,11 +1568,16 @@ int scoutfs_data_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
 	if (ret)
 		goto out;

-	page = alloc_page(GFP_KERNEL);
-	if (!page) {
-		ret = -ENOMEM;
-		goto out;
-	}
+	inode_lock(inode);
+	down_read(&si->extent_sem);
+
+	ret = scoutfs_lock_inode(sb, SCOUTFS_LOCK_READ, 0, inode, &lock);
+	if (ret)
+		goto unlock;
+
+	args.ino = ino;
+	args.inode = inode;
+	args.lock = lock;

 	/* use a dummy extent to track */
 	memset(&cur, 0, sizeof(cur));
@@ -1672,93 +1586,48 @@ int scoutfs_data_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
 	iblock = start >> SCOUTFS_BLOCK_SM_SHIFT;
 	last = (start + len - 1) >> SCOUTFS_BLOCK_SM_SHIFT;

-	args.ino = ino;
-	args.inode = inode;
-
-	/* outer loop */
 	while (iblock <= last) {
-		/* lock */
-		inode_lock(inode);
-		down_read(&si->extent_sem);
-
-		ret = scoutfs_lock_inode(sb, SCOUTFS_LOCK_READ, 0, inode, &lock);
-		if (ret) {
-			up_read(&si->extent_sem);
-			inode_unlock(inode);
-			break;
-		}
-
-		args.lock = lock;
-
-		/* collect entries */
-		info = page_address(page);
-		memset(info, 0, PAGE_SIZE);
-		while (entries < (PAGE_SIZE / sizeof(struct fiemap_extent)) - 1) {
-			ret = scoutfs_ext_next(sb, &data_ext_ops, &args,
-					       iblock, 1, &ext);
-			if (ret < 0) {
-				if (ret == -ENOENT)
-					ret = 0;
-				complete = 1;
-				last_flags = FIEMAP_EXTENT_LAST;
-				break;
-			}
-
-			trace_scoutfs_data_fiemap_extent(sb, ino, &ext);
-
-			if (ext.start > last) {
-				/* not setting _LAST, it's for end of file */
+		ret = scoutfs_ext_next(sb, &data_ext_ops, &args,
+				       iblock, 1, &ext);
+		if (ret < 0) {
+			if (ret == -ENOENT)
 				ret = 0;
-				complete = 1;
-				break;
-			}
-
-			if (scoutfs_ext_can_merge(&cur, &ext)) {
-				/* merged extents could be greater than input len */
-				cur.len += ext.len;
-			} else {
-				/* fill it */
-				memcpy(info, &cur, sizeof(cur));
-
-				entries++;
-				info++;
-
-				cur = ext;
-			}
-
-			iblock = ext.start + ext.len;
+			last_flags = FIEMAP_EXTENT_LAST;
+			break;
 		}

-		/* unlock */
-		scoutfs_unlock(sb, lock, SCOUTFS_LOCK_READ);
-		up_read(&si->extent_sem);
-		inode_unlock(inode);
+		trace_scoutfs_data_fiemap_extent(sb, ino, &ext);

-		if (ret)
+		if (ext.start > last) {
+			/* not setting _LAST, it's for end of file */
+			ret = 0;
 			break;
+		}

-		/* emit entries */
-		info = page_address(page);
-		for (; entries > 0; entries--) {
-			ret = fill_extent(fieinfo, info, 0);
+		if (scoutfs_ext_can_merge(&cur, &ext)) {
+			/* merged extents could be greater than input len */
+			cur.len += ext.len;
+		} else {
+			ret = fill_extent(fieinfo, &cur, 0);
 			if (ret != 0)
-				goto out;
-			info++;
+				goto unlock;
+			cur = ext;
 		}

-		if (complete)
-			break;
+		iblock = ext.start + ext.len;
 	}

-	/* still one left, it's in cur */
 	if (cur.len)
 		ret = fill_extent(fieinfo, &cur, last_flags);
+unlock:
+	scoutfs_unlock(sb, lock, SCOUTFS_LOCK_READ);
+	up_read(&si->extent_sem);
+	inode_unlock(inode);

 out:
 	if (ret == 1)
 		ret = 0;
-	if (page)
-		__free_page(page);
+
 	trace_scoutfs_data_fiemap(sb, start, len, ret);

 	return ret;
@@ -2045,236 +1914,6 @@ int scoutfs_data_waiting(struct super_block *sb, u64 ino, u64 iblock,
 	return ret;
 }

-#ifdef KC_MM_VM_FAULT_T
-static vm_fault_t scoutfs_data_page_mkwrite(struct vm_fault *vmf)
-{
-	struct vm_area_struct *vma = vmf->vma;
-#else
-static int scoutfs_data_page_mkwrite(struct vm_area_struct *vma,
-				     struct vm_fault *vmf)
-{
-#endif
-	struct page *page = vmf->page;
-	struct file *file = vma->vm_file;
-	struct inode *inode = file_inode(file);
-	struct scoutfs_inode_info *si = SCOUTFS_I(inode);
-	struct super_block *sb = inode->i_sb;
-	struct scoutfs_lock *lock = NULL;
-	SCOUTFS_DECLARE_PER_TASK_ENTRY(pt_ent);
-	DECLARE_DATA_WAIT(dw);
-	struct write_begin_data wbd;
-	u64 ind_seq;
-	loff_t pos;
-	loff_t size;
-	unsigned int len = PAGE_SIZE;
-	vm_fault_t ret = VM_FAULT_SIGBUS;
-	int err;
-
-	pos = vmf->pgoff << PAGE_SHIFT;
-
-	sb_start_pagefault(sb);
-
-	err = scoutfs_lock_inode(sb, SCOUTFS_LOCK_WRITE,
-				 SCOUTFS_LKF_REFRESH_INODE, inode, &lock);
-	if (err) {
-		ret = vmf_error(err);
-		goto out;
-	}
-
-	size = i_size_read(inode);
-
-	if (scoutfs_per_task_add_excl(&si->pt_data_lock, &pt_ent, lock)) {
-		/* data_version is per inode, whole file must be online */
-		err = scoutfs_data_wait_check(inode, 0, size,
-					      SEF_OFFLINE,
-					      SCOUTFS_IOC_DWO_WRITE,
-					      &dw, lock);
-		if (err != 0) {
-			if (err < 0)
-				ret = vmf_error(err);
-			goto out_unlock;
-		}
-	}
-
-
-	/* scoutfs_write_begin */
-	memset(&wbd, 0, sizeof(wbd));
-	INIT_LIST_HEAD(&wbd.ind_locks);
-	wbd.lock = lock;
-
-	/*
-	 * Start transaction before taking page locks - we want to make sure we're
-	 * not locking a page, then waiting for trans, because writeback might race
-	 * against it and cause a lock inversion hang - as demonstrated by both
-	 * holetest and fsstress tests in xfstests.
-	 */
-	do {
-		err = scoutfs_inode_index_start(sb, &ind_seq) ?:
-			scoutfs_inode_index_prepare(sb, &wbd.ind_locks, inode,
-						    true) ?:
-			scoutfs_inode_index_try_lock_hold(sb, &wbd.ind_locks,
-							  ind_seq, false);
-	} while (err > 0);
-	if (err < 0) {
-		ret = vmf_error(err);
-		goto out_trans;
-	}
-
-	down_write(&si->extent_sem);
-
-	if (!trylock_page(page)) {
-		ret = VM_FAULT_NOPAGE;
-		goto out_sem;
-	}
-	ret = VM_FAULT_LOCKED;
-
-	if ((page->mapping != inode->i_mapping) ||
-	    (!PageUptodate(page)) ||
-	    (page_offset(page) > size))	 {
-		unlock_page(page);
-		ret = VM_FAULT_NOPAGE;
-		goto out_sem;
-	}
-
-	if (page->index == (size - 1) >> PAGE_SHIFT)
-		len = ((size - 1) & ~PAGE_MASK) + 1;
-
-	err = __block_write_begin(page, pos, PAGE_SIZE, scoutfs_get_block);
-	if (err) {
-		ret = vmf_error(err);
-		unlock_page(page);
-		goto out_sem;
-	}
-	/* end scoutfs_write_begin */
-
-	/*
-	 * We mark the page dirty already here so that when freeze is in
-	 * progress, we are guaranteed that writeback during freezing will
-	 * see the dirty page and writeprotect it again.
-	 */
-	set_page_dirty(page);
-	wait_for_stable_page(page);
-
-	/* scoutfs_write_end */
-	scoutfs_inode_set_data_seq(inode);
-	scoutfs_inode_inc_data_version(inode);
-
-	file_update_time(vma->vm_file);
-
-	scoutfs_update_inode_item(inode, wbd.lock, &wbd.ind_locks);
-	scoutfs_inode_queue_writeback(inode);
-
-out_sem:
-	up_write(&si->extent_sem);
-out_trans:
-	scoutfs_release_trans(sb);
-	scoutfs_inode_index_unlock(sb, &wbd.ind_locks);
-	/* end scoutfs_write_end */
-
-out_unlock:
-	scoutfs_per_task_del(&si->pt_data_lock, &pt_ent);
-	scoutfs_unlock(sb, lock, SCOUTFS_LOCK_WRITE);
-
-out:
-	sb_end_pagefault(sb);
-
-	if (scoutfs_data_wait_found(&dw)) {
-		/*
-		 * It'd be really nice to not hold the mmap_sem lock here
-		 * before waiting for data, and then return VM_FAULT_RETRY
-		 */
-		err = scoutfs_data_wait(inode, &dw);
-		if (err == 0)
-			ret = VM_FAULT_NOPAGE;
-		else
-			ret = vmf_error(err);
-	}
-
-	trace_scoutfs_data_page_mkwrite(sb, scoutfs_ino(inode), pos, (__force u32)ret);
-
-	return ret;
-}
-
-#ifdef KC_MM_VM_FAULT_T
-static vm_fault_t scoutfs_data_filemap_fault(struct vm_fault *vmf)
-{
-	struct vm_area_struct *vma = vmf->vma;
-#else
-static int scoutfs_data_filemap_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
-{
-#endif
-	struct file *file = vma->vm_file;
-	struct inode *inode = file_inode(file);
-	struct scoutfs_inode_info *si = SCOUTFS_I(inode);
-	struct super_block *sb = inode->i_sb;
-	struct scoutfs_lock *inode_lock = NULL;
-	SCOUTFS_DECLARE_PER_TASK_ENTRY(pt_ent);
-	DECLARE_DATA_WAIT(dw);
-	loff_t pos;
-	int err;
-	vm_fault_t ret = VM_FAULT_SIGBUS;
-
-	pos = vmf->pgoff;
-	pos <<= PAGE_SHIFT;
-
-retry:
-	err = scoutfs_lock_inode(sb, SCOUTFS_LOCK_READ,
-				 SCOUTFS_LKF_REFRESH_INODE, inode, &inode_lock);
-	if (err < 0)
-		return vmf_error(err);
-
-	if (scoutfs_per_task_add_excl(&si->pt_data_lock, &pt_ent, inode_lock)) {
-		/* protect checked extents from stage/release */
-		atomic_inc(&inode->i_dio_count);
-
-		err = scoutfs_data_wait_check(inode, pos, PAGE_SIZE,
-					      SEF_OFFLINE, SCOUTFS_IOC_DWO_READ,
-					      &dw, inode_lock);
-		if (err != 0) {
-			if (err < 0)
-				ret = vmf_error(err);
-			goto out;
-		}
-	}
-
-#ifdef KC_MM_VM_FAULT_T
-	ret = filemap_fault(vmf);
-#else
-	ret = filemap_fault(vma, vmf);
-#endif
-
-out:
-	if (scoutfs_per_task_del(&si->pt_data_lock, &pt_ent))
-		kc_inode_dio_end(inode);
-	scoutfs_unlock(sb, inode_lock, SCOUTFS_LOCK_READ);
-	if (scoutfs_data_wait_found(&dw)) {
-		err = scoutfs_data_wait(inode, &dw);
-		if (err == 0)
-			goto retry;
-
-		ret = VM_FAULT_RETRY;
-	}
-
-	trace_scoutfs_data_filemap_fault(sb, scoutfs_ino(inode), pos, (__force u32)ret);
-
-	return ret;
-}
-
-static const struct vm_operations_struct scoutfs_data_file_vm_ops = {
-	.fault		= scoutfs_data_filemap_fault,
-	.page_mkwrite	= scoutfs_data_page_mkwrite,
-#ifdef KC_MM_REMAP_PAGES
-	.remap_pages	= generic_file_remap_pages,
-#endif
-};
-
-static int scoutfs_file_mmap(struct file *file, struct vm_area_struct *vma)
-{
-	file_accessed(file);
-	vma->vm_ops = &scoutfs_data_file_vm_ops;
-	return 0;
-}
-
 const struct address_space_operations scoutfs_file_aops = {
 #ifdef KC_MPAGE_READ_FOLIO
 	.dirty_folio		= block_dirty_folio,
@@ -2306,7 +1945,6 @@ const struct file_operations scoutfs_file_fops = {
 	.splice_read	= generic_file_splice_read,
 	.splice_write	= iter_file_splice_write,
 #endif
-	.mmap		= scoutfs_file_mmap,
 	.unlocked_ioctl	= scoutfs_ioctl,
 	.fsync		= scoutfs_file_fsync,
 	.llseek		= scoutfs_file_llseek,
--- a/kmod/src/data.h
+++ b/kmod/src/data.h
@@ -57,8 +57,6 @@ int scoutfs_data_init_offline_extent(struct inode *inode, u64 size,
 int scoutfs_data_move_blocks(struct inode *from, u64 from_off,
 			     u64 byte_len, struct inode *to, u64 to_off, bool to_stage,
 			     u64 data_version);
-int scoutfs_data_punch_offline(struct inode *inode, u64 iblock, u64 last, u64 data_version,
-			       struct scoutfs_lock *lock);

 int scoutfs_data_wait_check(struct inode *inode, loff_t pos, loff_t len,
 			    u8 sef, u8 op, struct scoutfs_data_wait *ow,
--- a/kmod/src/dir.c
+++ b/kmod/src/dir.c
@@ -11,13 +11,11 @@
 * General Public License for more details.
 */
 #include <linux/kernel.h>
-#include <linux/stddef.h>
 #include <linux/fs.h>
 #include <linux/slab.h>
 #include <linux/uio.h>
 #include <linux/xattr.h>
 #include <linux/namei.h>
-#include <linux/mm.h>

 #include "format.h"
 #include "file.h"
@@ -436,15 +434,6 @@ out:
 		return d_splice_alias(inode, dentry);
 }

-/*
- * Helper to make iterating through dirent ptrs aligned
- */
-static inline struct scoutfs_dirent *next_aligned_dirent(struct scoutfs_dirent *dent, u8 len)
-{
-	return (void *)dent +
-		ALIGN(offsetof(struct scoutfs_dirent, name[len]), __alignof__(struct scoutfs_dirent));
-}
-
 /*
 * readdir simply iterates over the dirent items for the dir inode and
 * uses their offset as the readdir position.
@@ -452,112 +441,76 @@ static inline struct scoutfs_dirent *next_aligned_dirent(struct scoutfs_dirent *
 * It will need to be careful not to read past the region of the dirent
 * hash offset keys that it has access to.
 */
-static int scoutfs_readdir(struct file *file, struct dir_context *ctx)
+static int KC_DECLARE_READDIR(scoutfs_readdir, struct file *file,
+			      void *dirent, kc_readdir_ctx_t ctx)
 {
 	struct inode *inode = file_inode(file);
 	struct super_block *sb = inode->i_sb;
 	struct scoutfs_lock *dir_lock = NULL;
 	struct scoutfs_dirent *dent = NULL;
-/* we'll store name_len in dent->__pad[0] */
-#define hacky_name_len __pad[0]
 	struct scoutfs_key last_key;
 	struct scoutfs_key key;
-	struct page *page = NULL;
 	int name_len;
 	u64 pos;
-	int entries = 0;
 	int ret;
-	int complete = 0;
-	struct scoutfs_dirent *end;

-	if (!dir_emit_dots(file, ctx))
+	if (!kc_dir_emit_dots(file, dirent, ctx))
 		return 0;

-	page = alloc_page(GFP_KERNEL);
-	if (!page)
+	dent = alloc_dirent(SCOUTFS_NAME_LEN);
+	if (!dent) {
 		return -ENOMEM;
-
-	end = page_address(page) + PAGE_SIZE;
+	}

 	init_dirent_key(&last_key, SCOUTFS_READDIR_TYPE, scoutfs_ino(inode),
 			SCOUTFS_DIRENT_LAST_POS, 0);

-	/*
-	 * lock and fetch dirent items, until the page no longer fits
-	 * a max size dirent (288b). Then unlock and dir_emit the ones
-	 * we stored in the page.
-	 */
+	ret = scoutfs_lock_inode(sb, SCOUTFS_LOCK_READ, 0, inode, &dir_lock);
+	if (ret)
+		goto out;
+
 	for (;;) {
-		/* lock */
-		ret = scoutfs_lock_inode(sb, SCOUTFS_LOCK_READ, 0, inode, &dir_lock);
-		if (ret)
-			break;
+		init_dirent_key(&key, SCOUTFS_READDIR_TYPE, scoutfs_ino(inode),
+				kc_readdir_pos(file, ctx), 0);

-		dent = page_address(page);
-		pos = ctx->pos;
-		while (next_aligned_dirent(dent, SCOUTFS_NAME_LEN) < end) {
-			init_dirent_key(&key, SCOUTFS_READDIR_TYPE, scoutfs_ino(inode),
-					pos, 0);
-
-			ret = scoutfs_item_next(sb, &key, &last_key, dent,
-						dirent_bytes(SCOUTFS_NAME_LEN),
-						dir_lock);
-			if (ret < 0) {
-				if (ret == -ENOENT) {
-					ret = 0;
-					complete = 1;
-				}
-				break;
-			}
-
-			name_len = ret - sizeof(struct scoutfs_dirent);
-			dent->hacky_name_len = name_len;
-			if (name_len < 1 || name_len > SCOUTFS_NAME_LEN) {
-				scoutfs_corruption(sb, SC_DIRENT_READDIR_NAME_LEN,
-						   corrupt_dirent_readdir_name_len,
-						   "dir_ino %llu pos %llu key "SK_FMT" len %d",
-						   scoutfs_ino(inode),
-						   pos,
-						   SK_ARG(&key), name_len);
-				ret = -EIO;
-				break;
-			}
-
-			pos = le64_to_cpu(dent->pos) + 1;
-
-			dent = next_aligned_dirent(dent, name_len);
-			entries++;
-		}
-
-		/* unlock */
-		scoutfs_unlock(sb, dir_lock, SCOUTFS_LOCK_READ);
-
-		if (ret < 0)
-			break;
-
-		dent = page_address(page);
-		for (; entries > 0; entries--) {
-			ctx->pos = le64_to_cpu(dent->pos);
-			if (!dir_emit(ctx, dent->name, dent->hacky_name_len,
-					le64_to_cpu(dent->ino),
-					dentry_type(dent->type))) {
+		ret = scoutfs_item_next(sb, &key, &last_key, dent,
+					dirent_bytes(SCOUTFS_NAME_LEN),
+					dir_lock);
+		if (ret < 0) {
+			if (ret == -ENOENT)
 				ret = 0;
-				goto out;
-			}
-
-			dent = next_aligned_dirent(dent, dent->hacky_name_len);
-
-			/* always advance ctx->pos past */
-			ctx->pos++;
+			break;
 		}

-		if (complete)
+		name_len = ret - sizeof(struct scoutfs_dirent);
+		if (name_len < 1 || name_len > SCOUTFS_NAME_LEN) {
+			scoutfs_corruption(sb, SC_DIRENT_READDIR_NAME_LEN,
+					   corrupt_dirent_readdir_name_len,
+					   "dir_ino %llu pos %llu key "SK_FMT" len %d",
+					   scoutfs_ino(inode),
+					   kc_readdir_pos(file, ctx),
+					   SK_ARG(&key), name_len);
+			ret = -EIO;
+			goto out;
+		}
+
+		pos = le64_to_cpu(key.skd_major);
+		kc_readdir_pos(file, ctx) = pos;
+
+		if (!kc_dir_emit(ctx, dirent, dent->name, name_len, pos,
+				le64_to_cpu(dent->ino),
+				dentry_type(dent->type))) {
+			ret = 0;
 			break;
+		}
+
+		kc_readdir_pos(file, ctx) = pos + 1;
 	}

 out:
-	if (page)
-		__free_page(page);
+	scoutfs_unlock(sb, dir_lock, SCOUTFS_LOCK_READ);
+
+	kfree(dent);
 	return ret;
 }

@@ -1812,7 +1765,7 @@ retry:
 	}
 	old_inode->i_ctime = now;
 	if (new_inode)
-		new_inode->i_ctime = now;
+		old_inode->i_ctime = now;

 	inode_inc_iversion(old_dir);
 	inode_inc_iversion(old_inode);
@@ -2020,7 +1973,7 @@ const struct inode_operations scoutfs_symlink_iops = {
 };

 const struct file_operations scoutfs_dir_fops = {
-	.iterate	= scoutfs_readdir,
+	.KC_FOP_READDIR	= scoutfs_readdir,
 #ifdef KC_FMODE_KABI_ITERATE
 	.open		= scoutfs_dir_open,
 #endif
--- a/kmod/src/ioctl.c
+++ b/kmod/src/ioctl.c
@@ -58,23 +58,25 @@
 * key space after we find no items in a given lock region.  This is
 * relatively cheap because reading is going to check the segments
 * anyway.
+ *
+ * This is copying to userspace while holding a read lock.  This is safe
+ * because faulting can send a request for a write lock while the read
+ * lock is being used.  The cluster locks don't block tasks in a node,
+ * they match and the tasks fall back to local locking.  In this case
+ * the spin locks around the item cache.
 */
 static long scoutfs_ioc_walk_inodes(struct file *file, unsigned long arg)
 {
 	struct super_block *sb = file_inode(file)->i_sb;
 	struct scoutfs_ioctl_walk_inodes __user *uwalk = (void __user *)arg;
 	struct scoutfs_ioctl_walk_inodes walk;
-	struct scoutfs_ioctl_walk_inodes_entry *ent = NULL;
-	struct scoutfs_ioctl_walk_inodes_entry *end;
+	struct scoutfs_ioctl_walk_inodes_entry ent;
 	struct scoutfs_key next_key;
 	struct scoutfs_key last_key;
 	struct scoutfs_key key;
 	struct scoutfs_lock *lock;
-	struct page *page = NULL;
 	u64 last_seq;
-	u64 entries = 0;
 	int ret = 0;
-	int complete = 0;
 	u32 nr = 0;
 	u8 type;

@@ -105,10 +107,6 @@ static long scoutfs_ioc_walk_inodes(struct file *file, unsigned long arg)
 		}
 	}

-	page = alloc_page(GFP_KERNEL);
-	if (!page)
-		return -ENOMEM;
-
 	scoutfs_inode_init_index_key(&key, type, walk.first.major,
 				     walk.first.minor, walk.first.ino);
 	scoutfs_inode_init_index_key(&last_key, type, walk.last.major,
@@ -117,107 +115,77 @@ static long scoutfs_ioc_walk_inodes(struct file *file, unsigned long arg)
 	/* cap nr to the max the ioctl can return to a compat task */
 	walk.nr_entries = min_t(u64, walk.nr_entries, INT_MAX);

-	end = page_address(page) + PAGE_SIZE;
+	ret = scoutfs_lock_inode_index(sb, SCOUTFS_LOCK_READ, type,
+				       walk.first.major, walk.first.ino,
+				       &lock);
+	if (ret < 0)
+		goto out;

-	/* outer loop */
-	for (nr = 0;;) {
-		ent = page_address(page);
-		/* make sure _pad and minor are zeroed */
-		memset(ent, 0, PAGE_SIZE);
+	for (nr = 0; nr < walk.nr_entries; ) {

-		ret = scoutfs_lock_inode_index(sb, SCOUTFS_LOCK_READ, type,
-					       le64_to_cpu(key.skii_major),
-					       le64_to_cpu(key.skii_ino),
-					       &lock);
-		if (ret)
+		ret = scoutfs_item_next(sb, &key, &last_key, NULL, 0, lock);
+		if (ret < 0 && ret != -ENOENT)
 			break;

-		/* inner loop 1 */
-		while (ent + 1 < end) {
-			ret = scoutfs_item_next(sb, &key, &last_key, NULL, 0, lock);
-			if (ret < 0 && ret != -ENOENT)
+		if (ret == -ENOENT) {
+
+			/* done if lock covers last iteration key */
+			if (scoutfs_key_compare(&last_key, &lock->end) <= 0) {
+				ret = 0;
 				break;
-
-			if (ret == -ENOENT) {
-				/* done if lock covers last iteration key */
-				if (scoutfs_key_compare(&last_key, &lock->end) <= 0) {
-					ret = 0;
-					complete = 1;
-					break;
-				}
-
-				/* continue iterating after locked empty region */
-				key = lock->end;
-				scoutfs_key_inc(&key);
-
-				scoutfs_unlock(sb, lock, SCOUTFS_LOCK_READ);
-				/* avoid double-unlocking here after break */
-				lock = NULL;
-
-				ret = scoutfs_forest_next_hint(sb, &key, &next_key);
-				if (ret < 0 && ret != -ENOENT)
-					break;
-
-				if (ret == -ENOENT ||
-				    scoutfs_key_compare(&next_key, &last_key) > 0) {
-					ret = 0;
-					complete = 1;
-					break;
-				}
-
-				key = next_key;
-
-				ret = scoutfs_lock_inode_index(sb, SCOUTFS_LOCK_READ,
-							type,
-							le64_to_cpu(key.skii_major),
-							le64_to_cpu(key.skii_ino),
-							&lock);
-				if (ret)
-					break;
-
-				continue;
 			}

-			ent->major = le64_to_cpu(key.skii_major);
-			ent->ino = le64_to_cpu(key.skii_ino);
-
+			/* continue iterating after locked empty region */
+			key = lock->end;
 			scoutfs_key_inc(&key);

-			ent++;
-			entries++;
+			scoutfs_unlock(sb, lock, SCOUTFS_LOCK_READ);

-			if (nr + entries >= walk.nr_entries) {
-				complete = 1;
-				break;
-			}
-		}
+			ret = scoutfs_forest_next_hint(sb, &key, &next_key);
+			if (ret < 0 && ret != -ENOENT)
+				goto out;

-		scoutfs_unlock(sb, lock, SCOUTFS_LOCK_READ);
-		if (ret < 0)
-			break;
-
-		/* inner loop 2 */
-		ent = page_address(page);
-		for (; entries > 0; entries--) {
-			if (copy_to_user((void __user *)walk.entries_ptr, ent,
-					 sizeof(struct scoutfs_ioctl_walk_inodes_entry))) {
-				ret = -EFAULT;
+			if (ret == -ENOENT ||
+			    scoutfs_key_compare(&next_key, &last_key) > 0) {
+				ret = 0;
 				goto out;
 			}
-			walk.entries_ptr += sizeof(struct scoutfs_ioctl_walk_inodes_entry);
-			ent++;
-			nr++;
+
+			key = next_key;
+
+			ret = scoutfs_lock_inode_index(sb, SCOUTFS_LOCK_READ,
+						key.sk_type,
+						le64_to_cpu(key.skii_major),
+						le64_to_cpu(key.skii_ino),
+						&lock);
+			if (ret < 0)
+				goto out;
+
+			continue;
 		}

-		if (complete)
+		ent.major = le64_to_cpu(key.skii_major);
+		ent.minor = 0;
+		ent.ino = le64_to_cpu(key.skii_ino);
+
+		if (copy_to_user((void __user *)walk.entries_ptr, &ent,
+				 sizeof(ent))) {
+			ret = -EFAULT;
 			break;
+		}
+
+		nr++;
+		walk.entries_ptr += sizeof(ent);
+
+		scoutfs_key_inc(&key);
 	}

+	scoutfs_unlock(sb, lock, SCOUTFS_LOCK_READ);
+
 out:
-	if (page)
-		__free_page(page);
 	if (nr > 0)
 		ret = nr;
+
 	return ret;
 }

@@ -1195,15 +1163,11 @@ static long scoutfs_ioc_get_allocated_inos(struct file *file, unsigned long arg)
 	struct scoutfs_lock *lock = NULL;
 	struct scoutfs_key key;
 	struct scoutfs_key end;
-	struct page *page = NULL;
 	u64 __user *uinos;
 	u64 bytes;
-	u64 *ino;
-	u64 *ino_end;
-	int entries = 0;
+	u64 ino;
 	int nr;
 	int ret;
-	int complete = 0;

 	if (!(file->f_mode & FMODE_READ)) {
 		ret = -EBADF;
@@ -1225,83 +1189,47 @@ static long scoutfs_ioc_get_allocated_inos(struct file *file, unsigned long arg)
 		goto out;
 	}

-	page = alloc_page(GFP_KERNEL);
-	if (!page) {
-		ret = -ENOMEM;
-		goto out;
-	}
-	ino_end = page_address(page) + PAGE_SIZE;
-
 	scoutfs_inode_init_key(&key, gai.start_ino);
 	scoutfs_inode_init_key(&end, gai.start_ino | SCOUTFS_LOCK_INODE_GROUP_MASK);
 	uinos = (void __user *)gai.inos_ptr;
 	bytes = gai.inos_bytes;
 	nr = 0;

-	for (;;) {
+	ret = scoutfs_lock_ino(sb, SCOUTFS_LOCK_READ, 0, gai.start_ino, &lock);
+	if (ret < 0)
+		goto out;

-		ret = scoutfs_lock_ino(sb, SCOUTFS_LOCK_READ, 0, gai.start_ino, &lock);
-		if (ret < 0)
-			goto out;
+	while (bytes >= sizeof(*uinos)) {

-		ino = page_address(page);
-		while (ino < ino_end) {
-
-			ret = scoutfs_item_next(sb, &key, &end, NULL, 0, lock);
-			if (ret < 0) {
-				if (ret == -ENOENT) {
-					ret = 0;
-					complete = 1;
-				}
-				break;
-			}
-
-			if (key.sk_zone != SCOUTFS_FS_ZONE) {
+		ret = scoutfs_item_next(sb, &key, &end, NULL, 0, lock);
+		if (ret < 0) {
+			if (ret == -ENOENT)
 				ret = 0;
-				complete = 1;
-				break;
-			}
-
-			/* all fs items are owned by allocated inodes, and _first is always ino */
-			*ino = le64_to_cpu(key._sk_first);
-			scoutfs_inode_init_key(&key, *ino + 1);
-
-			ino++;
-			entries++;
-			nr++;
-
-			bytes -= sizeof(*uinos);
-			if (bytes < sizeof(*uinos)) {
-				complete = 1;
-				break;
-			}
-
-			if (nr == INT_MAX) {
-				complete = 1;
-				break;
-			}
+			break;
 		}

-		scoutfs_unlock(sb, lock, SCOUTFS_LOCK_READ);
-
-		if (ret < 0)
+		if (key.sk_zone != SCOUTFS_FS_ZONE) {
+			ret = 0;
 			break;
+		}

-		ino = page_address(page);
-		if (copy_to_user(uinos, ino, entries * sizeof(*uinos))) {
+		/* all fs items are owned by allocated inodes, and _first is always ino */
+		ino = le64_to_cpu(key._sk_first);
+		if (put_user(ino, uinos)) {
 			ret = -EFAULT;
-			goto out;
+			break;
 		}

-		uinos += entries;
-		entries = 0;
-
-		if (complete)
+		uinos++;
+		bytes -= sizeof(*uinos);
+		if (++nr == INT_MAX)
 			break;
+
+		scoutfs_inode_init_key(&key, ino + 1);
 	}
+
+	scoutfs_unlock(sb, lock, SCOUTFS_LOCK_READ);
 out:
-	if (page)
-		__free_page(page);
 	return ret ?: nr;
 }

@@ -1668,78 +1596,6 @@ out:
 	return ret;
 }

-static long scoutfs_ioc_punch_offline(struct file *file, unsigned long arg)
-{
-	struct inode *inode = file_inode(file);
-	struct super_block *sb = inode->i_sb;
-	struct scoutfs_ioctl_punch_offline __user *upo = (void __user *)arg;
-	struct scoutfs_ioctl_punch_offline po;
-	struct scoutfs_lock *lock = NULL;
-	u64 iblock;
-	u64 last;
-	u64 tmp;
-	int ret;
-
-	if (copy_from_user(&po, upo, sizeof(po)))
-		return -EFAULT;
-
-	if (po.len == 0)
-		return 0;
-
-	if (check_add_overflow(po.offset, po.len - 1, &tmp) ||
-	    (po.offset & SCOUTFS_BLOCK_SM_MASK) ||
-	    (po.len & SCOUTFS_BLOCK_SM_MASK))
-		return -EOVERFLOW;
-
-	if (po.flags)
-		return -EINVAL;
-
-	ret = mnt_want_write_file(file);
-	if (ret < 0)
-		return ret;
-
-	inode_lock(inode);
-
-	ret = scoutfs_lock_inode(sb, SCOUTFS_LOCK_WRITE,
-				 SCOUTFS_LKF_REFRESH_INODE, inode, &lock);
-	if (ret)
-		goto out;
-
-	if (!S_ISREG(inode->i_mode)) {
-		ret = -EINVAL;
-		goto out;
-	}
-
-	if (!(file->f_mode & FMODE_WRITE)) {
-		ret = -EINVAL;
-		goto out;
-	}
-
-	ret = inode_permission(KC_VFS_INIT_NS inode, MAY_WRITE);
-	if (ret < 0)
-		goto out;
-
-	if (scoutfs_inode_data_version(inode) != po.data_version) {
-		ret = -ESTALE;
-		goto out;
-	}
-
-	if ((ret = scoutfs_inode_check_retention(inode)))
-		goto out;
-
-	iblock = po.offset >> SCOUTFS_BLOCK_SM_SHIFT;
-	last = (po.offset + po.len - 1) >> SCOUTFS_BLOCK_SM_SHIFT;
-
-	ret = scoutfs_data_punch_offline(inode, iblock, last, po.data_version, lock);
-
-out:
-	scoutfs_unlock(sb, lock, SCOUTFS_LOCK_WRITE);
-	inode_unlock(inode);
-	mnt_drop_write_file(file);
-
-	return ret;
-}
-
 long scoutfs_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
 {
 	switch (cmd) {
@@ -1789,8 +1645,6 @@ long scoutfs_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
 		return scoutfs_ioc_mod_quota_rule(file, arg, false);
 	case SCOUTFS_IOC_READ_XATTR_INDEX:
 		return scoutfs_ioc_read_xattr_index(file, arg);
-	case SCOUTFS_IOC_PUNCH_OFFLINE:
-		return scoutfs_ioc_punch_offline(file, arg);
 	}

 	return -ENOTTY;
--- a/kmod/src/ioctl.h
+++ b/kmod/src/ioctl.h
@@ -843,32 +843,4 @@ struct scoutfs_ioctl_read_xattr_index {
 #define SCOUTFS_IOC_READ_XATTR_INDEX \
 	_IOR(SCOUTFS_IOCTL_MAGIC, 23, struct scoutfs_ioctl_read_xattr_index)

-/*
- * This is a limited and specific version of hole punching.  It's an
- * archive layer operation that only converts unmapped offline extents
- * into sparse extents.  It is intended to be used when restoring sparse
- * files after the initial creation set the entire file size offline.
- *
- * The offset and len fields are in units of bytes and must be aligned
- * to the small (4KiB) block size.  All regions of offline extents
- * covered by the region will be converted into sparse online extents,
- * including regions that straddle the boundaries of the region.  Any
- * existing sparse extents in the region are ignored.
- *
- * The data_version must match the inode or EINVAL is returned.  The
- * data_version is not modified by this operation.
- *
- * EINVAL is returned if any mapped extents are found in the region.  If
- * an error is returned then partial progress may have been made.
- */
-struct scoutfs_ioctl_punch_offline {
-	__u64 offset;
-	__u64 len;
-	__u64 data_version;
-	__u64 flags;
-};
-
-#define SCOUTFS_IOC_PUNCH_OFFLINE \
-	_IOW(SCOUTFS_IOCTL_MAGIC, 24, struct scoutfs_ioctl_punch_offline)
-
 #endif
--- a/kmod/src/kernelcompat.h
+++ b/kmod/src/kernelcompat.h
@@ -29,6 +29,50 @@ do {						\
 })
 #endif

+#ifndef KC_ITERATE_DIR_CONTEXT
+typedef filldir_t kc_readdir_ctx_t;
+#define KC_DECLARE_READDIR(name, file, dirent, ctx) name(file, dirent, ctx)
+#define KC_FOP_READDIR readdir
+#define kc_readdir_pos(filp, ctx) (filp)->f_pos
+#define kc_dir_emit_dots(file, dirent, ctx) dir_emit_dots(file, dirent, ctx)
+#define kc_dir_emit(ctx, dirent, name, name_len, pos, ino, dt) \
+	(ctx(dirent, name, name_len, pos, ino, dt) == 0)
+#else
+typedef struct dir_context * kc_readdir_ctx_t;
+#define KC_DECLARE_READDIR(name, file, dirent, ctx) name(file, ctx)
+#define KC_FOP_READDIR iterate
+#define kc_readdir_pos(filp, ctx) (ctx)->pos
+#define kc_dir_emit_dots(file, dirent, ctx) dir_emit_dots(file, ctx)
+#define kc_dir_emit(ctx, dirent, name, name_len, pos, ino, dt) \
+	dir_emit(ctx, name, name_len, ino, dt)
+#endif
+
+#ifndef KC_DIR_EMIT_DOTS
+/*
+ * Kernels before ->iterate and don't have dir_emit_dots so we give them
+ * one that works with the ->readdir() filldir() method.
+ */
+static inline int dir_emit_dots(struct file *file, void *dirent,
+				filldir_t filldir)
+{
+	if (file->f_pos == 0) {
+		if (filldir(dirent, ".", 1, 1,
+			    file->f_path.dentry->d_inode->i_ino, DT_DIR))
+			return 0;
+		file->f_pos = 1;
+	}
+
+	if (file->f_pos == 1) {
+		if (filldir(dirent, "..", 2, 1,
+			    parent_ino(file->f_path.dentry), DT_DIR))
+			return 0;
+		file->f_pos = 2;
+	}
+
+	return 1;
+}
+#endif
+
 #ifdef KC_POSIX_ACL_VALID_USER_NS
 #define kc_posix_acl_valid(user_ns, acl) posix_acl_valid(user_ns, acl)
 #else
@@ -394,20 +438,4 @@ static inline int kc_tcp_sock_set_nodelay(struct socket *sock)
 }
 #endif

-#ifdef KC_INODE_DIO_END
-#define kc_inode_dio_end inode_dio_end
-#else
-#define kc_inode_dio_end inode_dio_done
-#endif
-
-#ifndef KC_MM_VM_FAULT_T
-typedef unsigned int vm_fault_t;
-static inline vm_fault_t vmf_error(int err)
-{
-	if (err == -ENOMEM)
-		return VM_FAULT_OOM;
-	return VM_FAULT_SIGBUS;
-}
-#endif
-
 #endif
--- a/kmod/src/lock.c
+++ b/kmod/src/lock.c
@@ -302,7 +302,6 @@ static void lock_inc_count(unsigned int *counts, enum scoutfs_lock_mode mode)
 static void lock_dec_count(unsigned int *counts, enum scoutfs_lock_mode mode)
 {
 	BUG_ON(mode < 0 || mode >= SCOUTFS_LOCK_NR_MODES);
-	BUG_ON(counts[mode] == 0);
 	counts[mode]--;
 }

--- a/kmod/src/scoutfs_trace.h
+++ b/kmod/src/scoutfs_trace.h
@@ -286,52 +286,6 @@ TRACE_EVENT(scoutfs_data_alloc_block_enter,
 		  STE_ENTRY_ARGS(ext))
 );

-TRACE_EVENT(scoutfs_data_page_mkwrite,
-	TP_PROTO(struct super_block *sb, __u64 ino, __u64 pos, __u32 ret),
-
-	TP_ARGS(sb, ino, pos, ret),
-
-	TP_STRUCT__entry(
-		SCSB_TRACE_FIELDS
-		__field(__u64, ino)
-		__field(__u64, pos)
-		__field(__u32, ret)
-	),
-
-	TP_fast_assign(
-		SCSB_TRACE_ASSIGN(sb);
-		__entry->ino = ino;
-		__entry->pos = pos;
-		__entry->ret = ret;
-	),
-
-	TP_printk(SCSBF" ino %llu pos %llu ret %u ",
-		  SCSB_TRACE_ARGS, __entry->ino, __entry->pos, __entry->ret)
-);
-
-TRACE_EVENT(scoutfs_data_filemap_fault,
-	TP_PROTO(struct super_block *sb, __u64 ino, __u64 pos, __u32 ret),
-
-	TP_ARGS(sb, ino, pos, ret),
-
-	TP_STRUCT__entry(
-		SCSB_TRACE_FIELDS
-		__field(__u64, ino)
-		__field(__u64, pos)
-		__field(__u32, ret)
-	),
-
-	TP_fast_assign(
-		SCSB_TRACE_ASSIGN(sb);
-		__entry->ino = ino;
-		__entry->pos = pos;
-		__entry->ret = ret;
-	),
-
-	TP_printk(SCSBF" ino %llu pos %llu ret %u ",
-		  SCSB_TRACE_ARGS, __entry->ino, __entry->pos, __entry->ret)
-);
-
 DECLARE_EVENT_CLASS(scoutfs_data_file_extent_class,
 	TP_PROTO(struct super_block *sb, __u64 ino, struct scoutfs_extent *ext),

--- a/kmod/src/server.c
+++ b/kmod/src/server.c
@@ -668,14 +668,16 @@ static void scoutfs_server_commit_func(struct work_struct *work)
 	 * the reserved blocks after having filled the log trees's avail
 	 * allocator during its transaction.  To avoid prematurely
 	 * setting the low flag and causing enospc we make sure that the
-	 * next transaction's meta_avail has 2x the reserved blocks so
+	 * next transaction's meta_avail has 3x the reserved blocks so
 	 * that it can consume a full reserved amount and still have
 	 * enough to avoid enospc.  We swap to freed if avail is under
-	 * the buffer and freed is larger.
+	 * the buffer and freed is larger by 50%. This results in much less
+	 * swapping overall and allows the pools to refill naturally.
 	 */
 	if ((le64_to_cpu(server->meta_avail->total_len) <
-	     (scoutfs_server_reserved_meta_blocks(sb) * 2)) &&
-	    (le64_to_cpu(server->meta_freed->total_len) >
+	     (scoutfs_server_reserved_meta_blocks(sb) * 3)) &&
+	    ((le64_to_cpu(server->meta_freed->total_len) +
+	     (le64_to_cpu(server->meta_freed->total_len) >> 1)) >
 	     le64_to_cpu(server->meta_avail->total_len)))
 		swap(server->meta_avail, server->meta_freed);

@@ -1299,10 +1301,12 @@ static int finalize_and_start_log_merge(struct super_block *sb, struct scoutfs_l
 * is nested inside holding commits so we recheck the persistent item
 * each time we commit to make sure it's still what we think.   The
 * caller is still going to send the item to the client so we update the
- * caller's each time we make progress.  If we hit an error applying the
- * changes we make then we can't send the log_trees to the client.
+ * caller's each time we make progress.  This is a best-effort attempt
+ * to clean up and it's valid to leave extents in data_freed we don't
+ * return errors to the caller.  The client will continue the work later
+ * in get_log_trees or as the rid is reclaimed.
 */
-static int try_drain_data_freed(struct super_block *sb, struct scoutfs_log_trees *lt)
+static void try_drain_data_freed(struct super_block *sb, struct scoutfs_log_trees *lt)
 {
 	DECLARE_SERVER_INFO(sb, server);
 	struct scoutfs_super_block *super = DIRTY_SUPER_SB(sb);
@@ -1311,7 +1315,6 @@ static int try_drain_data_freed(struct super_block *sb, struct scoutfs_log_trees
 	struct scoutfs_log_trees drain;
 	struct scoutfs_key key;
 	COMMIT_HOLD(hold);
-	bool apply = false;
 	int ret = 0;
 	int err;

@@ -1320,27 +1323,22 @@ static int try_drain_data_freed(struct super_block *sb, struct scoutfs_log_trees
 	while (lt->data_freed.total_len != 0) {
 		server_hold_commit(sb, &hold);
 		mutex_lock(&server->logs_mutex);
-		apply = true;

 		ret = find_log_trees_item(sb, &super->logs_root, false, rid, U64_MAX, &drain);
-		if (ret < 0) {
-			ret = 0;
+		if (ret < 0)
 			break;
-		}

 		/* careful to only keep draining the caller's specific open trans */
 		if (drain.nr != lt->nr || drain.get_trans_seq != lt->get_trans_seq ||
 		    drain.commit_trans_seq != lt->commit_trans_seq || drain.flags != lt->flags) {
-			ret = 0;
+			ret = -ENOENT;
 			break;
 		}

 		ret = scoutfs_btree_dirty(sb, &server->alloc, &server->wri,
 					  &super->logs_root, &key);
-		if (ret < 0) {
-			ret = 0;
+		if (ret < 0)
 			break;
-		}

 		/* moving can modify and return errors, always update caller and item */
 		mutex_lock(&server->alloc_mutex);
@@ -1356,19 +1354,19 @@ static int try_drain_data_freed(struct super_block *sb, struct scoutfs_log_trees
 		BUG_ON(err < 0); /* dirtying must guarantee success */

 		mutex_unlock(&server->logs_mutex);
+
 		ret = server_apply_commit(sb, &hold, ret);
-		apply = false;
-
-		if (ret < 0)
+		if (ret < 0) {
+			ret = 0; /* don't try to abort, ignoring ret */
 			break;
+		}
 	}

-	if (apply) {
+	/* try to cleanly abort and write any partial dirty btree blocks, but ignore result */
+	if (ret < 0) {
 		mutex_unlock(&server->logs_mutex);
-		server_apply_commit(sb, &hold, ret);
+		server_apply_commit(sb, &hold, 0);
 	}
-
-	return ret;
 }

 /*
@@ -1576,9 +1574,9 @@ out:
 		scoutfs_err(sb, "error %d getting log trees for rid %016llx: %s",
 			    ret, rid, err_str);

-	/* try to drain excessive data_freed with additional commits, if needed */
+	/* try to drain excessive data_freed with additional commits, if needed, ignoring err */
 	if (ret == 0)
-		ret = try_drain_data_freed(sb, &lt);
+		try_drain_data_freed(sb, &lt);

 	return scoutfs_net_response(sb, conn, cmd, id, ret, &lt, sizeof(lt));
 }
@@ -4153,7 +4151,7 @@ static void fence_pending_recov_worker(struct work_struct *work)
 	struct server_info *server = container_of(work, struct server_info,
 						  fence_pending_recov_work);
 	struct super_block *sb = server->sb;
-	union scoutfs_inet_addr addr = {{0,}};
+	union scoutfs_inet_addr addr;
 	u64 rid = 0;
 	int ret = 0;

--- a/kmod/src/trans.c
+++ b/kmod/src/trans.c
@@ -159,58 +159,6 @@ static bool drained_holders(struct trans_info *tri)
 	return holders == 0;
 }

-static int commit_current_log_trees(struct super_block *sb, char **str)
-{
-	DECLARE_TRANS_INFO(sb, tri);
-
-	return (*str = "data submit", scoutfs_inode_walk_writeback(sb, true)) ?:
-	       (*str = "item dirty", scoutfs_item_write_dirty(sb))  ?:
-	       (*str = "data prepare", scoutfs_data_prepare_commit(sb))  ?:
-	       (*str = "alloc prepare", scoutfs_alloc_prepare_commit(sb, &tri->alloc, &tri->wri)) ?:
-	       (*str = "meta write", scoutfs_block_writer_write(sb, &tri->wri))  ?:
-	       (*str = "data wait", scoutfs_inode_walk_writeback(sb, false)) ?:
-	       (*str = "commit log trees", commit_btrees(sb)) ?:
-	       scoutfs_item_write_done(sb);
-}
-
-static int get_next_log_trees(struct super_block *sb, char **str)
-{
-	return (*str = "get log trees", scoutfs_trans_get_log_trees(sb));
-}
-
-static int retry_forever(struct super_block *sb, int (*func)(struct super_block *sb, char **str))
-{
-	bool retrying = false;
-	char *str;
-	int ret;
-
-	do {
-		str = NULL;
-
-		ret = func(sb, &str);
-		if (ret < 0) {
-			if (!retrying) {
-				scoutfs_warn(sb, "critical transaction commit failure: %s = %d, retrying",
-					    str, ret);
-				retrying = true;
-			}
-
-			if (scoutfs_forcing_unmount(sb)) {
-				ret = -EIO;
-				break;
-			}
-
-			msleep(2 * MSEC_PER_SEC);
-
-		} else if (retrying) {
-			scoutfs_info(sb, "retried transaction commit succeeded");
-		}
-
-	} while (ret < 0);
-
-	return ret;
-}
-
 /*
 * This work func is responsible for writing out all the dirty blocks
 * that make up the current dirty transaction.  It prevents writers from
@@ -236,6 +184,8 @@ void scoutfs_trans_write_func(struct work_struct *work)
 	struct trans_info *tri = container_of(work, struct trans_info, write_work.work);
 	struct super_block *sb = tri->sb;
 	struct scoutfs_sb_info *sbi = SCOUTFS_SB(sb);
+	bool retrying = false;
+	char *s = NULL;
 	int ret = 0;

 	tri->task = current;
@@ -264,9 +214,37 @@ void scoutfs_trans_write_func(struct work_struct *work)

 	scoutfs_inc_counter(sb, trans_commit_written);

-	/* retry {commit,get}_log_trees until they succeeed, can only fail when forcing unmount */
-	ret = retry_forever(sb, commit_current_log_trees) ?:
-	      retry_forever(sb, get_next_log_trees);
+	do {
+		ret = (s = "data submit", scoutfs_inode_walk_writeback(sb, true)) ?:
+		      (s = "item dirty", scoutfs_item_write_dirty(sb))  ?:
+		      (s = "data prepare", scoutfs_data_prepare_commit(sb))  ?:
+		      (s = "alloc prepare", scoutfs_alloc_prepare_commit(sb, &tri->alloc,
+									 &tri->wri))  ?:
+		      (s = "meta write", scoutfs_block_writer_write(sb, &tri->wri))  ?:
+		      (s = "data wait", scoutfs_inode_walk_writeback(sb, false)) ?:
+		      (s = "commit log trees", commit_btrees(sb)) ?:
+		      scoutfs_item_write_done(sb) ?:
+		      (s = "get log trees", scoutfs_trans_get_log_trees(sb));
+		if (ret < 0) {
+			if (!retrying) {
+				scoutfs_warn(sb, "critical transaction commit failure: %s = %d, retrying",
+					    s, ret);
+				retrying = true;
+			}
+
+			if (scoutfs_forcing_unmount(sb)) {
+				ret = -EIO;
+				break;
+			}
+
+			msleep(2 * MSEC_PER_SEC);
+
+		} else if (retrying) {
+			scoutfs_info(sb, "retried transaction commit succeeded");
+		}
+
+	} while (ret < 0);
+
 out:
 	spin_lock(&tri->write_lock);
 	tri->write_count++;
--- a/tests/.gitignore
+++ b/tests/.gitignore
@@ -10,5 +10,3 @@ src/stage_tmpfile
 src/create_xattr_loop
 src/o_tmpfile_umask
 src/o_tmpfile_linkat
-src/mmap_stress
-src/mmap_validate
--- a/tests/Makefile
+++ b/tests/Makefile
@@ -13,9 +13,7 @@ BIN := src/createmany			\
 	src/create_xattr_loop		\
 	src/fragmented_data_extents	\
 	src/o_tmpfile_umask		\
-	src/o_tmpfile_linkat		\
-	src/mmap_stress			\
-	src/mmap_validate
+	src/o_tmpfile_linkat

 DEPS := $(wildcard src/*.d)

@@ -25,10 +23,8 @@ ifneq ($(DEPS),)
 -include $(DEPS)
 endif

-src/mmap_stress: LIBS+=-lpthread
-
 $(BIN): %: %.c Makefile
-	gcc $(CFLAGS) -MD -MP -MF $*.d $< -o $@ $(LIBS)
+	gcc $(CFLAGS) -MD -MP -MF $*.d $< -o $@

 .PHONY: clean
 clean:
--- a/tests/funcs/exec.sh
+++ b/tests/funcs/exec.sh
@@ -80,15 +80,3 @@ t_compare_output()
 {
 	"$@" >&7 2>&1
 }
-
-#
-# usually bash prints an annoying output message when jobs
-# are killed.  We can avoid that by redirecting stderr for
-# the bash process when it reaps the jobs that are killed.
-#
-t_silent_kill() {
-	exec {ERR}>&2 2>/dev/null
-	kill "$@"
-	wait "$@"
-	exec 2>&$ERR {ERR}>&-
-}
--- a/tests/funcs/filter.sh
+++ b/tests/funcs/filter.sh
@@ -160,9 +160,6 @@ t_filter_dmesg()
 	re="$re|Pipe handler or fully qualified core dump path required.*"
 	re="$re|Set kernel.core_pattern before fs.suid_dumpable.*"

-	# perf warning that it adjusted sample rate
-	re="$re|perf: interrupt took too long.*lowering kernel.perf_event_max_sample_rate.*"
-
 	egrep -v "($re)" | \
 		ignore_harmless_unwind_kasan_stack_oob
 }
--- a/tests/funcs/tap.sh
+++ b/tests/funcs/tap.sh
@@ -1,88 +0,0 @@
-
-#
-# Generate TAP format test results
-#
-
-t_tap_header()
-{
-	local runid=$1
-	local sequence=( $(echo $tests) )
-	local count=${#sequence[@]}
-
-	# avoid recreating the same TAP result over again - harness sets this
-	[[ -z "$runid" ]] && runid="*test*"
-
-	cat > $T_RESULTS/scoutfs.tap <<TAPEOF
-TAP version 14
-1..${count}
-#
-# TAP results for run ${runid}
-#
-# host/run info:
-#
-#   hostname: ${HOSTNAME}
-#   test start time: $(date --utc)
-#   uname -r: $(uname -r)
-#   scoutfs commit id: $(git describe --tags)
-#
-# sequence for this run:
-#
-TAPEOF
-
-	# Sequence
-	for t in ${tests}; do
-		 echo ${t/.sh/}
-	done | cat -n | expand | column -c 120 | expand | sed 's/^ /#/' >> $T_RESULTS/scoutfs.tap
-	echo "#" >> $T_RESULTS/scoutfs.tap
-}
-
-t_tap_progress()
-{
-(
-	local i=$(( testcount + 1 ))
-	local testname=$1
-	local result=$2
-
-	local diff=""
-	local dmsg=""
-
-	if [[ -s "$T_RESULTS/tmp/${testname}/dmesg.new" ]]; then
-		dmsg="1"
-	fi
-
-	if ! cmp -s golden/${testname} $T_RESULTS/output/${testname}; then
-		diff="1"
-	fi
-
-	if [[ "${result}" == "100" ]] && [[ -z "${dmsg}" ]] && [[ -z "${diff}" ]]; then
-		echo "ok ${i} - ${testname}"
-	elif [[ "${result}" == "103" ]]; then
-		echo "ok ${i} - ${testname}"
-		echo "# ${testname} ** skipped - permitted **"
-	else
-		echo "not ok ${i} - ${testname}"
-		case ${result} in
-		101)
-			echo "# ${testname} ** skipped **"
-			;;
-		102)
-			echo "# ${testname} ** failed **"
-			;;
-		esac
-
-		if [[ -n "${diff}" ]]; then
-			echo "#"
-			echo "# diff:"
-			echo "#"
-			diff -u golden/${testname} $T_RESULTS/output/${testname} | expand | sed 's/^/#   /'
-		fi
-
-		if [[ -n "${dmsg}" ]]; then
-			echo "#"
-			echo "# dmesg:"
-			echo "#"
-			cat "$T_RESULTS/tmp/${testname}/dmesg.new" | sed 's/^/#   /'
-		fi
-	fi
-) >> $T_RESULTS/scoutfs.tap
-}
--- a/tests/golden/mmap
+++ b/tests/golden/mmap
@@ -1,27 +0,0 @@
-== mmap_stress
-thread 0 complete
-thread 1 complete
-thread 2 complete
-thread 3 complete
-thread 4 complete
-== basic mmap/read/write consistency checks
-== mmap read from offline extent
-0: offset: 0 length: 2 flags: O.L
-extents: 1
-1
-00000200:  ea ea ea ea ea ea ea ea ea ea ea ea ea ea ea ea  ................
-0
-0: offset: 0 length: 2 flags: ..L
-extents: 1
-== mmap write to an offline extent
-0: offset: 0 length: 2 flags: O.L
-extents: 1
-1
-0
-0: offset: 0 length: 2 flags: ..L
-extents: 1
-00000000  ea ea ea ea ea ea ea ea  ea ea ea ea ea ea ea ea  |................|
-00000010  11 11 11 11 11 11 11 11  11 11 11 11 11 11 11 11  |................|
-00000020  ea ea ea ea ea ea ea ea  ea ea ea ea ea ea ea ea  |................|
-00000030
-== done
--- a/tests/golden/simple-readdir
+++ b/tests/golden/simple-readdir
@@ -1,97 +0,0 @@
-== create content
-== readdir all
-00000000: d_off: 0x00000001 d_reclen: 0x18 d_type: DT_DIR d_name: .
-00000001: d_off: 0x00000002 d_reclen: 0x18 d_type: DT_DIR d_name: ..
-00000002: d_off: 0x00000003 d_reclen: 0x18 d_type: DT_REG d_name: a
-00000003: d_off: 0x00000004 d_reclen: 0x20 d_type: DT_REG d_name: aaaaaaaa
-00000004: d_off: 0x00000005 d_reclen: 0x28 d_type: DT_REG d_name: aaaaaaaaaaaaaaa
-00000005: d_off: 0x00000006 d_reclen: 0x30 d_type: DT_REG d_name: aaaaaaaaaaaaaaaaaaaaaa
-00000006: d_off: 0x00000007 d_reclen: 0x38 d_type: DT_REG d_name: aaaaaaaaaaaaaaaaaaaaaaaaaaaaa
-00000007: d_off: 0x00000008 d_reclen: 0x38 d_type: DT_REG d_name: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
-00000008: d_off: 0x00000009 d_reclen: 0x40 d_type: DT_REG d_name: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
-00000009: d_off: 0x0000000a d_reclen: 0x48 d_type: DT_REG d_name: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
-0000000a: d_off: 0x0000000b d_reclen: 0x50 d_type: DT_REG d_name: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
-0000000b: d_off: 0x0000000c d_reclen: 0x58 d_type: DT_REG d_name: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
-0000000c: d_off: 0x0000000d d_reclen: 0x60 d_type: DT_REG d_name: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
-0000000d: d_off: 0x0000000e d_reclen: 0x68 d_type: DT_REG d_name: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
-0000000e: d_off: 0x0000000f d_reclen: 0x70 d_type: DT_REG d_name: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
-0000000f: d_off: 0x00000010 d_reclen: 0x70 d_type: DT_REG d_name: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
-00000010: d_off: 0x00000011 d_reclen: 0x78 d_type: DT_REG d_name: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
-00000011: d_off: 0x00000012 d_reclen: 0x80 d_type: DT_REG d_name: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
-00000012: d_off: 0x00000013 d_reclen: 0x88 d_type: DT_REG d_name: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
-00000013: d_off: 0x00000014 d_reclen: 0x90 d_type: DT_REG d_name: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
-00000014: d_off: 0x00000015 d_reclen: 0x98 d_type: DT_REG d_name: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
-00000015: d_off: 0x00000016 d_reclen: 0xa0 d_type: DT_REG d_name: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
-00000016: d_off: 0x00000017 d_reclen: 0xa8 d_type: DT_REG d_name: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
-00000017: d_off: 0x00000018 d_reclen: 0xa8 d_type: DT_REG d_name: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
-00000018: d_off: 0x00000019 d_reclen: 0xb0 d_type: DT_REG d_name: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
-00000019: d_off: 0x0000001a d_reclen: 0xb8 d_type: DT_REG d_name: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
-0000001a: d_off: 0x0000001b d_reclen: 0xc0 d_type: DT_REG d_name: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
-0000001b: d_off: 0x0000001c d_reclen: 0xc8 d_type: DT_REG d_name: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
-0000001c: d_off: 0x0000001d d_reclen: 0xd0 d_type: DT_REG d_name: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
-0000001d: d_off: 0x0000001e d_reclen: 0xd8 d_type: DT_REG d_name: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
-0000001e: d_off: 0x0000001f d_reclen: 0xe0 d_type: DT_REG d_name: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
-0000001f: d_off: 0x00000020 d_reclen: 0xe0 d_type: DT_REG d_name: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
-00000020: d_off: 0x00000021 d_reclen: 0xe8 d_type: DT_REG d_name: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
-00000021: d_off: 0x00000022 d_reclen: 0xf0 d_type: DT_REG d_name: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
-00000022: d_off: 0x00000023 d_reclen: 0xf8 d_type: DT_REG d_name: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
-00000023: d_off: 0x00000024 d_reclen: 0x100 d_type: DT_REG d_name: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
-00000024: d_off: 0x00000025 d_reclen: 0x108 d_type: DT_REG d_name: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
-00000025: d_off: 0x00000026 d_reclen: 0x110 d_type: DT_REG d_name: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
-== readdir offset
-00000014: d_off: 0x00000015 d_reclen: 0x98 d_type: DT_REG d_name: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
-00000015: d_off: 0x00000016 d_reclen: 0xa0 d_type: DT_REG d_name: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
-00000016: d_off: 0x00000017 d_reclen: 0xa8 d_type: DT_REG d_name: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
-00000017: d_off: 0x00000018 d_reclen: 0xa8 d_type: DT_REG d_name: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
-00000018: d_off: 0x00000019 d_reclen: 0xb0 d_type: DT_REG d_name: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
-00000019: d_off: 0x0000001a d_reclen: 0xb8 d_type: DT_REG d_name: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
-0000001a: d_off: 0x0000001b d_reclen: 0xc0 d_type: DT_REG d_name: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
-0000001b: d_off: 0x0000001c d_reclen: 0xc8 d_type: DT_REG d_name: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
-0000001c: d_off: 0x0000001d d_reclen: 0xd0 d_type: DT_REG d_name: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
-0000001d: d_off: 0x0000001e d_reclen: 0xd8 d_type: DT_REG d_name: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
-0000001e: d_off: 0x0000001f d_reclen: 0xe0 d_type: DT_REG d_name: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
-0000001f: d_off: 0x00000020 d_reclen: 0xe0 d_type: DT_REG d_name: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
-00000020: d_off: 0x00000021 d_reclen: 0xe8 d_type: DT_REG d_name: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
-00000021: d_off: 0x00000022 d_reclen: 0xf0 d_type: DT_REG d_name: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
-00000022: d_off: 0x00000023 d_reclen: 0xf8 d_type: DT_REG d_name: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
-00000023: d_off: 0x00000024 d_reclen: 0x100 d_type: DT_REG d_name: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
-00000024: d_off: 0x00000025 d_reclen: 0x108 d_type: DT_REG d_name: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
-00000025: d_off: 0x00000026 d_reclen: 0x110 d_type: DT_REG d_name: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
-== readdir len (bytes)
-00000000: d_off: 0x00000001 d_reclen: 0x18 d_type: DT_DIR d_name: .
-00000001: d_off: 0x00000002 d_reclen: 0x18 d_type: DT_DIR d_name: ..
-00000002: d_off: 0x00000003 d_reclen: 0x18 d_type: DT_REG d_name: a
-00000003: d_off: 0x00000004 d_reclen: 0x20 d_type: DT_REG d_name: aaaaaaaa
-00000004: d_off: 0x00000005 d_reclen: 0x28 d_type: DT_REG d_name: aaaaaaaaaaaaaaa
-00000005: d_off: 0x00000006 d_reclen: 0x30 d_type: DT_REG d_name: aaaaaaaaaaaaaaaaaaaaaa
-00000006: d_off: 0x00000007 d_reclen: 0x38 d_type: DT_REG d_name: aaaaaaaaaaaaaaaaaaaaaaaaaaaaa
-== introduce gap
-00000000: d_off: 0x00000001 d_reclen: 0x18 d_type: DT_DIR d_name: .
-00000001: d_off: 0x00000002 d_reclen: 0x18 d_type: DT_DIR d_name: ..
-00000002: d_off: 0x00000003 d_reclen: 0x18 d_type: DT_REG d_name: a
-00000003: d_off: 0x00000004 d_reclen: 0x20 d_type: DT_REG d_name: aaaaaaaa
-00000004: d_off: 0x00000005 d_reclen: 0x28 d_type: DT_REG d_name: aaaaaaaaaaaaaaa
-00000005: d_off: 0x00000006 d_reclen: 0x30 d_type: DT_REG d_name: aaaaaaaaaaaaaaaaaaaaaa
-00000006: d_off: 0x00000007 d_reclen: 0x38 d_type: DT_REG d_name: aaaaaaaaaaaaaaaaaaaaaaaaaaaaa
-00000007: d_off: 0x00000008 d_reclen: 0x38 d_type: DT_REG d_name: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
-00000008: d_off: 0x00000009 d_reclen: 0x40 d_type: DT_REG d_name: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
-00000009: d_off: 0x00000014 d_reclen: 0x48 d_type: DT_REG d_name: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
-00000014: d_off: 0x00000015 d_reclen: 0x98 d_type: DT_REG d_name: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
-00000015: d_off: 0x00000016 d_reclen: 0xa0 d_type: DT_REG d_name: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
-00000016: d_off: 0x00000017 d_reclen: 0xa8 d_type: DT_REG d_name: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
-00000017: d_off: 0x00000018 d_reclen: 0xa8 d_type: DT_REG d_name: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
-00000018: d_off: 0x00000019 d_reclen: 0xb0 d_type: DT_REG d_name: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
-00000019: d_off: 0x0000001a d_reclen: 0xb8 d_type: DT_REG d_name: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
-0000001a: d_off: 0x0000001b d_reclen: 0xc0 d_type: DT_REG d_name: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
-0000001b: d_off: 0x0000001c d_reclen: 0xc8 d_type: DT_REG d_name: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
-0000001c: d_off: 0x0000001d d_reclen: 0xd0 d_type: DT_REG d_name: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
-0000001d: d_off: 0x0000001e d_reclen: 0xd8 d_type: DT_REG d_name: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
-0000001e: d_off: 0x0000001f d_reclen: 0xe0 d_type: DT_REG d_name: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
-0000001f: d_off: 0x00000020 d_reclen: 0xe0 d_type: DT_REG d_name: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
-00000020: d_off: 0x00000021 d_reclen: 0xe8 d_type: DT_REG d_name: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
-00000021: d_off: 0x00000022 d_reclen: 0xf0 d_type: DT_REG d_name: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
-00000022: d_off: 0x00000023 d_reclen: 0xf8 d_type: DT_REG d_name: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
-00000023: d_off: 0x00000024 d_reclen: 0x100 d_type: DT_REG d_name: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
-00000024: d_off: 0x00000025 d_reclen: 0x108 d_type: DT_REG d_name: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
-00000025: d_off: 0x00000026 d_reclen: 0x110 d_type: DT_REG d_name: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
-== cleanup
--- a/tests/golden/xfstests
+++ b/tests/golden/xfstests
@@ -22,8 +22,6 @@ generic/024
 generic/025
 generic/026
 generic/028
-generic/029
-generic/030
 generic/031
 generic/032
 generic/033
@@ -55,7 +53,6 @@ generic/073
 generic/076
 generic/078
 generic/079
-generic/080
 generic/081
 generic/082
 generic/084
@@ -84,12 +81,10 @@ generic/116
 generic/117
 generic/118
 generic/119
-generic/120
 generic/121
 generic/122
 generic/123
 generic/124
-generic/126
 generic/128
 generic/129
 generic/130
@@ -100,7 +95,6 @@ generic/136
 generic/138
 generic/139
 generic/140
-generic/141
 generic/142
 generic/143
 generic/144
@@ -159,7 +153,6 @@ generic/210
 generic/211
 generic/212
 generic/214
-generic/215
 generic/216
 generic/217
 generic/218
@@ -180,9 +173,6 @@ generic/238
 generic/240
 generic/244
 generic/245
-generic/246
-generic/247
-generic/248
 generic/249
 generic/250
 generic/252
@@ -241,7 +231,6 @@ generic/317
 generic/319
 generic/322
 generic/324
-generic/325
 generic/326
 generic/327
 generic/328
@@ -255,7 +244,6 @@ generic/337
 generic/341
 generic/342
 generic/343
-generic/346
 generic/348
 generic/353
 generic/355
@@ -317,9 +305,7 @@ generic/424
 generic/425
 generic/426
 generic/427
-generic/428
 generic/436
-generic/437
 generic/439
 generic/440
 generic/443
@@ -329,7 +315,6 @@ generic/448
 generic/449
 generic/450
 generic/451
-generic/452
 generic/453
 generic/454
 generic/456
@@ -453,7 +438,6 @@ generic/610
 generic/611
 generic/612
 generic/613
-generic/614
 generic/618
 generic/621
 generic/623
@@ -467,7 +451,6 @@ generic/632
 generic/634
 generic/635
 generic/637
-generic/638
 generic/639
 generic/640
 generic/644
@@ -879,4 +862,4 @@ generic/688
 generic/689
 shared/002
 shared/032
-Passed all 512 tests
+Passed all 495 tests
--- a/tests/run-tests.sh
+++ b/tests/run-tests.sh
@@ -512,11 +512,6 @@ msg "running tests"
 > "$T_RESULTS/skip.log"
 > "$T_RESULTS/fail.log"

-# generate a test ID to make sure we can de-duplicate TAP results in aggregation
-. funcs/tap.sh
-t_tap_header $(uuidgen)
-
-testcount=0
 passed=0
 skipped=0
 failed=0
@@ -532,15 +527,12 @@ for t in $tests; do
 	cmd rm -rf "$T_TMPDIR"
 	cmd mkdir -p "$T_TMPDIR"

-	# create a test name dir in the fs, clean up old data as needed
+	# create a test name dir in the fs
 	T_DS=""
 	for i in $(seq 0 $((T_NR_MOUNTS - 1))); do
 		dir="${T_M[$i]}/test/$test_name"

-		test $i == 0 && (
-			test -d "$dir" && cmd rm -rf "$dir"
-			cmd mkdir -p "$dir"
-		)
+		test $i == 0 && cmd mkdir -p "$dir"

 		eval T_D$i=$dir
 		T_D[$i]=$dir
@@ -645,11 +637,6 @@ for t in $tests; do

 		test -n "$T_ABORT" && die "aborting after first failure"
 	fi
-
-	# record results for TAP format output
-	t_tap_progress $test_name $sts
-	((testcount++))
-
 done

 msg "all tests run: $passed passed, $skipped skipped, $skipped_permitted skipped (permitted), $failed failed"
--- a/tests/sequence
+++ b/tests/sequence
@@ -6,7 +6,6 @@ inode-items-updated.sh
 simple-inode-index.sh
 simple-staging.sh
 simple-release-extents.sh
-simple-readdir.sh
 get-referring-entries.sh
 fallocate.sh
 basic-truncate.sh
@@ -18,7 +17,6 @@ projects.sh
 large-fragmented-free.sh
 format-version-forward-back.sh
 enospc.sh
-mmap.sh
 srch-safe-merge-pos.sh
 srch-basic-functionality.sh
 simple-xattr-unit.sh
--- a/tests/src/mmap_stress.c
+++ b/tests/src/mmap_stress.c
@@ -1,181 +0,0 @@
-#define _GNU_SOURCE
-/*
- * mmap() stress test for scoutfs
- *
- * This test exercises the scoutfs kernel module's locking by
- * repeatedly reading/writing using mmap and pread/write calls
- * across 5 clients (mounts).
- *
- * Each thread operates on a single thread/client, and performs
- * operations in a random order on the file.
- *
- * The goal is to assure that locking between _page_mkwrite vfs
- * calls and the normal read/write paths do not cause deadlocks.
- *
- * There is no content validation performed. All that is done is
- * assure that the programs continues without errors.
- */
-
-#include <sys/types.h>
-#include <stdio.h>
-#include <sys/stat.h>
-#include <fcntl.h>
-#include <unistd.h>
-#include <stdlib.h>
-#include <string.h>
-#include <stdbool.h>
-#include <sys/mman.h>
-#include <pthread.h>
-#include <errno.h>
-
-static int size = 0;
-static int count = 0; /* XXX make this duration instead */
-
-struct thread_info {
-	int nr;
-	int fd;
-};
-
-static void *run_test_func(void *ptr)
-{
-	void *buf = NULL;
-	char *addr = NULL;
-	struct thread_info *tinfo = ptr;
-	int c = 0;
-	int fd;
-	ssize_t read, written, ret;
-	int preads = 0, pwrites = 0, mreads = 0, mwrites = 0;
-
-	fd = tinfo->fd;
-
-	if (posix_memalign(&buf, 4096, size) != 0) {
-		perror("calloc");
-		exit(-1);
-	}
-
-	addr = mmap(NULL, size, PROT_WRITE | PROT_READ, MAP_SHARED, fd, 0);
-	if (addr == MAP_FAILED) {
-		perror("mmap");
-		exit(-1);
-	}
-
-	usleep(100000); /* 0.1sec to allow all threads to start roughly at the same time */
-
-	for (;;) {
-		if (++c > count)
-			break;
-
-		switch (rand() % 4) {
-		case 0: /* pread */
-			preads++;
-			for (read = 0; read < size;) {
-				ret = pread(fd, buf, size - read, read);
-				if (ret < 0) {
-					perror("pwrite");
-					exit(-1);
-				}
-				read += ret;
-			}
-			break;
-		case 1: /* pwrite */
-			pwrites++;
-			memset(buf, (char)(c & 0xff), size);
-			for (written = 0; written < size;) {
-				ret = pwrite(fd, buf, size - written, written);
-				if (ret < 0) {
-					perror("pwrite");
-					exit(-1);
-				}
-				written += ret;
-			}
-			break;
-		case 2: /* mmap read */
-			mreads++;
-			memcpy(buf, addr, size); /* noerr */
-			break;
-		case 3: /* mmap write */
-			mwrites++;
-			memset(buf, (char)(c & 0xff), size);
-			memcpy(addr, buf, size); /* noerr */
-			break;
-		}
-	}
-
-	munmap(addr, size);
-
-	free(buf);
-
-	printf("thread %u complete: preads %u pwrites %u mreads %u mwrites %u\n", tinfo->nr,
-		mreads, mwrites, preads, pwrites);
-
-	return NULL;
-}
-
-int main(int argc, char **argv)
-{
-	pthread_t thread[5];
-	struct thread_info tinfo[5];
-	int fd[5];
-	int ret;
-	int i;
-
-	if (argc != 8) {
-		fprintf(stderr, "%s requires 7 arguments - size count file1 file2 file3 file4 file5\n", argv[0]);
-		exit(-1);
-	}
-
-	size = atoi(argv[1]);
-	if (size <= 0) {
-		fprintf(stderr, "invalid size, must be greater than 0\n");
-		exit(-1);
-	}
-
-	count = atoi(argv[2]);
-	if (count < 0) {
-		fprintf(stderr, "invalid count, must be greater than 0\n");
-		exit(-1);
-	}
-
-	/* create and truncate one fd */
-	fd[0] = open(argv[3], O_RDWR | O_CREAT | O_TRUNC, 00644);
-	if (fd[0] < 0) {
-		perror("open");
-		exit(-1);
-	}
-
-	/* make it the test size */
-	if (posix_fallocate(fd[0], 0, size) != 0) {
-		perror("fallocate");
-		exit(-1);
-	}
-
-	/* now open the rest of the fds */
-	for (i = 1; i < 5; i++) {
-		fd[i] = open(argv[3+i], O_RDWR);
-		if (fd[i] < 0) {
-			perror("open");
-			exit(-1);
-		}
-	}
-
-	/* start threads */
-	for (i = 0; i < 5; i++) {
-		tinfo[i].fd = fd[i];
-		tinfo[i].nr = i;
-		ret = pthread_create(&thread[i], NULL, run_test_func, (void*)&tinfo[i]);
-
-		if (ret) {
-			perror("pthread_create");
-			exit(-1);
-		}
-	}
-
-	/* wait for complete */
-	for (i = 0; i < 5; i++)
-		pthread_join(thread[i], NULL);
-
-	for (i = 0; i < 5; i++)
-		close(fd[i]);
-
-	exit(0);
-}
--- a/tests/src/mmap_validate.c
+++ b/tests/src/mmap_validate.c
@@ -1,159 +0,0 @@
-#define _GNU_SOURCE
-/*
- * mmap() content consistency checking for scoutfs
- *
- * This test program validates that content from memory mappings
- * are consistent across clients, whether written/read with mmap or
- * normal writes/reads.
- *
- * One side of (read/write) will always be memory mapped. It may
- * be that both sides do memory mapped (33% of the time).
- */
-
-#include <stdio.h>
-#include <stdlib.h>
-#include <unistd.h>
-#include <string.h>
-#include <sys/mman.h>
-#include <fcntl.h>
-#include <errno.h>
-
-static int count = 0;
-static int size = 0;
-
-static void run_test_func(int fd1, int fd2)
-{
-	void *buf1 = NULL;
-	void *buf2 = NULL;
-	char *addr1 = NULL;
-	char *addr2 = NULL;
-	int c = 0;
-	ssize_t read, written, ret;
-
-	/* buffers for both sides to compare */
-	if (posix_memalign(&buf1, 4096, size) != 0) {
-		perror("calloc1");
-		exit(-1);
-	}
-
-	if (posix_memalign(&buf2, 4096, size) != 0) {
-		perror("calloc1");
-		exit(-1);
-	}
-
-	/* memory maps for both sides */
-	addr1 = mmap(NULL, size, PROT_WRITE | PROT_READ, MAP_SHARED, fd1, 0);
-	if (addr1 == MAP_FAILED) {
-		perror("mmap1");
-		exit(-1);
-	}
-
-	addr2 = mmap(NULL, size, PROT_WRITE | PROT_READ, MAP_SHARED, fd2, 0);
-	if (addr2 == MAP_FAILED) {
-		perror("mmap2");
-		exit(-1);
-	}
-
-	for (;;) {
-		if (++c > count) /* 10k iterations */
-			break;
-
-		/* put a pattern in buf1 */
-		memset(buf1, c & 0xff, size);
-
-		/* pwrite or mmap write from buf1 */
-		switch (c % 3) {
-		case 0:	/* pwrite */
-			for (written = 0; written < size;) {
-				ret = pwrite(fd1, buf1, size - written, written);
-				if (ret < 0) {
-					perror("pwrite");
-					exit(-1);
-				}
-				written += ret;
-			}
-			break;
-		default: /* mmap write */
-			memcpy(addr1, buf1, size);
-			break;
-		}
-
-		/* pread or mmap read to buf2 */
-		switch (c % 3) {
-		case 2: /* pread */
-			for (read = 0; read < size;) {
-				ret = pread(fd2, buf2, size - read, read);
-				if (ret < 0) {
-					perror("pwrite");
-					exit(-1);
-				}
-				read += ret;
-			}
-			break;
-		default: /* mmap read */
-			memcpy(buf2, addr2, size);
-			break;
-		}
-
-		/* compare bufs */
-		if (memcmp(buf1, buf2, size) != 0) {
-			fprintf(stderr, "memcmp() failed\n");
-			exit(-1);
-		}
-	}
-
-	munmap(addr1, size);
-	munmap(addr2, size);
-
-	free(buf1);
-	free(buf2);
-}
-
-int main(int argc, char **argv)
-{
-	int fd[1];
-
-	if (argc != 5) {
-		fprintf(stderr, "%s requires 4 arguments - size count file1 file2\n", argv[0]);
-		exit(-1);
-	}
-
-	size = atoi(argv[1]);
-	if (size <= 0) {
-		fprintf(stderr, "invalid size, must be greater than 0\n");
-		exit(-1);
-	}
-
-	count = atoi(argv[2]);
-	if (count < 3) {
-		fprintf(stderr, "invalid count, must be greater than 3\n");
-		exit(-1);
-	}
-
-	/* create and truncate one fd */
-	fd[0] = open(argv[3], O_RDWR | O_CREAT | O_TRUNC, 00644);
-	if (fd[0] < 0) {
-		perror("open");
-		exit(-1);
-	}
-
-	fd[1] = open(argv[4], O_RDWR , 00644);
-	if (fd[1] < 0) {
-		perror("open");
-		exit(-1);
-	}
-
-	/* make it the test size */
-	if (posix_fallocate(fd[0], 0, size) != 0) {
-		perror("fallocate");
-		exit(-1);
-	}
-
-	/* run the test function */
-	run_test_func(fd[0], fd[1]);
-
-	close(fd[0]);
-	close(fd[1]);
-
-	exit(0);
-}
--- a/tests/tests/basic-truncate.sh
+++ b/tests/tests/basic-truncate.sh
@@ -11,7 +11,7 @@ FILE="$T_D0/file"
 # final block as we truncated past it.
 #
 echo "== truncate writes zeroed partial end of file block"
-yes 2>/dev/null | dd of="$FILE" bs=8K count=1 status=none iflag=fullblock
+yes | dd of="$FILE" bs=8K count=1 status=none iflag=fullblock
 sync

 # not passing iflag=fullblock causes the file occasionally to just be
--- a/tests/tests/enospc.sh
+++ b/tests/tests/enospc.sh
@@ -88,11 +88,6 @@ rm -rf "$SCR/xattrs"

 echo "== make sure we can create again"
 file="$SCR/file-after"
-C=120
-while (( C-- )); do
-	touch $file 2> /dev/null && break
-	sleep 1
-done
 touch $file
 setfattr -n user.scoutfs-enospc -v 1 "$file"
 sync
--- a/tests/tests/lock-recover-invalidate.sh
+++ b/tests/tests/lock-recover-invalidate.sh
@@ -38,6 +38,6 @@ while [ "$SECONDS" -lt "$END" ]; do
 done

 echo "== stopping background load"
-t_silent_kill $load_pids
+kill $load_pids

 t_pass
--- a/tests/tests/mmap.sh
+++ b/tests/tests/mmap.sh
@@ -1,54 +0,0 @@
-#
-# test mmap() and normal read/write consistency between different nodes
-#
-
-t_require_commands mmap_stress mmap_validate scoutfs xfs_io
-
-echo "== mmap_stress"
-mmap_stress 8192 2000 "$T_D0/mmap_stress" "$T_D1/mmap_stress" "$T_D2/mmap_stress" "$T_D3/mmap_stress" "$T_D4/mmap_stress" | sed 's/:.*//g' | sort
-
-echo "== basic mmap/read/write consistency checks"
-mmap_validate 256 1000 "$T_D0/mmap_val1" "$T_D1/mmap_val1"
-mmap_validate 8192 1000 "$T_D0/mmap_val2" "$T_D1/mmap_val2"
-mmap_validate 88400 1000 "$T_D0/mmap_val3" "$T_D1/mmap_val3"
-
-echo "== mmap read from offline extent"
-F="$T_D0/mmap-offline"
-touch "$F"
-xfs_io -c "pwrite -S 0xEA 0 8192" "$F" > /dev/null
-cp "$F" "${F}-stage"
-vers=$(scoutfs stat -s data_version "$F")
-scoutfs release "$F" -V "$vers" -o 0 -l 8192
-scoutfs get-fiemap -L "$F"
-xfs_io -c "mmap -rwx 0 8192" \
-	-c "mread -v 512 16" "$F" &
-sleep 1
-# should be 1 - data waiting
-jobs | wc -l
-scoutfs stage "${F}-stage" "$F" -V "$vers" -o 0 -l 8192
-# xfs_io thread <here> will output 16 bytes of read data
-sleep 1
-# should be 0 - no more waiting jobs, xfs_io should have exited
-jobs | wc -l
-scoutfs get-fiemap -L "$F"
-
-echo "== mmap write to an offline extent"
-# reuse the same file
-scoutfs release "$F" -V "$vers" -o 0 -l 8192
-scoutfs get-fiemap -L "$F"
-xfs_io -c "mmap -rwx 0 8192" \
-	-c "mwrite -S 0x11 528 16" "$F" &
-sleep 1
-# should be 1 job waiting
-jobs | wc -l
-scoutfs stage "${F}-stage" "$F" -V "$vers" -o 0 -l 8192
-# no output here from write
-sleep 1
-# should be 0 - no more waiting jobs, xfs_io should have exited
-jobs | wc -l
-scoutfs get-fiemap -L "$F"
-# read back contents to assure write changed the file
-dd status=none if="$F" bs=1 count=48 skip=512 | hexdump -C
-
-echo "== done"
-t_pass
--- a/tests/tests/orphan-inodes.sh
+++ b/tests/tests/orphan-inodes.sh
@@ -5,6 +5,18 @@
 t_require_commands sleep touch sync stat handle_cat kill rm
 t_require_mounts 2

+#
+# usually bash prints an annoying output message when jobs
+# are killed.  We can avoid that by redirecting stderr for
+# the bash process when it reaps the jobs that are killed.
+#
+silent_kill() {
+	exec {ERR}>&2 2>/dev/null
+	kill "$@"
+	wait "$@"
+	exec 2>&$ERR {ERR}>&-
+}
+
 #
 # We don't have a great way to test that inode items still exist.   We
 # don't prevent opening handles with nlink 0 today, so we'll use that.
@@ -40,7 +52,7 @@ inode_exists $ino || echo "$ino didn't exist"

 echo "== orphan from failed evict deletion is picked up"
 # pending kill signal stops evict from getting locks and deleting
-t_silent_kill $pid
+silent_kill $pid
 t_set_sysfs_mount_option 0 orphan_scan_delay_ms 1000
 sleep 5
 inode_exists $ino && echo "$ino still exists"
@@ -58,7 +70,7 @@ for nr in $(t_fs_nrs); do
 	rm -f "$path"
 done
 sync
-t_silent_kill $pids
+silent_kill $pids
 for nr in $(t_fs_nrs); do
 	t_force_umount $nr
 done
@@ -70,15 +82,7 @@ done
 # wait for orphan scans to run
 t_set_all_sysfs_mount_options orphan_scan_delay_ms 1000
 # also have to wait for delayed log merge work from mount
-C=120
-while (( C-- )); do
-	brk=1
-	for ino in $inos; do
-		inode_exists $ino && brk=0
-	done
-	test $brk -eq 1 && break
-	sleep 1
-done
+sleep 15
 for ino in $inos; do
 	inode_exists $ino && echo "$ino still exists"
 done
@@ -127,7 +131,7 @@ while [ $SECONDS -lt $END ]; do
 	done

 	# trigger eviction deletion of each file in each mount
-	t_silent_kill $pids
+	silent_kill $pids

 	wait || t_fail "handle_fsetxattr failed"

--- a/tests/tests/simple-readdir.sh
+++ b/tests/tests/simple-readdir.sh
@@ -1,37 +0,0 @@
-#
-# verify d_off output of xfs_io is consistent.
-#
-
-t_require_commands xfs_io
-
-filt()
-{
-	grep d_off | cut -d ' ' -f 1,4-
-}
-
-echo "== create content"
-for s in $(seq 1 7 250); do
-	f=$(printf '%*s' $s | tr ' ' 'a')
-	touch ${T_D0}/$f
-done
-
-echo "== readdir all"
-xfs_io -c "readdir -v" $T_D0 | filt
-
-echo "== readdir offset"
-xfs_io -c "readdir -v -o 20" $T_D0 | filt
-
-echo "== readdir len (bytes)"
-xfs_io -c "readdir -v -l 193" $T_D0 | filt
-
-echo "== introduce gap"
-for s in $(seq 57 7 120); do
-	f=$(printf '%*s' $s | tr ' ' 'a')
-	rm -f ${T_D0}/$f
-done
-xfs_io -c "readdir -v" $T_D0 | filt
-
-echo "== cleanup"
-rm -rf $T_D0
-
-t_pass
--- a/tests/tests/xfstests.sh
+++ b/tests/tests/xfstests.sh
@@ -65,14 +65,26 @@ EOF

 cat << EOF > local.exclude
 generic/003	# missing atime update in buffered read
+generic/029	# mmap missing
+generic/030	# mmap missing
 generic/075	# file content mismatch failures (fds, etc)
+generic/080	# mmap missing
 generic/103	# enospc causes trans commit failures
 generic/108	# mount fails on failing device?
 generic/112	# file content mismatch failures (fds, etc)
+generic/120	# (can't exec 'cause no mmap)
+generic/126	# (can't exec 'cause no mmap)
+generic/141	# mmap missing
 generic/213	# enospc causes trans commit failures
+generic/215	# mmap missing
+generic/246	# mmap missing
+generic/247	# mmap missing
+generic/248	# mmap missing
 generic/318	# can't support user namespaces until v5.11
 generic/321	# requires selinux enabled for '+' in ls?
+generic/325	# mmap missing
 generic/338	# BUG_ON update inode error handling
+generic/346	# mmap missing
 generic/347	# _dmthin_mount doesn't work?
 generic/356	# swap
 generic/357	# swap
@@ -80,13 +92,16 @@ generic/409	# bind mounts not scripted yet
 generic/410	# bind mounts not scripted yet
 generic/411	# bind mounts not scripted yet
 generic/423	# symlink inode size is strlen() + 1 on scoutfs
+generic/428	# mmap missing
 generic/430	# xfs_io copy_range missing in el7
 generic/431	# xfs_io copy_range missing in el7
 generic/432	# xfs_io copy_range missing in el7
 generic/433	# xfs_io copy_range missing in el7
 generic/434	# xfs_io copy_range missing in el7
+generic/437	# mmap missing
 generic/441	# dm-mapper
 generic/444	# el9's posix_acl_update_mode is buggy ?
+generic/452	# exec test - no mmap
 generic/467	# open_by_handle ESTALE
 generic/472	# swap
 generic/484	# dm-mapper
@@ -103,9 +118,11 @@ generic/565	# xfs_io copy_range missing in el7
 generic/568	# falloc not resulting in block count increase
 generic/569	# swap
 generic/570	# swap
+generic/614	# mmap missing
 generic/620	# dm-hugedisk
-generic/633	# id-mapped mounts missing in el7
+generic/633	# mmap, id-mapped mounts missing in el7
 generic/636	# swap
+generic/638	# mmap missing
 generic/641	# swap
 generic/643	# swap
 EOF
--- a/utils/src/util.c
+++ b/utils/src/util.c
@@ -7,6 +7,7 @@
 #include <errno.h>
 #include <stdio.h>
 #include <stdlib.h>
+#include <wordexp.h>

 #include "util.h"
 #include "format.h"
@@ -17,15 +18,26 @@

 static int open_path(char *path, int flags)
 {
+	wordexp_t exp_result;
 	int ret;

-	ret = open(path, flags);
+	ret = wordexp(path, &exp_result, WRDE_NOCMD | WRDE_SHOWERR | WRDE_UNDEF);
+	if (ret) {
+		fprintf(stderr, "wordexp() failure for \"%s\": %d\n", path, ret);
+		ret = -EINVAL;
+		goto out;
+	}
+
+	ret = open(exp_result.we_wordv[0], flags);
 	if (ret < 0) {
 		ret = -errno;
 		fprintf(stderr, "failed to open '%s': %s (%d)\n",
 			path, strerror(errno), errno);
 	}

+out:
+	wordfree(&exp_result);
+
 	return ret;
 }