need to understand the locking around that field. Instead of setting
B_ERROR, set b_error instead. b_error is 'owned' by whoever completes
the I/O request.
WQ_PERCPU flag for workqueue and additional argument for workqueue_enqueue()
to assign a CPU might be used. Notes:
- For now, the list is used for workqueue_queue, which is non-optimal,
and will be changed with array, where index would be CPU ID.
- The data structures should be changed to be cache-friendly.
Reviewed by: <yamt>, <tech-kern>
an init method. So get rid of it and #ifdef _LKM and just always
init in the init method. Give malloc types the same treatment.
Makes file systems nicer to work with in linksetless environments
and fixes a few LKM discrepancies.
the "smooth" syncer, as if vfs.sync.*delay = 0, but only for LFS. The
default is "on", i.e., ignore lazy sync.
Reduce the amount of polling/busy-waiting done by lfs_putpages(). To
accomplish this, copied genfs_putpages() and modified it to indicate which
page it was that caused it to return with EDEADLK. fsync()/fdatasync()
should no longer ever fail with EAGAIN, and should not consume huge
quantities of cpu.
Also, try to make dirops less likely to be written as the result of a
VOP_PUTPAGES(), while ensuring that they are written regularly.
- finish implementing splraiseipl (and makeiplcookie).
http://mail-index.NetBSD.org/tech-kern/2006/07/01/0000.html
- complete workqueue(9) and fix its ipl problem, which is reported
to cause audio skipping.
- fix netbt (at least compilation problems) for some ports.
- fix PR/33218.
vnodes were synced and processed backwards. This meant that the last
accessed node was processed first and the earlierst last.
An extra benefit is the removal of the ugly hack from the Berkly days on
LFS.
In the proces, i've also replaced the various variations hand written loops
by the TAILQ_FOREACH() macro's.
LFCNWRAPSTOP and LFCNWRAPGO.
Be less verbose about the various looping checks: use log() rather than
printf(), and only log anything if we are really looping ("count = 2" is
not an error condition).
Allow dirops sleeping on available space to be interruptible.
* Mark being-deleted files in the Ifile so we can finish deleting them
at fs mount time.
* Flag the Ifile with "cleaner must clean" when writers are waiting for
the cleaner, rather than relying solely on the cleaner's estimation of
whether it should clean or not.
* Note partial segments written by a user agent (in particular,
fsck_lfs) so that repeated rolls forward don't interfere with one
another.
* Add a new fcntl, LFCNPASS, that allows the log to wrap exactly once,
for better testing of the validity of checkpoints.
* Keep track of the on-disk nlink count when cleaning, so that we don't
partially complete directory operations while cleaning.
* Ensure that every single Ifile inode write represents a consistent
view of the filesystem. In particular, the accounting for the segment
we are writing the inode into must be correct, and the accounting for
the segment that inode used to reside in must be correct. Rather than
just rewriting the inode if we wrote it wrong, rewrite the necessary
ifile blocks before writing the inode so we never write it wrong.
* Don't unmark any VDIROP vnodes if we haven't written them to disk,
avoiding yet another problem with the "wait for the cleaner" error
return from lfs_putpages().
Also, move the last callback to an aiodone call, so we no longer do any
memory management from interrupt context.
particular, the caller can now choose whether to wait for the condition
to be met, and if the caller of LFCNWRAPSTOP dies or otherwise closes
the descriptor, the filesystem is started again. Updated the ckckp
regression test to use the new semantics.
dump_lfs(8) now uses the fcntls to implement LFS-style snapshotting through
the -X flag, addressing PR#33457 albeit not using fss(4). Fixed a couple
other problems with dump_lfs that manifested themselves during testing.
the precision of getnanotime() is not suitable for file timestamps.
esp. when it's nfs-exported.
- introduce vfs_timestamp().
(the name is from freebsd. currently merely a wrapper of nanotime())
- for ufs-like filesystems, use it rather than getnanotime().
XXX check other filesystems.
- struct timeval time is gone
time.tv_sec -> time_second
- struct timeval mono_time is gone
mono_time.tv_sec -> time_uptime
- access to time via
{get,}{micro,nano,bin}time()
get* versions are fast but less precise
- support NTP nanokernel implementation (NTP API 4)
- further reading:
Timecounter Paper: http://phk.freebsd.dk/pubs/timecounter.pdf
NTP Nanokernel: http://www.eecis.udel.edu/~mills/ntp/html/kern.html
many inodes are cleaned at once. Make sure that we write all the pages
on vnodes that are being flushed, even if we don't think there's room;
drain v_numoutput before lfs_vflush() completes.
Also, don't allow a vnode that is in the process of being cleaned to be
chosen by getnewvnode(); this avoids a segment accounting panic in the case
that a large number of inodes are fed to lfs_markv() all at once.
inode that makes those changes valid is either written to disk by
lfs_writeinode() or discarded by lfs_vfree().
A couple of locking fixes are also included as well.
Move the stop for LFCNWRAPSTOP to the point at which writing at segment 0
is really about to commence, since this is what the test expects (and
incidentally what a snapshotting utility wants as well).
More correctly reconstruct the on-disk state at every checkpoint, rather
than relying on the entire state at the point of wrapping to be accurate
(that is only true the first time we wrap). Add a "make abort" target to
make rerunning the test more convenient when it has failed and we're done
analyzing the failure.
where segment 0 is being considered for writing. This allows for automated
checkpoint vailidity scanning, and could be used (in conjunction with the
existing LFCNREWIND) for e.g. snapshot dumps as well.
Include a regression test that does such scanning.
When writing the Ifile, loop through the dirty block list three times to
make sure that the checkpoint is always consistent (the first and second
times the Ifile blocks can cross a segment boundary; not so the third time
unless the segments are very small). Discovered by using the aforementioned
regression test.
explicitly (especially since we didn't know about VFREEING at all before),
but notice the EBUSY return from vget() instead.
Fix some more MP locking protocol issues, most of which were pointed out by
Christian Ehrhardt this morning on tech-kern.
* Correct (weak) segment lock assertions in lfs_fragextend and lfs_putpages.
* Keep IN_MODIFIED set if we run out of avail in lfs_putpages.
* Don't try to (re)write buffers on a VBLK vnode; fixes a panic I found
while running with an LFS root.
* Raise priority of LFCNSEGWAIT to PVFS; PUSER is way too low for
something the pagedaemon is relying on.
* Acknowledge that sometimes there are more dirty pages to be written to
disk than clean segments. When we reach the danger line,
lfs_gop_write() now returns EAGAIN. The caller of VOP_PUTPAGES(), if
it holds the segment lock, drops it and waits for the cleaner to make
room before continuing.
* Note and avoid a three-way deadlock in lfs_putpages (a writer holding
a page busy blocks on the cleaner while the cleaner blocks on the
segment lock while lfs_putpages blocks on the page).
from macros to real functions. Original patch and review from chuq.
Note: ext2fs only keeps seconds in the on-disk inode, and msdosfs does not
have enough precision for all fields, so this is not very useful for those
two.
lfs_balloc(), and use that to estimate the number of dirty pages belonging
to LFS (subsystem or filesystem). This is almost certainly wrong for
the case of a large mmap()ed region, but the accounting is tighter than
what we had before, and performs much better in the typical case of pages
dirtied through write().
be assured that the last byte of a file is always allocated. Previously
a file extension could cause the filesystem to be flushed, writing an
inconsistent inode to disk. Although this condition would be corrected
the next time blocks were written to disk, an intervening crash would leave
the filesystem in an inconsistent state, leaving fsck_lfs to complain
of an inode "partially truncated".
stuff under '#ifdef DEBUG', and use sysctl knobs to turn on/off particular
parts of the debugging reporting (if DEBUG is enabled). Re-enable the LFS
statistics in sysctl, while I'm there. A bit of a rototill.
* Note when lfs_putpages(9) thinks it is not going to be writing any
pages before calling genfs_putpages(9). This prevents a situation in
which blocks can be queued for writing without a segment header.
* Correct computation of NRESERVE(), though it is still a gross
overestimate in most cases. Note that if NRESERVE() is too high, it
may be impossible to create files on the filesystem. We catch this
case on filesystem mount and refuse to mount r/w.
* Allow filesystems to be mounted whose block size is == MAXBSIZE.
* Somewhere along the line, ufs_bmaparray(9) started mangling UNWRITTEN
entries in indirect blocks again, triggering a failed assertion "daddr
<= LFS_MAX_DADDR". Explicitly convert to and from int32_t to correct
this.
* Add a high-water mark for the number of dirty pages any given LFS can
hold before triggering a flush. This is settable by sysctl, but off
(zero) by default.
* Be more careful about the MAX_BYTES and MAX_BUFS computations so we
shouldn't see "please increase to at least zero" messages.
* Note that VBLK and VCHR vnodes can have nonzero values in di_db[0]
even though their v_size == 0. Don't panic when we see this.
* Change lfs_bfree to a signed quantity. The manner in which it is
processed before being passed to the cleaner means that sometimes it
may drop below zero, and the cleaner must be aware of this.
* Never report bfree < 0 (or higher than lfs_dsize) through
lfs_statvfs(9). This prevents df(1) from ever telling us that our full
filesystems have 16TB free.
* Account space allocated through lfs_balloc(9) that does not have
associated buffer headers, so that the pagedaemon doesn't run us out
of segments.
* Return ENOSPC from lfs_balloc(9) when bfree drops to zero.
* Address a deadlock in lfs_bmapv/lfs_markv when the filesystem is being
unmounted. Because vfs_busy() is a shared lock, and
lfs_bmapv/lfs_markv mark the filesystem vfs_busy(), the cleaner can be
holding the lock that umount() is blocking on, then try to vfs_busy()
again in getnewvnode().
setting those flags, it does not cause the inode to be written in the periodic
sync. This is used for writes to special files (devices and named pipes) and
FIFOs.
Do not preemptively sync updates to access times and modification times. They
are now updated in the inode only opportunistically, or when the file or device
is closed. (Really, it should be delayed beyond close, but this is enough to
help substantially with device nodes.)
And the most amusing part:
Trickle sync was broken on both FFS and ext2fs, in different ways. In FFS, the
periodic call to VFS_SYNC(MNT_LAZY) was still causing all file data to be
synced. In ext2fs, it was causing the metadata to *not* be synced. We now
only call VOP_UPDATE() on the node if we're doing MNT_LAZY. I've confirmed
that we do in fact trickle correctly now.
