All hash sizes are power-of-2, but the compiler does not know that for sure
and 'foo % size' forces doing a division.
Store the size - 1 and use 'foo & hash' instead which allows mere shift.
The size can be changed by side effect of modifying kern.maxvnodes.
Since numbucketlocks was not modified, setting a sufficiently low value
would give more locks than actual buckets, which would then lead to
corruption.
Force the number of buckets to be not smaller.
Note this should not matter for real world cases.
Reported and tested by: pho
The negative list shrinker can demote an entry with only hotlist + neglist
locks held. On the other hand entry removal possibly sets the NCF_DVDROP
without aformentioned locks held prior to detaching it from the respective
netlist., which can lose the update made by the shrinker.
Reported and tested by: truckman
vp->v_mount->mnt_vnodecovered unlocked. This allowed unmount to race.
Lock vnode after we noticed the VV_ROOT flag. See comments for
explanation why unlocked check for the flag is considered safe.
Reported and tested by: avg
Sponsored by: The FreeBSD Foundation
MFC after: 1 week
If no negative entry is found on the last list, the ncp pointer will be
left uninitialized and a non-null value will make the function assume an
entry was found.
Fix the problem by initializing to NULL on entry.
Reported by: glebius
This splits the ncneg_mtx lock while preserving the hit ratio at least
during buildworld.
Create N dedicated lists for new negative entries.
Entries with at least one hit get promoted to the hot list, where they
get requeued every M hits.
Shrinking demotes one hot entry and performs a round-robin shrinking of
regular lists.
Reviewed by: kib
Other uses of cache_purgevfs() do rely on the cache purge for correct
operations, when paths are invalidated without unmount.
Reported and tested by: jkim
Discussed with: mjg
Sponsored by: The FreeBSD Foundation
purgevfs is purely optional and induces lock contention in workloads
which frequently mount and unmount filesystems.
In particular, poudriere will do this for filesystems with 4 vnodes or
less. Full cache scan is clearly wasteful.
Since there is no explicit counter for namecache entries, the number of
vnodes used by the target fs is checked.
The default limit is the number of bucket locks.
Reviewed by: kib
Add a table of vnode locks and use them along with bucketlocks to provide
concurrent modification support. The approach taken is to preserve the
current behaviour of the namecache and just lock all relevant parts before
any changes are made.
Lookups still require the relevant bucket to be locked.
Discussed with: kib
Tested by: pho
An array of bucket locks is added.
All modifications still require the global cache_lock to be held for
writing. However, most readers only need the relevant bucket lock and in
effect can run concurrently to the writer as long as they use a
different lock. See the added comment for more details.
This is an intermediate step towards removal of the global lock.
Reviewed by: kib
Tested by: pho
Since negative entries are managed with a LRU list, a hit requires a
modificaton.
Currently the code tries to upgrade the global lock if needed and is
forced to retry the lookup if it fails.
Provide a dedicated lock for use when the cache is only shared-locked.
Reviewed by: kib
MFC after: 1 week
the virtvnodes calculation. Include the size of fs-specific v_data as
the nfs nclnode inline, the NFS nclnode is bigger than either ZFS
znode or UFS inode. Include the size of namecache_ts and short cache
path element, multiplied by the name cache population factor, again
inline.
Inline defines are used to avoid pollution of the vnode.h with the
subsystem-private objects. Non-significant unsynchronized changes of
the definitions are fine, we do not care about that precision, and
e.g. ZFS consumes much malloced memory per vnode for reasons
unaccounted in the formula.
Lower the partition of kmem dedicated to vnodes, from 1/7 to 1/10.
The measures reduce vnode cache pressure on kmem and bring the vnode
cache memory use below some apparent thresholds that were exceeded by
r291244 due to more robust vnode reuse.
Reported and tested by: marius (i386, previous version)
Reviewed by: bde
Sponsored by: The FreeBSD Foundation
MFC after: 2 weeks
1. vhold and zap immediately instead of postponing few lines later
2. increment numneg after new entry is added
No functional changes.
No objections: kib
Previously the code would just increment statistics while only holding a
shared lock, in effect losing updates.
Separate tracking for nchstats is removed as values can be obtained from
existing counters. Note that some fields are updated by external
consumers and are left unfixed. This should not be a serious issue as
this structure looks quite obsolete.
No strong objections: kib
- Use SDT_PROBE<N>() instead of SDT_PROBE(). This has no functional effect
at the moment, but will be needed for some future changes.
- Don't hardcode the module component of the probe identifier. This is
set automatically by the SDT framework.
MFC after: 1 week
SDT_PROBE requires 5 parameters whereas SDT_PROBE<n> requires n parameters
where n is typically smaller than 5.
Perhaps SDT_PROBE should be made a private implementation detail.
MFC after: 20 days
the size of the name cache hash table (mapping file names to vnodes)
and the vnode hash table (mapping mount point and inode number to vnode).
An appropriate locking strategy is the key to changing hash table sizes
while they are in active use.
Reviewed by: kib
Tested by: Peter Holm
Differential Revision: https://reviews.freebsd.org/D2265
MFC after: 2 weeks
Transitions 0->1 and 1->0 (which decide e.g. on putting the vnode on the free
list) of either counter are still guarded with vnode interlock.
Reviewed by: kib (earlier version)
Tested by: pho
argument. This will be used for the Linux emulation layer - for Linux,
PATH_MAX is 4096 and not 1024.
Differential Revision: https://reviews.freebsd.org/D2335
Reviewed by: kib@
MFC after: 1 month
Sponsored by: The FreeBSD Foundation
sysctl_debug_hashstat_nchash() and sysctl_debug_hashstat_rawnchash().
These changes are in preparation for allowing changes in the size
of the vnode hash tables driven by increases and decreases in the
maximum number of vnodes in the system.
Reviewed by: kib@
Phabric: D2265
in r276564, change path type to char * (pathnames are always char *).
And remove bogus casts of malloc().
kern___getcwd() internally doesn't actually use or support u_char *
paths, except to copy them to a normal char * path.
These changes are not visible to libc as libc/gen/getcwd.c misdeclares
__getcwd() as taking a plain char * path.
While here remove _SYS_SYSPROTO_H_ for __getcwd() syscall as
we always have sysproto.h.
Pointed out by: bde
MFC after: 1 week
- Wrong integer type was specified.
- Wrong or missing "access" specifier. The "access" specifier
sometimes included the SYSCTL type, which it should not, except for
procedural SYSCTL nodes.
- Logical OR where binary OR was expected.
- Properly assert the "access" argument passed to all SYSCTL macros,
using the CTASSERT macro. This applies to both static- and dynamically
created SYSCTLs.
- Properly assert the the data type for both static and dynamic
SYSCTLs. In the case of static SYSCTLs we only assert that the data
pointed to by the SYSCTL data pointer has the correct size, hence
there is no easy way to assert types in the C language outside a
C-function.
- Rewrote some code which doesn't pass a constant "access" specifier
when creating dynamic SYSCTL nodes, which is now a requirement.
- Updated "EXAMPLES" section in SYSCTL manual page.
MFC after: 3 days
Sponsored by: Mellanox Technologies
Having ncneg diverge with the actual length of the ncneg tailq causes
NULL dereference.
Add assertion that an entry taken from ncneg queue is indeed negative.
Reported by and discussed with: avg
Sponsored by: The FreeBSD Foundation
MFC after: 1 week
In its stead use the Solaris / illumos approach of emulating '-' (dash)
in probe names with '__' (two consecutive underscores).
Reviewed by: markj
MFC after: 3 weeks
option, unbreak the lock tracing release semantic by embedding
calls to LOCKSTAT_PROFILE_RELEASE_LOCK() direclty in the inlined
version of the releasing functions for mutex, rwlock and sxlock.
Failing to do so skips the lockstat_probe_func invokation for
unlocking.
- As part of the LOCKSTAT support is inlined in mutex operation, for
kernel compiled without lock debugging options, potentially every
consumer must be compiled including opt_kdtrace.h.
Fix this by moving KDTRACE_HOOKS into opt_global.h and remove the
dependency by opt_kdtrace.h for all files, as now only KDTRACE_FRAMES
is linked there and it is only used as a compile-time stub [0].
[0] immediately shows some new bug as DTRACE-derived support for debug
in sfxge is broken and it was never really tested. As it was not
including correctly opt_kdtrace.h before it was never enabled so it
was kept broken for a while. Fix this by using a protection stub,
leaving sfxge driver authors the responsibility for fixing it
appropriately [1].
Sponsored by: EMC / Isilon storage division
Discussed with: rstone
[0] Reported by: rstone
[1] Discussed with: philip
we need to call ufs_checkpath() to walk from our new location to
the root of the filesystem to ensure that we do not encounter
ourselves along the way. Until now, we accomplished this by reading
the ".." entries of each directory in our path until we reached
the root (or encountered an error). This change tries to avoid the
I/O of reading the ".." entries by first looking them up in the
name cache and only doing the I/O when the name cache lookup fails.
Reviewed by: kib
Tested by: Peter Holm
MFC after: 4 weeks
In particular, do not lock Giant conditionally when calling into the
filesystem module, remove the VFS_LOCK_GIANT() and related
macros. Stop handling buffers belonging to non-mpsafe filesystems.
The VFS_VERSION is bumped to indicate the interface change which does
not result in the interface signatures changes.
Conducted and reviewed by: attilio
Tested by: pho
significantly. Upon investigation this was caused by name cache
misses for lookups of "..". For name cache entries for non-".."
directories, the cache entry serves double duty. It maps both the
named directory plus ".." for the parent of the directory. As such,
two ctime values (one for each of the directory and its parent) need
to be saved in the name cache entry.
This patch adds an entry for ctime of the parent directory to the
name cache. It also adds an additional uma zone for large entries
with this time value, in order to minimize memory wastage.
As well, it fixes a couple of cases where the mtime of the parent
directory was being saved instead of ctime for positive name cache
entries. With this patch, Lookup RPC counts return to values similar
to pre-r230394 kernels.
Reported by: bde
Discussed with: kib
Reviewed by: jhb
MFC after: 2 weeks
appropriate timestamps. Restore the assertions which verify that
NCF_TS is set when timestamp is asked for.
Reviewed by: jhb (previous version)
MFC after: 2 weeks
consistently, creating some namecache entries without NCF_TS flag.
This causes panic due to failed assertion.
As a temporal relief, remove the assert. Return epoch timestamp for
the entries without timestamp if asked.
While there, consolidate the code which returns timestamps, into a
helper cache_out_ts().
Discussed with: jhb
MFC after: 2 weeks
provide struct namecache_ts which is the old struct namecache. Only
allocate struct namecache_ts if non-null struct timespec *tsp was
passed to cache_enter_time, otherwise use struct namecache.
Change struct namecache allocation and deallocation macros into static
functions, since logic becomes somewhat twisty. Provide accessor for
the nc_name member of struct namecache to hide difference between
struct namecache and namecache_ts.
The aim of the change is to not waste 20 bytes per small namecache
entry.
Reviewed by: jhb
MFC after: 2 weeks
X-MFC-note: after r230394
entries on one client when a directory was renamed on another client. The
root cause for the stale entry being trusted is that each per-vnode nfsnode
structure has a single 'n_ctime' timestamp used to validate positive name
cache entries. However, if there are multiple entries for a single vnode,
they all share a single timestamp. To fix this, extend the name cache
to allow filesystems to optionally store a timestamp value in each name
cache entry. The NFS clients now fetch the timestamp associated with
each name cache entry and use that to validate cache hits instead of the
timestamps previously stored in the nfsnode. Another part of the fix is
that the NFS clients now use timestamps from the post-op attributes of
RPCs when adding name cache entries rather than pulling the timestamps out
of the file's attribute cache. The latter is subject to races with other
lookups updating the attribute cache concurrently. Some more details:
- Add a variant of nfsm_postop_attr() to the old NFS client that can return
a vattr structure with a copy of the post-op attributes.
- Handle lookups of "." as a special case in the NFS clients since the name
cache does not store name cache entries for ".", so we cannot get a
useful timestamp. It didn't really make much sense to recheck the
attributes on the the directory to validate the namecache hit for "."
anyway.
- ABI compat shims for the name cache routines are present in this commit
so that it is safe to MFC.
MFC after: 2 weeks
