early in boot and broken early in boot by requiring a partly static
structure with another structure that must be present by the time
any uses are performed. theoretically platform code could allocate
a chunk while seting up memory and assign it here, giving a dynamic
sizing for the entry list, but the reality is that all users have
a statically allocated entry list as well.
the existing KERNHIST_LINK_STATIC() is used in conjunction with
KERNHIST_INITIALIZER() instead.
this stops a NULL pointer deref when the _LOG() macro is called
before the storage is linked in, which happens with GCC 10 on OCTEON
with UVMHIST enabled, crashing in very early kernel init.
then rather than do more try-locks and eventually sleep for a tick,
take a hold on the current owner's lock, drop the page interlock,
and acquire the lock that we took the hold on in a blocking fashion.
After we get the lock, check if the lock that we acquired is still
the lock for the owner of the page that we're interested in.
If the owner hasn't changed then can proceed with this page,
otherwise we will skip this page and move on to a different page.
This dramatically reduces the amount of time that the pagedaemon
sleeps trying to get locks, since even 1 tick is an eternity to sleep
in this context and it was easy to trigger that case in practice,
and with this new method the pagedaemon only very rarely actually blocks
to acquire the lock that it wants since the object locks are adaptive,
and when the pagedaemon does block then the amount of time it spends
sleeping will be generally be much less than 1 tick.
- Don't need to count anonpages+filepages any more; clean+unknown+dirty for
each kind of page can be summed to get the totals.
- Track the number of free pages with a counter so that it's one less thing
for the allocator to do, which opens up further options there.
- Remove cpu_count_sync_one(). It has no users and doesn't save a whole lot.
For the cheap option, give cpu_count_sync() a boolean parameter indicating
that a cached value is okay, and rate limit the updates for cached values
to hz.
cached value will do, or if the very latest total must be fetched. It can
be called thousands of times a second and fetching the totals impacts not
only the calling LWP but other CPUs doing unrelated activity in the VM
system.
- Change the lock on uvm_object, vm_amap and vm_anon to be a RW lock.
- Break v_interlock and vmobjlock apart. v_interlock remains a mutex.
- Do partial PV list locking in the x86 pmap. Others to follow later.
for doing page cache iodone work, but since then biodone() has changed to
hand off all iodone work to a softint thread, so we no longer need the
special-purpose aiodoned thread.
- Reduce unnecessary page scan in putpages esp. when an object has a ton of
pages cached but only a few of them are dirty.
- Reduce the number of pmap operations by tracking page dirtiness more
precisely in uvm layer.
of page interlocks. Require that the page interlock be held over calls to
uvm_pageactivate(), uvm_pagewire() and similar.
- Solve the concurrency problem with page replacement state. Rather than
updating the global state synchronously, set an intended state on
individual pages (active, inactive, enqueued, dequeued) while holding the
page interlock. After the interlock is released put the pages on a 128
entry per-CPU queue for their state changes to be made real in batch.
This results in in a ~400 fold decrease in contention on my test system.
Proposed on tech-kern but modified to use the page interlock rather than
atomics to synchronise as it's much easier to maintain that way, and
cheaper.
- Use marker pages to keep place in the queue when scanning, rather than
relying on assumptions.
- In uvmpdpol_balancequeue(), lock the object once instead of twice.
- When draining pools, the situation is getting desperate, but try to avoid
saturating the system with xcall, lock and interrupt activity by sleeping
for 1 clock tick if being continually awoken and all pools have been
cycled through at least once.
- Pause & resume the freelist cache during pool draining.
PR kern/54209: NetBSD 8 large memory performance extremely low
PR kern/54210: NetBSD-8 processes presumably not exiting
PR kern/54727: writing a large file causes unreasonable system behaviour
- Have a single lock (uvmpd_lock) to protect pagedaemon state that was
previously covered by uvmpd_pool_drain_lock plus uvm_fpageqlock.
- Don't require any locks be held when calling uvm_kick_pdaemon().
- Use uvm_free().
lock for use of the pagedaemon policy code. Discussed on tech-kern.
PR kern/54209: NetBSD 8 large memory performance extremely low
PR kern/54210: NetBSD-8 processes presumably not exiting
PR kern/54727: writing a large file causes unreasonable system behaviour
a pool can involve taking a lock which can be held by a thread which is
blocked waiting for memory. Avoid this by moving the pool-draining work
to a separate worker thread.
in PR kern/52639, as well as some general cleaning-up...
(As proposed on tech-kern@ with additional changes and enhancements.)
Details of changes:
* All history arguments are now stored as uintmax_t values[1], both in
the kernel and in the structures used for exporting the history data
to userland via sysctl(9). This avoids problems on some architectures
where passing a 64-bit (or larger) value to printf(3) can cause it to
process the value as multiple arguments. (This can be particularly
problematic when printf()'s format string is not a literal, since in
that case the compiler cannot know how large each argument should be.)
* Update the data structures used for exporting kernel history data to
include a version number as well as the length of history arguments.
* All [2] existing users of kernhist(9) have had their format strings
updated. Each format specifier now includes an explicit length
modifier 'j' to refer to numeric values of the size of uintmax_t.
* All [2] existing users of kernhist(9) have had their format strings
updated to replace uses of "%p" with "%#jx", and the pointer
arguments are now cast to (uintptr_t) before being subsequently cast
to (uintmax_t). This is needed to avoid compiler warnings about
casting "pointer to integer of a different size."
* All [2] existing users of kernhist(9) have had instances of "%s" or
"%c" format strings replaced with numeric formats; several instances
of mis-match between format string and argument list have been fixed.
* vmstat(1) has been modified to handle the new size of arguments in the
history data as exported by sysctl(9).
* vmstat(1) now provides a warning message if the history requested with
the -u option does not exist (previously, this condition was silently
ignored, with only a single blank line being printed).
* vmstat(1) now checks the version and argument length included in the
data exported via sysctl(9) and exits if they do not match the values
with which vmstat was built.
* The kernhist(9) man-page has been updated to note the additional
requirements imposed on the format strings, along with several other
minor changes and enhancements.
[1] It would have been possible to use an explicit length (for example,
uint64_t) for the history arguments. But that would require another
"rototill" of all the users in the future when we add support for an
architecture that supports a larger size. Also, the printf(3) format
specifiers for explicitly-sized values, such as "%"PRIu64, are much
more verbose (and less aesthetically appealing, IMHO) than simply
using "%ju".
[2] I've tried very hard to find "all [the] existing users of kernhist(9)"
but it is possible that I've missed some of them. I would be glad to
update any stragglers that anyone identifies.
caches, merge together pool_drain_start() and pool_drain_end() into
bool pool_drain(struct pool **ppp);
"bool" value indicates whether reclaiming was fully done (true) or not (false)
"ppp" will contain a pointer to the pool that was drained (optional).
See http://mail-index.netbsd.org/tech-kern/2012/06/04/msg013287.html
simplifying uvm_map handling (no special kernel entries anymore no relocking)
make malloc(9) a thin wrapper around kmem(9)
(with private interface for interrupt safety reasons)
releng@ acknowledged
- Reorganize locking in UVM and provide extra serialisation for pmap(9).
New lock order: [vmpage-owner-lock] -> pmap-lock.
- Simplify locking in some pmap(9) modules by removing P->V locking.
- Use lock object on vmobjlock (and thus vnode_t::v_interlock) to share
the locks amongst UVM objects where necessary (tmpfs, layerfs, unionfs).
- Rewrite and optimise x86 TLB shootdown code, make it simpler and cleaner.
Add TLBSTATS option for x86 to collect statistics about TLB shootdowns.
- Unify /dev/mem et al in MI code and provide required locking (removes
kernel-lock on some ports). Also, avoid cache-aliasing issues.
Thanks to Andrew Doran and Joerg Sonnenberger, as their initial patches
formed the core changes of this branch.
- Addresses the issue described in PR/38828.
- Some simplification in threading and sleepq subsystems.
- Eliminates pmap_collect() and, as a side note, allows pmap optimisations.
- Eliminates XS_CTL_DATA_ONSTACK in scsipi code.
- Avoids few scans on LWP list and thus potentially long holds of proc_lock.
- Cuts ~1.5k lines of code. Reduces amd64 kernel size by ~4k.
- Removes __SWAP_BROKEN cases.
Tested on x86, mips, acorn32 (thanks <mpumford>) and partly tested on
acorn26 (thanks to <bjh21>).
Discussed on <tech-kern>, reviewed by <ad>.
uvmpd_scan_queue:
- Fix a bug that prevented the pagedaemon from making forward progress
if (a) swap was full (b) the first 16 pages on the inactive list were
unbusy anons not already backed by swap.
- Remove redundant uvm_swapisfull() check and just try to allocate a slot.
If it fails we know swap is full.
unused kernel modules.
- Try to unload any autoloaded kernel modules 10 seconds after their
load was successful.
- Keep a counter to track module load/unload events.
