We update `shard->last_purge` on each call of `hpa_try_purge` if we
purged something. This means, when `hpa_strict_min_purge_interval`
option is set only one slab will be purged, because on the next
call condition for too frequent purge protection
`since_last_purge_ms < shard->opts.min_purge_interval_ms` will always
be true. This is not an intended behaviour.
Instead, we need to check `min_purge_interval_ms` once and purge as many
pages as needed to satisfy requirements for `hpa_dirty_mult` option.
Make possible to count number of actions performed in unit tests (purge,
hugify, dehugify) instead of binary: called/not called. Extended current
unit tests with cases where we need to purge more than one page for a
purge phase.
It doesn't make much sense to repeat purging once we done with
hugification, because we can de-hugify pages that were hugified just
moment ago for no good reason. Let them wait next deferred work phase
instead. And if they still meeting purging conditions then, purge them.
There are few long options (`bin_shards` and `slab_sizes` for example)
when they are specified and we emit statistics value gets truncated.
Moved emitting logic for strings into separate `emitter_emit_str`
function. It will try to emit string same way as before and if value is
too long will fallback emiting rest partially with chunks of `BUF_SIZE`.
Justification for long strings (longer than `BUF_SIZE`) is not
supported.
Tag 101 is assigned to "CoreMedia Capture Data", which makes for confusing output when debugging.
To avoid conflicts, use a tag in the reserved application-specific range from 240–255 (inclusive).
All assigned tags: 94d3b45284/osfmk/mach/vm_statistics.h (L773-L775)
Change in `hpa_min_purge_interval_ms` handling logic is not backward
compatible as it might increase memory usage. Now this logic guarded by
`hpa_strict_min_purge_interval` option.
When `hpa_strict_min_purge_interval` is true, we will purge no more than
`hpa_min_purge_interval_ms`. When `hpa_strict_min_purge_interval` is
false, old purging logic behaviour is preserved.
Long term strategy migrate all users of hpa to new logic and then delete
`hpa_strict_min_purge_interval` option.
Currently, hugepages aware allocator backend works together with classic
one as a fallback for not yet supported allocations. When background
threads are enabled wake up time for classic interfere with hpa as there
were no checks inside hpa purging logic to check if we are not purging too
frequently. If background thread is running and `hpa_should_purge`
returns true, then we will purge, even if we purged less than
hpa_min_purge_interval_ms ago.
This lets us easily see what fraction of flush load is being taken up by the
bins, and helps guide future optimization approaches (for example: should we
prefetch during cache bin fills? It depends on how many objects the average fill
pops out of the batch).
This adds a fast-path for threads freeing a small number of allocations to
bins which are not their "home-base" and which encounter lock contention in
attempting to do so. In producer-consumer workflows, such small lock hold times
can cause lock convoying that greatly increases overall bin mutex contention.
This accomplishes two things:
- It avoids a full array scan (and any attendant branch prediction misses, etc.)
while holding the bin lock.
- It allows us to know the number of items that will be flushed before flushing
them, which will (in an upcoming commit) let us know if it's safe to use the
batched flush (in which case we won't acquire the bin mutex).
The main bits of shared code are the edata filtering and the stats flushing
logic, both of which are fairly simple to read and not so painful to duplicate.
The shared code comes at the cost of guarding all the subtle logic with
`if (small)`, which doesn't feel worth it.
In the next commit, we'll start using the batcher to eliminate mutex traffic.
To avoid cluttering up that commit with the random bits of busy-work it entails,
we'll centralize them here. This commit introduces:
- A batched bin type.
- The ability to mix batched and unbatched bins in the arena.
- Conf parsing to set batches per size and a max batched size.
- mallctl access to the corresponding opt-namespace keys.
- Stats output of the above.
Bypassing background thread creation for the oversize_arena used to be an
optimization since that arena had eager purging. However #2466 changed the
purging policy for the oversize_arena -- specifically it switched to the default
decay time when background_thread is enabled.
This issue is noticable when the number of arenas is low: whenever the total #
of arenas is <= 4 (which is the default max # of background threads), in which
case the purging will be stalled since no background thread is created for the
oversize_arena.
One of the condition to start purging is `hpa_hugify_blocked_by_ndirty`
function call returns true. This can happen in cases where we have no
dirty memory for this shard at all. In this case purging loop will be an
infinite loop.
`hpa_hugify_blocked_by_ndirty` was introduced at 0f6c420, but at that
time purging loop has different form and additional `break` was not
required. Purging loop form was re-written at 6630c5989, but additional
exit condition wasn't added there at the time.
Repo code was shared by Patrik Dokoupil at [1], I stripped it down to
minimum to reproduce issue in jemalloc unit tests.
[1]: https://github.com/jemalloc/jemalloc/pull/2533
When there were many items stashed, it's possible that after flushing stashed,
ncached is already lower than the remain, in which case the flush can simply
return at that point.
This change adds support for writing pid namespaces to the filename of a
heap profile. When running with namespaces pids may reused across
namespaces and if mounts are shared where profiles are written there is
not a great way to differentiate profiles between pids.
Signed-off-by: Daniel Hodges <hodges.daniel.scott@gmail.com>
Signed-off-by: Daniel Hodges <hodgesd@fb.com>
realloc() and rallocx() shares path, and realloc() should set errno to
ENOMEM upon OOM failures.
Fixes: ee961c2310 ("Merge realloc and rallocx pathways.")
Signed-off-by: Juhyung Park <qkrwngud825@gmail.com>
Access nactive, ndirty and nmuzzy throught getters and not directly.
There are no functional change, but getters are required to propagate
HPA's statistics up to Page Allocator's statitics.
Instead of failing on assertions. Previously the same change was made for
posix_memalign and aligned_alloc (#1554). Make memalign behave the same way
even though it's obsolete.
it's within the huge page size. These requests do not concern internal
fragmentation with huge pages, since the entire range is expected to be
accessed.
```
sub cleanup {
unlink($main::tmpfile_sym);
unlink(keys %main::tempnames);
# We leave any collected profiles in $HOME/jeprof in case the user wants
# to look at them later. We print a message informing them of this.
if ((scalar(@main::profile_files) > 0) &&
defined($main::collected_profile)) {
if (scalar(@main::profile_files) == 1) {
print STDERR "Dynamically gathered profile is in $main::collected_profile\n";
}
print STDERR "If you want to investigate this profile further, you can do:\n";
print STDERR "\n";
print STDERR " jeprof \\\n";
print STDERR " $main::prog \\\n";
print STDERR " $main::collected_profile\n";
print STDERR "\n";
}
}
```
On cleanup, it would print out a message for the collected profile.
If there is only one collected profile, it would pop by L691, then `scalar(@main::profile_files)` would be 0, and no message would be printed.
The current autogen.sh script doesn't allow receiving quoted extra
options.
If someone wants to pass extra CFLAGS that is split into multiple
options with a whitespace, then a quote is required.
However, the configure inside autogen.sh fails in this case as follows.
$ ./autogen.sh CFLAGS="-Dmmap=cxl_mmap -Dmunmap=cxl_munmap"
autoconf
./configure --enable-autogen CFLAGS=-Dmmap=cxl_mmap -Dmunmap=cxl_munmap
configure: error: unrecognized option: `-Dmunmap=cxl_munmap'
Try `./configure --help' for more information
Error 0 in ./configure
It's because the quote discarded unexpectedly when calling configure.
This patch is to fix this problem.
Signed-off-by: Honggyu Kim <honggyu.kim@sk.com>
Dmitry Ilvokhin