1cdbb7b7bf
ck_hs: Remove unused return value from ck_hs_fas.
12 years ago
693ad68b86
ck_hs: Existence requires generation check.
...
It is possible for a defragmenting set or swap operation
to set a tombstone. If the probe sequence does not encounter
an empty slot and hits maximum write-side probe limit first
for it to fail to reprobe defragmenting store.
12 years ago
86619b3c38
ck_hs: Add atomic swap operation (requires existence).
12 years ago
6c7781d8c3
ck_hs: Simplify marshal path for inserted pointer.
...
ck_hs_marshal function has been added which mutates
pointer to appropriate representation for insertion.
12 years ago
58af5c3072
ck_epoch: Elaborate on ck_epoch_register load fence.
12 years ago
4492325ccc
ck_hs: Migrate to ck_pr_fence_X_Y.
12 years ago
855a1472a8
ck_ht: Add ck_ht_reset_size_spmc operation.
...
The ck_ht_reset_size_spmc operation takes an additional argument
that allows the user to specify the size of the new generation
of the hashtable.
12 years ago
73531e9e48
ck_hs: Add ck_hs_reset_size operation.
...
The ck_hs_reset_size operation takes an additional argument
that allows the user to specify the size of the new generation
of the hashset.
12 years ago
4132ec4998
ck_epoch: Add ck_epoch_reclaim function.
...
This function allows for explicit execution of all
deferred callbacks in an epoch_record. The primary
motivation is currently for performance profiling
but there are other use-cases where best-effort
semantics could be applied.
12 years ago
c6ff128510
ck_hs: Move replacement comment to ck_hs_set.
12 years ago
8bad50240d
ck_hs: Eliminate pointless legacy branch.
12 years ago
bdadd7bf6b
whitespace: More style fixes.
12 years ago
b4e9045c9b
ck_barrier_tournament: Remove old/stale comments.
...
ck_pr_load is unnecessary. It is assumed a strong fence follows
initialization (through thread creation boundary, for example
or explicit IPI).
12 years ago
7c56d73433
ck_barrier_mcs: Style clean-up.
12 years ago
3587d8e51b
build: Remove debug left-over.
12 years ago
e6e97f3ae5
build: Out-of-source builds for primary CK distribution.
...
Out of source regressions target still needs additional work
(because it's not there).
12 years ago
1a0b4122ec
ck_hs: Re-use tombstones near load factor.
...
This is similar to the set of changes done to ck_ht.
In addition to this, a bug was caught were minimal
probe sequence was based on last rather than first
tombstone observed.
This hashset will now face long-running bursty
write -> delete -> write workloads much more effectively
and includes significant performance improvements for
delete heavy workloads (at least 2x measured).
12 years ago
2116dfee3c
ck_ht: Increment n_entries on empty and tombstone insertions.
12 years ago
9a0d97c6ef
ck_ht: Set previous entry to empty on tombstone insert.
12 years ago
452cab1ef6
ck_ht: Return snapshot of object IFF we are not at end of probe sequence.
12 years ago
5a4dc765d8
ck_ht: Remember to set cursor to NULL on probe end.
12 years ago
1631f2ff84
ck_ht: Enable aggressive re-use of tombstones.
...
Previously, a probe to an empty slot was necessary in order
to avoid hash table growth. As long as a tombstone is available,
re-use it. This prevents excessive growth on workloads involving
long bursts of writes (near 0.5 load factor) followed by long
bursts of deletes.
12 years ago
33a9222923
legal: Update Copyright statements.
12 years ago
0631e396e0
ck_backoff: Replace ck_backoff_eb with ck_backoff_gb.
...
The distinction between additive/exponential implementation
and geometric implementation does little but confuse users.
The terminology used in ck_backoff now reflects terminology
used in literature.
ck_backoff_gb has been removed.
12 years ago
3cc43c4229
ck_epoch: Skip current record if it is marked as free.
...
Pointed out by Matt Johnson <jonhso87@crhc...>.
12 years ago
0c56b1b8c6
ck_epoch: Remember to mark entry availability on unregister.
...
Pointed out by Matt Johnson (johnso87@crhc....>.
12 years ago
05f36bc476
ck_internal: Follow-up to previous commit.
12 years ago
a7d79970e7
ck_{ht,internal}: Explicitly use unsigned for bitwise operations.
12 years ago
749a40159d
ck_hs: Fix ck_hs_next to check key value.
12 years ago
e5d701ca79
ck_hs: Whitespace changes.
12 years ago
51516312ce
ck_hs: Clear bits in iterator.
12 years ago
e9ca398123
ck_hs: Add ck_hs_destroy.
12 years ago
6fded0c0a1
ck_hs: Silence false positives from GCC.
12 years ago
f2dfd828c3
Merge pull request #7 from abelmathew/master
...
CK_MD_VMA_BITS
12 years ago
ece2895e9e
ck_hs: Drop ck_hs_hash_t abstraction.
...
No need for opaque type anymore.
12 years ago
00d0320767
ck_bag: Fix usage of CK_MD_VMA_BITS.
12 years ago
b4ab193944
ck_hs: Re-order map elements according to reader use.
...
Try to get generation, probe_maximum, mask and step on same
cache line.
12 years ago
adaf20b31c
ck_ht: Add ck_ht_stat function.
...
This can be used to expose certain performance metrics.
12 years ago
0f5e540afa
ck_hs: Lock-free set loosely modeled after ck_ht.
...
Currently only SPMC, but MPMC transformation is relatively trivial.
Documentation will come in a follow-up commit.
12 years ago
9ff3c2d017
Merge remote-tracking branch 'upstream/master'
12 years ago
981e0a49a2
ck_bag: Use CK_MD_VMA_BITS
12 years ago
01cd3a0256
build: Drop ck_hs, not ready to merge.
12 years ago
90713046e9
ck_ht: Use CK_MD_VMA_BITS.
...
Documentation update is necessary to point out CK_HT_KEY_LENGTH.
12 years ago
5fad753d6e
ck_epoch: No need for the fence on synchronize for TSO.
...
We still require a CAS on fast path, which acts as serializing.
12 years ago
c45098b21b
ck_epoch: Emit fence instructions for TSO, do not emit for recursive calls.
...
Unfortunately, there are still workloads which will not
serialize. Recursive calls into ck_epoch_begin have no
need for fence instructions.
12 years ago
dac91d1edd
ck_epoch: Short-circuit on scan block if epoch tick is encountered.
12 years ago
1c4183cf44
ck_epoch: Reload epoch value on scan failure.
12 years ago
7821be8a60
ck_epoch: If all threads are inactive, then we are at a grace period.
12 years ago
5d013028d9
ck_epoch_poll: Update writer epoch snapshot on poll.
...
If our CAS operation fails, we should grab a snapshot of epoch
for future ck_epoch_call invocations.
12 years ago
8a9f29a354
ck_epoch: Add comment to clarify short-circuit logic.
12 years ago
Samy Al Bahra
Samy Al Bahra
Abel Mathew