| Commit message (Expand) | Author | Age | Files | Lines |
* | Most allocation of pages to objects proceeds from lower to higher | alc | 2013-03-17 | 1 | -5/+5 |
* | Simplify the interface to vm_radix_insert() by eliminating the parameter | alc | 2013-03-17 | 1 | -3/+3 |
* | MFC | attilio | 2013-03-12 | 1 | -4/+1 |
* | When transferring the page from one object to another, don't insert the | alc | 2013-03-12 | 1 | -1/+1 |
* | MFC | attilio | 2013-03-11 | 1 | -1/+1 |
|\ |
|
| * | Update a comment: The object lock is no longer a mutex. | alc | 2013-03-09 | 1 | -1/+1 |
* | | Introduce vm_radix_is_empty(), and use it in place of | alc | 2013-03-10 | 1 | -4/+4 |
* | | Merge from vmcontention. | attilio | 2013-03-09 | 1 | -37/+38 |
|\ \ |
|
| * \ | MFC | attilio | 2013-03-09 | 1 | -59/+160 |
| |\ \
| | |/ |
|
| | * | Switch the vm_object mutex to be a rwlock. This will enable in the | attilio | 2013-03-09 | 1 | -37/+38 |
| | |\ |
|
| | | * | As VM_OBJECT_SLEEP() is a vm_object_t specific function, make | attilio | 2013-02-26 | 1 | -1/+1 |
| | | * | Hide the details for the assertion for VM_OBJECT_LOCK operations. | attilio | 2013-02-21 | 1 | -31/+31 |
| | | * | Rename VM_OBJECT_LOCK(), VM_OBJECT_UNLOCK() and VM_OBJECT_TRYLOCK() to | attilio | 2013-02-20 | 1 | -6/+6 |
| | | * | Switch vm_object lock to be a rwlock. | attilio | 2013-02-20 | 1 | -32/+33 |
| | * | | Merge from vmc-playground: | attilio | 2013-03-09 | 1 | -7/+9 |
* | | | | Evaluations on the likelyhood of empty object cache cannot be made in | attilio | 2013-03-04 | 1 | -2/+2 |
* | | | | A Boolean is more appropriate than an int here. Use what I think is a | alc | 2013-03-04 | 1 | -5/+4 |
* | | | | Two out of three times that vm_page_find_least() is called, it's going to | alc | 2013-03-03 | 1 | -1/+4 |
* | | | | Merge from vmcontention | attilio | 2013-02-26 | 1 | -1/+1 |
|\ \ \ \
| |/ / / |
|
| * | | | MFC | attilio | 2013-02-26 | 1 | -1/+1 |
| |\ \ \
| | |/ / |
|
| | * | | Wrap the sleeps synchronized by the vm_object lock into the specific | attilio | 2013-02-26 | 1 | -1/+1 |
| | |/ |
|
* | | | Revert wrongly added asserts: lookup and remove from the collection | attilio | 2013-02-26 | 1 | -8/+2 |
* | | | Remove an unuseful check as looking up into an empty trie should be | attilio | 2013-02-15 | 1 | -3/+1 |
* | | | Remove whitespace. | attilio | 2013-02-15 | 1 | -1/+1 |
* | | | - Fix style in vm_page_lookup(): there is no whiteline between | attilio | 2013-02-15 | 1 | -1/+16 |
* | | | Remove an unuseful check on resident_page_count. | attilio | 2013-02-14 | 1 | -3/+1 |
* | | | The radix preallocation pages can overfow the biggestone segment, so | attilio | 2013-02-14 | 1 | -19/+16 |
* | | | Implement a new algorithm for managing the radix trie which also | attilio | 2013-02-13 | 1 | -18/+20 |
* | | | Fix style. | attilio | 2013-02-10 | 1 | -1/+1 |
* | | | Style. | attilio | 2013-02-07 | 1 | -1/+1 |
* | | | Cleanup vm_radix KPI: | attilio | 2013-02-06 | 1 | -7/+3 |
* | | | Enrich comments on newly added assertions. | attilio | 2013-02-06 | 1 | -2/+4 |
* | | | Reduce diffs against HEAD. | attilio | 2013-02-06 | 1 | -2/+1 |
* | | | Now that vm_page_cache_free() and vm_page_cache_transfer() are | attilio | 2013-02-06 | 1 | -4/+6 |
* | | | Reduce diffs against HEAD: | attilio | 2013-02-06 | 1 | -30/+41 |
* | | | Reduce diffs against HEAD: | attilio | 2013-02-05 | 1 | -12/+34 |
* | | | Reduce differences with HEAD. | attilio | 2013-02-04 | 1 | -4/+4 |
* | | | Merge from vmcontention | attilio | 2013-02-04 | 1 | -201/+197 |
|\ \ \
| |/ / |
|
| * | | MFC | attilio | 2012-12-11 | 1 | -85/+136 |
| |\ \
| | |/ |
|
| | * | In the past four years, we've added two new vm object types. Each time, | alc | 2012-12-09 | 1 | -8/+5 |
| | * | Correct an error in r230623. When both VM_ALLOC_NODUMP and VM_ALLOC_ZERO | alc | 2012-11-21 | 1 | -2/+2 |
| | * | Replace the single, global page queues lock with per-queue locks on the | alc | 2012-11-13 | 1 | -64/+119 |
| | * | In general, we call pmap_remove_all() before calling vm_page_cache(). So, | alc | 2012-11-01 | 1 | -3/+3 |
| | * | Rework the known mutexes to benefit about staying on their own | attilio | 2012-10-31 | 1 | -4/+4 |
| | * | Replace the page hold queue, PQ_HOLD, by a new page flag, PG_UNHOLDFREE, | alc | 2012-10-29 | 1 | -5/+4 |
| * | | MFC | attilio | 2012-10-22 | 1 | -63/+26 |
| |\ \
| | |/ |
|
| | * | Move vm_page_requeue() to the only file that uses it. | alc | 2012-10-13 | 1 | -22/+0 |
| | * | Eliminate the conditional for releasing the page queues lock in | alc | 2012-10-13 | 1 | -4/+1 |
| | * | Tidy up a bit: | alc | 2012-10-03 | 1 | -37/+25 |
| * | | MFC | attilio | 2012-08-27 | 1 | -0/+39 |
| |\ \
| | |/ |
|