| Commit message (Expand) | Author | Age | Files | Lines |
* | Reduce the chunk size in evict-lsm wtperf workload.mongodb-2.8-rc22.8-rc2 | Alex Gorrod | 2014-12-03 | 1 | -1/+1 |
* | Merge pull request #1427 from wiredtiger/split-fixes | Alex Gorrod | 2014-12-03 | 2 | -23/+21 |
|\ |
|
| * | Don't try in-memory splits when closing a tree. | Michael Cahill | 2014-12-03 | 1 | -1/+1 |
| * | Only do in-memory splits on large, dirty pages. | Michael Cahill | 2014-12-03 | 1 | -5/+4 |
| * | Don't attempt to split pages when checkpoints are active in a tree. | Michael Cahill | 2014-12-03 | 1 | -18/+17 |
|/ |
|
* | fix a comment typo | Keith Bostic | 2014-12-02 | 1 | -1/+1 |
* | whitespace | Keith Bostic | 2014-12-02 | 1 | -1/+1 |
* | Merge pull request #1422 from wiredtiger/split-ref-key | Alex Gorrod | 2014-12-02 | 1 | -3/+33 |
|\ |
|
| * | Use the original approach to finding the first key on a page: search the smal... | Michael Cahill | 2014-12-02 | 1 | -9/+9 |
| * | Remove stray debugging. | Michael Cahill | 2014-12-02 | 1 | -2/+0 |
| * | Instantiate a full key for the parent ref of a page during in-memory splits. ... | Michael Cahill | 2014-12-02 | 1 | -3/+35 |
|/ |
|
* | Merge pull request #1419 from wiredtiger/split-right | Michael Cahill | 2014-12-02 | 15 | -278/+656 |
|\ |
|
| * | Inherit the original page's dirty transaction during a split so that checkpoi... | Michael Cahill | 2014-12-02 | 1 | -4/+3 |
| * | Tweak the logic to delay eviction after splits: only check inmem_split_txn fo... | Michael Cahill | 2014-12-02 | 1 | -2/+2 |
| * | Don't force-evict pages that have just been through an in-memory split. | Michael Cahill | 2014-12-02 | 3 | -2/+23 |
| * | Merge branch 'develop' into split-right | Michael Cahill | 2014-12-02 | 10 | -90/+131 |
| |\ |
|
| * | | Look for an in-memory split in the reconciliation path before checking | Alex Gorrod | 2014-12-02 | 1 | -13/+18 |
| * | | Merge branch 'develop' into split-right | Keith Bostic | 2014-12-01 | 0 | -0/+0 |
| |\ \ |
|
| * | | | Don't drop core on LSM-only runs, we can't open a cursor to verify with. | Keith Bostic | 2014-12-01 | 2 | -2/+8 |
| * | | | Push the checkpoint program a little harder, it's failing in some | Keith Bostic | 2014-12-01 | 2 | -2/+23 |
| * | | | Add error-handling code to the insert split, if the split into the | Keith Bostic | 2014-12-01 | 1 | -43/+58 |
| * | | | Reviewing the code, minor whitespace changes. | Keith Bostic | 2014-12-01 | 1 | -12/+7 |
| * | | | Instead of checking for a single level-5 skip list entry, check for two | Keith Bostic | 2014-12-01 | 1 | -15/+17 |
| * | | | whitespace | Keith Bostic | 2014-12-01 | 1 | -3/+2 |
| * | | | Fix a comment. | Keith Bostic | 2014-12-01 | 1 | -2/+1 |
| * | | | return after a jump to the error label or a jump to the error label | Keith Bostic | 2014-12-01 | 1 | -1/+1 |
| * | | | Add warning messages when we ignore errors after a split completes. | Keith Bostic | 2014-12-01 | 1 | -0/+9 |
| * | | | Some fixes for in-memory splits: | Michael Cahill | 2014-12-01 | 3 | -33/+57 |
| * | | | More re-factoring of the parent-split function: handle the WT_REF's | Keith Bostic | 2014-11-30 | 1 | -26/+33 |
| * | | | Fix a comment. | Keith Bostic | 2014-11-30 | 1 | -4/+4 |
| * | | | If exclusive is set, we may not be operating on a locked WT_REF, | Keith Bostic | 2014-11-30 | 1 | -1/+0 |
| * | | | The parent split function shouldn't free the passed-in array of WT_REFs, | Keith Bostic | 2014-11-30 | 1 | -1/+2 |
| * | | | Add code to split a too-large insert list onto a new page as part of | Keith Bostic | 2014-11-30 | 8 | -143/+421 |
| * | | | Don't set an "alloc_ref" count when allocating leaf pages, that | Keith Bostic | 2014-11-30 | 1 | -4/+4 |
| * | | | Rename __wt_rec_evict to __wt_evict, eviction and reconciliation have | Keith Bostic | 2014-11-28 | 5 | -9/+9 |
| * | | | Rename __wt_rec_write to __wt_reconcile, there's no __wt_rec_read. | Keith Bostic | 2014-11-28 | 5 | -10/+10 |
| * | | | Refactor the split code so there's a split-the-parent function that can | Keith Bostic | 2014-11-28 | 3 | -109/+134 |
| * | | | Minor renaming. | Keith Bostic | 2014-11-28 | 1 | -6/+6 |
* | | | | Update wtperf multi-lsm configurations. | Alex Gorrod | 2014-12-02 | 2 | -2/+2 |
| |_|/
|/| | |
|
* | | | Add a statistic to count how much eviction application threads are doing. | Michael Cahill | 2014-12-02 | 5 | -87/+97 |
* | | | Fixup wtperf config documentation. | Alex Gorrod | 2014-12-01 | 1 | -1/+1 |
* | | | Merge pull request #1415 from wiredtiger/wtperf-log-workloads | sueloverso | 2014-12-01 | 3 | -0/+31 |
|\ \ \
| |_|/
|/| | |
|
| * | | Add some wtperf workloads that turn logging on. | Alex Gorrod | 2014-11-28 | 3 | -0/+31 |
* | | | Don't drop core on LSM-only runs, we can't open a cursor to verify with. | Keith Bostic | 2014-12-01 | 2 | -2/+8 |
* | | | Push the checkpoint program a little harder, it's failing in some | Keith Bostic | 2014-12-01 | 2 | -2/+23 |
| |/
|/| |
|
* | | When we switched from converting off_t's to/from uint32_t's in file | Keith Bostic | 2014-11-28 | 2 | -30/+21 |
* | | Merge pull request #1416 from wiredtiger/lsm-ckpt-fixes | Alex Gorrod | 2014-11-28 | 5 | -28/+25 |
|\ \ |
|
| * | | Deal with deleted pages if a file discard is interrupted. | Michael Cahill | 2014-11-28 | 3 | -12/+7 |
| * | | Close a window switching LSM chunks where a newer transaction could modify a ... | Michael Cahill | 2014-11-28 | 1 | -8/+9 |
| * | | We don't need to checkpoint a clean file just because the previous checkpoint... | Michael Cahill | 2014-11-28 | 1 | -8/+9 |