Todd Gruben
d41f998932
cleaned up constant
2016-09-23 16:04:22 -05:00
Todd Gruben
11a2013f2d
fix roaring.Difference crash
2016-09-23 13:27:35 -05:00
Todd Gruben
415507ffe3
fix for intersect and updated tests
2016-09-22 16:47:39 -05:00
Todd Gruben
57810f8ab6
merge
2016-09-22 03:05:53 -05:00
Todd Gruben
f53c2d07d8
merge
2016-09-22 03:05:26 -05:00
tgruben
7c1bf40ff5
Merge pull request #113 from benbjohnson/sort-import
...
Add import sorting command
2016-09-21 16:30:05 -05:00
Ben Johnson
432bf74368
Add import sorting command.
...
Introduces new `pilosactl sort` to sort import files by bit
position so they can be inserted faster. Also optimizes container
scanning and adds a `-buffer-size` flag to `import`.
2016-09-21 14:33:24 -06:00
tgruben
1071f193c0
Merge pull request #112 from benbjohnson/import-cache-2
...
Update cache on Import (alternative)
2016-09-16 15:54:13 -05:00
Ben Johnson
7c07cdf304
Remove import count optimization.
2016-09-16 11:36:54 -06:00
Todd Gruben
3907414a10
cache update on import adjustment
2016-09-16 11:20:31 -06:00
Todd Gruben
3009abbeef
corrected ClearBit
2016-09-16 11:20:12 -06:00
Todd Gruben
60853a6bef
ignore checksum on single node clusters
2016-09-16 11:18:44 -06:00
Todd Gruben
b7780518cc
cache update on import adjustment
2016-09-15 13:37:10 -05:00
Todd Gruben
15e425ae8f
Merge branch 'master' of github.com:umbel/pilosa
2016-09-13 20:59:23 -05:00
tgruben
84d010e66d
Merge pull request #110 from benbjohnson/optimize-top-n
...
Optimize TopN() w/ source query.
2016-09-13 20:58:53 -05:00
Ben Johnson
947eea4668
Optimize TopN() w/ source query.
...
This commit makes several changes to optimize the TopN() query:
- Reduce highbits() back from 24-bits to 16-bits.
- Reduce MaxArraySize back from 2^20 to 4096.
- Optimize bitmap count invalidation.
- Parallelize TopN() across nodes.
- Parallelize TopN() across slices.
2016-09-13 14:55:56 -06:00
Todd Gruben
df2ac89558
Merge branch 'master' of github.com:umbel/pilosa
2016-09-07 14:15:10 -05:00
tgruben
7a349fca54
Merge pull request #109 from benbjohnson/opt-int-count
...
Optimize IntersectionCount for Array+Bitmap
2016-09-07 14:14:41 -05:00
Ben Johnson
44540abd1d
Optimize IntersectionCount for Array+Bitmap
...
Reworks the `roaring.intersectionCountArrayBitmap()` call to avoid
using an iterator. Performance of the included benchmark went from
2.5ms to 1.1ms.
Some of the issue with intersectionCount is the increased size of
bitmaps and slices and I need to do additional testing with various
sizes.
2016-09-07 10:13:31 -06:00
Todd Gruben
aea68cbbd8
Merge branch 'master' of github.com:umbel/pilosa
2016-09-01 12:07:27 -05:00
tgruben
361c5fbeb4
Merge pull request #108 from benbjohnson/remove-mmap-resizing
...
Remove post-mmap resizing
2016-09-01 12:06:38 -05:00
Ben Johnson
0879bab148
Remove post-mmap resizing
2016-09-01 09:18:52 -06:00
Todd Gruben
1968972a17
Merge branch 'master' of github.com:umbel/pilosa
2016-08-30 17:36:21 -05:00
Todd Gruben
d4067ef34e
corrected ClearBit
2016-08-30 17:36:00 -05:00
tgruben
e130d99a18
Merge pull request #107 from benbjohnson/export
...
Add export command to pilosactl
2016-08-30 17:25:30 -05:00
Ben Johnson
157b7eb966
Add export command to pilosactl
...
CSV exports can now be done with the pilosactl application:
$ pilosactl -d mydb -f myframe -o MYFILE.csv
If `-o` is not specified then the CSV is written to STDOUT. The
exporter combines all slices for the db/frame to into a single
concatenated CSV file.
2016-08-30 16:18:12 -06:00
Todd Gruben
758bed45ac
Merge branch 'master' of github.com:umbel/pilosa
2016-08-26 12:59:55 -05:00
tgruben
f5a32395fc
Merge pull request #105 from benbjohnson/optimize-bitmap
...
Optimize bitmap with zero copy (WIP)
2016-08-25 15:33:00 -05:00
Ben Johnson
54f12b655f
Optimize bitmap with zero copy
...
Segments bitmaps by slice and changes `Fragment.Bitmap()` to return
bitmaps with segments which are offset ranges of mmapped bitmaps.
2016-08-25 13:30:25 -06:00
Todd Gruben
6f7031652f
Merge branch 'master' of github.com:umbel/pilosa
2016-08-15 18:36:08 -05:00
tgruben
9659f61420
Merge pull request #104 from benbjohnson/count-range
...
CountRange()
2016-08-15 18:35:58 -05:00
Ben Johnson
888040c26c
add CountRange()
...
This commit adds `roaring.Bitmap.CountRange()` to return the number
of bits in a subrange of a bitmap. This significantly improves
server start time and is needed for upcoming zero copy bitmap
optimizations.
2016-08-15 16:03:25 -06:00
Todd Gruben
5eabf67a11
Merge branch 'master' of github.com:umbel/pilosa
2016-08-12 15:10:57 -05:00
Todd Gruben
13f8ce673e
cache loading
2016-08-12 15:10:50 -05:00
tgruben
d2106de4c0
Merge pull request #103 from benbjohnson/fix-count-cache
...
Fix count() cache retrieval
2016-08-12 15:06:53 -05:00
Ben Johnson
76af8b53a3
fix count() cache retrieval
2016-08-12 11:02:52 -06:00
Ben Johnson
07a815eb55
add http trace profiling
2016-08-12 10:58:45 -06:00
Ben Johnson
edce8c537c
add CLI profiling
...
This commit adds the `-cpuprofile` flag to the `pilosa` binary so
that startup can be profiled.
2016-08-12 10:58:45 -06:00
Ben Johnson
f50fc24749
fix bitmap reference bug
2016-08-09 14:57:37 -06:00
Todd Gruben
a833624e20
Merge branch 'master' of github.com:umbel/pilosa
2016-08-08 09:35:43 -05:00
tgruben
d354335374
Merge pull request #102 from benbjohnson/serialize-cache-flush
...
Serialize cache flush
2016-08-08 09:30:47 -05:00
Ben Johnson
15cc4d7d5a
serialize cache flush
...
This commit moves the cache flush to the `Index` and only serializes
a single fragment at a time.
Also included in this commit is the `inspect` command for the
`pilsoactl` binary. This provides insight into pilosa data files.
2016-08-05 14:58:37 -06:00
Todd Gruben
0fd6543497
Merge branch 'master' of github.com:umbel/pilosa
2016-07-25 11:43:58 -05:00
tgruben
916a22da29
Merge pull request #100 from benbjohnson/cluster-attr
...
Forward bitmap & profile attributes
2016-07-25 11:42:52 -05:00
Ben Johnson
eb8c0eee28
forward bitmap & profile attributes
...
This commit adds forwarding of bitmap and profile attributes to
other servers in the cluster.
2016-07-19 13:54:01 -06:00
Todd Gruben
0513dfd9ae
Merge branch 'master' of github.com:umbel/pilosa
2016-07-07 11:23:50 -05:00
Todd Gruben
3b32db998d
ignore checksum on single node clusters
2016-07-07 11:22:15 -05:00
tgruben
b189961f69
Merge pull request #99 from benbjohnson/optimize-block-checksumming
...
Optimize sparse bitmap block checksums
2016-07-07 11:18:58 -05:00
Ben Johnson
3fdf63f84f
optimize sparse bitmap block checksums
...
This commit refactors the block checksumming by removing the
iteration over each block and instead only checking blocks which
have data. This requires merging the cache inspection with the
roaring iterator to reduce CPU time and memory allocations.
2016-07-07 10:03:38 -06:00
tgruben
148c9105fb
Merge pull request #95 from benbjohnson/sync-closing
...
Check for early close during AAE
2016-06-29 11:25:56 -05:00