Vitaliy Filippov
57837a1cc6
Capture all by value in qemu_proxy
1 day ago
Vitaliy Filippov
058dcac2a7
Make flusher_count adaptive and limit write iodepth
2 days ago
Vitaliy Filippov
22071eea26
A little better systemd unit generator
3 days ago
Vitaliy Filippov
635abefa17
Add a test for the no_same_sector_overwrites mode
3 days ago
Vitaliy Filippov
185a1fe7dd
Use packages/ subdir instead of build/ for Docker package builds
4 days ago
Vitaliy Filippov
36cdeaf6dc
Move C/C++ sources to src subdirectory
1 week ago
Vitaliy Filippov
1ac1dae639
Use CMake
1 week ago
Vitaliy Filippov
663637a510
Slightly clean up the build script
1 week ago
Vitaliy Filippov
5f086624ee
Add .gitignore
1 week ago
Vitaliy Filippov
5f9d7c82bb
Add LICENSE
1 week ago
Vitaliy Filippov
d6e43c7dd0
Allow to enable AddressSanitizer with "ASAN=1 make"
1 week ago
Vitaliy Filippov
cf772cbe8e
Use LSAN suppressions in qemu-img tests
1 week ago
Vitaliy Filippov
6624bf9cf6
Use w=8 with jerasure
1 week ago
Vitaliy Filippov
c56525c515
Add Russian version of the README
1 week ago
Vitaliy Filippov
be51cd81e7
Introduce image names and metadata storage in etcd
Each inode has: image name, parent inode number & pool, size and readonly flag
Snapshots are created by switching image name to a different inode number
while using the older inode as parent.
2 weeks ago
Vitaliy Filippov
14d0f58b52
Add another test for failure domains
2 weeks ago
Vitaliy Filippov
c8a7318edf
Use clean_entry_bitmap_size instead of entry_attr_size back because of changed bitmap handling
2 weeks ago
Vitaliy Filippov
a8791ad9c5
Add a test for snapshots, fix bugs. Now the test passes
2 weeks ago
Vitaliy Filippov
c67805698e
Update the license to VNPL 1.1
VNPL 1.1 is slightly reworded to make it clear that proprietary software
interacting with Vitastor and providing some kind of service to end users isn't
a "Proxy Program" if it's not specially designed to be used with Vitastor.
For example, Windows OS running in a virtual machine stored in a Vitastor
cluster clearly isn't.
2 weeks ago
Vitaliy Filippov
068f24150a
Begin snapshot test
3 weeks ago
Vitaliy Filippov
b62b88cbba
Fix small memory leak in etcd_state_client
3 weeks ago
Vitaliy Filippov
14569854fa
Fix part bitmap addresses
3 weeks ago
Vitaliy Filippov
f84af76276
Fix several snapshot I/O bugs
3 weeks ago
Vitaliy Filippov
21e093f14e
Fix subop generation for snapshot implementation
3 weeks ago
Vitaliy Filippov
96d68fb3e7
Actual snapshot support (untested)
3 weeks ago
Vitaliy Filippov
c47a973d13
Generate randomly permutated OSD combinations when optimizing for compressed chunks
3 weeks ago
Vitaliy Filippov
88e0d070fe
Report inode I/O statistics, aggregate it in the monitor
1 month ago
Vitaliy Filippov
a9968e167b
Report inode space usage statistics to etcd, aggregate it in the monitor
1 month ago
Vitaliy Filippov
4baee01b0b
Do not break subsequent small writes badly when a big write is canceled
1 month ago
Vitaliy Filippov
9dd6fdddfd
Add inode space usage statistics tracking to blockstore
1 month ago
Vitaliy Filippov
e883084a8b
Mirror afr.js from /vitalif/ceph-afr-calc
1 month ago
Vitaliy Filippov
b980218f17
Send bitmaps with primary-reads, actually read bitmaps for READ ops
1 month ago
Vitaliy Filippov
dae3f8896e
Allocate bitmaps along with stripes to avoid memory fragmentation
1 month ago
Vitaliy Filippov
6f0f92db8c
Remove cryptic bitmap inlining from bs_op_t and osd_op_t, use bitmap in primary OSD code
1 month ago
Vitaliy Filippov
5fc4f19d4d
Add "external" bitmap support to the secondary OSD protocol
1 month ago
Vitaliy Filippov
257360fd7c
Use bitmap granularity for alignment checks
1 month ago
Vitaliy Filippov
d26fa02a7f
Add "external" bitmap support into blockstore
1 month ago
Vitaliy Filippov
ee4827aa35
Add "external" bitmap support to osd_rmw
1 month ago
Vitaliy Filippov
b9e7d31aa1
Release v0.5.4
- Fix a rare hang, more or less reproducible with very slow drives
- Fix a hang with the no_same_sector_overwrites mode
1 day ago
Vitaliy Filippov
2d9f09dcb6
Attempt forced trim when stopping an overrun flusher
Fixes a rare hang happening in the event of journal space running out without
new work to do for flushers except the current sector.
The hang could be reproduced more or less consistently with very slow drives.
1 day ago
Vitaliy Filippov
7cc59260c5
Fix no_same_sector_overwrites related bug
3 days ago
Vitaliy Filippov
ca0a11ec85
Release 0.5.3
3 weeks ago
Vitaliy Filippov
51c0b5afee
Whitelist more leaks
3 weeks ago
Vitaliy Filippov
e1e01d042e
Rename sector_info.usage_count to flush_count
3 weeks ago
Vitaliy Filippov
534a4a657e
Rename space_check.sectors_required to sectors_to_write
3 weeks ago
Vitaliy Filippov
9b5d8b9ad4
Fix multiple-sector journal writes, add assertions to not miss any SQEs
3 weeks ago
Vitaliy Filippov
e66ed47515
Clear SQEs before returning them to the caller to prevent erroneous double submissions
3 weeks ago
Vitaliy Filippov
036c6d4c42
Add a simple test case
3 weeks ago
Vitaliy Filippov
4cb79a3bf8
Allow to calculate simple-offsets for files
3 weeks ago
Vitaliy Filippov
3bf53754c2
Fix several I/O bugs
3 weeks ago