Vitaliy Filippov
97795ea1b1
Use pg_minsize=2 in the pg_count change test
Also don't check for has_degraded because it's not a bug that objects
are _temporarily_ listed as degraded during PG peering as it's not
required for the new primary to connect to _all_ older peers to start
peering. The test may be improved in the future by temporarily disabling
degraded recovery during it and returning the has_degraded check back.
7 months ago
Vitaliy Filippov
24e7075f08
Fix monitor's statistics aggregation
7 months ago
Vitaliy Filippov
6155b23a7e
Replace pgs[id] with pgs.at(id) to prevent accidental auto-vivification
7 months ago
Vitaliy Filippov
7d49706c07
Improve the pg_count change test: add more OSDs and actually move data between them
7 months ago
Vitaliy Filippov
46e79f3306
Wait for PGs to become clean before stopping them
7 months ago
Vitaliy Filippov
41fd14e024
Fix deletes not increasing write_iodepth
7 months ago
Vitaliy Filippov
bb2d9a3afe
Release 0.5.5
- Transition to CMake build system
- Fix Monitor being unable to change PG sizes
- Fix PG optimizer not using some OSDs in some cases
- Fix inability to change PG count online
- Improve journal flusher performance
- Add a little better systemd unit generator
- Use w=8 with jerasure (breaking change for EC pools)
7 months ago
Vitaliy Filippov
e899ed2c25
Make OSDs with 256 flushers (as they are now dynamic)
7 months ago
Vitaliy Filippov
e21b14b72c
Fix rpm specs for building with CMake
7 months ago
Vitaliy Filippov
5af8eddaa9
Add the remaining build script for Debian
7 months ago
Vitaliy Filippov
4f5a94c07a
Modify instructions for the CMake build
7 months ago
Vitaliy Filippov
e16b87ecc8
Rename random_combinations() parameter from "unordered" to "ordered" as it's more correct
7 months ago
Vitaliy Filippov
fcb4aa0a11
Fix Monitor being unable to change PG sizes
7 months ago
Vitaliy Filippov
12adfa470c
Add a test for changing PG size
7 months ago
Vitaliy Filippov
7f15e0c084
Add a simple test for the PG optimizer
7 months ago
Vitaliy Filippov
08d4bef419
Fix PG optimizer removing PGs without adding new ones
This happened when the distribution was already valid for the current OSD tree,
but didn't use all OSDs. For example, OSDs 1 2 3 and all PGs equal to [ 1, 2 ]
remained unchanged.
7 months ago
Vitaliy Filippov
2d73b19a6c
Fix online PG count change bugs
7 months ago
Vitaliy Filippov
69c87009e9
Add a test for changing PG count
7 months ago
Vitaliy Filippov
c974cb539c
Make flusher_count adaptive and limit write iodepth
7 months ago
Vitaliy Filippov
00e98f64f3
A little better systemd unit generator
7 months ago
Vitaliy Filippov
91a70dfb1b
Add a test for the no_same_sector_overwrites mode
7 months ago
Vitaliy Filippov
178388ac8c
Use packages/ subdir instead of build/ for Docker package builds
7 months ago
Vitaliy Filippov
bf9a175efc
Move C/C++ sources to src subdirectory
7 months ago
Vitaliy Filippov
08aed962de
Use CMake
7 months ago
Vitaliy Filippov
8c65e890b9
Slightly clean up the build script
7 months ago
Vitaliy Filippov
8cda70b889
Allow to enable AddressSanitizer with "ASAN=1 make"
7 months ago
Vitaliy Filippov
61ab22403a
Use w=8 with jerasure
7 months ago
Vitaliy Filippov
16da663a66
Add another test for failure domains
7 months ago
Vitaliy Filippov
4a2dcf7b6b
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.
8 months ago
Vitaliy Filippov
8d48cc56b0
Generate randomly permutated OSD combinations when optimizing for compressed chunks
8 months ago
Vitaliy Filippov
9f58f01425
Mirror afr.js from /vitalif/ceph-afr-calc
8 months 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
7 months 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.
7 months ago
Vitaliy Filippov
7cc59260c5
Fix no_same_sector_overwrites related bug
7 months ago
Vitaliy Filippov
ca0a11ec85
Release 0.5.3
8 months ago
Vitaliy Filippov
51c0b5afee
Whitelist more leaks
8 months ago
Vitaliy Filippov
e1e01d042e
Rename sector_info.usage_count to flush_count
8 months ago
Vitaliy Filippov
534a4a657e
Rename space_check.sectors_required to sectors_to_write
8 months ago
Vitaliy Filippov
9b5d8b9ad4
Fix multiple-sector journal writes, add assertions to not miss any SQEs
8 months ago
Vitaliy Filippov
e66ed47515
Clear SQEs before returning them to the caller to prevent erroneous double submissions
8 months ago
Vitaliy Filippov
036c6d4c42
Add a simple test case
8 months ago
Vitaliy Filippov
4cb79a3bf8
Allow to calculate simple-offsets for files
8 months ago
Vitaliy Filippov
3bf53754c2
Fix several I/O bugs
8 months ago
Vitaliy Filippov
6023cac361
Do not stop clients before they are connected
8 months ago
Vitaliy Filippov
915d04c446
Allow empty global configuration, report OSD statistics faster
8 months ago
Vitaliy Filippov
21e06ea40d
Fix memory leaks in fio engines
8 months ago
Vitaliy Filippov
9ef7f865b0
Fix incorrect calls to prepare_journal_sector_write() when flushing multiple sectors
8 months ago
Vitaliy Filippov
9dd20a31aa
Do not use pg_minsize in the client code!
8 months ago
Vitaliy Filippov
28be049909
Dump only actual part of the journal by default
9 months ago
Vitaliy Filippov
78fbaacf1f
External jerasure's w into defines
In fact, w=8 looks better than w=32, so it may be changed in the future
9 months ago
