Details
-
Bug
-
Status: Closed (View Workflow)
-
Critical
-
Resolution: Won't Fix
-
None
-
2021-7, 2021-8, 2021-9, 2021-10, 2021-11, 2021-12
Description
First pointed out by Quinnstreet, now confirmed by drrtuy. This requires profiling in both releases and identification of where the extra time is eaten.
While it also shows lack of user scaling in both releases, that part is not the focus of this ticket (there is related ticket for that). This one is only about raw difference between releases. drrtuy has the environment and a reproduction.
tail_num is VARCHAR(6). The table's charset is utf8.
In 1.2 tests
root@ip-172-31-23-117:/data/slapit# ./sysbench_series.sh slap4.lua
|
select s from (select count(*) as s from flights group by tail_num)sub;
|
#users Average time
|
1 avg: 133.84
|
2 avg: 141.78
|
3 avg: 175.30
|
4 avg: 215.92
|
5 avg: 251.24
|
6 avg: 281.05
|
7 avg: 327.09
|
8 avg: 366.62
|
9 avg: 411.97
|
10 avg: 456.93
|
11 avg: 506.55
|
in 5.2.2 tests
select s from (select count(*) as s from flights group by tail_num)sub;
|
root@ip-172-31-3-254:/data/slapit# ./sysbench_series.sh slap4.lua
|
1 avg: 381.95
|
2 avg: 284.49
|
3 avg: 336.59
|
4 avg: 427.69
|
5 avg: 527.38
|
6 avg: 622.61
|
7 avg: 720.63
|
8 avg: 830.55
|
9 avg: 927.50
|
10 avg: 1032.59
|
Attachments
Issue Links
- is blocked by
-
MCOL-4791 Fix ColumnCommand fudged data type format to clearly identify CHAR vs VARCHAR
- Stalled
-
MCOL-4801 Replace Row methods getStringLength() and getStringPointer() to getConstString()
- Closed
-
MDEV-26572 Improve simple multibyte collation performance on the ASCII range
- Closed
- relates to
-
MCOL-2000 varchar specified sizing is not in characters
- Closed
-
MCOL-5043 Reduce a number of pre-spawned ExeMgr threads
- Stalled
-
MCOL-5044 Improve PP thread pool with a fair scheduler
- Closed
-
MCOL-4593 Multiple concurrent queries with aggregates are bottlenecked, result in lack of user scalability
- Stalled