Details
Major Description
To execute any command, a THD needs to be "attached" to the OS thread, which means, that
some variables in THD needs to be reset. This includes :
- set_current_thd() TLS variable, to thd
- mysys_var TLS variable., to thd->mysys_var
- THD::thread_stack and mysys_var.stack_ends_here
- THD::thread_id (pthread_self) "for debugging"
- os_thread_id (Linux only) - to be shown in SHOW PROCESSLIST. That's a system call
- some PFS thread local storage
Some of that is expensive, when run millions of times, specifically, getting the os_thread_id on Linux is a system call. pthread_self, while not as expensive is still a library call.
Also, current code used in THD::store_globals does a lot more currently, than it should do for threadpool, making thread_attach() on Linux about half as expensive as the inevitable epoll_ctl().
For simple commands like "do 1", thread_attaching can take as much as about 7% of the query execution overhead (excluding network IO)
Attachments
Activity
| Field | Original Value | New Value |
|---|---|---|
| Description |
To execute any command, a THD needs to be "attached" to the OS thread, which means, that
some variables in THD needs to be reset. This includes : * set_current_thd() TLS variable, to thd * mysys_var TLS variable. to thd->mysys_var * THD::thread_stack and mysys_var.stack_ends_here * THD::thread_id (pthread_self) "for debugging" * os_thread_id (Linux only) - to be shown in SHOW PROCESSLIST. That's a system call * some PFS thread local storage set and read from Some of that is expensive, when run millions of times, specifically, getting the os_thread_id on Linux is a system call. pthread_self, while not as expensive is still a library call. Also, current code used in THD::store_globals does a lot more currently, than it should do for threadpool, making thread_attach() on Linux about half as expensive as the inevitable epoll_ctl(). For simple commands like "do 1", thread_attaching can take as much as about 7% of the query execution overhead (excluding network IO) |
To execute any command, a THD needs to be "attached" to the OS thread, which means, that
some variables in THD needs to be reset. This includes : * set_current_thd() TLS variable, to thd * mysys_var TLS variable., to thd->mysys_var * THD::thread_stack and mysys_var.stack_ends_here * THD::thread_id (pthread_self) "for debugging" * os_thread_id (Linux only) - to be shown in SHOW PROCESSLIST. That's a system call * some PFS thread local storage * Some of that is expensive, when run millions of times, specifically, getting the os_thread_id on Linux is a system call. pthread_self, while not as expensive is still a library call. Also, current code used in THD::store_globals does a lot more currently, than it should do for threadpool, making thread_attach() on Linux about half as expensive as the inevitable epoll_ctl(). For simple commands like "do 1", thread_attaching can take as much as about 7% of the query execution overhead (excluding network IO) |
| Description |
To execute any command, a THD needs to be "attached" to the OS thread, which means, that
some variables in THD needs to be reset. This includes : * set_current_thd() TLS variable, to thd * mysys_var TLS variable., to thd->mysys_var * THD::thread_stack and mysys_var.stack_ends_here * THD::thread_id (pthread_self) "for debugging" * os_thread_id (Linux only) - to be shown in SHOW PROCESSLIST. That's a system call * some PFS thread local storage * Some of that is expensive, when run millions of times, specifically, getting the os_thread_id on Linux is a system call. pthread_self, while not as expensive is still a library call. Also, current code used in THD::store_globals does a lot more currently, than it should do for threadpool, making thread_attach() on Linux about half as expensive as the inevitable epoll_ctl(). For simple commands like "do 1", thread_attaching can take as much as about 7% of the query execution overhead (excluding network IO) |
To execute any command, a THD needs to be "attached" to the OS thread, which means, that
some variables in THD needs to be reset. This includes : * set_current_thd() TLS variable, to thd * mysys_var TLS variable., to thd->mysys_var * THD::thread_stack and mysys_var.stack_ends_here * THD::thread_id (pthread_self) "for debugging" * os_thread_id (Linux only) - to be shown in SHOW PROCESSLIST. That's a system call * some PFS thread local storage Some of that is expensive, when run millions of times, specifically, getting the os_thread_id on Linux is a system call. pthread_self, while not as expensive is still a library call. Also, current code used in THD::store_globals does a lot more currently, than it should do for threadpool, making thread_attach() on Linux about half as expensive as the inevitable epoll_ctl(). For simple commands like "do 1", thread_attaching can take as much as about 7% of the query execution overhead (excluding network IO) |
| Priority | Minor [ 4 ] | Major [ 3 ] |
| Status | Open [ 1 ] | In Progress [ 3 ] |
| issue.field.resolutiondate | 2022-10-11 06:53:29.0 | 2022-10-11 06:53:29.404 |
| Fix Version/s | 10.6.11 [ 28441 ] | |
| Fix Version/s | 10.7.7 [ 28442 ] | |
| Fix Version/s | 10.8.6 [ 28443 ] | |
| Fix Version/s | 10.9.4 [ 28444 ] | |
| Fix Version/s | 10.10.2 [ 28410 ] | |
| Fix Version/s | 10.6 [ 24028 ] | |
| Resolution | Fixed [ 1 ] | |
| Status | In Progress [ 3 ] | Closed [ 6 ] |