* refactor: use var accross the Makefile instead of sledgert string
* refactor bash libraries
- remove hash symbol for scv_to_dat
- add set_print_pretty for gdb mode
- add logging for client
- change printf format for perf log in table from float to int since usec
* cleanup: generalize redundant files in the experiments:
- remove individual gitignore, have single gitignore in parent (tests)
- remove individual env files, have single copies in 'common' dir
- remove individual install.sh, have install_tools.sh (in bash libs)
* - add comment into install_tools.sh
- rename mts to mtds
* update the env files dir to common
* move multi-tenancy env files to another directory (temp)
* apply the deferable server to the new master
* add the deferrable server env file to github CI test
* clang-format
* add deferable server attributes to all experiment specs
* remove previously added generic interface that was only for Def Serv
* Accomodated important changes Sean requested:
- remove unnecessary assertions from pri_queue.h
- set the runtime queue size to MAX_TENANT
- add the scheduler updates back to the sandbox_interrupt state transition
This experiment drives a bimodal distribution of long-running low-priority and short-running high-priority workloads
Relative Deadlines are tuned such that the scheduler should always preempt the low-priority workload for the high-priority workload if preemption is disabled.
The two workloads are run separately as a baseline. They are then run concurrently, starting the low-priority long-running workload first such that the system begins execution and accumulates requests in the data structures. The high-priority short-running workload then begins.