* feature: added SJF scheduler
added REGRESSION based prediction support
* fix: error handling
* fixed the default values for def.server when not given
* fix: replace GET by POST for hey requests (fix by Xioasu)
* - update .clang-format props to match composite (almost)
- reformat C codes in the repo
- refactor the format.sh script
- fetch latest AWSM master
* Addressed Gabe's comments
* error handling for when model_scale and model_beta2 is zero
* fix the multi-tenantcy-predictions run.sh script
* - upgraded to LLVM_VERSION=13 both on sledge & AWSM
- updated dockerfile, main.yaml
- added new uninstall_llvm.sh script to ease LLVM removal
* 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
Emil
Sean McBride