Tie to task scheduler code to track sleep and try_to_wake_up()Īssuming sleeps cause waits, try_to_wake_up()s would be theĮvents that those are waiting for, of course with proper DEPTĪnnotations, sdt_might_sleep_weak(), sdt_might_sleep_strong()Īnd so on. The stack trace helping find the problematic code is locatedġ. E(event) in each context cannot be triggered because of theĢ. To add any missing tags of wait/event in the kernel.ġ. To use Dept as a dependency engine for Lockdep.Ĥ. To improves performance in terms of time and space.ģ. Deduplication control on multiple reports.Ĩ. Works with wait_for_completion()/complete().ħ. Tracking wait/event rather than lock(?) acquisition order to try toĬover all synchonization machanisms. I've been developing a tool for detecting deadlock possibilities by Just for those who want to try the latest version of DEPT. Rodrigosiqueiramelo, melissa.srw, hamohammed.sa, 42.hyeyoo, Jack, jlayton, dan.j.williams, hch, djwong, dri-devel, Ngupta, linux-block, paolo.valente, josef, linux-fsdevel, viro, v, sj, jglisse, dennis, cl, penberg, rientjes, vbabka, Gregkh, kernel-team, linux-mm, akpm, mhocko, minchan, hannes, Mingo, peterz, will, tglx, rostedt, joel, sashal, daniel.vetter,ĭuyuyang, johannes.berg, tj, tytso, willy, david, amir73il, DEPT(Dependency Tracker) All of help / color / mirror / Atom feed * DEPT(Dependency Tracker) 3:33 ` Byungchul Park 0 siblings, 0 replies 102+ messages in threadįrom: Byungchul Park 3:33 UTC ( / raw)Ĭc: torvalds, damien.lemoal, linux-ide, adilger.kernel, linux-ext4,
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |