Date: Sun, 8 Apr 2018 16:34:10 +0000 (UTC) From: Mateusz Guzik <mjg@FreeBSD.org> To: src-committers@freebsd.org, svn-src-all@freebsd.org, svn-src-head@freebsd.org Subject: svn commit: r332285 - head/sys/kern Message-ID: <201804081634.w38GYA8N097150@repo.freebsd.org>
next in thread | raw e-mail | index | archive | help
Author: mjg Date: Sun Apr 8 16:34:10 2018 New Revision: 332285 URL: https://svnweb.freebsd.org/changeset/base/332285 Log: locks: tweak backoff a little bit Previous limits were chosen when locking primitives had spurious lock accesses. Flipping the starting point to 1 (or rather 2 as the first call shifts it) provides a modest win when mild contention is seen while not hurting worse cases. Tested on a bunch of one, two and four socket old and new systems (Westmere, Skylake, Threadreaper and others) by doing concurrent page faults, buildkernel/buildworld and other stuff (although not all systems got all the tests). Another thing is the upper limit. It is semi-arbitrarily chosen as it was getting out of hand for slightly less small systems (e.g. a 128-thread one). Note that backoff is fundamentally a speculative bandaid and this change just makes it fit a little bit better. It remains completely oblivious to the hardware topology or the contention pattern. This is being experimented with. Modified: head/sys/kern/subr_lock.c Modified: head/sys/kern/subr_lock.c ============================================================================== --- head/sys/kern/subr_lock.c Sun Apr 8 16:29:24 2018 (r332284) +++ head/sys/kern/subr_lock.c Sun Apr 8 16:34:10 2018 (r332285) @@ -156,8 +156,10 @@ void lock_delay_default_init(struct lock_delay_config *lc) { - lc->base = lock_roundup_2(mp_ncpus) / 4; - lc->max = lc->base * 1024; + lc->base = 1; + lc->max = lock_roundup_2(mp_ncpus) * 256; + if (lc->max > 32678) + lc->max = 32678; } #ifdef DDB
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?201804081634.w38GYA8N097150>