FreeBSD source tree https://cgit-dev.freebsd.org/src-test/atom?h=main 2020-09-01T22:12:32Z 2020-09-01T22:12:32Z Mateusz Guzik mjg@FreeBSD.org 2020-09-01T22:12:32Z urn:sha1:6fed89b17970606e6b9562d8f9dc7ffee732839c 2020-02-26T14:26:36Z Pawel Biernacki kaktus@FreeBSD.org 2020-02-26T14:26:36Z urn:sha1:7029da5c36f2d3cf6bb6c81bf551229f416399e8 r357614 added CTLFLAG_NEEDGIANT to make it easier to find nodes that are still not MPSAFE (or already are but aren’t properly marked). Use it in preparation for a general review of all nodes. This is non-functional change that adds annotations to SYSCTL_NODE and SYSCTL_PROC nodes using one of the soon-to-be-required flags. Mark all obvious cases as MPSAFE. All entries that haven't been marked as MPSAFE before are by default marked as NEEDGIANT Approved by: kib (mentor, blanket) Commented by: kib, gallatin, melifaro Differential Revision: https://reviews.freebsd.org/D23718 2020-01-05T12:48:19Z Mateusz Guzik mjg@FreeBSD.org 2020-01-05T12:48:19Z urn:sha1:2e77cad11dc5ec9c14c074dfc127f8420075aa7c Use it for all primitives. This makes everything fit in 8 bytes. 2020-01-05T12:47:29Z Mateusz Guzik mjg@FreeBSD.org 2020-01-05T12:47:29Z urn:sha1:6b8dd26e7c5f2caf9e5094d6fa15d8edcace65a0 int is just a waste of space for this purpose. 2019-11-30T17:24:42Z Mateusz Guzik mjg@FreeBSD.org 2019-11-30T17:24:42Z urn:sha1:3ac2ac2e085ac3be61caddc3ec9982443e641c4b The previously used quiesce_all_cpus walks all CPUs and waits until curthread can run on them. Even on contemporary machines this becomes a significant problem under load when it can literally take minutes for the operation to complete. With the patch the stall is normally less than 1 second. Reviewed by: kib, jeff (previous version) Sponsored by: The FreeBSD Foundation Differential Revision: https://reviews.freebsd.org/D21740 2019-09-22T20:44:24Z Mateusz Guzik mjg@FreeBSD.org 2019-09-22T20:44:24Z urn:sha1:d2be3ef05c1fbcd66e9554f513e9f6816f56de6e Reviewed by: kib Sponsored by: The FreeBSD Foundation Differential Revision: https://reviews.freebsd.org/D21747 2019-09-21T19:05:38Z Mateusz Guzik mjg@FreeBSD.org 2019-09-21T19:05:38Z urn:sha1:cbba2cb367c2e8ebbf99b9e74a96fa1501f70093 Sponsored by: The FreeBSD Foundation 2019-03-06T22:11:45Z John Baldwin jhb@FreeBSD.org 2019-03-06T22:11:45Z urn:sha1:2e43efd0bb1e9cd780f02fa5b888f9264e66e37b Reviewed by: rgrimes MFC after: 1 month Differential Revision: https://reviews.freebsd.org/D19485 2018-04-08T16:34:10Z Mateusz Guzik mjg@FreeBSD.org 2018-04-08T16:34:10Z urn:sha1:a045941bd2a73aafd6755461e61cd6a6e963f670 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. 2017-11-27T15:20:12Z Pedro F. Giffuni pfg@FreeBSD.org 2017-11-27T15:20:12Z urn:sha1:8a36da99deb0e19363ec04e4d3facd869c1028f5 Mainly focus on files that use BSD 2-Clause license, however the tool I was using misidentified many licenses so this was mostly a manual - error prone - task. The Software Package Data Exchange (SPDX) group provides a specification to make it easier for automated tools to detect and summarize well known opensource licenses. We are gradually adopting the specification, noting that the tags are considered only advisory and do not, in any way, superceed or replace the license texts.