Date: Tue, 13 Jul 2021 01:51:00 +0300 From: Vitaliy Gusev <gusev.vitaliy@gmail.com> To: Konstantin Belousov <kostikbel@gmail.com> Cc: freebsd-hackers@freebsd.org, gljennjohn@gmail.com, Mark Johnston <markj@freebsd.org>, Peter Grehan <grehan@freebsd.org> Subject: Re: madvise(MADV_FREE) doesn't work in some cases? Message-ID: <CDBE4678-7FD0-452F-8754-55F8B82A27F9@gmail.com> In-Reply-To: <YOydf9F3ROkXqpDp@kib.kiev.ua> References: <D5749BDF-36B5-4AE9-A75F-2A702DF71F8C@gmail.com> <20210703065420.6dbafb5f@ernst.home> <D542E8C1-4E97-48E8-8748-BBA19B2216EC@gmail.com> <2390FA9B-319E-45D4-BEA7-10878E43AD4B@gmail.com> <YONVgjgqREDAucok@kib.kiev.ua> <2A7A1E60-766D-427B-8288-E92B4090022E@gmail.com> <A3E8A5E9-5912-4358-B384-1FC5847DCBE6@gmail.com> <YOmmicfMXPHQ4eY2@kib.kiev.ua> <4C23FE3C-4FC3-41B2-9A6A-5C267CC0A0E0@gmail.com> <YOydf9F3ROkXqpDp@kib.kiev.ua>
next in thread | previous in thread | raw e-mail | index | archive | help
--Apple-Mail=_EC505346-0E0F-465D-B3B3-FED423966AA0 Content-Transfer-Encoding: quoted-printable Content-Type: text/plain; charset=utf-8 > On 12 Jul 2021, at 22:52, Konstantin Belousov <kostikbel@gmail.com> = wrote: >=20 > On Mon, Jul 12, 2021 at 02:55:37PM +0300, Vitaliy Gusev wrote: >> I guess madvise() should work well even with PAGE_SIZE granularity. = Usually a caller doesn=E2=80=99t need to free the whole region. As I = reported earlier madvise(PAGE_SIZE) works well in Linux and illumos.=20 >>=20 >> Current behaviour in FreeBSD can confuse programmers and brings = impossibility to effectively give back unused memory. Also I have = another case with madvise() but with shared memory that also doesn=E2=80=99= t work (but works in Linux and illumos), will report it in new thread. >>=20 >=20 > I want the confirmation or report that it still did not worked, for = the > case when my latest patch was applied and the test program switched to > the single call to madvise(2) for the whole region. >=20 Understood, checked. Patched kernel with single call of madvise(len, MADV_FREE) from = userspace still doesn=E2=80=99t work. The same condition if = (obj->backing_object !=3D NULL) is met, but once. =E2=80=94=E2=80=94 Vitaliy Gusev > After that, I can claim that the problem is understood and might = consider > some solutions. --Apple-Mail=_EC505346-0E0F-465D-B3B3-FED423966AA0--
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?CDBE4678-7FD0-452F-8754-55F8B82A27F9>