From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Message-ID: <1515443170.3305.73.camel@debian.org> Subject: Re: Feedback on 4.9 performance after PTI fixes From: Yves-Alexis Perez To: Willy Tarreau Cc: linux-kernel@vger.kernel.org, stable@vger.kernel.org Date: Mon, 08 Jan 2018 21:26:10 +0100 In-Reply-To: <20180108182622.GM10913@1wt.eu> References: <20180107101856.GA9590@1wt.eu> <1515431274.3305.59.camel@debian.org> <20180108182622.GM10913@1wt.eu> Content-Type: multipart/signed; micalg="pgp-sha256"; protocol="application/pgp-signature"; boundary="=-C8pS62qYajWFx4WxT1x9" Mime-Version: 1.0 Sender: linux-kernel-owner@vger.kernel.org List-ID: --=-C8pS62qYajWFx4WxT1x9 Content-Type: text/plain; charset="UTF-8" Content-Transfer-Encoding: quoted-printable On Mon, 2018-01-08 at 19:26 +0100, Willy Tarreau wrote: > You're totally right, I discovered during my later developments that > indeed PCID is not exposed there. So we take the hit of a full TLB > flush twice per syscall. So I really think it might make sense to redo the tests with PCID, because = the assumptions you're basing your patch series on might actually not hold. Regards, --=20 Yves-Alexis --=-C8pS62qYajWFx4WxT1x9 Content-Type: application/pgp-signature; name="signature.asc" Content-Description: This is a digitally signed message part -----BEGIN PGP SIGNATURE----- iQEzBAABCAAdFiEE8vi34Qgfo83x35gF3rYcyPpXRFsFAlpT0+IACgkQ3rYcyPpX RFsJrwf/XFK6DvRe3BmRvbL5ARHMoanfhwPqj+xEnuQyc/kXaKhAQ/snhpAlMwcF 1ZOU39Gy9VT9fIQGHT3QvfnrETWqkfFNNQdIUNUD7vpakMi182Dq/dTqdS47aEnR JHHvUsr3xTu6g/saihNIvlvvkBb3u30EAqrJ/eJEb1MtJz/pCV3kPYvm/i9KR+Nn uzhdtTULpdV2MNXWDHs/GncoPzQyXVnTMak9sybDfMSpA3dfjyCNraQpTxBKXdWE 8ZetVNr+ACjJCSvUxt/M176yRO2V4XQKyYivEVKcoaFzu7acadCJv/9kkLUN0Rzo yUH3uyY/4pXgdlLlgM1e13apMOl2FA== =/Soq -----END PGP SIGNATURE----- --=-C8pS62qYajWFx4WxT1x9--