From mboxrd@z Thu Jan 1 00:00:00 1970 From: Leon Romanovsky Subject: Re: [PATCH v2 2/2] IB/mlx5: set UMR wqe fence according to HCA cap Date: Mon, 29 May 2017 19:06:09 +0300 Message-ID: <20170529160609.GA17751@mtr-leonro.local> References: <1495957991-19223-1-git-send-email-maxg@mellanox.com> <1495957991-19223-2-git-send-email-maxg@mellanox.com> <20170528090705.GM13083@lst.de> <19a1d347-91da-7e5f-8877-86772204a80a@mellanox.com> <20170529100504.GZ17751@mtr-leonro.local> <89409b6d-466d-070a-7082-1f7bbb9ad7c7@mellanox.com> Mime-Version: 1.0 Content-Type: multipart/signed; micalg=pgp-sha256; protocol="application/pgp-signature"; boundary="D2rVImvqWGvKULsk" Return-path: Content-Disposition: inline In-Reply-To: <89409b6d-466d-070a-7082-1f7bbb9ad7c7-VPRAkNaXOzVWk0Htik3J/w@public.gmane.org> Sender: linux-rdma-owner-u79uwXL29TY76Z2rM5mHXA@public.gmane.org To: Max Gurtovoy Cc: Christoph Hellwig , linux-nvme-IAPFreCvJWM7uuMidbF8XUB+6BGkLq7r@public.gmane.org, sagi-NQWnxTmZq1alnMjI0IkVqw@public.gmane.org, linux-rdma-u79uwXL29TY76Z2rM5mHXA@public.gmane.org, shahar.salzman-Re5JQEeQqe8AvxtiuMwx3w@public.gmane.org, joseph.r.gruher-ral2JQCrhuEAvxtiuMwx3w@public.gmane.org, mrybczyn-FNhOzJFKnXGHXe+LvDLADg@public.gmane.org, vladimirk-VPRAkNaXOzVWk0Htik3J/w@public.gmane.org, oren-VPRAkNaXOzVWk0Htik3J/w@public.gmane.org List-Id: linux-rdma@vger.kernel.org --D2rVImvqWGvKULsk Content-Type: text/plain; charset=us-ascii Content-Disposition: inline On Mon, May 29, 2017 at 03:21:11PM +0300, Max Gurtovoy wrote: > > > On 5/29/2017 1:05 PM, Leon Romanovsky wrote: > > On Sun, May 28, 2017 at 12:53:00PM +0300, Max Gurtovoy wrote: > > > > > > > > > On 5/28/2017 12:07 PM, Christoph Hellwig wrote: > > > > On Sun, May 28, 2017 at 10:53:11AM +0300, Max Gurtovoy wrote: > > > > > Cache the needed umr_fence and set the wqe ctrl segmennt > > > > > accordingly. > > > > > > > > Looks good, > > > > > > > > Reviewed-by: Christoph Hellwig > > > > > > Thanks. > > > > > > > > > > > But that whole fence logic looks awkward to me. Does the following > > > > patch to reorder it make sense to you? > > > > > > > > > > > > > Yes it make sense to me. > > > Sagi/Leon, any comments ? > > > > Max, > > > > Do you see any performance impact for IB_WR_RDMA_READ, IB_WR_RDMA_WRITE > > and IB_WR_RDMA_WRITE_WITH_IMM flows? They don't need fences and such > > change can cause to performance losses. > > > > Thanks > > > > We don't fence those WR's. > Christoph just re-write it to be more intuitive code. I don't see logic > difference, am I wrong here ? A little bit, before Christoph's suggestion, we calculated fence for the paths which need such fence, after we will calculate for all paths. Thanks > > > > > > > > > > > > -- > > > To unsubscribe from this list: send the line "unsubscribe linux-rdma" in > > > the body of a message to majordomo-u79uwXL29TY76Z2rM5mHXA@public.gmane.org > > > More majordomo info at http://vger.kernel.org/majordomo-info.html --D2rVImvqWGvKULsk Content-Type: application/pgp-signature; name="signature.asc" -----BEGIN PGP SIGNATURE----- iQIzBAEBCAAdFiEEkhr/r4Op1/04yqaB5GN7iDZyWKcFAlksRvEACgkQ5GN7iDZy WKdlmg/+MHYdGiUaypLVniOkHEDa6tbW590y8/uWHLbEIqSOySKGhH5zZghQR3sV oFsYIBKYrD8Dmdegr15aNykVfsBKp2//n+4cK1/T0KPlc5O/RRvhFXYPaTkqf7gT 6R0jng/LohV2d2gjiKSWkJCZUApC7UveM9VI/XYt4wf4DcW86liDVbOnzGJRm/sb 5hjQ6V2tX/TafJdBw6jO5uVNlpOTEv7y75U3JJJgc+1b2iMHkgxK0g0HNnms6Iji TcJ79aZv0r8BdMDBx3PzAB7rn3X5Pl36IfC6tSAFVlP5hpcBGN5UBfrdSXtuvkLV Kmuf6BWS+5md/7rIul/gxO5/uUFs+UB8FfZsDv4pslSJvDVuBdoId0K0OLUWjJuf hhghD5BECww71ief5LByPtLooMAYnsiCqgveXlW4Tc47BRSNH2thRvtge0dkVvJc wshZK4+x1dFv+EC2MeTPK1JctWkh0miG0UHo4G9tUcYIWtDahkCe6WP2Dh9HkIIO jc9gKFWzGCtHueqS3cG0+qAPbkZNcsdJHqRke6+WZXeOE6BnMoQqOhA8pWNKFxxp L7dqisnU2LU06CbED7gO/h6NNlKM0ZVLpJQlOGixqUR96BGDZuVvAkwUFZE76N+e FXCRbLbhLSUnBnWtb1I6VREcL+dSqeauWHVfDZLv3ThZ5/D+aZM= =ZOuv -----END PGP SIGNATURE----- --D2rVImvqWGvKULsk-- -- To unsubscribe from this list: send the line "unsubscribe linux-rdma" in the body of a message to majordomo-u79uwXL29TY76Z2rM5mHXA@public.gmane.org More majordomo info at http://vger.kernel.org/majordomo-info.html