From: Doug Ledford <dledford-H+wXaHxf7aLQT0dZR+AlfA@public.gmane.org>
To: Sagi Grimberg <sagig-VPRAkNaXOzVWk0Htik3J/w@public.gmane.org>
Cc: linux-rdma-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
Subject: Re: [PATCH v1 00/22] iser patches for 4.3
Date: Fri, 14 Aug 2015 21:08:53 -0400 [thread overview]
Message-ID: <55CE9125.1080407@redhat.com> (raw)
In-Reply-To: <1438875186-4310-1-git-send-email-sagig-VPRAkNaXOzVWk0Htik3J/w@public.gmane.org>
[-- Attachment #1: Type: text/plain, Size: 3027 bytes --]
On 08/06/2015 11:32 AM, Sagi Grimberg wrote:
> This set is a resend that includes some extra patches that
> piled up in the meantime.
>
> I still have some patches in the pipe (including initiator/target
> support for remote invalidate) but I'm targeting those to 4.4
>
> I postponed the comment from Steve on using system PAGE_SIZE
> in patch 20 until I have access to a relevant arch to test on.
>
> This patch set includes:
> - Small fixes for bugs encountered in testing
> - Small fixes detected by static checkers
> - Memory registration code path rework (consolidate to
> a single code path that branches only at the actual registration
> FRWR vs. FMR). This reduces code duplication that exists in current code.
> - Larger IO transfer size support (up to 8MB at the moment) depending on
> the device capabilities.
> - Optimize Io path by chaining send work requests and posting them
> only once.
>
> Changes from v0:
> - Added Fixes: tags to patches 4,6
> - Modified change logs for patche 20,22 to add some more details
> (comments from Or)
>
> Adir Lev (1):
> IB/iser: Maintain connection fmr_pool under a single registration
> descriptor
>
> Jenny Falkovich (1):
> IB/iser: Change some module parameters to be RO
>
> Sagi Grimberg (20):
> IB/iser: Change minor assignments and logging prints
> IB/iser: Remove '.' from log message
> IB/iser: Fix missing return status check in iser_send_data_out
> IB/iser: Get rid of un-maintained counters
> IB/iser: Fix possible bogus DMA unmapping
> IB/iser: Remove a redundant always-false condition
> IB/iser: Remove an unneeded print for unaligned memory
> IB/iser: Introduce struct iser_reg_resources
> IB/iser: Rename struct fast_reg_descriptor -> iser_fr_desc
> IB/iser: Remove dead code in fmr_pool alloc/free
> IB/iser: Introduce iser_reg_ops
> IB/iser: Move fastreg descriptor allocation to
> iser_create_fastreg_desc
> IB/iser: Introduce iser registration pool struct
> IB/iser: Rename iser_reg_page_vec to iser_fast_reg_fmr
> IB/iser: Make reg_desc_get a per device routine
> IB/iser: Unify fast memory registration flows
> IB/iser: Pass registration pool a size parameter
> IB/iser: Support up to 8MB data transfer in a single command
> IB/iser: Add debug prints to the various memory registration methods
> IB/iser: Chain all iser transaction send work requests
>
> drivers/infiniband/ulp/iser/iscsi_iser.c | 89 +++--
> drivers/infiniband/ulp/iser/iscsi_iser.h | 206 ++++++++----
> drivers/infiniband/ulp/iser/iser_initiator.c | 34 +-
> drivers/infiniband/ulp/iser/iser_memory.c | 480 +++++++++++++++------------
> drivers/infiniband/ulp/iser/iser_verbs.c | 328 ++++++++++--------
> 5 files changed, 645 insertions(+), 492 deletions(-)
>
I've pulled these in as a replacement for the v0 patches.
--
Doug Ledford <dledford-H+wXaHxf7aLQT0dZR+AlfA@public.gmane.org>
GPG KeyID: 0E572FDD
[-- Attachment #2: OpenPGP digital signature --]
[-- Type: application/pgp-signature, Size: 884 bytes --]
prev parent reply other threads:[~2015-08-15 1:08 UTC|newest]
Thread overview: 24+ messages / expand[flat|nested] mbox.gz Atom feed top
2015-08-06 15:32 [PATCH v1 00/22] iser patches for 4.3 Sagi Grimberg
[not found] ` <1438875186-4310-1-git-send-email-sagig-VPRAkNaXOzVWk0Htik3J/w@public.gmane.org>
2015-08-06 15:32 ` [PATCH v1 01/22] IB/iser: Change some module parameters to be RO Sagi Grimberg
2015-08-06 15:32 ` [PATCH v1 02/22] IB/iser: Change minor assignments and logging prints Sagi Grimberg
2015-08-06 15:32 ` [PATCH v1 03/22] IB/iser: Remove '.' from log message Sagi Grimberg
2015-08-06 15:32 ` [PATCH v1 04/22] IB/iser: Fix missing return status check in iser_send_data_out Sagi Grimberg
2015-08-06 15:32 ` [PATCH v1 05/22] IB/iser: Get rid of un-maintained counters Sagi Grimberg
2015-08-06 15:32 ` [PATCH v1 06/22] IB/iser: Fix possible bogus DMA unmapping Sagi Grimberg
2015-08-06 15:32 ` [PATCH v1 07/22] IB/iser: Remove a redundant always-false condition Sagi Grimberg
2015-08-06 15:32 ` [PATCH v1 08/22] IB/iser: Remove an unneeded print for unaligned memory Sagi Grimberg
2015-08-06 15:32 ` [PATCH v1 09/22] IB/iser: Introduce struct iser_reg_resources Sagi Grimberg
2015-08-06 15:32 ` [PATCH v1 10/22] IB/iser: Rename struct fast_reg_descriptor -> iser_fr_desc Sagi Grimberg
2015-08-06 15:32 ` [PATCH v1 11/22] IB/iser: Remove dead code in fmr_pool alloc/free Sagi Grimberg
2015-08-06 15:32 ` [PATCH v1 12/22] IB/iser: Introduce iser_reg_ops Sagi Grimberg
2015-08-06 15:32 ` [PATCH v1 13/22] IB/iser: Move fastreg descriptor allocation to iser_create_fastreg_desc Sagi Grimberg
2015-08-06 15:32 ` [PATCH v1 14/22] IB/iser: Introduce iser registration pool struct Sagi Grimberg
2015-08-06 15:32 ` [PATCH v1 15/22] IB/iser: Maintain connection fmr_pool under a single registration descriptor Sagi Grimberg
2015-08-06 15:33 ` [PATCH v1 16/22] IB/iser: Rename iser_reg_page_vec to iser_fast_reg_fmr Sagi Grimberg
2015-08-06 15:33 ` [PATCH v1 17/22] IB/iser: Make reg_desc_get a per device routine Sagi Grimberg
2015-08-06 15:33 ` [PATCH v1 18/22] IB/iser: Unify fast memory registration flows Sagi Grimberg
2015-08-06 15:33 ` [PATCH v1 19/22] IB/iser: Pass registration pool a size parameter Sagi Grimberg
2015-08-06 15:33 ` [PATCH v1 20/22] IB/iser: Support up to 8MB data transfer in a single command Sagi Grimberg
2015-08-06 15:33 ` [PATCH v1 21/22] IB/iser: Add debug prints to the various memory registration methods Sagi Grimberg
2015-08-06 15:33 ` [PATCH v1 22/22] IB/iser: Chain all iser transaction send work requests Sagi Grimberg
2015-08-15 1:08 ` Doug Ledford [this message]
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=55CE9125.1080407@redhat.com \
--to=dledford-h+wxahxf7alqt0dzr+alfa@public.gmane.org \
--cc=linux-rdma-u79uwXL29TY76Z2rM5mHXA@public.gmane.org \
--cc=sagig-VPRAkNaXOzVWk0Htik3J/w@public.gmane.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.