linux-scsi.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Jens Axboe <jens.axboe@oracle.com>
To: "Martin K. Petersen" <martin.petersen@oracle.com>
Cc: John Stoffel <john@stoffel.org>,
	linux-kernel@vger.kernel.org, linux-scsi@vger.kernel.org
Subject: Re: [PATCH 00/33] SG table chaining support
Date: Mon, 16 Jul 2007 16:43:32 +0200	[thread overview]
Message-ID: <20070716144331.GY5195@kernel.dk> (raw)
In-Reply-To: <yq1d4ysv35d.fsf@sermon.lab.mkp.net>

On Mon, Jul 16 2007, Martin K. Petersen wrote:
> >>>>> "John" == John Stoffel <john@stoffel.org> writes:
> 
> John> Will this help out tape drive performance at all?  I looked
> John> through the patches quickly, esp the AIC7xxx stuff since that's
> John> what I use, but nothing jumped out at me...
> 
> Yes.  Most modern tape drives want a block size of 1MB or higher.
> With the old stack we'd be stuck at 512KB because the sg limitations
> caused us to come just short of 1MB...

Indeed. John, note that the driver changes aren't related to enabling
some hardware feature. Drivers just need to be converted to use the sg
walker helpers instead of doing it manually, then they'll also gain
larger IO support. The SCSI drivers are currently being transitioned to
that seperately, my patchset just contains patches for remaining drivers
(which include non-SCSI ones as well).

The hardware has to support a big number of segments of course, looking
at aic7xxx it seems to be limited at 128. From the comment that looks
like it can be increased though, see AHD_NSEG in
drivers/scsi/aic7xxx/aic79xx_osm.h:

/*
 * Number of SG segments we require.  So long as the S/G segments for
 * a particular transaction are allocated in a physically contiguous
 * manner and are allocated below 4GB, the number of S/G segments is
 * unrestricted.
 */
#define AHD_NSEG 128

-- 
Jens Axboe


  reply	other threads:[~2007-07-16 14:44 UTC|newest]

Thread overview: 74+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2007-07-16  9:47 [PATCH 00/33] SG table chaining support Jens Axboe
2007-07-16  9:47 ` [PATCH 01/33] crypto: don't pollute the global namespace with sg_next() Jens Axboe
2007-07-16  9:47 ` [PATCH 02/33] Add sg helpers for iterating over a scatterlist table Jens Axboe
2007-07-16  9:47 ` [PATCH 03/33] block: convert to using sg helpers Jens Axboe
2007-07-16 19:21   ` Bartlomiej Zolnierkiewicz
2007-07-16 19:14     ` Jens Axboe
2007-07-16  9:47 ` [PATCH 04/33] scsi: " Jens Axboe
2007-07-16  9:47 ` [PATCH 05/33] Add chained sg support to linux/scatterlist.h Jens Axboe
2007-07-16 19:21   ` Bartlomiej Zolnierkiewicz
2007-07-16 19:15     ` Jens Axboe
2007-07-16  9:47 ` [PATCH 06/33] i386 dma_map_sg: convert to using sg helpers Jens Axboe
2007-07-16  9:47 ` [PATCH 07/33] i386: enable sg chaining Jens Axboe
2007-07-16  9:47 ` [PATCH 08/33] swiotlb: sg chaining support Jens Axboe
2007-07-16  9:47 ` [PATCH 09/33] x86-64: update iommu/dma mapping functions to sg helpers Jens Axboe
2007-07-16 20:06   ` Andrew Morton
2007-07-16 20:10     ` Jens Axboe
2007-07-16 20:34       ` Andrew Morton
2007-07-16 22:08         ` Muli Ben-Yehuda
2007-07-17  7:38           ` Jens Axboe
2007-07-17  8:49             ` Muli Ben-Yehuda
2007-07-17  8:51               ` Jens Axboe
2007-07-17  9:00                 ` Muli Ben-Yehuda
2007-07-17  7:02         ` Jens Axboe
2007-07-17  7:56           ` Jens Axboe
2007-07-17 11:03   ` Muli Ben-Yehuda
2007-07-17 11:05     ` Jens Axboe
2007-07-17 11:10       ` Muli Ben-Yehuda
2007-07-16  9:47 ` [PATCH 10/33] x86-64: enable sg chaining Jens Axboe
2007-07-16  9:47 ` [PATCH 11/33] IA64: sg chaining support Jens Axboe
2007-07-16  9:47 ` [PATCH 12/33] PPC: " Jens Axboe
2007-07-16  9:47 ` [PATCH 13/33] SPARC: " Jens Axboe
2007-07-16 11:29   ` David Miller
2007-07-16  9:47 ` [PATCH 14/33] SPARC64: " Jens Axboe
2007-07-16 11:29   ` David Miller
2007-07-16  9:47 ` [PATCH 15/33] scsi: simplify scsi_free_sgtable() Jens Axboe
2007-07-16  9:47 ` [PATCH 16/33] SCSI: support for allocating large scatterlists Jens Axboe
2007-07-16  9:47 ` [PATCH 17/33] ll_rw_blk: temporarily enable max_segments tweaking Jens Axboe
2007-07-16  9:47 ` [PATCH 18/33] libata: convert to using sg helpers Jens Axboe
2007-07-16  9:47 ` [PATCH 19/33] scsi_debug: support sg chaining Jens Axboe
2007-09-08 14:53   ` Douglas Gilbert
2007-07-16  9:47 ` [PATCH 20/33] scsi generic: sg chaining support Jens Axboe
2007-07-16  9:47 ` [PATCH 21/33] qla1280: " Jens Axboe
2007-07-16  9:47 ` [PATCH 22/33] aic94xx: " Jens Axboe
2007-07-16  9:47 ` [PATCH 23/33] qlogicpti: " Jens Axboe
2007-07-16  9:47 ` [PATCH 24/33] ide-scsi: " Jens Axboe
2007-07-18 21:03   ` Bartlomiej Zolnierkiewicz
2007-07-16  9:47 ` [PATCH 25/33] gdth: " Jens Axboe
2007-07-16  9:47 ` [PATCH 26/33] aha1542: convert to use the data buffer accessors Jens Axboe
2007-07-16  9:47 ` [PATCH 27/33] advansys: " Jens Axboe
2007-07-16  9:47 ` [PATCH 28/33] ia64 simscsi: convert to use " Jens Axboe
2007-07-16  9:47 ` [PATCH 29/33] infiniband: sg chaining support Jens Axboe
2007-07-16 13:21   ` FUJITA Tomonori
2007-07-16 13:26     ` Jens Axboe
2007-07-16  9:47 ` [PATCH 30/33] USB storage: " Jens Axboe
2007-07-17  6:12   ` Greg KH
2007-07-17  7:01     ` Jens Axboe
2007-07-17  7:05       ` Greg KH
2007-07-17  7:07         ` Jens Axboe
2007-07-16  9:47 ` [PATCH 31/33] Fusion: " Jens Axboe
2007-07-16 13:20   ` FUJITA Tomonori
2007-07-16 13:25     ` Jens Axboe
2007-07-16  9:47 ` [PATCH 32/33] i2o: " Jens Axboe
2007-07-16  9:47 ` [PATCH 33/33] IDE: " Jens Axboe
2007-07-18 20:56   ` Bartlomiej Zolnierkiewicz
2007-07-19  6:19     ` Jens Axboe
2007-07-16 13:19 ` [PATCH 00/33] SG table " FUJITA Tomonori
2007-07-16 13:23   ` Jens Axboe
2007-07-16 13:19 ` FUJITA Tomonori
2007-07-16 13:24   ` Jens Axboe
2007-07-16 14:05 ` John Stoffel
2007-07-16 14:23   ` Martin K. Petersen
2007-07-16 14:43     ` Jens Axboe [this message]
2007-07-16 16:02     ` Kai Makisara
2007-07-16 16:43       ` Jens Axboe

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=20070716144331.GY5195@kernel.dk \
    --to=jens.axboe@oracle.com \
    --cc=john@stoffel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-scsi@vger.kernel.org \
    --cc=martin.petersen@oracle.com \
    /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 a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).