Re: [PATCH 2/2] Migrate zone cache from RB-Tree to arrays of descriptors

From: Hannes Reinecke <hare@suse.de>
To: Shaun Tancheff <shaun@tancheff.com>,
	linux-block@vger.kernel.org, linux-scsi@vger.kernel.org,
	linux-kernel@vger.kernel.org
Cc: Jens Axboe <axboe@kernel.dk>, Jens Axboe <axboe@fb.com>,
	Christoph Hellwig <hch@lst.de>,
	"James E . J . Bottomley" <jejb@linux.vnet.ibm.com>,
	"Martin K . Petersen" <martin.petersen@oracle.com>,
	Damien Le Moal <damien.lemoal@hgst.com>,
	Dan Williams <dan.j.williams@intel.com>,
	Sagi Grimberg <sagig@mellanox.com>,
	Mike Christie <mchristi@redhat.com>,
	Ming Lei <ming.lei@canonical.com>,
	Josh Bingaman <josh.bingaman@seagate.com>,
	Shaun Tancheff <shaun.tancheff@seagate.com>
Subject: Re: [PATCH 2/2] Migrate zone cache from RB-Tree to arrays of descriptors
Date: Mon, 22 Aug 2016 09:11:58 +0200	[thread overview]
Message-ID: <ad5c983d-ae7c-bd5b-edef-b56552c3038b@suse.de> (raw)
In-Reply-To: <20160822043402.8855-3-shaun@tancheff.com>

On 08/22/2016 06:34 AM, Shaun Tancheff wrote:
> Currently the RB-Tree zone cache is fast and flexible. It does
> use a rather largish amount of ram. This model reduces the ram
> required from 120 bytes per zone to 16 bytes per zone with a
> moderate transformation of the blk_zone_lookup() api.
> 
> This model is predicated on the belief that most variations
> on zoned media will follow a pattern of using collections of same
> sized zones on a single device. Similar to the pattern of erase
> blocks on flash devices being progressivly larger 16K, 64K, ...
> 
> The goal is to be able to build a descriptor which is both memory
> efficient, performant, and flexible.
> 
> Signed-off-by: Shaun Tancheff <shaun.tancheff@seagate.com>
> ---
>  block/blk-core.c       |    2 +-
>  block/blk-sysfs.c      |   31 +-
>  block/blk-zoned.c      |  103 +++--
>  drivers/scsi/sd.c      |    5 +-
>  drivers/scsi/sd.h      |    4 +-
>  drivers/scsi/sd_zbc.c  | 1025 +++++++++++++++++++++++++++---------------------
>  include/linux/blkdev.h |   82 +++-
>  7 files changed, 716 insertions(+), 536 deletions(-)
> 
Have you measure the performance impact here?
The main idea behind using an RB-tree is that each single element will
fit in the CPU cache; using an array will prevent that.
So we will increase the number of cache flushes, and most likely a
performance penalty, too.
Hence I'd rather like to see a performance measurement here before going
down that road.

Cheers,

Hannes
-- 
Dr. Hannes Reinecke		   Teamlead Storage & Networking
hare@suse.de			               +49 911 74053 688
SUSE LINUX GmbH, Maxfeldstr. 5, 90409 Nï¿½rnberg
GF: F. Imendï¿½rffer, J. Smithard, J. Guild, D. Upmanyu, G. Norton
HRB 21284 (AG Nï¿½rnberg)