From: Chaitanya Kulkarni <kch@nvidia.com>
To: <minchan@kernel.org>, <senozhatsky@chromium.org>
Cc: <axboe@kernel.dk>, <linux-block@vger.kernel.org>,
Chaitanya Kulkarni <kch@nvidia.com>
Subject: [PATCH 1/3] zram: allow user to set QUEUE_FLAG_NOWAIT
Date: Fri, 12 May 2023 01:29:56 -0700 [thread overview]
Message-ID: <20230512082958.6550-2-kch@nvidia.com> (raw)
In-Reply-To: <20230512082958.6550-1-kch@nvidia.com>
Allow user to set the QUEUE_FLAG_NOWAIT optionally using module
parameter to retain the default behaviour. Also, update respective
allocation flags in the write path. Following are the performance
numbers with io_uring fio engine for random read, note that device has
been populated fully with randwrite workload before taking these
numbers :-
* linux-block (for-next) # grep IOPS zram*fio | column -t
default-nowait-off-1.fio: read: IOPS=802k, BW=3133MiB/s
default-nowait-off-2.fio: read: IOPS=796k, BW=3111MiB/s
default-nowait-off-3.fio: read: IOPS=796k, BW=3108MiB/s
nowait-on-1.fio: read: IOPS=857k, BW=3346MiB/s
nowait-on-2.fio: read: IOPS=857k, BW=3347MiB/s
nowait-on-3.fio: read: IOPS=858k, BW=3353MiB/s
* linux-block (for-next) # grep cpu zram*fio | column -t
default-nowait-off-1.fio: cpu : usr=5.82%, sys=13.54%, ctx=36301915
default-nowait-off-2.fio: cpu : usr=5.84%, sys=13.03%, ctx=37781937
default-nowait-off-3.fio: cpu : usr=5.84%, sys=12.90%, ctx=37492533
nowait-on-1.fio: cpu : usr=1.74%, sys=97.62%, ctx=24068,
nowait-on-2.fio: cpu : usr=1.74%, sys=97.57%, ctx=24674,
nowait-on-3.fio: cpu : usr=1.76%, sys=97.59%, ctx=24725,
Signed-off-by: Chaitanya Kulkarni <kch@nvidia.com>
---
drivers/block/zram/zram_drv.c | 9 ++++++++-
1 file changed, 8 insertions(+), 1 deletion(-)
diff --git a/drivers/block/zram/zram_drv.c b/drivers/block/zram/zram_drv.c
index f6d90f1ba5cf..b2e419f15f71 100644
--- a/drivers/block/zram/zram_drv.c
+++ b/drivers/block/zram/zram_drv.c
@@ -36,6 +36,10 @@
#include "zram_drv.h"
+static bool g_nowait;
+module_param_named(nowait, g_nowait, bool, 0444);
+MODULE_PARM_DESC(nowait, "set QUEUE_FLAG_NOWAIT. Default: False");
+
static DEFINE_IDR(zram_index_idr);
/* idr index must be protected */
static DEFINE_MUTEX(zram_index_mutex);
@@ -1540,9 +1544,10 @@ static int zram_write_page(struct zram *zram, struct page *page, u32 index)
static int zram_bvec_write_partial(struct zram *zram, struct bio_vec *bvec,
u32 index, int offset, struct bio *bio)
{
- struct page *page = alloc_page(GFP_NOIO);
+ struct page *page;
int ret;
+ page = alloc_page(bio->bi_opf & REQ_NOWAIT ? GFP_NOWAIT : GFP_NOIO);
if (!page)
return -ENOMEM;
@@ -2215,6 +2220,8 @@ static int zram_add(void)
/* zram devices sort of resembles non-rotational disks */
blk_queue_flag_set(QUEUE_FLAG_NONROT, zram->disk->queue);
blk_queue_flag_set(QUEUE_FLAG_SYNCHRONOUS, zram->disk->queue);
+ if (g_nowait)
+ blk_queue_flag_set(QUEUE_FLAG_NOWAIT, zram->disk->queue);
/*
* To ensure that we always get PAGE_SIZE aligned
--
2.40.0
next prev parent reply other threads:[~2023-05-12 8:30 UTC|newest]
Thread overview: 17+ messages / expand[flat|nested] mbox.gz Atom feed top
2023-05-12 8:29 [PATCH 0/3] zram: queue flag nowait and mior cleanup Chaitanya Kulkarni
2023-05-12 8:29 ` Chaitanya Kulkarni [this message]
2023-05-12 14:31 ` [PATCH 1/3] zram: allow user to set QUEUE_FLAG_NOWAIT Christoph Hellwig
2023-05-12 14:34 ` Jens Axboe
2023-05-13 1:06 ` Chaitanya Kulkarni
2023-05-16 5:51 ` Chaitanya Kulkarni
2023-05-16 13:08 ` Sergey Senozhatsky
2023-05-16 20:41 ` Chaitanya Kulkarni
2023-05-16 20:43 ` Jens Axboe
2023-05-16 21:32 ` Chaitanya Kulkarni
2023-05-16 22:03 ` Jens Axboe
2023-05-13 1:05 ` Chaitanya Kulkarni
2023-05-12 8:29 ` [PATCH 2/3] zram: consolidate zram_bio_read()_zram_bio_write() Chaitanya Kulkarni
2023-05-12 14:32 ` Christoph Hellwig
2023-05-13 1:06 ` Chaitanya Kulkarni
2023-05-12 8:29 ` [PATCH 3/3] zram: add flush_dcache_page() call for write Chaitanya Kulkarni
2023-05-12 14:34 ` Christoph Hellwig
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=20230512082958.6550-2-kch@nvidia.com \
--to=kch@nvidia.com \
--cc=axboe@kernel.dk \
--cc=linux-block@vger.kernel.org \
--cc=minchan@kernel.org \
--cc=senozhatsky@chromium.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 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).