From: "Matias Bjørling" <mb@lightnvm.io>
To: Chaitanya Kulkarni <Chaitanya.Kulkarni@wdc.com>,
Bart Van Assche <bvanassche@acm.org>,
"axboe@fb.com" <axboe@fb.com>, "hch@lst.de" <hch@lst.de>,
Damien Le Moal <Damien.LeMoal@wdc.com>,
Dmitry Fomichev <Dmitry.Fomichev@wdc.com>,
Ajay Joshi <Ajay.Joshi@wdc.com>,
Aravind Ramesh <Aravind.Ramesh@wdc.com>,
"martin.petersen@oracle.com" <martin.petersen@oracle.com>,
"James.Bottomley@HansenPartnership.com"
<James.Bottomley@HansenPartnership.com>,
"agk@redhat.com" <agk@redhat.com>,
"snitzer@redhat.com" <snitzer@redhat.com>
Cc: "linux-block@vger.kernel.org" <linux-block@vger.kernel.org>,
"linux-kernel@vger.kernel.org" <linux-kernel@vger.kernel.org>,
"linux-scsi@vger.kernel.org" <linux-scsi@vger.kernel.org>,
"dm-devel@redhat.com" <dm-devel@redhat.com>,
Matias Bjorling <Matias.Bjorling@wdc.com>
Subject: Re: [PATCH 1/4] block: add zone open, close and finish support
Date: Tue, 25 Jun 2019 12:35:01 +0200 [thread overview]
Message-ID: <cce08df0-0b4d-833d-64ce-f9b81f7ad7ca@lightnvm.io> (raw)
In-Reply-To: <BYAPR04MB5749CEFBB45EA34BD3345CD686E00@BYAPR04MB5749.namprd04.prod.outlook.com>
On 6/25/19 12:27 AM, Chaitanya Kulkarni wrote:
> On 6/24/19 12:43 PM, Bart Van Assche wrote:
>> On 6/21/19 6:07 AM, Matias Bjørling wrote:
>>> diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h
>>> index 95202f80676c..067ef9242275 100644
>>> --- a/include/linux/blk_types.h
>>> +++ b/include/linux/blk_types.h
>>> @@ -284,13 +284,20 @@ enum req_opf {
>>> REQ_OP_DISCARD = 3,
>>> /* securely erase sectors */
>>> REQ_OP_SECURE_ERASE = 5,
>>> - /* reset a zone write pointer */
>>> - REQ_OP_ZONE_RESET = 6,
>>> /* write the same sector many times */
>>> REQ_OP_WRITE_SAME = 7,
>>> /* write the zero filled sector many times */
>>> REQ_OP_WRITE_ZEROES = 9,
>>>
>>> + /* reset a zone write pointer */
>>> + REQ_OP_ZONE_RESET = 16,
>>> + /* Open zone(s) */
>>> + REQ_OP_ZONE_OPEN = 17,
>>> + /* Close zone(s) */
>>> + REQ_OP_ZONE_CLOSE = 18,
>>> + /* Finish zone(s) */
>>> + REQ_OP_ZONE_FINISH = 19,
>>> +
>>> /* SCSI passthrough using struct scsi_request */
>>> REQ_OP_SCSI_IN = 32,
>>> REQ_OP_SCSI_OUT = 33,
>>> @@ -375,6 +382,22 @@ static inline void bio_set_op_attrs(struct bio *bio, unsigned op,
>>> bio->bi_opf = op | op_flags;
>>> }
>>
>> Are the new operation types ever passed to op_is_write()? The definition
>> of that function is as follows:
>>
> May be we should change numbering since blktrace also relies on the
> having on_is_write() without looking at the rq_ops().
>
> 197 * Data direction bit lookup
> 198 */
> 199 static const u32 ddir_act[2] = { BLK_TC_ACT(BLK_TC_READ),
> 200 BLK_TC_ACT(BLK_TC_WRITE) }; <----
> 201
> 202 #define BLK_TC_RAHEAD BLK_TC_AHEAD
> 203 #define BLK_TC_PREFLUSH BLK_TC_FLUSH
> 204
> 205 /* The ilog2() calls fall out because they're constant */
> 206 #define MASK_TC_BIT(rw, __name) ((rw & REQ_ ## __name) << \
> 207 (ilog2(BLK_TC_ ## __name) + BLK_TC_SHIFT - __REQ_ ##
> __name))
> 208
> 209 /*
> 210 * The worker for the various blk_add_trace*() types. Fills out a
> 211 * blk_io_trace structure and places it in a per-cpu subbuffer.
> 212 */
> 213 static void __blk_add_trace(struct blk_trace *bt, sector_t sector,
> int bytes,
> 214 int op, int op_flags, u32 what, int error,
> int pdu_len,
> 215 void *pdu_data, union kernfs_node_id *cgid)
> 216 {
> 217 struct task_struct *tsk = current;
> 218 struct ring_buffer_event *event = NULL;
> 219 struct ring_buffer *buffer = NULL;
> 220 struct blk_io_trace *t;
> 221 unsigned long flags = 0;
> 222 unsigned long *sequence;
> 223 pid_t pid;
> 224 int cpu, pc = 0;
> 225 bool blk_tracer = blk_tracer_enabled;
> 226 ssize_t cgid_len = cgid ? sizeof(*cgid) : 0;
> 227
> 228 if (unlikely(bt->trace_state != Blktrace_running &&
> !blk_tracer))
> 229 return;
> 230
> 231 what |= ddir_act[op_is_write(op) ? WRITE : READ]; <---
>
>
>> static inline bool op_is_write(unsigned int op)
>> {
>> return (op & 1);
>> }
>>
>
The zone mgmt commands are neither write nor reads commands. I guess,
one could characterize them as write commands, but they don't write any
data, they update a state of a zone on a drive. One should keep it as
is? and make sure the zone mgmt commands don't get categorized as either
read/write.
next prev parent reply other threads:[~2019-06-25 10:35 UTC|newest]
Thread overview: 25+ messages / expand[flat|nested] mbox.gz Atom feed top
2019-06-21 13:07 [PATCH 0/4] open, close, finish zone support Matias Bjørling
2019-06-21 13:07 ` [PATCH 1/4] block: add zone open, close and finish support Matias Bjørling
2019-06-22 0:51 ` Damien Le Moal
2019-06-24 10:36 ` Matias Bjørling
2019-06-22 6:04 ` Minwoo Im
2019-06-24 19:43 ` Bart Van Assche
2019-06-24 22:27 ` Chaitanya Kulkarni
2019-06-25 10:35 ` Matias Bjørling [this message]
2019-06-25 15:55 ` Bart Van Assche
2019-06-25 16:30 ` Javier González
2019-06-25 16:51 ` Chaitanya Kulkarni
2019-06-25 16:53 ` Matias Bjørling
2019-06-26 0:44 ` Damien Le Moal
2019-06-26 0:42 ` Damien Le Moal
2019-06-21 13:07 ` [PATCH 2/4] null_blk: add zone open, close, " Matias Bjørling
2019-06-22 1:02 ` Damien Le Moal
2019-06-25 11:06 ` Matias Bjørling
2019-06-25 12:36 ` Damien Le Moal
2019-06-25 13:03 ` Matias Bjørling
2019-06-21 13:07 ` [PATCH 3/4] scsi: sd_zbc: " Matias Bjørling
2019-06-22 1:12 ` Damien Le Moal
2019-06-24 19:46 ` Bart Van Assche
2019-06-25 10:32 ` Matias Bjørling
2019-06-21 13:07 ` [PATCH 4/4] dm: add zone open, close " Matias Bjørling
2019-06-22 1:15 ` Damien Le Moal
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=cce08df0-0b4d-833d-64ce-f9b81f7ad7ca@lightnvm.io \
--to=mb@lightnvm.io \
--cc=Ajay.Joshi@wdc.com \
--cc=Aravind.Ramesh@wdc.com \
--cc=Chaitanya.Kulkarni@wdc.com \
--cc=Damien.LeMoal@wdc.com \
--cc=Dmitry.Fomichev@wdc.com \
--cc=James.Bottomley@HansenPartnership.com \
--cc=Matias.Bjorling@wdc.com \
--cc=agk@redhat.com \
--cc=axboe@fb.com \
--cc=bvanassche@acm.org \
--cc=dm-devel@redhat.com \
--cc=hch@lst.de \
--cc=linux-block@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-scsi@vger.kernel.org \
--cc=martin.petersen@oracle.com \
--cc=snitzer@redhat.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).