From: Richard Weinberger <richard@nod.at>
To: Andrea Scian <rnd4@dave-tech.it>
Cc: boris.brezillon@free-electrons.com,
linux-mtd@lists.infradead.org, linux-kernel@vger.kernel.org,
dedekind1@gmail.com
Subject: Re: [PATCH 4/4] UBI: Implement bitrot checking
Date: Thu, 02 Apr 2015 19:54:21 +0200 [thread overview]
Message-ID: <551D824D.3000004@nod.at> (raw)
In-Reply-To: <551D7DB4.9010607@dave-tech.it>
Hi!
Am 02.04.2015 um 19:34 schrieb Andrea Scian:
>
> Richard,
>
> Il 29/03/2015 14:13, Richard Weinberger ha scritto:
>> + mutex_lock(&ubi->buf_mutex);
>> + err = ubi_io_read(ubi, ubi->peb_buf, e->pnum, 0, ubi->peb_size);
>> + mutex_unlock(&ubi->buf_mutex);
>> + if (err == UBI_IO_BITFLIPS) {
>> + dbg_wl("found bitflips in PEB %d", e->pnum);
>> + spin_lock(&ubi->wl_lock);
>> +
>
> IIUC you trigger the action as soon as you have a bitflip error, is this
> correct?
I trigger it as soon UBI sees the bitflip. This depends on the configured MTD
bitflip_threshold.
> Isn't this too much conservative? You usually have a RBER on MLC devices
> that's between 1E-7 (for brand new devices) and 1E-4 (for devices with
> 1k-2k P/E cycle after 100k-300k read-without-P/E)
>
> Having a few bitflips on a block read is more that usual and current ECC
> can correct more that 16 bit error over 512/1KiB.
Please see above. :)
Thanks,
//richard
WARNING: multiple messages have this Message-ID (diff)
From: Richard Weinberger <richard@nod.at>
To: Andrea Scian <rnd4@dave-tech.it>
Cc: linux-mtd@lists.infradead.org,
boris.brezillon@free-electrons.com, linux-kernel@vger.kernel.org,
dedekind1@gmail.com
Subject: Re: [PATCH 4/4] UBI: Implement bitrot checking
Date: Thu, 02 Apr 2015 19:54:21 +0200 [thread overview]
Message-ID: <551D824D.3000004@nod.at> (raw)
In-Reply-To: <551D7DB4.9010607@dave-tech.it>
Hi!
Am 02.04.2015 um 19:34 schrieb Andrea Scian:
>
> Richard,
>
> Il 29/03/2015 14:13, Richard Weinberger ha scritto:
>> + mutex_lock(&ubi->buf_mutex);
>> + err = ubi_io_read(ubi, ubi->peb_buf, e->pnum, 0, ubi->peb_size);
>> + mutex_unlock(&ubi->buf_mutex);
>> + if (err == UBI_IO_BITFLIPS) {
>> + dbg_wl("found bitflips in PEB %d", e->pnum);
>> + spin_lock(&ubi->wl_lock);
>> +
>
> IIUC you trigger the action as soon as you have a bitflip error, is this
> correct?
I trigger it as soon UBI sees the bitflip. This depends on the configured MTD
bitflip_threshold.
> Isn't this too much conservative? You usually have a RBER on MLC devices
> that's between 1E-7 (for brand new devices) and 1E-4 (for devices with
> 1k-2k P/E cycle after 100k-300k read-without-P/E)
>
> Having a few bitflips on a block read is more that usual and current ECC
> can correct more that 16 bit error over 512/1KiB.
Please see above. :)
Thanks,
//richard
next prev parent reply other threads:[~2015-04-02 17:54 UTC|newest]
Thread overview: 49+ messages / expand[flat|nested] mbox.gz Atom feed top
2015-03-29 12:13 UBI: Bitrot checking Richard Weinberger
2015-03-29 12:13 ` Richard Weinberger
2015-03-29 12:13 ` [PATCH 1/4] UBI: Introduce ubi_schedule_fm_work() Richard Weinberger
2015-03-29 12:13 ` Richard Weinberger
2015-03-29 12:13 ` [PATCH 2/4] UBI: Introduce prepare_erase_work() Richard Weinberger
2015-03-29 12:13 ` Richard Weinberger
2015-03-29 12:13 ` [PATCH 3/4] UBI: Introduce in_pq() Richard Weinberger
2015-03-29 12:13 ` Richard Weinberger
2015-03-29 12:13 ` [PATCH 4/4] UBI: Implement bitrot checking Richard Weinberger
2015-03-29 12:13 ` Richard Weinberger
2015-04-02 17:34 ` Andrea Scian
2015-04-02 17:34 ` Andrea Scian
2015-04-02 17:54 ` Richard Weinberger [this message]
2015-04-02 17:54 ` Richard Weinberger
2015-04-02 19:19 ` Andrea Scian
2015-04-02 19:19 ` Andrea Scian
2015-04-08 10:34 ` Richard Weinberger
2015-04-08 10:34 ` Richard Weinberger
2015-04-08 21:02 ` Andrea Scian
2015-04-08 21:02 ` Andrea Scian
2015-04-08 11:48 ` David Oberhollenzer
2015-04-12 14:12 ` Boris Brezillon
2015-04-12 16:09 ` Richard Weinberger
2015-04-12 16:43 ` Boris Brezillon
2015-04-12 16:55 ` Richard Weinberger
2015-04-12 20:42 ` [PATCH 4/4] UBI: Implement bitrot checking (linux-mtd Digest, Vol 145, Issue 24) Andrea Scian
2015-04-12 20:42 ` Andrea Scian
2015-04-12 21:01 ` Richard Weinberger
2015-04-12 21:01 ` Richard Weinberger
2015-04-12 21:30 ` Boris Brezillon
2015-04-12 21:37 ` Richard Weinberger
2015-04-12 21:33 ` Andrea Scian
2015-04-12 21:33 ` Andrea Scian
2015-04-12 21:42 ` Richard Weinberger
2015-04-12 21:42 ` Richard Weinberger
2015-04-13 17:17 ` linux-mtd digest emails (was Re: [PATCH 4/4] UBI: Implement bitrot checking) Brian Norris
2015-04-13 17:17 ` Brian Norris
2015-04-12 15:14 ` [PATCH 4/4] UBI: Implement bitrot checking Boris Brezillon
2015-04-12 16:14 ` Richard Weinberger
2015-04-12 16:31 ` Boris Brezillon
2015-04-12 16:32 ` Richard Weinberger
2015-04-12 17:01 ` Boris Brezillon
2015-04-12 17:09 ` Richard Weinberger
2015-04-12 19:20 ` Boris Brezillon
2015-04-12 19:53 ` Richard Weinberger
2015-04-12 21:24 ` Boris Brezillon
2015-04-12 21:34 ` Richard Weinberger
2015-04-13 3:36 ` nick
2015-04-12 17:36 ` Richard Weinberger
[not found] <mailman.38750.1427638218.22890.linux-mtd@lists.infradead.org>
[not found] <mailman.40253.1428858576.22890.linux-mtd@lists.infradead.org>
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=551D824D.3000004@nod.at \
--to=richard@nod.at \
--cc=boris.brezillon@free-electrons.com \
--cc=dedekind1@gmail.com \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mtd@lists.infradead.org \
--cc=rnd4@dave-tech.it \
/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.