Hi Hu,
On 12/29/2014 5:14 AM, hujianyang wrote:
On 2014/11/3 21:58, Tanya Brokhman wrote:
If there is more then one UBI device mounted, there is no way to
distinguish between messages from different UBI devices.
Add device number to all ubi layer message types.
The R/O block driver messages
On 12/8/2014 11:11 AM, Richard Weinberger wrote:
Hi!
Am 08.12.2014 um 07:58 schrieb Tanya Brokhman:
On 12/7/2014 4:22 PM, Richard Weinberger wrote:
Am 07.12.2014 um 14:59 schrieb Tanya Brokhman:
Hi Richard,
On 11/30/2014 1:35 PM, Richard Weinberger wrote:
If ubi_update_fastmap() fails
On 12/8/2014 11:14 AM, Richard Weinberger wrote:
Am 08.12.2014 um 09:36 schrieb Tanya Brokhman:
On 11/30/2014 1:35 PM, Richard Weinberger wrote:
There is no need to allocate new ones every time, we can reuse
the existing ones.
This makes the code cleaner and more easy to follow.
Signed-off-by
;
- }
- }
-
old_fm = ubi->fm;
ubi->fm = NULL;
Thanks,
Tanya Brokhman
--
Qualcomm Israel, on behalf of Qualcomm Innovation Center, Inc.
The Qualcomm Innovation Center, Inc. is a member of the Code Aurora Forum,
a Linux Foundation Collaborative Pro
On 12/7/2014 4:22 PM, Richard Weinberger wrote:
Am 07.12.2014 um 14:59 schrieb Tanya Brokhman:
Hi Richard,
On 11/30/2014 1:35 PM, Richard Weinberger wrote:
If ubi_update_fastmap() fails notify the user.
This is not a hard error as ubi_update_fastmap() makes sure that upon failure
the current
On 11/30/2014 1:35 PM, Richard Weinberger wrote:
There is no need to switch to ro mode if ubi_update_fastmap() fails.
Also get rid of the ifdef.
Signed-off-by: Richard Weinberger
Reviewed-by: Tanya Brokhman
---
drivers/mtd/ubi/build.c | 11 +--
1 file changed, 5 insertions
On 11/30/2014 1:35 PM, Richard Weinberger wrote:
...such that we can implement NOP variants of some functions.
This will help to reduce fastmap specific ifdefs in other c files.
Signed-off-by: Richard Weinberger
Reviewed-by: Tanya Brokhman
---
drivers/mtd/ubi/ubi.h | 4
1 file
bi_msg but against "return -ENOSPC;"
+ }
spin_lock(&ubi->wl_lock);
}
Thanks,
Tanya Brokhman
--
Qualcomm Israel, on behalf of Qualcomm Innovation Center, Inc.
The Qualcomm Innovation Center, Inc. is a member of the Code Aurora
Forum, a Linux Foundation Coll
On 11/30/2014 1:35 PM, Richard Weinberger wrote:
There is no need to allocate new ones every time, we can reuse
the existing ones.
This makes the code cleaner and more easy to follow.
Signed-off-by: Richard Weinberger
Reviewed-by: Tanya Brokhman
---
drivers/mtd/ubi/fastmap.c | 31
On 12/7/2014 1:34 PM, Richard Weinberger wrote:
Am 07.12.2014 um 12:32 schrieb Tanya Brokhman:
On 12/7/2014 11:54 AM, Richard Weinberger wrote:
Am 07.12.2014 um 09:13 schrieb Tanya Brokhman:
On 11/30/2014 1:35 PM, Richard Weinberger wrote:
Add a ubi_fastmap_close() to free all resources used
On 12/7/2014 11:54 AM, Richard Weinberger wrote:
Am 07.12.2014 um 09:13 schrieb Tanya Brokhman:
On 11/30/2014 1:35 PM, Richard Weinberger wrote:
Add a ubi_fastmap_close() to free all resources used by fastmap
at WL shutdown.
Signed-off-by: Richard Weinberger
---
drivers/mtd/ubi/wl.c | 21
i)
void ubi_wl_close(struct ubi_device *ubi)
{
dbg_wl("close the WL sub-system");
-#ifdef CONFIG_MTD_UBI_FASTMAP
- flush_work(&ubi->fm_work);
-#endif
+ ubi_fastmap_close(ubi);
shutdown_work(ubi);
protection_queue_destroy(ubi);
tree_dest
e.
We want a PEB to be used for wear-leveling not for "end users" like UBIFS.
sorry, my mistake. I meant wl_get_wle() (the new function). the only
diff between wl_get_wle() and the above is that you use find_wl_entry()
and wl_get_wle() uses find_mean_wl_entry() and takes the anchor into
;s why the "retry" bugs me a bit.
You mean a cond_resched()?
This retry-logic is common pattern in UBI. For exmaple see ubi_wl_put_peb().
you're right. didn't pay much attention to ubi_wl_put_peb() before.
don't like it there either :)
perhaps we can rethink this
enough++;
+
+ if (enough == 2)
break;
}
+
+ wl_pool->used = 0;
pool->used = 0;
-}
-/**
- * ubi_refill_pools - refills all fastmap PEB pools.
- * @ubi: UBI device description object
- */
-void ubi_refill_pools(struct ubi
@@ -704,7 +719,7 @@ int ubi_wl_get_peb(struct ubi_device *ubi)
int peb, err;
spin_lock(&ubi->wl_lock);
- peb = __wl_get_peb(ubi);
+ peb = wl_get_peb(ubi);
spin_unlock(&ubi->wl_lock);
if (peb < 0)
Thanks,
Tanya Brokhman
--
Qualcomm Israel,
Hi Richard
On 12/5/2014 3:20 PM, Richard Weinberger wrote:
Tanya,
Am 05.12.2014 um 14:09 schrieb Tanya Brokhman:
On 11/24/2014 3:20 PM, Richard Weinberger wrote:
ubi_wl_get_peb() has two problems, it reads the pool
size and usage counters without any protection.
While reading one value would
7 +671,7 @@ static struct ubi_wl_entry *get_peb_for_wl(struct
ubi_device *ubi)
struct ubi_fm_pool *pool = &ubi->fm_wl_pool;
int pnum;
- if (pool->used == pool->size || !pool->size) {
+ if (pool->used == pool->size) {
/* We cann
. I am missing explanations why I am
wrong...
__
Linux MTD discussion mailing list
http://lists.infradead.org/mailman/listinfo/linux-mtd/
Thanks,
Tanya Brokhman
--
Qualcomm Israel, on behalf of Qualcomm Innovation Center, Inc.
The Qualcomm Innovation Center, Inc. is a member of the Code Aurora
Forum
bitflips are detected.
Reviewed-by: Tanya Brokhman
Signed-off-by: Richard Weinberger
---
drivers/mtd/ubi/ubi.h | 4 +++-
drivers/mtd/ubi/wl.c | 8 +++-
2 files changed, 10 insertions(+), 2 deletions(-)
diff --git a/drivers/mtd/ubi/ubi.h b/drivers/mtd/ubi/ubi.h
index f80ffab..04c4c05
On 12/4/2014 1:04 PM, Richard Weinberger wrote:
Tanya,
Am 04.12.2014 um 12:00 schrieb Tanya Brokhman:
Hi Richard
On 10/29/2014 2:45 PM, Richard Weinberger wrote:
In some error paths the WL sub-system gives up on a PEB
and frees it's ubi_wl_entry struct but does not set
the entry i
i->lookuptbl[e2->pnum] = NULL
there on purpose.
Thanks,
Tanya Brokhman
--
Qualcomm Israel, on behalf of Qualcomm Innovation Center, Inc.
The Qualcomm Innovation Center, Inc. is a member of the Code Aurora
Forum, a Linux Foundation Collaborative Project
--
To unsubscribe from this list:
On 10/29/2014 2:45 PM, Richard Weinberger wrote:
Using this debugfs knob fastmap self checks can be controlled.
Reviewed-by: Tanya Brokhman
Signed-off-by: Richard Weinberger
---
drivers/mtd/ubi/debug.c | 11 +++
drivers/mtd/ubi/debug.h | 5 +
drivers/mtd/ubi/ubi.h | 4
On 11/10/2014 7:57 PM, Joe Perches wrote:
On Mon, 2014-11-10 at 18:37 +0100, Richard Weinberger wrote:
Am 03.11.2014 um 14:58 schrieb Tanya Brokhman:
If there is more then one UBI device mounted, there is no way to
distinguish between messages from different UBI devices.
Add device number to
On 11/10/2014 2:18 PM, Artem Bityutskiy wrote:
On Sun, 2014-11-09 at 13:06 +0200, Tanya Brokhman wrote:
/* Normal UBI messages */
#define ubi_msg(ubi, fmt, ...) pr_notice("UBI-%d: %s:" fmt "\n", \
-ubi->ubi_num,
Some cosmetic fixes to the patch "UBI: Extend UBI layer debug/messaging
capabilities".
Signed-off-by: Tanya Brokhman
---
Changes from original patch:
- Added ptr verification @ ubi_err/ubi_msg/ubi_warn
Removed extra printing of ubi number
Removed new messages.
On 11/7/2014 12:08 PM, hujianyang wrote:
On 2014/11/5 23:35, Artem Bityutskiy wrote:
On Mon, 2014-11-03 at 15:58 +0200, Tanya Brokhman wrote:
If there is more then one UBI device mounted, there is no way to
distinguish between messages from different UBI devices.
Add device number to all ubi
.
Signed-off-by: Tanya Brokhman
Signed-off-by: Artem Bityutskiy
---
Changes from V1:
- Compilation error fixed
- macros were updated to receive the ubi structure as
parameter and not just ubi_number
- Places in code, where ubi-messaging macros were used, but
On 11/3/2014 5:08 AM, hujianyang wrote:
Hi Tanya,
On 2014/11/3 1:14, Tanya Brokhman wrote:
This patch add 'struct ubi_device *' for 3 functions. We can get 'ubi_device'
from
'ubi_volume'. So I think it's because when we call these functions, the &#x
try_to_freeze())
continue;
Here are two new adding messages. Maybe a separate patch is better? Just a
suggestion.
Done.
@@ -1415,8 +1418,9 @@ int ubi_self_check_all_ff(struct ubi_device *ubi, int
pnum, int offset, int len)
return 0;
fail:
- ubi_er
On 10/30/2014 10:40 AM, Artem Bityutskiy wrote:
Yeah, lets' correct this too.
Thanks for ferview Hujianyang!
Tanya, would you send a follow-up patch these?
Yes, sure.
Sorry, was pulled into some urgent stuff. Will post a new patch early
next week.
Artem.
Thanks,
Tanya Bro
.
Signed-off-by: Dolev Raviv
Signed-off-by: Tanya Brokhman
---
drivers/mtd/ubi/attach.c | 137 +++---
drivers/mtd/ubi/debug.c | 11
drivers/mtd/ubi/fastmap.c | 118 ++-
drivers/mtd/ubi/io.c | 28
ubi->scrub
list.
Signed-off-by: Tanya Brokhman
---
drivers/mtd/ubi/eba.c | 7 ++-
drivers/mtd/ubi/wl.c | 56 +--
2 files changed, 56 insertions(+), 7 deletions(-)
diff --git a/drivers/mtd/ubi/eba.c b/drivers/mtd/ubi/eba.c
index 0e116
Make the in_wl_tree function public to be used outside of wl.c.
Rename it to ubi_in_wl_tree.
Signed-off-by: Tanya Brokhman
---
drivers/mtd/ubi/ubi.h | 1 +
drivers/mtd/ubi/wl.c | 18 +-
2 files changed, 10 insertions(+), 9 deletions(-)
diff --git a/drivers/mtd/ubi/ubi.h b
Signed-off-by: Tanya Brokhman
---
drivers/mtd/ubi/build.c | 32 +--
drivers/mtd/ubi/ubi.h | 3 +
drivers/mtd/ubi/wl.c| 143 +++-
3 files changed, 171 insertions(+), 7 deletions(-)
diff --git a/drivers/mtd/ubi/build.c b/drivers/mtd/ubi
statistics
Signed-off-by: Tanya Brokhman
---
Changes from V1:
- Documentation file was added
Documentation/mtd/ubi/ubi-read-disturb.txt | 145 +
drivers/mtd/ubi/build.c| 57
drivers/mtd/ubi/fastmap.c | 14 ++-
drivers
On 10/21/2014 10:56 AM, Artem Bityutskiy wrote:
On Mon, 2014-10-20 at 19:57 +0300, Tanya Brokhman wrote:
If there is more then one UBI device mounted, there is no way to
distinguish between messages from different UBI devices.
Add device number to all ubi layer message types.
The R/O block
If there is more then one UBI device mounted, there is no way to
distinguish between messages from different UBI devices.
Add device number to all ubi layer message types.
The R/O block driver messages were replaced by pr_* since
ubi_device structure is not used by it.
Signed-off-by: Tanya
em insists on it.
Thanks,
Tanya Brokhman
--
Qualcomm Israel, on behalf of Qualcomm Innovation Center, Inc.
The Qualcomm Innovation Center, Inc. is a member of the Code Aurora
Forum, a Linux Foundation Collaborative Project
--
To unsubscribe from this list: send the line "unsubscribe linux-kerne
On 10/14/2014 5:13 PM, Tanya Brokhman wrote:
If there is more then one UBI device mounted, there is no way to
distinguish between messages from different UBI devices.
Add device number to all ubi layer message types.
The R/O block driver messages were replaced by pr_* since
ubi_device structure
If there is more then one UBI device mounted, there is no way to
distinguish between messages from different UBI devices.
Add device number to all ubi layer message types.
The R/O block driver messages were replaced by pr_* since
ubi_device structure is not used by it.
Signed-off-by: Tanya
On 10/14/2014 4:02 PM, Artem Bityutskiy wrote:
On Tue, 2014-10-14 at 15:21 +0300, Tanya Brokhman wrote:
Hi Artem/Richard
I think your discussion here stopped being relevant to this specific
patch but went on to the fastmap feature design in general :)
This patch fixes a real bug in the current
erhaps this one can be merged and will be "fixed" later on
when you agree on how you would like FM to access WL data structures in
general?
Thanks,
Tanya Brokhman
--
Qualcomm Israel, on behalf of Qualcomm Innovation Center, Inc.
The Qualcomm Innovation Center, Inc. is a member o
On 10/13/2014 6:59 PM, Artem Bityutskiy wrote:
On Mon, 2014-10-13 at 18:37 +0300, Artem Bityutskiy wrote:
On Mon, 2014-10-06 at 14:01 +0300, Tanya Brokhman wrote:
If there is more then one UBI device mounted, there is no way to
distinguish between messages from different UBI devices.
Add
If there is more then one UBI device mounted, there is no way to
distinguish between messages from different UBI devices.
Add device number to all ubi layer message types.
Signed-off-by: Tanya Brokhman
---
Changes from V1:
- Compilation error fixed
- macros were updated to
On 9/30/2014 10:44 AM, Richard Weinberger wrote:
Am 30.09.2014 09:39, schrieb Bityutskiy, Artem:
On Tue, 2014-09-30 at 08:59 +0200, Richard Weinberger wrote:
Am 30.09.2014 08:45, schrieb Bityutskiy, Artem:
On Tue, 2014-09-30 at 00:20 +0200, Richard Weinberger wrote:
+ spin_lock(&ubi->wl
On 10/2/2014 4:32 PM, Richard Weinberger wrote:
Am 02.10.2014 15:28, schrieb Tanya Brokhman:
Hi Richard
On 9/30/2014 1:20 AM, Richard Weinberger wrote:
Fastmap can miss a PEB if it is in the protection queue
and not jet in the used tree.
Treat every protected PEB as used.
Signed-off-by
On 10/2/2014 4:36 PM, Richard Weinberger wrote:
Am 02.10.2014 14:50, schrieb Tanya Brokhman:
Hi Richard,
Sorry it took me some time to answer, got per-occupied with some urgent staff.
On 9/28/2014 1:54 PM, Richard Weinberger wrote:
Am 28.09.2014 12:46, schrieb Tanya Brokhman:
On 9/28/2014
) + \
sizeof(struct ubi_fm_scan_pool) + \
sizeof(struct ubi_fm_scan_pool) + \
(ubi->peb_count * sizeof(struct ubi_fm_ec)) + \
Reviewed-by: Tanya Brokhman
--
Employee of Qualcomm Innovation Center, Inc.
Qualcomm Innovation Center, Inc. is a member of Code Aur
On 10/2/2014 4:24 PM, Richard Weinberger wrote:
Am 02.10.2014 14:50, schrieb Tanya Brokhman:
Consider the case where you have a board with a fastmap enabled bootloader and
a Linux OS.
The bootloader does a fastmap attach and boots the kernel from UBI and the
kernel it self has the rootfs
on
ith this addition or does it needs updating as well?
+ }
+ }
fmh->used_peb_count = cpu_to_be32(used_peb_count);
for (node = rb_first(&ubi->scrub); node; node = rb_next(node)) {
Thanks
Tanya Brokhman
--
Employee of Qualcomm Innovation Center, Inc.
Qua
bit more on the
commit message.
Thanks,
Tanya Brokhman
--
Employee of Qualcomm Innovation Center, Inc.
Qualcomm Innovation Center, Inc. is a member of Code Aurora Forum,
hosted by The Linux Foundation
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the bo
);
+#ifdef CONFIG_MTD_UBI_FASTMAP
+ flush_work(&ubi->fm_work);
flush_work returns bool. It might be useful to print that value for
debugging.
+#endif
cancel_pending(ubi);
protection_queue_destroy(ubi);
tree_destroy(&ubi->used);
Thanks
Tanya Brokhman
Hi Richard,
Sorry it took me some time to answer, got per-occupied with some urgent
staff.
On 9/28/2014 1:54 PM, Richard Weinberger wrote:
Am 28.09.2014 12:46, schrieb Tanya Brokhman:
On 9/28/2014 11:54 AM, Richard Weinberger wrote:
Am 28.09.2014 10:48, schrieb Tanya Brokhman:
@@ -424,6
If there is more then one UBI device mounted, there is no way to
distinguish between messages from different UBI devices.
Add device number to all ubi layer message types.
Signed-off-by: Tanya Brokhman
---
Changes from V1:
- Compilation error fixed
- macros were updated to
On 9/28/2014 3:01 PM, Artem Bityutskiy wrote:
On Sun, 2014-09-28 at 09:36 +0300, Tanya Brokhman wrote:
If there is more then one UBI device mounted, there is no way to
distinguish between messages from different UBI devices.
Add device number to all ubi layer message types.
Hi, the goal looks
On 9/29/2014 3:37 PM, Richard Weinberger wrote:
Am 29.09.2014 14:32, schrieb Kiran Padwal:
On Monday 29 September 2014 05:31 PM, Richard Weinberger wrote:
Am 29.09.2014 12:50, schrieb Kiran Padwal:
Hi Tanya,
On Sunday 28 September 2014 12:06 PM, Tanya Brokhman wrote:
If there is more then
Hi Jeremiah,
On 9/28/2014 9:13 PM, Jeremiah Mahler wrote:
Tanya,
On Sun, Sep 28, 2014 at 09:37:00AM +0300, Tanya Brokhman wrote:
The need for performing read disturb is determined according to new
statistics collected per eraseblock:
- read counter: incremented at each read operation
On 9/28/2014 3:11 PM, Artem Bityutskiy wrote:
On Sun, 2014-09-28 at 09:37 +0300, Tanya Brokhman wrote:
The need for performing read disturb is determined according to new
statistics collected per eraseblock:
- read counter: incremented at each read operation
reset at each erase
On 9/28/2014 11:54 AM, Richard Weinberger wrote:
Am 28.09.2014 10:48, schrieb Tanya Brokhman:
@@ -424,6 +440,8 @@ struct ubi_fm_sb {
__be32 used_blocks;
__be32 block_loc[UBI_FM_MAX_BLOCKS];
__be32 block_ec[UBI_FM_MAX_BLOCKS];
+__be32 block_rc[UBI_FM_MAX_BLOCKS
On 9/28/2014 11:42 AM, Richard Weinberger wrote:
Tanya,
On Sun, Sep 28, 2014 at 8:38 AM, Tanya Brokhman wrote:
A given eraseblock can be read many times or not at all.
We do not have the account of such eraseblocks that have
not been accessed since a pre-defined threshold interval.
By means
Hi Richard
On 9/28/2014 11:18 AM, Richard Weinberger wrote:
index 0431b46..5399aa2 100644
--- a/drivers/mtd/ubi/fastmap.c
+++ b/drivers/mtd/ubi/fastmap.c
@@ -1,5 +1,7 @@
/*
* Copyright (c) 2012 Linutronix GmbH
+ * Copyright (c) 2014, Linux Foundation. All rights reserved.
+ *
Diffstat s
On 9/28/2014 11:01 AM, Richard Weinberger wrote:
Tanya,
Am 28.09.2014 08:36, schrieb Tanya Brokhman:
If there is more then one UBI device mounted, there is no way to
distinguish between messages from different UBI devices.
Add device number to all ubi layer message types.
Signed-off-by
A given eraseblock can be read many times or not at all.
We do not have the account of such eraseblocks that have
not been accessed since a pre-defined threshold interval.
By means of scanning the entire flash device it is possible to identify
all such eraseblocks.
Add a sysfs entry to force scan
scrubbing is added to the ubi->scrub
list.
Signed-off-by: Tanya Brokhman
---
drivers/mtd/ubi/eba.c | 7 ++-
drivers/mtd/ubi/wl.c | 56 +--
2 files changed, 56 insertions(+), 7 deletions(-)
diff --git a/drivers/mtd/ubi/eba.c b/drivers/mtd/
From: Tatyana Brokhman
Fill in eraseblock statistics needed for read disturb decision making:
1. read counter: incremented at each read operation
reset at each erase operation
Saved only as part of the meta data in RAM
On attach: if fastmap data is missing a default value
statistics
Signed-off-by: Tanya Brokhman
---
drivers/mtd/ubi/build.c | 57 +
drivers/mtd/ubi/fastmap.c | 14 +++
drivers/mtd/ubi/ubi-media.h | 32 ++---
drivers/mtd/ubi/ubi.h | 34 +++
drivers/mtd
From: Tatyana Brokhman
Make the in_wl_tree function public to be used outside of wl.c.
Rename it to ubi_in_wl_tree.
Signed-off-by: Tanya Brokhman
---
drivers/mtd/ubi/ubi.h | 1 +
drivers/mtd/ubi/wl.c | 18 +-
2 files changed, 10 insertions(+), 9 deletions(-)
diff --git a
If there is more then one UBI device mounted, there is no way to
distinguish between messages from different UBI devices.
Add device number to all ubi layer message types.
Signed-off-by: Tanya Brokhman
---
drivers/mtd/ubi/attach.c | 138
drivers/mtd/ubi
On 4/7/2014 4:02 PM, Richard Weinberger wrote:
On Tue, Apr 1, 2014 at 10:01 AM, Tanya Brokhman wrote:
At first mount it's possible that there are not enough free PEBs since
there are PEB's pending to be erased. In such scenario, fm_pool (which is
the pool from which user require
At first mount it's possible that there are not enough free PEBs since
there are PEB's pending to be erased. In such scenario, fm_pool (which is
the pool from which user required PEBs are allocated) will be empty.
Try fixing the above described situation by synchronously performing
pending erase wo
The ubi->free_count should be updated with every insert/remove to/from
the ubi->free list.
Signed-off-by: Tanya Brokhman
diff --git a/drivers/mtd/ubi/wl.c b/drivers/mtd/ubi/wl.c
index 9a36f78..ca74d19 100644
--- a/drivers/mtd/ubi/wl.c
+++ b/drivers/mtd/ubi/wl.c
@@ -690,6 +690,8 @@ static
In case of an error (if there are not free PEB's for example),
__wl_get_peb will return a negative value. In order to prevent access
violation we need to test the returned value prior to using it later on.
Signed-off-by: Tatyana Brokhman
diff --git a/drivers/mtd/ubi/wl.c b/drivers/mtd/ubi/wl.c
i
This patch add support in block & elevator layers for handling
urgent requests. The decision if a request is urgent or not is taken
by the scheduler. Request is marked as urgent in cmd_flags (by the
scheduler) with a new flag - REQ_URGENT.
Urgent request notification is passed to the underlying
blo
When the scheduler reports to the block layer that there is an urgent
request pending, the device driver may decide to stop the transmission
of the current request in order to handle the urgent one. This is done
in order to reduce the latency of an urgent request. For example:
long WRITE may be sto
Add support for reinserting a dispatched request back to the
scheduler's internal data structures.
This capability is used by the device driver when it chooses to
interrupt the current request transmission and execute another (more
urgent) pending request. For example: interrupting long write in or
From: Jens Axboe
We have officially run out of flags in a 32-bit space. Extend it
to 64-bit even on 32-bit archs.
Signed-off-by: Jens Axboe
diff --git a/block/blk-core.c b/block/blk-core.c
index 93a18d1..cfa4dd3 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -174,9 +174,9 @@ void blk_
Hello Jeff
Thank you for your comments. Please see inline.
On 7/11/2013 9:41 PM, Jeff Moyer wrote:
Tanya Brokhman writes:
When the scheduler reports to the block layer that there is an urgent
request pending, the device driver may decide to stop the transmission
of the current request in
This patch add support in block & elevator layers for handling
urgent requests. The decision if a request is urgent or not is taken
by the scheduler. Request is marked as urgent in cmd_flags (by the
scheduler) with a new flag - REQ_URGENT.
Urgent request notification is passed to the underlying
blo
When the scheduler reports to the block layer that there is an urgent
request pending, the device driver may decide to stop the transmission
of the current request in order to handle the urgent one. This is done
in order to reduce the latency of an urgent request. For example:
long WRITE may be sto
Add support for reinserting a dispatched request back to the
scheduler's internal data structures.
This capability is used by the device driver when it chooses to
interrupt the current request transmission and execute another (more
urgent) pending request. For example: interrupting long write in or
From: Jens Axboe
We have officially run out of flags in a 32-bit space. Extend it
to 64-bit even on 32-bit archs.
Signed-off-by: Jens Axboe
diff --git a/block/blk-core.c b/block/blk-core.c
index 93a18d1..cfa4dd3 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -174,9 +174,9 @@ void blk_
This patch adds the implementation of a new scheduling algorithm - ROW.
The policy of this algorithm is to prioritize READ requests over WRITE
as much as possible without starving the WRITE requests.
The requests are kept in queues according to their priority. The dispatch
is done in a Round Robin
Add support for reinserting a dispatched request back to the
scheduler's internal data structures.
This capability is used by the device driver when it chooses to
interrupt the current request transmission and execute another (more
urgent) pending request. For example: interrupting long write in or
This patch add support in block & elevator layers for handling
urgent requests. The decision if a request is urgent or not is taken
by the scheduler. Request is marked as urgent in cmd_flags (by the
scheduler) with a new flag - REQ_URGENT.
Urgent request notification is passed to the underlying
blo
From: Jens Axboe
We have officially run out of flags in a 32-bit space. Extend it
to 64-bit even on 32-bit archs.
Signed-off-by: Jens Axboe
diff --git a/block/blk-core.c b/block/blk-core.c
index 0852e5d..0256a5b 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -174,9 +174,9 @@ void blk_
This patch add support in block & elevator layers for handling
urgent requests. The decision if a request is urgent or not is taken
by the scheduler. Request is marked as urgent in cmd_flags (by the
scheduler) with a new flag - REQ_URGENT.
Urgent request notification is passed to the underlying
blo
This patch adds the implementation of a new scheduling algorithm - ROW.
The policy of this algorithm is to prioritize READ requests over WRITE
as much as possible without starving the WRITE requests.
The requests are kept in queues according to their priority. The dispatch
is done in a Round Robin
At the moment no new request flags can be added to enum rq_flag_bits
due to cmd_flags field size limitation. This commit adds a new filed to be used
as
an extensions to cmd_flags.
Signed-off-by: Tanya Brokhman
diff --git a/block/blk-core.c b/block/blk-core.c
index fe3683c..3a14987 100644
--- a
Add support for reinserting a dispatched request back to the
scheduler's internal data structures.
This capability is used by the device driver when it chooses to
interrupt the current request transmission and execute another (more
urgent) pending request. For example: interrupting long write in or
This patch adds the implementation of a new scheduling algorithm - ROW.
The policy of this algorithm is to prioritize READ requests over WRITE
as much as possible without starving the WRITE requests.
The requests are kept in queues according to their priority. The dispatch
is done in a Round Robin
Add support for reinserting a dispatched request back to the
scheduler's internal data structures.
This capability is used by the device driver when it chooses to
interrupt the current request transmission and execute another (more
urgent) pending request. For example: interrupting long write in or
At the moment no new request flags can be added to enum rq_flag_bits
due to cmd_flags field size limitation. This commit adds a new filed to be used
as
an extensions to cmd_flags.
Signed-off-by: Tanya Brokhman
diff --git a/block/blk-core.c b/block/blk-core.c
index fe3683c..3a14987 100644
--- a
This patch add support in block & elevator layers for handling
urgent requests. The decision if a request is urgent or not is taken
by the scheduler. Request is marked as urgent in cmd_flags (by the
scheduler) with a new flag - REQ_URGENT.
Urgent request notification is passed to the underlying
blo
This patch adds the implementation of a new scheduling algorithm - ROW.
The policy of this algorithm is to prioritize READ requests over WRITE
as much as possible without starving the WRITE requests.
The requests are kept in queues according to their priority. The dispatch
is done in a Round Robin
This patch add support in block & elevator layers for handling
urgent requests. The decision if a request is urgent or not is taken
by the scheduler. Request is marked as urgent in cmd_flags (by the
scheduler) with a new flag - REQ_URGENT.
Urgent request notification is passed to the underlying
blo
Add support for reinserting a dispatched request back to the
scheduler's internal data structures.
This capability is used by the device driver when it chooses to
interrupt the current request transmission and execute another (more
urgent) pending request. For example: interrupting long write in or
On 3/25/2013 2:40 PM, Jens Axboe wrote:
On Mon, Mar 25 2013, Tanya Brokhman wrote:
This patch add support in block & elevator layers for handling
urgent requests. The decision if a request is urgent or not is taken
by the scheduler. Request is marked as urgent in cmd_flags (by the
sched
nt the existing
> requeue event, or a reinsert event.
>
Thank you for the input. Will do and upload a new patch.
Thanks,
Tanya Brokhman
--
QUALCOMM ISRAEL, on behalf of Qualcomm Innovation Center, Inc. is a member
of Code Aurora Forum, hosted by The Linux Foundation
--
To unsubscribe fro
This patch adds the implementation of a new scheduling algorithm - ROW.
The policy of this algorithm is to prioritize READ requests over WRITE
as much as possible without starving the WRITE requests.
The requests are kept in queues according to their priority. The dispatch
is done in a Round Robin
1 - 100 of 110 matches
Mail list logo
