On Sun, Feb 17 2008 at 19:24 +0200, James Bottomley [EMAIL PROTECTED] wrote:
On Sun, 2008-02-17 at 18:46 +0200, Boaz Harrosh wrote:
On Thu, Feb 14 2008 at 20:47 +0200, Boaz Harrosh [EMAIL PROTECTED] wrote:
Submitted are a new set of patches, that fix lots of problems
with the gdth driver.
It
Bart Van Assche wrote:
On Feb 5, 2008 6:01 PM, Erez Zilber [EMAIL PROTECTED] wrote:
Using such large values for FirstBurstLength will give you poor
performance numbers for WRITE commands (with iSER). FirstBurstLength
means how much data should you send as unsolicited data (i.e. without
On Feb 18, 2008 10:43 AM, Erez Zilber [EMAIL PROTECTED] wrote:
If you use a high value for FirstBurstLength, all (or most) of your data
will be sent as unsolicited data-out PDUs. These PDUs don't use the RDMA
engine, so you miss the advantage of IB.
Hello Erez,
Did you notice the e-mail
On Tue, Feb 12 2008, James Bottomley wrote:
On Tue, 2008-02-12 at 15:40 -0500, Pete Wyckoff wrote:
If blk_rq_map_user requires more than one bio, and fails mapping
somewhere after the first bio, it will return with rq-bio set to
non-NULL, but it will have already unmapped the partial bio.
Hello people !
I have an x86 SLES 10 system that is connected to some disks on two
EnterpriseStorageSystems (ESS) via two QLogic FibreChannel SCSI Adapters.
Each adapter has one path to each disk, so I have a real multipathing
environment.
Now, I have the need to re-configure the available
On Sun, 17 Feb 2008 18:46:03 +0200 Boaz Harrosh [EMAIL PROTECTED] wrote:
...
All my testers have reported back that with these 5 patches applied they can
now run with a 2.6.24 kernel the same way they ran before. However there is
that reported issue, with the dma_free_coherent WARN_ON
On Mon, Feb 18 2008 at 14:57 +0200, Andrew Morton [EMAIL PROTECTED] wrote:
On Sun, 17 Feb 2008 18:46:03 +0200 Boaz Harrosh [EMAIL PROTECTED] wrote:
...
All my testers have reported back that with these 5 patches applied they can
now run with a 2.6.24 kernel the same way they ran before.
On Sun, 17 Feb 2008 15:37:02 -0800
Tim Pepper [EMAIL PROTECTED] wrote:
On Mon 19 Feb at 07:31:56 +0900 [EMAIL PROTECTED] said:
Can you apply the 0001 and 0002 against 2.6.24 and see how it works?
If it works well, then please apply the 0001, 0002 and 0003.
Fujita-san,
I've started
On Sun, 17 Feb 2008, FUJITA Tomonori wrote:
ps3rom does:
scsi_for_each_sg(cmd, sgpnt, scsi_sg_count(cmd), k) {
kaddr = kmap_atomic(sg_page(sgpnt), KM_IRQ0);
We cannot do something like that with the clustering enabled (or we
can use scsi_kmap_atomic_sg).
Signed-off-by: FUJITA
http://bugzilla.kernel.org/show_bug.cgi?id=9769
[EMAIL PROTECTED] changed:
What|Removed |Added
CC||[EMAIL PROTECTED]
On Mon, Feb 18, 2008 at 04:57:36AM -0800, Andrew Morton wrote:
But arm and mips require enabled local irqs because their
dma_free_coherent() needs to do a cross-cpu IPI call. Presumably because
of certain unusual TLB protocols.
Consider that TLB flushing needs to call a function on another
On Mon, 18 Feb 2008 13:55:08 +0100
Jens Axboe [EMAIL PROTECTED] wrote:
On Tue, Feb 12 2008, James Bottomley wrote:
On Tue, 2008-02-12 at 15:40 -0500, Pete Wyckoff wrote:
If blk_rq_map_user requires more than one bio, and fails mapping
somewhere after the first bio, it will return with
On Mon, Feb 18 2008, FUJITA Tomonori wrote:
On Mon, 18 Feb 2008 13:55:08 +0100
Jens Axboe [EMAIL PROTECTED] wrote:
On Tue, Feb 12 2008, James Bottomley wrote:
On Tue, 2008-02-12 at 15:40 -0500, Pete Wyckoff wrote:
If blk_rq_map_user requires more than one bio, and fails mapping
On Mon, 2008-02-18 at 14:02 +, Russell King wrote:
Another solution jejb suggested was to make dma_free_coherent() lazy,
but (a) I'm unconvinced that this'll work with drivers which
constantly
alloc+free in IRQ context since there's generally only 2MB of VM space
for such mappings, and it
The path needs to be triggered, it is the path to handle spoofing of the
Adapter's inquiry.
You need more printk instrumentation to determine *why* it is not reaching that
code path. What is the result of scb-scsi_cmd. scb-bus,
ips_is_passthru(scb-scsi_cmd)?
The sg breakup issue may need to
Support for extended CDBs in iscsi.
All we need is to check if command spills over 16 bytes then allocate
an iscsi-extended-header for the leftovers.
Signed-off-by: Boaz Harrosh [EMAIL PROTECTED]
Reviewed-by: Pete Wyckoff [EMAIL PROTECTED]
Signed-off-by: Mike Christie [EMAIL PROTECTED]
---
On Mon, 2008-02-18 at 15:46 +0100, Jens Axboe wrote:
Seems symmetric to me now, either we fail and everything is cleaned up,
or return success. What remains?
My main symmetry complaint was the API: The map takes a request, the
unmap takes a bio.
James
-
To unsubscribe from this list: send
On Thu, Jan 31 2008 at 20:08 +0200, Boaz Harrosh [EMAIL PROTECTED] wrote:
Cheers after 1.3 years these can go in.
[PATCH 1/3] iscsi: extended cdb support
The varlen support is not yet in mainline for
block and scsi-ml. But the API for drivers will
not change. All LLD need to do is
On Tue, Feb 12 2008 at 22:17 +0200, Pete Wyckoff [EMAIL PROTECTED] wrote:
[EMAIL PROTECTED] wrote on Tue, 12 Feb 2008 15:12 -0500:
[EMAIL PROTECTED] wrote on Thu, 31 Jan 2008 20:08 +0200:
Cheers after 1.3 years these can go in.
[PATCH 1/3] iscsi: extended cdb support
The varlen support is
bidi support for iscsi_tcp
- access the right scsi_in() and/or scsi_out() side of things.
also for resid
Signed-off-by: Boaz Harrosh [EMAIL PROTECTED]
Reviewed-by: Pete Wyckoff [EMAIL PROTECTED]
Signed-off-by: Mike Christie [EMAIL PROTECTED]
---
drivers/scsi/iscsi_tcp.c | 31
iscsi bidi support at the generic libiscsi level
- prepare the additional bidi_read rlength header.
- access the right scsi_in() and/or scsi_out() side of things.
also for resid.
- Handle BIDI underflow overflow from target
Signed-off-by: Boaz Harrosh [EMAIL PROTECTED]
Reviewed-by:
[EMAIL PROTECTED] wrote on Mon, 18 Feb 2008 17:39 +0200:
On Tue, Feb 12 2008 at 22:17 +0200, Pete Wyckoff [EMAIL PROTECTED] wrote:
From: Pete Wyckoff [EMAIL PROTECTED]
Subject: [PATCH] iscsi iser: varlen
Handle variable-length CDBs in iSER.
Signed-off-by: Pete Wyckoff [EMAIL
gets
fixed, you just get to the next layer of errors.
Please grab the dmesg output in all its gory glory from here:
http://wiki.hopnet.net/dokuwiki/lib/exe/fetch.php?media=myit:sas:dmesg-20080218-wpatch-fail.txt.gz
The drive is a Dell OEM drive, but it's not in a Dell system. There
is at least
On Sat, 16 Feb 2008 00:25:22 -0800 Andrew Morton wrote:
ftp://ftp.kernel.org/pub/linux/kernel/people/akpm/patches/2.6/2.6.25-rc2/2.6.25-rc2-mm1/
cciss driver has a bad macro definition:
#else /* no CONFIG_CISS_SCSI_TAPE */
/* If no tape support, then these become defined out of existence */
On Mon, 2008-02-18 at 17:08 +0200, Boaz Harrosh wrote:
But ... James? is
there any chance these can go into scsi-rc-fixes for the 2.6.25
kernel? The reason they are so late was mainly because of a fallout
in the merge process and a bug that was introduced because of that,
but they were
On Monday 18 February 2008, Andrew Morton wrote:
Russell, Ralf: is there something we can do here to relax this requirement?
I'm thinking that perhaps we can do some rcu/refcounting tricks: launch the
IPI from within dma_free_coherent(), but don't wait for it to complete.
When all CPUs have
On Mon, Feb 18, 2008 at 04:57:36AM -0800, Andrew Morton wrote:
On Sun, 17 Feb 2008 18:46:03 +0200 Boaz Harrosh [EMAIL PROTECTED] wrote:
...
All my testers have reported back that with these 5 patches applied they can
now run with a 2.6.24 kernel the same way they ran before. However
On Mon 18 Feb at 22:32:46 +0900 [EMAIL PROTECTED] said:
diff --git a/drivers/scsi/ips.c b/drivers/scsi/ips.c
index 05bb6ea..39cdd68 100644
--- a/drivers/scsi/ips.c
+++ b/drivers/scsi/ips.c
@@ -6906,7 +6906,7 @@ ips_register_scsi(int index)
sh-max_channel = ha-nbus - 1;
On Mon 18 Feb at 06:57:14 -0800 [EMAIL PROTECTED] said:
The path needs to be triggered, it is the path to handle spoofing
of the Adapter's inquiry.
You need more printk instrumentation to determine *why* it is not
reaching that code path. What is the result of scb-scsi_cmd.
scb-bus,
Markus Naeher [EMAIL PROTECTED] wrote:
The missing disk is always the first one (LUN 000). I have tested this by
changing
the order of the disks on ESS 2.
I have also repeated the test scenario with only one path per disk.
In this testcase, I have divided the ESS's on the two Adapters
On Mon, 18 Feb 2008 15:30:58 -0800
Tim Pepper [EMAIL PROTECTED] wrote:
On Mon 18 Feb at 22:32:46 +0900 [EMAIL PROTECTED] said:
diff --git a/drivers/scsi/ips.c b/drivers/scsi/ips.c
index 05bb6ea..39cdd68 100644
--- a/drivers/scsi/ips.c
+++ b/drivers/scsi/ips.c
@@ -6906,7 +6906,7 @@
On Feb 18, 2008 4:11 PM, FUJITA Tomonori [EMAIL PROTECTED] wrote:
Can you please help me just once more? 2.6.25-rc2 fixed this bug in a
bit different way by chance. Please test 2.6.25-rc2 with the attached
patch to make sure that ips in 2.6.25 works well.
Confirmed...the patch below against
32 matches
Mail list logo