Writing performance problem with SAS1068

2007-02-06 Thread Bernardo Innocenti
Hello, I've stumbled onto a strange performance problem on a new server: reading from disks is fast (70-80MB/s), but writing is extremely slow (13-15MB/s). I've measured it like this: dd if=/dev/zero of=/dev/sdd bs=4096 count=65536 conv=fdatasync 65536+0 records in 65536+0 records out

Re: [patch 25/33] Fix the reproducible oops in scsi

2007-02-06 Thread James Bottomley
On Mon, 2007-02-05 at 16:38 -0800, [EMAIL PROTECTED] wrote: From: OGAWA Hirofumi [EMAIL PROTECTED] I got the oops after some hotplug events. And the similar oops can reproduce by the following step. James Smart already pointed out that this fix isn't valid ... it's a bandaid that doesn't fix

RE: [PATCH] scsi: Update Aic94xx SAS/SATA Linux open source devicedriver for new sequence firmware.

2007-02-06 Thread Wu, Gilbert
Hi James, We are investigating this issue here. We will update the status when we can duplicate the problem here and root cause. Thanks! Gilbert -Original Message- From: James Bottomley [mailto:[EMAIL PROTECTED] Sent: Saturday, February 03, 2007 2:29 PM To: Wu, Gilbert Cc:

Re: [patch 25/33] Fix the reproducible oops in scsi

2007-02-06 Thread Andrew Morton
On Tue, 06 Feb 2007 09:22:06 -0600 James Bottomley [EMAIL PROTECTED] wrote: On Mon, 2007-02-05 at 16:38 -0800, [EMAIL PROTECTED] wrote: From: OGAWA Hirofumi [EMAIL PROTECTED] I got the oops after some hotplug events. And the similar oops can reproduce by the following step. James

Re: [patch 25/33] Fix the reproducible oops in scsi

2007-02-06 Thread James Smart
Hannes and I will be fostering discussion at the upcoming IO summit to discuss options. -- james s Andrew Morton wrote: On Tue, 06 Feb 2007 09:22:06 -0600 James Bottomley [EMAIL PROTECTED] wrote: On Mon, 2007-02-05 at 16:38 -0800, [EMAIL PROTECTED] wrote: From: OGAWA Hirofumi [EMAIL

Re: [Bugme-new] [Bug 7951] New: ESP DMA error

2007-02-06 Thread Andrew Morton
On Tue, 6 Feb 2007 09:54:59 -0800 [EMAIL PROTECTED] wrote: http://bugzilla.kernel.org/show_bug.cgi?id=7951 Summary: ESP DMA error Kernel Version: 2.6.20 Status: NEW Severity: normal Owner: [EMAIL PROTECTED] Submitter: [EMAIL

Re: [Bugme-new] [Bug 7951] New: ESP DMA error

2007-02-06 Thread David Miller
From: Andrew Morton [EMAIL PROTECTED] Date: Tue, 6 Feb 2007 13:29:17 -0800 Apparently a recent regression. It's on sparc32 (and SMP on top of that, scary) which is only lightly maintained, so it could be anything. It would be interesting if running a uniprocessor kernel made the problem go

Re: Writing performance problem with SAS1068

2007-02-06 Thread Douglas Gilbert
Bernardo Innocenti wrote: Hello, I've stumbled onto a strange performance problem on a new server: reading from disks is fast (70-80MB/s), but writing is extremely slow (13-15MB/s). I've measured it like this: dd if=/dev/zero of=/dev/sdd bs=4096 count=65536 conv=fdatasync 65536+0

[-mm patch] drivers/scsi/aacraid/: cleanups

2007-02-06 Thread Adrian Bunk
On Mon, Jan 29, 2007 at 08:45:28PM -0800, Andrew Morton wrote: ... Changes since 2.6.20-rc6-mm2: ... git-scsi-misc.patch ... git trees ... This patch contains the following cleanups: - proper prototypes for global code in aacraid.h - aac_rx_start_adapter() can now become static

[PATCH 1/5] scsi: megaraid_sas - stop cmd processing if hw_crit_error is set

2007-02-06 Thread Sumant Patro
Checks if hw_crit_error is set before processing cmds. Added in megasas_queue_command and command completion routines. Signed-off-by: Sumant Patro [EMAIL PROTECTED] --- drivers/scsi/megaraid/megaraid_sas.c | 13 - 1 files changed, 12 insertions(+), 1 deletion(-) diff -uprN

[PATCH 2/5] scsi: megaraid_sas - added bios_param in scsi_host_template

2007-02-06 Thread Sumant Patro
Added bios_param in scsi_host_template to return disk geometry. Signed-off-by: Sumant Patro [EMAIL PROTECTED] --- drivers/scsi/megaraid/megaraid_sas.c | 45 + 1 files changed, 45 insertions(+) diff -uprN 2.6.new-p1/drivers/scsi/megaraid/megaraid_sas.c

[PATCH 3/5] scsi: megaraid_sas - throttle io if FW is busy

2007-02-06 Thread Sumant Patro
Checks added in megasas_queue_command to know if FW is able to process commands within timeout period. If number of retries is 2 or greater, the driver stops sending cmd to FW. IO is resumed if pending cmd count reduces to 16 or 5 seconds has elapsed from the time cmds were last sent to FW.

[PATCH 4/5] scsi: megaraid_sas - preallocate memory for ioctl processing

2007-02-06 Thread Sumant Patro
Preallocate memory for ioctl processing. This is to avoid situations where ioctl fails for lack of memory (when system under heavy stress). The memory pool will have 8*4K, 4*8K and 1*64K memory chunks Signed-off-by: Sumant Patro [EMAIL PROTECTED] drivers/scsi/megaraid/megaraid_sas.c | 257

[PATCH 5/5] scsi: megaraid_sas - update version and author info

2007-02-06 Thread Sumant Patro
Update version and author information. Signed-off-by: Sumant Patro [EMAIL PROTECTED] --- drivers/scsi/megaraid/megaraid_sas.c |8 +--- drivers/scsi/megaraid/megaraid_sas.h |6 +++--- 2 files changed, 8 insertions(+), 6 deletions(-) diff -uprN

chip 1000:0055 (LSI1068 PCI-X) Fusion-MPT/MegaRAID

2007-02-06 Thread Frederic TEMPORELLI
Hi LSI MegaRAID/Linux team, There's a LSI 1068 chip that can be found on NEC hardware (also Intel/Supermicro/Hitachi, ...) and that can provide RAID 0 and 1 based on a MegaRAID BIOS. By setting a jumper, LSI1068 chip can be used in 2 modes: - LSI1068 'MPT-Fusion': pciid 1000:0054 embedded