Re: [ewg] [PATCH]: Set open-iscsi for auto-startup when installing OFED
Erez Zilber wrote: Vlad, Please pull from git://git.openfabrics.org/~erezz/ofed_1_3_scripts.git. We would like to include this patch in OFED 1.3.1. Thanks, Done, Regards, Vladimir ___ ewg mailing list ewg@lists.openfabrics.org http://lists.openfabrics.org/cgi-bin/mailman/listinfo/ewg
[ewg] [PATCH 0/5] IB/ehca: IB compliance fix, tracing verbosity and module parameters
[1/5] makes the driver reject SQ WRs if the QP is not in RTS [2/5] bumps a lot of tracing into higher debug_levels [3/5] removes the mr_largepage parameter [4/5] changes some bool-ish module parms into actual bools, also updates some descriptions [5/5] bumps the version number to 0026 Please review these patches and queue them for inclusion into 2.6.26 if you think they're okay. Thanks! Joachim -- Joachim Fenkes -- eHCA Linux Driver Developer and Hardware Tamer IBM Deutschland Entwicklung GmbH -- Dept. 3627 (I/O Firmware Dev. 2) Schoenaicher Strasse 220 -- 71032 Boeblingen -- Germany eMail: [EMAIL PROTECTED] ___ ewg mailing list ewg@lists.openfabrics.org http://lists.openfabrics.org/cgi-bin/mailman/listinfo/ewg
[ewg] [PATCH 1/5] IB/ehca: Prevent posting of SQ WQEs if QP not in RTS
...as required by IB Spec, C10-29.
Signed-off-by: Joachim Fenkes [EMAIL PROTECTED]
---
drivers/infiniband/hw/ehca/ehca_classes.h |1 +
drivers/infiniband/hw/ehca/ehca_qp.c |3 +++
drivers/infiniband/hw/ehca/ehca_reqs.c|5 +
3 files changed, 9 insertions(+), 0 deletions(-)
diff --git a/drivers/infiniband/hw/ehca/ehca_classes.h
b/drivers/infiniband/hw/ehca/ehca_classes.h
index 0d13fe0..3d6d946 100644
--- a/drivers/infiniband/hw/ehca/ehca_classes.h
+++ b/drivers/infiniband/hw/ehca/ehca_classes.h
@@ -160,6 +160,7 @@ struct ehca_qp {
};
u32 qp_type;
enum ehca_ext_qp_type ext_type;
+ enum ib_qp_state state;
struct ipz_queue ipz_squeue;
struct ipz_queue ipz_rqueue;
struct h_galpas galpas;
diff --git a/drivers/infiniband/hw/ehca/ehca_qp.c
b/drivers/infiniband/hw/ehca/ehca_qp.c
index 3eb14a5..5a653d7 100644
--- a/drivers/infiniband/hw/ehca/ehca_qp.c
+++ b/drivers/infiniband/hw/ehca/ehca_qp.c
@@ -550,6 +550,7 @@ static struct ehca_qp *internal_create_qp(
spin_lock_init(my_qp-spinlock_r);
my_qp-qp_type = qp_type;
my_qp-ext_type = parms.ext_type;
+ my_qp-state = IB_QPS_RESET;
if (init_attr-recv_cq)
my_qp-recv_cq =
@@ -1508,6 +1509,8 @@ static int internal_modify_qp(struct ib_qp *ibqp,
if (attr_mask IB_QP_QKEY)
my_qp-qkey = attr-qkey;
+ my_qp-state = qp_new_state;
+
modify_qp_exit2:
if (squeue_locked) { /* this means: sqe - rts */
spin_unlock_irqrestore(my_qp-spinlock_s, flags);
diff --git a/drivers/infiniband/hw/ehca/ehca_reqs.c
b/drivers/infiniband/hw/ehca/ehca_reqs.c
index a20bbf4..0b2359e 100644
--- a/drivers/infiniband/hw/ehca/ehca_reqs.c
+++ b/drivers/infiniband/hw/ehca/ehca_reqs.c
@@ -421,6 +421,11 @@ int ehca_post_send(struct ib_qp *qp,
int ret = 0;
unsigned long flags;
+ if (unlikely(my_qp-state != IB_QPS_RTS)) {
+ ehca_err(qp-device, QP not in RTS state qpn=%x, qp-qp_num);
+ return -EINVAL;
+ }
+
/* LOCK the QUEUE */
spin_lock_irqsave(my_qp-spinlock_s, flags);
--
1.5.5
___
ewg mailing list
ewg@lists.openfabrics.org
http://lists.openfabrics.org/cgi-bin/mailman/listinfo/ewg
[ewg] [PATCH 2/5] IB/ehca: Move high-volume debug output to higher debug levels
Signed-off-by: Joachim Fenkes [EMAIL PROTECTED]
---
drivers/infiniband/hw/ehca/ehca_irq.c|2 +-
drivers/infiniband/hw/ehca/ehca_main.c | 14 ++--
drivers/infiniband/hw/ehca/ehca_mrmw.c | 16 ++
drivers/infiniband/hw/ehca/ehca_qp.c | 12
drivers/infiniband/hw/ehca/ehca_reqs.c | 46 ++---
drivers/infiniband/hw/ehca/ehca_uverbs.c |6 +--
drivers/infiniband/hw/ehca/hcp_if.c | 23 ---
7 files changed, 63 insertions(+), 56 deletions(-)
diff --git a/drivers/infiniband/hw/ehca/ehca_irq.c
b/drivers/infiniband/hw/ehca/ehca_irq.c
index b5ca94c..ca5eb0c 100644
--- a/drivers/infiniband/hw/ehca/ehca_irq.c
+++ b/drivers/infiniband/hw/ehca/ehca_irq.c
@@ -633,7 +633,7 @@ static inline int find_next_online_cpu(struct
ehca_comp_pool *pool)
unsigned long flags;
WARN_ON_ONCE(!in_interrupt());
- if (ehca_debug_level)
+ if (ehca_debug_level = 3)
ehca_dmp(cpu_online_map, sizeof(cpumask_t), );
spin_lock_irqsave(pool-last_cpu_lock, flags);
diff --git a/drivers/infiniband/hw/ehca/ehca_main.c
b/drivers/infiniband/hw/ehca/ehca_main.c
index 65b3362..4379bef 100644
--- a/drivers/infiniband/hw/ehca/ehca_main.c
+++ b/drivers/infiniband/hw/ehca/ehca_main.c
@@ -85,8 +85,8 @@ module_param_named(lock_hcalls, ehca_lock_hcalls, bool,
S_IRUGO);
MODULE_PARM_DESC(open_aqp1,
AQP1 on startup (0: no (default), 1: yes));
MODULE_PARM_DESC(debug_level,
-debug level
- (0: no debug traces (default), 1: with debug traces));
+Amount of debug output (0: none (default), 1: traces,
+2: some dumps, 3: lots));
MODULE_PARM_DESC(hw_level,
hardware level
(0: autosensing (default), 1: v. 0.20, 2: v. 0.21));
@@ -275,6 +275,7 @@ static int ehca_sense_attributes(struct ehca_shca *shca)
u64 h_ret;
struct hipz_query_hca *rblock;
struct hipz_query_port *port;
+ const char *loc_code;
static const u32 pgsize_map[] = {
HCA_CAP_MR_PGSIZE_4K, 0x1000,
@@ -283,6 +284,12 @@ static int ehca_sense_attributes(struct ehca_shca *shca)
HCA_CAP_MR_PGSIZE_16M, 0x100,
};
+ ehca_gen_dbg(Probing adapter %s...,
+shca-ofdev-node-full_name);
+ loc_code = of_get_property(shca-ofdev-node, ibm,loc-code, NULL);
+ if (loc_code)
+ ehca_gen_dbg( ... location lode=%s, loc_code);
+
rblock = ehca_alloc_fw_ctrlblock(GFP_KERNEL);
if (!rblock) {
ehca_gen_err(Cannot allocate rblock memory.);
@@ -567,8 +574,7 @@ static int ehca_destroy_aqp1(struct ehca_sport *sport)
static ssize_t ehca_show_debug_level(struct device_driver *ddp, char *buf)
{
- return snprintf(buf, PAGE_SIZE, %d\n,
- ehca_debug_level);
+ return snprintf(buf, PAGE_SIZE, %d\n, ehca_debug_level);
}
static ssize_t ehca_store_debug_level(struct device_driver *ddp,
diff --git a/drivers/infiniband/hw/ehca/ehca_mrmw.c
b/drivers/infiniband/hw/ehca/ehca_mrmw.c
index f26997f..46ae4eb 100644
--- a/drivers/infiniband/hw/ehca/ehca_mrmw.c
+++ b/drivers/infiniband/hw/ehca/ehca_mrmw.c
@@ -1794,8 +1794,9 @@ static int ehca_check_kpages_per_ate(struct scatterlist
*page_list,
int t;
for (t = start_idx; t = end_idx; t++) {
u64 pgaddr = page_to_pfn(sg_page(page_list[t])) PAGE_SHIFT;
- ehca_gen_dbg(chunk_page=%lx value=%016lx, pgaddr,
-*(u64 *)abs_to_virt(phys_to_abs(pgaddr)));
+ if (ehca_debug_level = 3)
+ ehca_gen_dbg(chunk_page=%lx value=%016lx, pgaddr,
+*(u64 *)abs_to_virt(phys_to_abs(pgaddr)));
if (pgaddr - PAGE_SIZE != *prev_pgaddr) {
ehca_gen_err(uncontiguous page found pgaddr=%lx
prev_pgaddr=%lx page_list_i=%x,
@@ -1862,10 +1863,13 @@ static int ehca_set_pagebuf_user2(struct ehca_mr_pginfo
*pginfo,
pgaddr
~(pginfo-hwpage_size - 1));
}
- ehca_gen_dbg(kpage=%lx chunk_page=%lx
-value=%016lx, *kpage, pgaddr,
-*(u64 *)abs_to_virt(
-phys_to_abs(pgaddr)));
+ if (ehca_debug_level = 3) {
+ u64 val = *(u64 *)abs_to_virt(
+ phys_to_abs(pgaddr));
+ ehca_gen_dbg(kpage=%lx chunk_page=%lx
+value=%016lx,
+*kpage,
[ewg] [PATCH 3/5] IB/ehca: Remove mr_largepage parameter
Always enable large page support; didn't seem to cause problems for anyone.
Signed-off-by: Joachim Fenkes [EMAIL PROTECTED]
---
drivers/infiniband/hw/ehca/ehca_main.c | 22 +++---
1 files changed, 3 insertions(+), 19 deletions(-)
diff --git a/drivers/infiniband/hw/ehca/ehca_main.c
b/drivers/infiniband/hw/ehca/ehca_main.c
index 4379bef..ab02ac8 100644
--- a/drivers/infiniband/hw/ehca/ehca_main.c
+++ b/drivers/infiniband/hw/ehca/ehca_main.c
@@ -60,7 +60,6 @@ MODULE_VERSION(HCAD_VERSION);
static int ehca_open_aqp1 = 0;
static int ehca_hw_level = 0;
static int ehca_poll_all_eqs = 1;
-static int ehca_mr_largepage = 1;
int ehca_debug_level = 0;
int ehca_nr_ports = 2;
@@ -79,7 +78,6 @@ module_param_named(port_act_time, ehca_port_act_time, int,
S_IRUGO);
module_param_named(poll_all_eqs, ehca_poll_all_eqs, int, S_IRUGO);
module_param_named(static_rate, ehca_static_rate, int, S_IRUGO);
module_param_named(scaling_code, ehca_scaling_code, int, S_IRUGO);
-module_param_named(mr_largepage, ehca_mr_largepage, int, S_IRUGO);
module_param_named(lock_hcalls, ehca_lock_hcalls, bool, S_IRUGO);
MODULE_PARM_DESC(open_aqp1,
@@ -104,9 +102,6 @@ MODULE_PARM_DESC(static_rate,
set permanent static rate (default: disabled));
MODULE_PARM_DESC(scaling_code,
set scaling code (0: disabled/default, 1: enabled));
-MODULE_PARM_DESC(mr_largepage,
-use large page for MR (0: use PAGE_SIZE (default),
-1: use large page depending on MR size);
MODULE_PARM_DESC(lock_hcalls,
serialize all hCalls made by the driver
(default: autodetect));
@@ -357,11 +352,9 @@ static int ehca_sense_attributes(struct ehca_shca *shca)
/* translate supported MR page sizes; always support 4K */
shca-hca_cap_mr_pgsize = EHCA_PAGESIZE;
- if (ehca_mr_largepage) { /* support extra sizes only if enabled */
- for (i = 0; i ARRAY_SIZE(pgsize_map); i += 2)
- if (rblock-memory_page_size_supported pgsize_map[i])
- shca-hca_cap_mr_pgsize |= pgsize_map[i + 1];
- }
+ for (i = 0; i ARRAY_SIZE(pgsize_map); i += 2)
+ if (rblock-memory_page_size_supported pgsize_map[i])
+ shca-hca_cap_mr_pgsize |= pgsize_map[i + 1];
/* query max MTU from first port -- it's the same for all ports */
port = (struct hipz_query_port *)rblock;
@@ -663,14 +656,6 @@ static ssize_t ehca_show_adapter_handle(struct device *dev,
}
static DEVICE_ATTR(adapter_handle, S_IRUGO, ehca_show_adapter_handle, NULL);
-static ssize_t ehca_show_mr_largepage(struct device *dev,
- struct device_attribute *attr,
- char *buf)
-{
- return sprintf(buf, %d\n, ehca_mr_largepage);
-}
-static DEVICE_ATTR(mr_largepage, S_IRUGO, ehca_show_mr_largepage, NULL);
-
static struct attribute *ehca_dev_attrs[] = {
dev_attr_adapter_handle.attr,
dev_attr_num_ports.attr,
@@ -687,7 +672,6 @@ static struct attribute *ehca_dev_attrs[] = {
dev_attr_cur_mw.attr,
dev_attr_max_pd.attr,
dev_attr_max_ah.attr,
- dev_attr_mr_largepage.attr,
NULL
};
--
1.5.5
___
ewg mailing list
ewg@lists.openfabrics.org
http://lists.openfabrics.org/cgi-bin/mailman/listinfo/ewg
[ewg] [PATCH 4/5] IB/ehca: Make some module parameters bool, update descriptions
Signed-off-by: Joachim Fenkes [EMAIL PROTECTED] --- drivers/infiniband/hw/ehca/ehca_main.c | 37 +++ 1 files changed, 18 insertions(+), 19 deletions(-) diff --git a/drivers/infiniband/hw/ehca/ehca_main.c b/drivers/infiniband/hw/ehca/ehca_main.c index ab02ac8..45fe35a 100644 --- a/drivers/infiniband/hw/ehca/ehca_main.c +++ b/drivers/infiniband/hw/ehca/ehca_main.c @@ -69,41 +69,40 @@ int ehca_static_rate = -1; int ehca_scaling_code = 0; int ehca_lock_hcalls = -1; -module_param_named(open_aqp1, ehca_open_aqp1, int, S_IRUGO); -module_param_named(debug_level, ehca_debug_level, int, S_IRUGO); -module_param_named(hw_level, ehca_hw_level, int, S_IRUGO); -module_param_named(nr_ports, ehca_nr_ports, int, S_IRUGO); -module_param_named(use_hp_mr, ehca_use_hp_mr, int, S_IRUGO); -module_param_named(port_act_time, ehca_port_act_time, int, S_IRUGO); -module_param_named(poll_all_eqs, ehca_poll_all_eqs, int, S_IRUGO); -module_param_named(static_rate, ehca_static_rate, int, S_IRUGO); -module_param_named(scaling_code, ehca_scaling_code, int, S_IRUGO); +module_param_named(open_aqp1, ehca_open_aqp1, bool, S_IRUGO); +module_param_named(debug_level, ehca_debug_level, int, S_IRUGO); +module_param_named(hw_level, ehca_hw_level, int, S_IRUGO); +module_param_named(nr_ports, ehca_nr_ports, int, S_IRUGO); +module_param_named(use_hp_mr, ehca_use_hp_mr, bool, S_IRUGO); +module_param_named(port_act_time, ehca_port_act_time, int, S_IRUGO); +module_param_named(poll_all_eqs, ehca_poll_all_eqs, bool, S_IRUGO); +module_param_named(static_rate, ehca_static_rate, int, S_IRUGO); +module_param_named(scaling_code, ehca_scaling_code, bool, S_IRUGO); module_param_named(lock_hcalls, ehca_lock_hcalls, bool, S_IRUGO); MODULE_PARM_DESC(open_aqp1, -AQP1 on startup (0: no (default), 1: yes)); +Open AQP1 on startup (default: no)); MODULE_PARM_DESC(debug_level, Amount of debug output (0: none (default), 1: traces, 2: some dumps, 3: lots)); MODULE_PARM_DESC(hw_level, -hardware level - (0: autosensing (default), 1: v. 0.20, 2: v. 0.21)); +Hardware level (0: autosensing (default), +0x10..0x14: eHCA, 0x20..0x23: eHCA2)); MODULE_PARM_DESC(nr_ports, number of connected ports (-1: autodetect, 1: port one only, 2: two ports (default)); MODULE_PARM_DESC(use_hp_mr, -high performance MRs (0: no (default), 1: yes)); +Use high performance MRs (default: no)); MODULE_PARM_DESC(port_act_time, -time to wait for port activation (default: 30 sec)); +Time to wait for port activation (default: 30 sec)); MODULE_PARM_DESC(poll_all_eqs, -polls all event queues periodically - (0: no, 1: yes (default))); +Poll all event queues periodically (default: yes)); MODULE_PARM_DESC(static_rate, -set permanent static rate (default: disabled)); +Set permanent static rate (default: no static rate)); MODULE_PARM_DESC(scaling_code, -set scaling code (0: disabled/default, 1: enabled)); +Enable scaling code (default: no)); MODULE_PARM_DESC(lock_hcalls, -serialize all hCalls made by the driver +Serialize all hCalls made by the driver (default: autodetect)); DEFINE_RWLOCK(ehca_qp_idr_lock); -- 1.5.5 ___ ewg mailing list ewg@lists.openfabrics.org http://lists.openfabrics.org/cgi-bin/mailman/listinfo/ewg
[ewg] [PATCH 5/5] IB/ehca: Bump version number to 0026
Signed-off-by: Joachim Fenkes [EMAIL PROTECTED] --- drivers/infiniband/hw/ehca/ehca_main.c |2 +- 1 files changed, 1 insertions(+), 1 deletions(-) diff --git a/drivers/infiniband/hw/ehca/ehca_main.c b/drivers/infiniband/hw/ehca/ehca_main.c index 45fe35a..6504897 100644 --- a/drivers/infiniband/hw/ehca/ehca_main.c +++ b/drivers/infiniband/hw/ehca/ehca_main.c @@ -50,7 +50,7 @@ #include ehca_tools.h #include hcp_if.h -#define HCAD_VERSION 0025 +#define HCAD_VERSION 0026 MODULE_LICENSE(Dual BSD/GPL); MODULE_AUTHOR(Christoph Raisch [EMAIL PROTECTED]); -- 1.5.5 ___ ewg mailing list ewg@lists.openfabrics.org http://lists.openfabrics.org/cgi-bin/mailman/listinfo/ewg
[ewg] Re: [PATCH 1/5] IB/ehca: Prevent posting of SQ WQEs if QP not in RTS
On Monday 21 April 2008 10:04, Joachim Fenkes wrote:
+ if (unlikely(my_qp-state != IB_QPS_RTS)) {
+ ehca_err(qp-device, QP not in RTS state qpn=%x, qp-qp_num);
+ return -EINVAL;
+ }
Myself, I'm not very happy with using EINVAL, but I can't think of a more
fitting return code. Also, this is what nes, amso and cxgb3 return in such a
case; ipath posts an error CQE and mthca/mlx4 don't do this check at all
(AFAICS).
Better suggestions, anyone?
Regards,
Joachim
___
ewg mailing list
ewg@lists.openfabrics.org
http://lists.openfabrics.org/cgi-bin/mailman/listinfo/ewg
Re: [ewg] [PATCH 2/2] IB/iser: Ask the user to stop open-iscsi before stopping openibd on RH4
Vladimir Sokolovsky wrote:
Erez Zilber wrote:
In RedHat 4, some OFED kernel modules (including open-iscsi modules)
use symbols that are encapsulated in ib_core (e.g. kfifo). ib_core
may not be unloaded before open-iscsi is unloaded. Therefore,
disconnecting
from open-iscsi over iSER sessions is not suffiecient if the user
tries to
stop openibd. The user must be prompted to stop open-iscsi before
stopping
openibd.
Signed-off-by: Erez Zilber [EMAIL PROTECTED]
---
ofed_scripts/ofa_kernel.spec |7 +++
1 files changed, 7 insertions(+), 0 deletions(-)
diff --git a/ofed_scripts/ofa_kernel.spec b/ofed_scripts/ofa_kernel.spec
index eed2484..01411e7 100755
--- a/ofed_scripts/ofa_kernel.spec
+++ b/ofed_scripts/ofa_kernel.spec
@@ -455,6 +455,13 @@ if [ -f /etc/SuSE-release ]; then
fi
fi
+# If it's RH4, open-iscsi must be stopped before openibd
+if [[ -f /etc/redhat-release $(grep -c Red Hat Enterprise Linux
AS release 4 /etc/redhat-release) -eq 1 ]]; then
+cat /etc/init.d/openibd | sed -e 's/Please logout from all
open-iscsi over iSER sessions/Please stop open-iscsi:
\/etc\/init.d\/iscsi stop/' /etc/init.d/openibd.$$
+mv /etc/init.d/openibd.$$ /etc/init.d/openibd
+chmod +x /etc/init.d/openibd
+fi
+
%if %{build_kernel_ib}
echo %{IB_CONF_DIR}/openib.conf
echo # Load UCM module %{IB_CONF_DIR}/openib.conf
Erez,
I changed your patch with the patch below:
See, if this is OK.
From b0409a7d6a1e8f2cfc1de69994420622c6d70b50 Mon Sep 17 00:00:00 2001
From: Vladimir Sokolovsky [EMAIL PROTECTED]
Date: Mon, 21 Apr 2008 11:59:14 +0300
Subject: [PATCH] In RedHat 4, some OFED kernel modules (including
open-iscsi modules)
use symbols that are encapsulated in ib_core (e.g. kfifo). ib_core
may not be unloaded before open-iscsi is unloaded. Therefore,
disconnecting
from open-iscsi over iSER sessions is not suffiecient if the user tries to
stop openibd. The user must be prompted to stop open-iscsi before stopping
openibd.
Signed-off-by: Erez Zilber [EMAIL PROTECTED]
Signed-off-by: Vladimir Sokolovsky [EMAIL PROTECTED]
---
ofed_scripts/openibd |7 ++-
1 files changed, 6 insertions(+), 1 deletions(-)
diff --git a/ofed_scripts/openibd b/ofed_scripts/openibd
index 0e1325d..8272def 100755
--- a/ofed_scripts/openibd
+++ b/ofed_scripts/openibd
@@ -1196,7 +1196,12 @@ stop()
if [ $iser_session_cnt -gt 0 ]; then
echo
-echo Please logout from all open-iscsi over
iSER sessions
+# If it's RH4, open-iscsi must be stopped
before openibd
+if [[ -f /etc/redhat-release $(grep -c
Red Hat Enterprise Linux AS release 4 /etc/redhat-release) -eq 1 ]];
then
+echo Please stop open-iscsi:
/etc/init.d/iscsi stop
+else
+echo Please logout from all open-iscsi
over iSER sessions
+fi
echo Then run \$0 $ACTION\
echo
exit 1
--
1.5.2.5
I'm ok with your fix.
Erez
___
ewg mailing list
ewg@lists.openfabrics.org
http://lists.openfabrics.org/cgi-bin/mailman/listinfo/ewg
Re: [ewg] [PATCH 2/2] IB/iser: Ask the user to stop open-iscsi before stopping openibd on RH4
Erez Zilber wrote:
In RedHat 4, some OFED kernel modules (including open-iscsi modules)
use symbols that are encapsulated in ib_core (e.g. kfifo). ib_core
may not be unloaded before open-iscsi is unloaded. Therefore, disconnecting
from open-iscsi over iSER sessions is not suffiecient if the user tries to
stop openibd. The user must be prompted to stop open-iscsi before stopping
openibd.
Signed-off-by: Erez Zilber [EMAIL PROTECTED]
---
ofed_scripts/ofa_kernel.spec |7 +++
1 files changed, 7 insertions(+), 0 deletions(-)
diff --git a/ofed_scripts/ofa_kernel.spec b/ofed_scripts/ofa_kernel.spec
index eed2484..01411e7 100755
--- a/ofed_scripts/ofa_kernel.spec
+++ b/ofed_scripts/ofa_kernel.spec
@@ -455,6 +455,13 @@ if [ -f /etc/SuSE-release ]; then
fi
fi
+# If it's RH4, open-iscsi must be stopped before openibd
+if [[ -f /etc/redhat-release $(grep -c Red Hat Enterprise Linux AS release
4 /etc/redhat-release) -eq 1 ]]; then
+cat /etc/init.d/openibd | sed -e 's/Please logout from all open-iscsi over
iSER sessions/Please stop open-iscsi: \/etc\/init.d\/iscsi stop/'
/etc/init.d/openibd.$$
+mv /etc/init.d/openibd.$$ /etc/init.d/openibd
+chmod +x /etc/init.d/openibd
+fi
+
%if %{build_kernel_ib}
echo %{IB_CONF_DIR}/openib.conf
echo # Load UCM module %{IB_CONF_DIR}/openib.conf
Erez,
I changed your patch with the patch below:
See, if this is OK.
From b0409a7d6a1e8f2cfc1de69994420622c6d70b50 Mon Sep 17 00:00:00 2001
From: Vladimir Sokolovsky [EMAIL PROTECTED]
Date: Mon, 21 Apr 2008 11:59:14 +0300
Subject: [PATCH] In RedHat 4, some OFED kernel modules (including open-iscsi
modules)
use symbols that are encapsulated in ib_core (e.g. kfifo). ib_core
may not be unloaded before open-iscsi is unloaded. Therefore, disconnecting
from open-iscsi over iSER sessions is not suffiecient if the user tries to
stop openibd. The user must be prompted to stop open-iscsi before stopping
openibd.
Signed-off-by: Erez Zilber [EMAIL PROTECTED]
Signed-off-by: Vladimir Sokolovsky [EMAIL PROTECTED]
---
ofed_scripts/openibd |7 ++-
1 files changed, 6 insertions(+), 1 deletions(-)
diff --git a/ofed_scripts/openibd b/ofed_scripts/openibd
index 0e1325d..8272def 100755
--- a/ofed_scripts/openibd
+++ b/ofed_scripts/openibd
@@ -1196,7 +1196,12 @@ stop()
if [ $iser_session_cnt -gt 0 ]; then
echo
-echo Please logout from all open-iscsi over iSER
sessions
+# If it's RH4, open-iscsi must be stopped before
openibd
+if [[ -f /etc/redhat-release $(grep -c Red Hat
Enterprise Linux AS release 4 /etc/redhat-release) -eq 1 ]]; then
+echo Please stop open-iscsi: /etc/init.d/iscsi
stop
+else
+echo Please logout from all open-iscsi over iSER
sessions
+fi
echo Then run \$0 $ACTION\
echo
exit 1
--
1.5.2.5
___
ewg mailing list
ewg@lists.openfabrics.org
http://lists.openfabrics.org/cgi-bin/mailman/listinfo/ewg
Re: [ewg] mlx4_core internal error with OFED 1.2.5.4
Hal Rosenstock wrote: Hi, I'm running OFED 1.2.5.4 and got the following: Is there any more information that can be provided by decoding this as to what the error was ? Thanks. Hi Hal, I will forward this info to our FW developers. Which FW version you are using? What have you run when this happened? Thanks, Tziporet ___ ewg mailing list ewg@lists.openfabrics.org http://lists.openfabrics.org/cgi-bin/mailman/listinfo/ewg
[ewg] OFED teleconference today
Friendly reminder: the OFED teleconference is today (21 April 2008). Noon US Eastern / 9am US Pacific / 7pm Israel 1. Monday, April 21, code 210020028 2. Monday, May 5, code 210020028 3. Monday, May 19, code 210020028 US/Canada: +1.866.432.9903 India: +91.80.4103.3979 Israel: +972.9.892.7026 Others: http://cisco.com/en/US/about/doing_business/conferencing/ -- Jeff Squyres Cisco Systems ___ ewg mailing list ewg@lists.openfabrics.org http://lists.openfabrics.org/cgi-bin/mailman/listinfo/ewg
Re: [ewg] mlx4_core internal error with OFED 1.2.5.4
Hi Tziporet, On Mon, 2008-04-21 at 14:45 +0300, Tziporet Koren wrote: Hal Rosenstock wrote: Hi, I'm running OFED 1.2.5.4 and got the following: Is there any more information that can be provided by decoding this as to what the error was ? Thanks. Hi Hal, I will forward this info to our FW developers. Thanks. Which FW version you are using? 2.3.0 What have you run when this happened? I'm not sure it's reproducible but was wondering if there were any clues as to what the internal error was and what could cause it in theory. -- Hal Thanks, Tziporet ___ ewg mailing list ewg@lists.openfabrics.org http://lists.openfabrics.org/cgi-bin/mailman/listinfo/ewg
[ewg] 70% discount. Coupon #NG4f
Dear ewg, be a smart guy, buy your meds from the most reliable shop since 1997.___ ewg mailing list ewg@lists.openfabrics.org http://lists.openfabrics.org/cgi-bin/mailman/listinfo/ewg
Re: [ewg] Agenda for the OFED meeting today
Hey Tziporet, Sorry I missed today's call. If possible, I'd like a few weeks to get the cxgb3 fixes tested and ready to go. That puts me around mid may. I'll try and pull that in to make a RC1 of May 6, but I'm thinking I might need another week or so. Steve. Tziporet Koren wrote: Hi, This is the agenda for the OFED meeting today: 1. OFED 1.3.1: 1.1 Planned changes: ULPs changes: IB-bonding - done SRP failover - on work SDP crashes - on work RDS fixes for RDMA API - already applied but not clear if these are all the changes librdmacm 1.0.7 - done Open MPI 1.2.6 - done Low level drivers: - each HW vendor should reply when the changes will be ready nes mlx4 cxgb3 Ipath ehca 1.2 Schedule: GA is planned for May-29 I suggest to have only two release candidates: - RC1 - May 6 - RC2 - May 20 Note: daily builds of 1.3.1 are already available at: _http://www.openfabrics.org/builds/ofed-1.3.1_ 2. OFED 1.4: Release features were presented at Sonoma (presentation available at _http://www.openfabrics.org/archives/april2008sonoma.htm_) Kernel tree is under work at: git://git.openfabrics.org/ofed_1_4/linux-2.6.git branch ofed_kernel Now failing on ipath drivers - waiting for an update. We should try to get the kernel code to compile as soon as possible so everybody will be able to contribute code 3. Follow up from Sonoma - open discussion Tziporet ___ ewg mailing list ewg@lists.openfabrics.org http://lists.openfabrics.org/cgi-bin/mailman/listinfo/ewg ___ ewg mailing list ewg@lists.openfabrics.org http://lists.openfabrics.org/cgi-bin/mailman/listinfo/ewg
