[PATCH 5/5] staging: lustre: mdc: use large xattr buffers for old servers

[James Simmons]

From: "John L. Hammond" 

Pre 2.10.1 MDTs will crash when they receive a listxattr (MDS_GETXATTR
with OBD_MD_FLXATTRLS) RPC for an orphan or dead object. So for
clients connected to these older MDTs, try to avoid sending listxattr
RPCs by making the bulk getxattr (MDS_GETXATTR with OBD_MD_FLXATTRALL)
more likely to succeed and thereby reducing the chances of falling
back to listxattr.

Signed-off-by: John L. Hammond 
Intel-bug-id: https://jira.hpdd.intel.com/browse/LU-10912
Reviewed-on: https://review.whamcloud.com/31990
Reviewed-by: Andreas Dilger 
Reviewed-by: Fan Yong 
Reviewed-by: Oleg Drokin 
Signed-off-by: James Simmons 
---
 drivers/staging/lustre/lustre/mdc/mdc_locks.c | 31 +--
 1 file changed, 24 insertions(+), 7 deletions(-)

diff --git a/drivers/staging/lustre/lustre/mdc/mdc_locks.c 
b/drivers/staging/lustre/lustre/mdc/mdc_locks.c
index a8aa0fa..b991c6f 100644
--- a/drivers/staging/lustre/lustre/mdc/mdc_locks.c
+++ b/drivers/staging/lustre/lustre/mdc/mdc_locks.c
@@ -326,8 +326,10 @@ static void mdc_realloc_openmsg(struct ptlrpc_request *req,
 {
struct ptlrpc_request   *req;
struct ldlm_intent  *lit;
+   u32 min_buf_size = 0;
int rc, count = 0;
LIST_HEAD(cancels);
+   u32 buf_size = 0;
 
req = ptlrpc_request_alloc(class_exp2cliimp(exp),
   _LDLM_INTENT_GETXATTR);
@@ -344,18 +346,33 @@ static void mdc_realloc_openmsg(struct ptlrpc_request 
*req,
lit = req_capsule_client_get(>rq_pill, _LDLM_INTENT);
lit->opc = IT_GETXATTR;
 
+#if LUSTRE_VERSION_CODE < OBD_OCD_VERSION(3, 0, 53, 0)
+   /* If the supplied buffer is too small then the server will
+* return -ERANGE and llite will fallback to using non cached
+* xattr operations. On servers before 2.10.1 a (non-cached)
+* listxattr RPC for an orphan or dead file causes an oops. So
+* let's try to avoid sending too small a buffer to too old a
+* server. This is effectively undoing the memory conservation
+* of LU-9417 when it would be *more* likely to crash the
+* server. See LU-9856.
+*/
+   if (exp->exp_connect_data.ocd_version < OBD_OCD_VERSION(2, 10, 1, 0))
+   min_buf_size = exp->exp_connect_data.ocd_max_easize;
+#endif
+   buf_size = max_t(u32, min_buf_size,
+GA_DEFAULT_EA_NAME_LEN * GA_DEFAULT_EA_NUM);
+
/* pack the intended request */
-   mdc_pack_body(req, _data->op_fid1, op_data->op_valid,
- GA_DEFAULT_EA_NAME_LEN * GA_DEFAULT_EA_NUM, -1, 0);
+   mdc_pack_body(req, _data->op_fid1, op_data->op_valid, buf_size,
+ -1, 0);
 
-   req_capsule_set_size(>rq_pill, _EADATA, RCL_SERVER,
-GA_DEFAULT_EA_NAME_LEN * GA_DEFAULT_EA_NUM);
+   req_capsule_set_size(>rq_pill, _EADATA, RCL_SERVER, buf_size);
 
-   req_capsule_set_size(>rq_pill, _EAVALS, RCL_SERVER,
-GA_DEFAULT_EA_NAME_LEN * GA_DEFAULT_EA_NUM);
+   req_capsule_set_size(>rq_pill, _EAVALS, RCL_SERVER, buf_size);
 
req_capsule_set_size(>rq_pill, _EAVALS_LENS, RCL_SERVER,
-sizeof(u32) * GA_DEFAULT_EA_NUM);
+max_t(u32, min_buf_size,
+  sizeof(u32) * GA_DEFAULT_EA_NUM));
 
req_capsule_set_size(>rq_pill, _ACL, RCL_SERVER, 0);
 
-- 
1.8.3.1

[PATCH 5/5] staging: lustre: mdc: use large xattr buffers for old servers

[James Simmons]

From: "John L. Hammond" 

Pre 2.10.1 MDTs will crash when they receive a listxattr (MDS_GETXATTR
with OBD_MD_FLXATTRLS) RPC for an orphan or dead object. So for
clients connected to these older MDTs, try to avoid sending listxattr
RPCs by making the bulk getxattr (MDS_GETXATTR with OBD_MD_FLXATTRALL)
more likely to succeed and thereby reducing the chances of falling
back to listxattr.

Signed-off-by: John L. Hammond 
Intel-bug-id: https://jira.hpdd.intel.com/browse/LU-10912
Reviewed-on: https://review.whamcloud.com/31990
Reviewed-by: Andreas Dilger 
Reviewed-by: Fan Yong 
Reviewed-by: Oleg Drokin 
Signed-off-by: James Simmons 
---
 drivers/staging/lustre/lustre/mdc/mdc_locks.c | 31 +--
 1 file changed, 24 insertions(+), 7 deletions(-)

diff --git a/drivers/staging/lustre/lustre/mdc/mdc_locks.c 
b/drivers/staging/lustre/lustre/mdc/mdc_locks.c
index a8aa0fa..b991c6f 100644
--- a/drivers/staging/lustre/lustre/mdc/mdc_locks.c
+++ b/drivers/staging/lustre/lustre/mdc/mdc_locks.c
@@ -326,8 +326,10 @@ static void mdc_realloc_openmsg(struct ptlrpc_request *req,
 {
struct ptlrpc_request   *req;
struct ldlm_intent  *lit;
+   u32 min_buf_size = 0;
int rc, count = 0;
LIST_HEAD(cancels);
+   u32 buf_size = 0;
 
req = ptlrpc_request_alloc(class_exp2cliimp(exp),
   _LDLM_INTENT_GETXATTR);
@@ -344,18 +346,33 @@ static void mdc_realloc_openmsg(struct ptlrpc_request 
*req,
lit = req_capsule_client_get(>rq_pill, _LDLM_INTENT);
lit->opc = IT_GETXATTR;
 
+#if LUSTRE_VERSION_CODE < OBD_OCD_VERSION(3, 0, 53, 0)
+   /* If the supplied buffer is too small then the server will
+* return -ERANGE and llite will fallback to using non cached
+* xattr operations. On servers before 2.10.1 a (non-cached)
+* listxattr RPC for an orphan or dead file causes an oops. So
+* let's try to avoid sending too small a buffer to too old a
+* server. This is effectively undoing the memory conservation
+* of LU-9417 when it would be *more* likely to crash the
+* server. See LU-9856.
+*/
+   if (exp->exp_connect_data.ocd_version < OBD_OCD_VERSION(2, 10, 1, 0))
+   min_buf_size = exp->exp_connect_data.ocd_max_easize;
+#endif
+   buf_size = max_t(u32, min_buf_size,
+GA_DEFAULT_EA_NAME_LEN * GA_DEFAULT_EA_NUM);
+
/* pack the intended request */
-   mdc_pack_body(req, _data->op_fid1, op_data->op_valid,
- GA_DEFAULT_EA_NAME_LEN * GA_DEFAULT_EA_NUM, -1, 0);
+   mdc_pack_body(req, _data->op_fid1, op_data->op_valid, buf_size,
+ -1, 0);
 
-   req_capsule_set_size(>rq_pill, _EADATA, RCL_SERVER,
-GA_DEFAULT_EA_NAME_LEN * GA_DEFAULT_EA_NUM);
+   req_capsule_set_size(>rq_pill, _EADATA, RCL_SERVER, buf_size);
 
-   req_capsule_set_size(>rq_pill, _EAVALS, RCL_SERVER,
-GA_DEFAULT_EA_NAME_LEN * GA_DEFAULT_EA_NUM);
+   req_capsule_set_size(>rq_pill, _EAVALS, RCL_SERVER, buf_size);
 
req_capsule_set_size(>rq_pill, _EAVALS_LENS, RCL_SERVER,
-sizeof(u32) * GA_DEFAULT_EA_NUM);
+max_t(u32, min_buf_size,
+  sizeof(u32) * GA_DEFAULT_EA_NUM));
 
req_capsule_set_size(>rq_pill, _ACL, RCL_SERVER, 0);
 
-- 
1.8.3.1