LU-9417 mdc: excessive memory consumption by the xattr cache

The refill operation of the xattr cache does not know the
reply size in advance, so it makes a guess based on
the maxeasize value returned by the MDS.

In practice, it allocates 16 KiB for the common case and
4 MiB for the large xattr case. However, a typical reply
is just a few hundred bytes. Even worse, RHEL6 has a very
bad vmalloc()/vfree() design with global locks.

If we follow the conservative approach, we can prepare a
single memory page for the reply. It is large enough for
any reasonable xattr set and, at the same time, it does
not require multiple page memory reclaim, which can be
costly.

If, for a specific file, the reply is larger than a single
page, the client is prepared to handle that and will fall back
to non-cached xattr code. Indeed, if this happens often and
xattrs are often used to store large values, it makes sense to
disable the xattr cache at all since it wasn't designed for
such [mis]use.

Change-Id: I98d97ffea5c83bccbc9f254717af8d2c0ac4d77f
Signed-off-by: Andrew Perepechko <andrew.perepechko@seagate.com>
Reviewed-on: https://review.whamcloud.com/26887
Reviewed-by: Fan Yong <fan.yong@intel.com>
Reviewed-by: Ben Evans <bevans@cray.com>
Tested-by: Jenkins
Tested-by: Maloo <hpdd-maloo@intel.com>
Reviewed-by: Oleg Drokin <oleg.drokin@intel.com>

diff --git a/lustre/mdc/mdc_locks.c b/lustre/mdc/mdc_locks.c
index a85324d..dad1954 100644 (file)
--- a/lustre/mdc/mdc_locks.c
+++ b/lustre/mdc/mdc_locks.c
@@ -336,6 +336,10 @@ mdc_intent_open_pack(struct obd_export *exp, struct lookup_intent *it,
         return req;
 }
 
         return req;
 }
 

+#define GA_DEFAULT_EA_NAME_LEN 20
+#define GA_DEFAULT_EA_VAL_LEN  250
+#define GA_DEFAULT_EA_NUM      10
+

 static struct ptlrpc_request *
 mdc_intent_getxattr_pack(struct obd_export *exp,
                         struct lookup_intent *it,
 static struct ptlrpc_request *
 mdc_intent_getxattr_pack(struct obd_export *exp,
                         struct lookup_intent *it,


@@ -344,7 +348,6 @@ mdc_intent_getxattr_pack(struct obd_export *exp,
        struct ptlrpc_request   *req;
        struct ldlm_intent      *lit;
        int                     rc, count = 0;
        struct ptlrpc_request   *req;
        struct ldlm_intent      *lit;
        int                     rc, count = 0;

-       __u32                   maxdata;

        struct list_head        cancels = LIST_HEAD_INIT(cancels);
 
        ENTRY;
        struct list_head        cancels = LIST_HEAD_INIT(cancels);
 
        ENTRY;


@@ -364,22 +367,21 @@ mdc_intent_getxattr_pack(struct obd_export *exp,
        lit = req_capsule_client_get(&req->rq_pill, &RMF_LDLM_INTENT);
        lit->opc = IT_GETXATTR;
 
        lit = req_capsule_client_get(&req->rq_pill, &RMF_LDLM_INTENT);
        lit->opc = IT_GETXATTR;
 

-       maxdata = class_exp2cliimp(exp)->imp_connect_data.ocd_max_easize;
-

        /* pack the intended request */
        /* pack the intended request */

-       mdc_pack_body(req, &op_data->op_fid1, op_data->op_valid, maxdata, -1,
-                     0);
+       mdc_pack_body(req, &op_data->op_fid1, op_data->op_valid,
+                     GA_DEFAULT_EA_NAME_LEN * GA_DEFAULT_EA_NUM,
+                     -1, 0);

 
 

-       req_capsule_set_size(&req->rq_pill, &RMF_EADATA,
-                               RCL_SERVER, maxdata);
+       req_capsule_set_size(&req->rq_pill, &RMF_EADATA, RCL_SERVER,
+                            GA_DEFAULT_EA_NAME_LEN * GA_DEFAULT_EA_NUM);

 
 

-       req_capsule_set_size(&req->rq_pill, &RMF_EAVALS,
-                               RCL_SERVER, maxdata);
+       req_capsule_set_size(&req->rq_pill, &RMF_EAVALS, RCL_SERVER,
+                            GA_DEFAULT_EA_VAL_LEN * GA_DEFAULT_EA_NUM);

 
 

-       req_capsule_set_size(&req->rq_pill, &RMF_EAVALS_LENS,
-                               RCL_SERVER, maxdata);
+       req_capsule_set_size(&req->rq_pill, &RMF_EAVALS_LENS, RCL_SERVER,
+                            sizeof(__u32) * GA_DEFAULT_EA_NUM);

 
 

-       req_capsule_set_size(&req->rq_pill, &RMF_ACL, RCL_SERVER, maxdata);
+       req_capsule_set_size(&req->rq_pill, &RMF_ACL, RCL_SERVER, 0);

 
        ptlrpc_request_set_replen(req);
 
 
        ptlrpc_request_set_replen(req);