OpenE2K/linux
6
0
Fork 0
Code Issues Pull Requests Releases Wiki Activity

staging: lustre: mdc: excessive memory consumption by the xattr cache

Browse Source 
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.

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.

Signed-off-by: Andrew Perepechko <c17827@cray.com>
Intel-bug-id: https://jira.hpdd.intel.com/browse/LU-9417
Reviewed-on: https://review.whamcloud.com/26887
Reviewed-by: Fan Yong <fan.yong@intel.com>
Reviewed-by: Ben Evans <bevans@cray.com>
Reviewed-by: Oleg Drokin <oleg.drokin@intel.com>
Signed-off-by: James Simmons <jsimmons@infradead.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
This commit is contained in:
Andrew Perepechko 2018-05-29 10:21:44 -04:00 committed by Greg Kroah-Hartman
parent 6f17a04439
commit 889cea43c5
1 changed files with 13 additions and 10 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

23
drivers/staging/lustre/lustre/mdc/mdc_locks.c
View File

@ -315,6 +315,10 @@ 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 * static struct ptlrpc_request *
mdc_intent_getxattr_pack(struct obd_export *exp, mdc_intent_getxattr_pack(struct obd_export *exp,
struct lookup_intent *it, struct lookup_intent *it,
@ -323,7 +327,6 @@ mdc_intent_getxattr_pack(struct obd_export *exp,
struct ptlrpc_request *req; struct ptlrpc_request *req;
struct ldlm_intent *lit; struct ldlm_intent *lit;
int rc, count = 0; int rc, count = 0;
u32 maxdata;
LIST_HEAD(cancels); LIST_HEAD(cancels);
req = ptlrpc_request_alloc(class_exp2cliimp(exp), req = ptlrpc_request_alloc(class_exp2cliimp(exp),
@ -341,20 +344,20 @@ mdc_intent_getxattr_pack(struct obd_export *exp,
lit = req_capsule_client_get(&req->rq_pill, &RMF_LDLM_INTENT); lit = req_capsule_client_get(&req->rq_pill, &RMF_LDLM_INTENT);
lit->opc = IT_GETXATTR; 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, mdc_pack_body(req, &op_data->op_fid1, op_data->op_valid,
0); 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_NAME_LEN * GA_DEFAULT_EA_NUM);
req_capsule_set_size(&req->rq_pill, &RMF_EAVALS_LENS, req_capsule_set_size(&req->rq_pill, &RMF_EAVALS_LENS, RCL_SERVER,
RCL_SERVER, maxdata); 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);