LU-13134 osc: re-declare ops_from/to to shrink osc_page

@ops_from and @ops_to is within PAGE_SIZE, use PAGE_SHIFT
bits to limit it is fine, on x86_64 platform, this patch
will reduce another 8 bytes.

Notice, previous @ops_to is exclusive which could be PAGE_SIZE,
this patch change it to inclusive which means max value will be
PAGE_SIZE - 1, and be careful to calculate its length.

After this patch, cl_page size could reduce from 320 to 312 bytes,
and we are able to allocate 13 objects using slab pool for 4K page.

Change-Id: Ic260c0a6580292301b5397276042e399c0f07e11
Signed-off-by: Wang Shilong <wshilong@ddn.com>
Reviewed-on: https://review.whamcloud.com/37487
Reviewed-by: Andreas Dilger <adilger@whamcloud.com>
Reviewed-by: Neil Brown <neilb@suse.de>
Tested-by: jenkins <devops@whamcloud.com>
Tested-by: Maloo <maloo@whamcloud.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>

diff --git a/lustre/include/lustre_osc.h b/lustre/include/lustre_osc.h
index ae7b06e..4072fbd 100644 (file)
--- a/lustre/include/lustre_osc.h
+++ b/lustre/include/lustre_osc.h
@@ -496,17 +496,17 @@ struct osc_page {
         * An offset within page from which next transfer starts. This is used
         * by cl_page_clip() to submit partial page transfers.
         */
-       int                   ops_from;
+       unsigned int            ops_from:PAGE_SHIFT,
        /**
-        * An offset within page at which next transfer ends.
+        * An offset within page at which next transfer ends(inclusive).
         *
         * \see osc_page::ops_from.
         */
-       int                   ops_to;
+                               ops_to:PAGE_SHIFT,
        /**
         * Boolean, true iff page is under transfer. Used for sanity checking.
         */
-       unsigned              ops_transfer_pinned:1,
+                               ops_transfer_pinned:1,
        /**
         * in LRU?
         */

diff --git a/lustre/osc/osc_cache.c b/lustre/osc/osc_cache.c
index e2b971d..795040d 100644 (file)
--- a/lustre/osc/osc_cache.c
+++ b/lustre/osc/osc_cache.c
@@ -2323,7 +2323,7 @@ int osc_queue_async_io(const struct lu_env *env, struct cl_io *io,
 
        oap->oap_cmd = cmd;
        oap->oap_page_off = ops->ops_from;
-       oap->oap_count = ops->ops_to - ops->ops_from;
+       oap->oap_count = ops->ops_to - ops->ops_from + 1;
        /* No need to hold a lock here,
         * since this page is not in any list yet. */
        oap->oap_async_flags = 0;
@@ -2584,7 +2584,8 @@ int osc_queue_sync_pages(const struct lu_env *env, const struct cl_io *io,
                ++page_count;
                mppr <<= (page_count > mppr);
 
-               if (unlikely(opg->ops_from > 0 || opg->ops_to < PAGE_SIZE))
+               if (unlikely(opg->ops_from > 0 ||
+                            opg->ops_to < PAGE_SIZE - 1))
                        can_merge = false;
        }
 

diff --git a/lustre/osc/osc_page.c b/lustre/osc/osc_page.c
index d981845..ae7d01b 100644 (file)
--- a/lustre/osc/osc_page.c
+++ b/lustre/osc/osc_page.c
@@ -214,7 +214,8 @@ static void osc_page_clip(const struct lu_env *env,
        struct osc_async_page *oap = &opg->ops_oap;
 
        opg->ops_from = from;
-       opg->ops_to   = to;
+       /* argument @to is exclusive, but @ops_to is inclusive */
+       opg->ops_to   = to - 1;
        spin_lock(&oap->oap_lock);
        oap->oap_async_flags |= ASYNC_COUNT_STABLE;
        spin_unlock(&oap->oap_lock);
@@ -249,30 +250,29 @@ static const struct cl_page_operations osc_page_ops = {
 };
 
 int osc_page_init(const struct lu_env *env, struct cl_object *obj,
-                 struct cl_page *page, pgoff_t index)
+                 struct cl_page *cl_page, pgoff_t index)
 {
        struct osc_object *osc = cl2osc(obj);
-       struct osc_page   *opg = cl_object_page_slice(obj, page);
+       struct osc_page *opg = cl_object_page_slice(obj, cl_page);
        struct osc_io *oio = osc_env_io(env);
        int result;
 
        opg->ops_from = 0;
-       opg->ops_to   = PAGE_SIZE;
+       opg->ops_to = PAGE_SIZE - 1;
 
        INIT_LIST_HEAD(&opg->ops_lru);
 
-       result = osc_prep_async_page(osc, opg, page->cp_vmpage,
+       result = osc_prep_async_page(osc, opg, cl_page->cp_vmpage,
                                     cl_offset(obj, index));
        if (result != 0)
                return result;
 
        opg->ops_srvlock = osc_io_srvlock(oio);
-       cl_page_slice_add(page, &opg->ops_cl, obj, &osc_page_ops);
-       page->cp_osc_index = index;
-
+       cl_page_slice_add(cl_page, &opg->ops_cl, obj, &osc_page_ops);
+       cl_page->cp_osc_index = index;
 
        /* reserve an LRU space for this page */
-       if (page->cp_type == CPT_CACHEABLE) {
+       if (cl_page->cp_type == CPT_CACHEABLE) {
                result = osc_lru_alloc(env, osc_cli(osc), opg);
                if (result == 0) {
                        result = radix_tree_preload(GFP_NOFS);
@@ -310,9 +310,9 @@ void osc_page_submit(const struct lu_env *env, struct osc_page *opg,
        LASSERT(oap->oap_async_flags & ASYNC_READY);
        LASSERT(oap->oap_async_flags & ASYNC_COUNT_STABLE);
 
-       oap->oap_cmd       = crt == CRT_WRITE ? OBD_BRW_WRITE : OBD_BRW_READ;
-       oap->oap_page_off  = opg->ops_from;
-       oap->oap_count     = opg->ops_to - opg->ops_from;
+       oap->oap_cmd = crt == CRT_WRITE ? OBD_BRW_WRITE : OBD_BRW_READ;
+       oap->oap_page_off = opg->ops_from;
+       oap->oap_count = opg->ops_to - opg->ops_from + 1;
        oap->oap_brw_flags = OBD_BRW_SYNC | brw_flags;
 
        if (oio->oi_cap_sys_resource) {