Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S932420Ab3CMHGK (ORCPT ); Wed, 13 Mar 2013 03:06:10 -0400 Received: from e28smtp07.in.ibm.com ([122.248.162.7]:44659 "EHLO e28smtp07.in.ibm.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1755978Ab3CMHF6 (ORCPT ); Wed, 13 Mar 2013 03:05:58 -0400 From: Wanpeng Li To: Andrew Morton Cc: Greg Kroah-Hartman , Dan Magenheimer , Seth Jennings , Konrad Rzeszutek Wilk , Minchan Kim , linux-mm@kvack.org, linux-kernel@vger.kernel.org, Wanpeng Li Subject: [PATCH 2/4] zcache: zero-filled pages awareness Date: Wed, 13 Mar 2013 15:05:19 +0800 Message-Id: <1363158321-20790-3-git-send-email-liwanp@linux.vnet.ibm.com> X-Mailer: git-send-email 1.7.5.4 In-Reply-To: <1363158321-20790-1-git-send-email-liwanp@linux.vnet.ibm.com> References: <1363158321-20790-1-git-send-email-liwanp@linux.vnet.ibm.com> X-TM-AS-MML: No X-Content-Scanned: Fidelis XPS MAILER x-cbid: 13031307-8878-0000-0000-0000063E2213 Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Length: 7339 Lines: 246 Compression of zero-filled pages can unneccessarily cause internal fragmentation, and thus waste memory. This special case can be optimized. This patch captures zero-filled pages, and marks their corresponding zcache backing page entry as zero-filled. Whenever such zero-filled page is retrieved, we fill the page frame with zero. Signed-off-by: Wanpeng Li --- drivers/staging/zcache/tmem.c | 4 +- drivers/staging/zcache/tmem.h | 5 ++ drivers/staging/zcache/zcache-main.c | 87 ++++++++++++++++++++++++++++++---- 3 files changed, 85 insertions(+), 11 deletions(-) diff --git a/drivers/staging/zcache/tmem.c b/drivers/staging/zcache/tmem.c index a2b7e03..62468ea 100644 --- a/drivers/staging/zcache/tmem.c +++ b/drivers/staging/zcache/tmem.c @@ -597,7 +597,9 @@ int tmem_put(struct tmem_pool *pool, struct tmem_oid *oidp, uint32_t index, if (unlikely(ret == -ENOMEM)) /* may have partially built objnode tree ("stump") */ goto delete_and_free; - (*tmem_pamops.create_finish)(pampd, is_ephemeral(pool)); + if (pampd != (void *)ZERO_FILLED) + (*tmem_pamops.create_finish)(pampd, is_ephemeral(pool)); + goto out; delete_and_free: diff --git a/drivers/staging/zcache/tmem.h b/drivers/staging/zcache/tmem.h index adbe5a8..6719dbd 100644 --- a/drivers/staging/zcache/tmem.h +++ b/drivers/staging/zcache/tmem.h @@ -204,6 +204,11 @@ struct tmem_handle { uint16_t client_id; }; +/* + * mark pampd to special vaule in order that later + * retrieve will identify zero-filled pages + */ +#define ZERO_FILLED 0x2 /* pampd abstract datatype methods provided by the PAM implementation */ struct tmem_pamops { diff --git a/drivers/staging/zcache/zcache-main.c b/drivers/staging/zcache/zcache-main.c index b71e033..ed5ef26 100644 --- a/drivers/staging/zcache/zcache-main.c +++ b/drivers/staging/zcache/zcache-main.c @@ -543,7 +543,23 @@ static void *zcache_pampd_eph_create(char *data, size_t size, bool raw, { void *pampd = NULL, *cdata = data; unsigned clen = size; + bool zero_filled = false; struct page *page = (struct page *)(data), *newpage; + char *user_mem; + + user_mem = kmap_atomic(page); + + /* + * Compressing zero-filled pages will waste memory and introduce + * serious fragmentation, skip it to avoid overhead + */ + if (page_zero_filled(user_mem)) { + kunmap_atomic(user_mem); + clen = 0; + zero_filled = true; + goto got_pampd; + } + kunmap_atomic(user_mem); if (!raw) { zcache_compress(page, &cdata, &clen); @@ -592,6 +608,8 @@ got_pampd: zcache_eph_zpages_max = zcache_eph_zpages; if (ramster_enabled && raw) ramster_count_foreign_pages(true, 1); + if (zero_filled) + pampd = (void *)ZERO_FILLED; out: return pampd; } @@ -600,15 +618,31 @@ static void *zcache_pampd_pers_create(char *data, size_t size, bool raw, struct tmem_handle *th) { void *pampd = NULL, *cdata = data; - unsigned clen = size; + unsigned clen = size, zero_filled = 0; struct page *page = (struct page *)(data), *newpage; unsigned long zbud_mean_zsize; unsigned long curr_pers_zpages, total_zsize; + char *user_mem; if (data == NULL) { BUG_ON(!ramster_enabled); goto create_pampd; } + + user_mem = kmap_atomic(page); + + /* + * Compressing zero-filled pages will waste memory and introduce + * serious fragmentation, skip it to avoid overhead + */ + if (page_zero_filled(page)) { + kunmap_atomic(user_mem); + clen = 0; + zero_filled = 1; + goto got_pampd; + } + kunmap_atomic(user_mem); + curr_pers_zpages = zcache_pers_zpages; /* FIXME CONFIG_RAMSTER... subtract atomic remote_pers_pages here? */ if (!raw) @@ -674,6 +708,8 @@ got_pampd: zcache_pers_zbytes_max = zcache_pers_zbytes; if (ramster_enabled && raw) ramster_count_foreign_pages(false, 1); + if (zero_filled) + pampd = (void *)ZERO_FILLED; out: return pampd; } @@ -780,6 +816,14 @@ static int zcache_pampd_get_data(char *data, size_t *sizep, bool raw, BUG_ON(preemptible()); BUG_ON(eph); /* fix later if shared pools get implemented */ BUG_ON(pampd_is_remote(pampd)); + + if (pampd == (void *)ZERO_FILLED) { + handle_zero_page(data); + if (!raw) + *sizep = PAGE_SIZE; + return 0; + } + if (raw) ret = zbud_copy_from_zbud(data, (struct zbudref *)pampd, sizep, eph); @@ -800,13 +844,24 @@ static int zcache_pampd_get_data_and_free(char *data, size_t *sizep, bool raw, void *pampd, struct tmem_pool *pool, struct tmem_oid *oid, uint32_t index) { - int ret; - bool eph = !is_persistent(pool); + int ret = 0; + bool eph = !is_persistent(pool), zero_filled = false; struct page *page = NULL; unsigned int zsize, zpages; BUG_ON(preemptible()); BUG_ON(pampd_is_remote(pampd)); + + if (pampd == (void *)ZERO_FILLED) { + handle_zero_page(data); + zero_filled = true; + zsize = 0; + zpages = 1; + if (!raw) + *sizep = PAGE_SIZE; + goto zero_fill; + } + if (raw) ret = zbud_copy_from_zbud(data, (struct zbudref *)pampd, sizep, eph); @@ -818,8 +873,9 @@ static int zcache_pampd_get_data_and_free(char *data, size_t *sizep, bool raw, } page = zbud_free_and_delist((struct zbudref *)pampd, eph, &zsize, &zpages); +zero_fill: if (eph) { - if (page) + if (page || zero_filled) zcache_eph_pageframes = atomic_dec_return(&zcache_eph_pageframes_atomic); zcache_eph_zpages = @@ -827,7 +883,7 @@ static int zcache_pampd_get_data_and_free(char *data, size_t *sizep, bool raw, zcache_eph_zbytes = atomic_long_sub_return(zsize, &zcache_eph_zbytes_atomic); } else { - if (page) + if (page || zero_filled) zcache_pers_pageframes = atomic_dec_return(&zcache_pers_pageframes_atomic); zcache_pers_zpages = @@ -837,7 +893,7 @@ static int zcache_pampd_get_data_and_free(char *data, size_t *sizep, bool raw, } if (!is_local_client(pool->client)) ramster_count_foreign_pages(eph, -1); - if (page) + if (page && !zero_filled) zcache_free_page(page); return ret; } @@ -851,18 +907,29 @@ static void zcache_pampd_free(void *pampd, struct tmem_pool *pool, { struct page *page = NULL; unsigned int zsize, zpages; + bool zero_filled = false; BUG_ON(preemptible()); - if (pampd_is_remote(pampd)) { + + if (pampd == (void *)ZERO_FILLED) { + zero_filled = true; + zsize = 0; + zpages = 1; + } + + if (pampd_is_remote(pampd) && !zero_filled) { + BUG_ON(!ramster_enabled); pampd = ramster_pampd_free(pampd, pool, oid, index, acct); if (pampd == NULL) return; } if (is_ephemeral(pool)) { - page = zbud_free_and_delist((struct zbudref *)pampd, + if (!zero_filled) + page = zbud_free_and_delist((struct zbudref *)pampd, + true, &zsize, &zpages); - if (page) + if (page || zero_filled) zcache_eph_pageframes = atomic_dec_return(&zcache_eph_pageframes_atomic); zcache_eph_zpages = @@ -883,7 +950,7 @@ static void zcache_pampd_free(void *pampd, struct tmem_pool *pool, } if (!is_local_client(pool->client)) ramster_count_foreign_pages(is_ephemeral(pool), -1); - if (page) + if (page && !zero_filled) zcache_free_page(page); } -- 1.7.7.6 -- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/