From patchwork Fri Oct 12 13:08:18 2018 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Luis Henriques X-Patchwork-Id: 10638653 Return-Path: Received: from mail.wl.linuxfoundation.org (pdx-wl-mail.web.codeaurora.org [172.30.200.125]) by pdx-korg-patchwork-2.web.codeaurora.org (Postfix) with ESMTP id 89C6913AD for ; Fri, 12 Oct 2018 13:07:31 +0000 (UTC) Received: from mail.wl.linuxfoundation.org (localhost [127.0.0.1]) by mail.wl.linuxfoundation.org (Postfix) with ESMTP id 78E1D2BA27 for ; Fri, 12 Oct 2018 13:07:31 +0000 (UTC) Received: by mail.wl.linuxfoundation.org (Postfix, from userid 486) id 6CFB02BAFF; Fri, 12 Oct 2018 13:07:31 +0000 (UTC) X-Spam-Checker-Version: SpamAssassin 3.3.1 (2010-03-16) on pdx-wl-mail.web.codeaurora.org X-Spam-Level: X-Spam-Status: No, score=-7.9 required=2.0 tests=BAYES_00,MAILING_LIST_MULTI, RCVD_IN_DNSWL_HI autolearn=ham version=3.3.1 Received: from vger.kernel.org (vger.kernel.org [209.132.180.67]) by mail.wl.linuxfoundation.org (Postfix) with ESMTP id DCF9A2BA27 for ; Fri, 12 Oct 2018 13:07:30 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1728687AbeJLUjw (ORCPT ); Fri, 12 Oct 2018 16:39:52 -0400 Received: from mx2.suse.de ([195.135.220.15]:47804 "EHLO mx1.suse.de" rhost-flags-OK-OK-OK-FAIL) by vger.kernel.org with ESMTP id S1728354AbeJLUjw (ORCPT ); Fri, 12 Oct 2018 16:39:52 -0400 X-Virus-Scanned: by amavisd-new at test-mx.suse.de Received: from relay2.suse.de (unknown [195.135.220.254]) by mx1.suse.de (Postfix) with ESMTP id BC792AEA7; Fri, 12 Oct 2018 13:07:26 +0000 (UTC) From: Luis Henriques To: "Yan, Zheng" , Sage Weil , Ilya Dryomov , Gregory Farnum Cc: ceph-devel@vger.kernel.org, Luis Henriques Subject: [RFC PATCH v6 2/4] libceph: support the RADOS copy-from operation Date: Fri, 12 Oct 2018 14:08:18 +0100 Message-Id: <20181012130820.27645-3-lhenriques@suse.com> In-Reply-To: <20181012130820.27645-1-lhenriques@suse.com> References: <20181012130820.27645-1-lhenriques@suse.com> MIME-Version: 1.0 Sender: ceph-devel-owner@vger.kernel.org Precedence: bulk List-ID: X-Mailing-List: ceph-devel@vger.kernel.org X-Virus-Scanned: ClamAV using ClamSMTP Add support for performing remote object copies using the 'copy-from' operation. Signed-off-by: Luis Henriques --- include/linux/ceph/osd_client.h | 16 ++++++ include/linux/ceph/rados.h | 28 ++++++++++ net/ceph/osd_client.c | 90 +++++++++++++++++++++++++++++++++ 3 files changed, 134 insertions(+) diff --git a/include/linux/ceph/osd_client.h b/include/linux/ceph/osd_client.h index 02096da01845..e780915dc226 100644 --- a/include/linux/ceph/osd_client.h +++ b/include/linux/ceph/osd_client.h @@ -136,6 +136,13 @@ struct ceph_osd_req_op { u64 expected_object_size; u64 expected_write_size; } alloc_hint; + struct { + u64 snapid; + u64 src_version; + u8 flags; + u32 src_fadvise_flags; + struct ceph_osd_data osd_data; + } copy_from; }; }; @@ -511,6 +518,15 @@ extern int ceph_osdc_writepages(struct ceph_osd_client *osdc, struct timespec64 *mtime, struct page **pages, int nr_pages); +int ceph_osdc_copy_from(struct ceph_osd_client *osdc, + u64 src_snapid, u64 src_version, + struct ceph_object_id *src_oid, + struct ceph_object_locator *src_oloc, + u32 src_fadvise_flags, + struct ceph_object_id *dst_oid, + struct ceph_object_locator *dst_oloc, + u8 copy_from_flags); + /* watch/notify */ struct ceph_osd_linger_request * ceph_osdc_watch(struct ceph_osd_client *osdc, diff --git a/include/linux/ceph/rados.h b/include/linux/ceph/rados.h index f1988387c5ad..cd8726b1b8a5 100644 --- a/include/linux/ceph/rados.h +++ b/include/linux/ceph/rados.h @@ -410,6 +410,14 @@ enum { enum { CEPH_OSD_OP_FLAG_EXCL = 1, /* EXCL object create */ CEPH_OSD_OP_FLAG_FAILOK = 2, /* continue despite failure */ + CEPH_OSD_OP_FLAG_FADVISE_RANDOM = 0x4, /* the op is random */ + CEPH_OSD_OP_FLAG_FADVISE_SEQUENTIAL = 0x8, /* the op is sequential */ + CEPH_OSD_OP_FLAG_FADVISE_WILLNEED = 0x10,/* data will be accessed in + the near future */ + CEPH_OSD_OP_FLAG_FADVISE_DONTNEED = 0x20,/* data will not be accessed + in the near future */ + CEPH_OSD_OP_FLAG_FADVISE_NOCACHE = 0x40,/* data will be accessed only + once by this client */ }; #define EOLDSNAPC ERESTART /* ORDERSNAP flag set; writer has old snapc*/ @@ -431,6 +439,15 @@ enum { CEPH_OSD_CMPXATTR_MODE_U64 = 2 }; +enum { + CEPH_OSD_COPY_FROM_FLAG_FLUSH = 1, /* part of a flush operation */ + CEPH_OSD_COPY_FROM_FLAG_IGNORE_OVERLAY = 2, /* ignore pool overlay */ + CEPH_OSD_COPY_FROM_FLAG_IGNORE_CACHE = 4, /* ignore osd cache logic */ + CEPH_OSD_COPY_FROM_FLAG_MAP_SNAP_CLONE = 8, /* map snap direct to + * cloneid */ + CEPH_OSD_COPY_FROM_FLAG_RWORDERED = 16, /* order with write */ +}; + enum { CEPH_OSD_WATCH_OP_UNWATCH = 0, CEPH_OSD_WATCH_OP_LEGACY_WATCH = 1, @@ -497,6 +514,17 @@ struct ceph_osd_op { __le64 expected_object_size; __le64 expected_write_size; } __attribute__ ((packed)) alloc_hint; + struct { + __le64 snapid; + __le64 src_version; + __u8 flags; /* CEPH_OSD_COPY_FROM_FLAG_* */ + /* + * CEPH_OSD_OP_FLAG_FADVISE_*: fadvise flags for src + * object, fadvise flags for dest object are in + * ceph_osd_op::flags. + */ + __le32 src_fadvise_flags; + } __attribute__ ((packed)) copy_from; }; __le32 payload_len; } __attribute__ ((packed)); diff --git a/net/ceph/osd_client.c b/net/ceph/osd_client.c index 60934bd8796c..f89943288a6f 100644 --- a/net/ceph/osd_client.c +++ b/net/ceph/osd_client.c @@ -402,6 +402,9 @@ static void osd_req_op_data_release(struct ceph_osd_request *osd_req, case CEPH_OSD_OP_LIST_WATCHERS: ceph_osd_data_release(&op->list_watchers.response_data); break; + case CEPH_OSD_OP_COPY_FROM: + ceph_osd_data_release(&op->copy_from.osd_data); + break; default: break; } @@ -955,6 +958,14 @@ static u32 osd_req_encode_op(struct ceph_osd_op *dst, case CEPH_OSD_OP_CREATE: case CEPH_OSD_OP_DELETE: break; + case CEPH_OSD_OP_COPY_FROM: + dst->copy_from.snapid = cpu_to_le64(src->copy_from.snapid); + dst->copy_from.src_version = + cpu_to_le64(src->copy_from.src_version); + dst->copy_from.flags = src->copy_from.flags; + dst->copy_from.src_fadvise_flags = + cpu_to_le32(src->copy_from.src_fadvise_flags); + break; default: pr_err("unsupported osd opcode %s\n", ceph_osd_op_name(src->op)); @@ -1875,6 +1886,9 @@ static void setup_request_data(struct ceph_osd_request *req, ceph_osdc_msg_data_add(msg, &op->notify_ack.request_data); break; + case CEPH_OSD_OP_COPY_FROM: + ceph_osdc_msg_data_add(msg, &op->copy_from.osd_data); + break; /* reply */ case CEPH_OSD_OP_STAT: @@ -5168,6 +5182,82 @@ int ceph_osdc_writepages(struct ceph_osd_client *osdc, struct ceph_vino vino, } EXPORT_SYMBOL(ceph_osdc_writepages); +static int osd_req_op_copy_from_init(struct ceph_osd_request *req, + u64 src_snapid, u64 src_version, + struct ceph_object_id *src_oid, + struct ceph_object_locator *src_oloc, + u32 src_fadvise_flags, + u8 copy_from_flags) +{ + struct ceph_osd_req_op *op; + struct page **pages; + void *p, *end; + + pages = ceph_alloc_page_vector(1, GFP_KERNEL); + if (IS_ERR(pages)) + return PTR_ERR(pages); + + op = _osd_req_op_init(req, 0, CEPH_OSD_OP_COPY_FROM, 0); + op->copy_from.snapid = src_snapid; + op->copy_from.src_version = src_version; + op->copy_from.flags = copy_from_flags; + op->copy_from.src_fadvise_flags = src_fadvise_flags; + + p = page_address(pages[0]); + end = p + PAGE_SIZE; + ceph_encode_string(&p, end, src_oid->name, src_oid->name_len); + encode_oloc(&p, end, src_oloc); + op->indata_len = PAGE_SIZE - (end - p); + + ceph_osd_data_pages_init(&op->copy_from.osd_data, pages, + op->indata_len, 0, + false, true); + return 0; +} + +int ceph_osdc_copy_from(struct ceph_osd_client *osdc, + u64 src_snapid, u64 src_version, + struct ceph_object_id *src_oid, + struct ceph_object_locator *src_oloc, + u32 src_fadvise_flags, + struct ceph_object_id *dst_oid, + struct ceph_object_locator *dst_oloc, + u8 copy_from_flags) +{ + struct ceph_osd_request *req = NULL; + int ret; + + req = ceph_osdc_alloc_request(osdc, NULL, 1, false, GFP_KERNEL); + if (!req) + return -ENOMEM; + + req->r_flags = CEPH_OSD_FLAG_WRITE; + req->r_snapid = CEPH_NOSNAP; + req->r_data_offset = 0; + + ceph_oloc_copy(&req->r_t.base_oloc, dst_oloc); + ceph_oid_copy(&req->r_t.base_oid, dst_oid); + + ret = ceph_osdc_alloc_messages(req, GFP_KERNEL); + if (ret) + goto out; + + ret = osd_req_op_copy_from_init(req, src_snapid, src_version, src_oid, + src_oloc, src_fadvise_flags, + copy_from_flags); + if (ret) + goto out; + + ceph_osdc_start_request(osdc, req, false); + ret = ceph_osdc_wait_request(osdc, req); + +out: + ceph_osdc_put_request(req); + + return ret; +} +EXPORT_SYMBOL(ceph_osdc_copy_from); + int __init ceph_osdc_setup(void) { size_t size = sizeof(struct ceph_osd_request) +