From patchwork Tue Jun 30 07:52:15 2020 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Xiubo Li X-Patchwork-Id: 11633413 Return-Path: Received: from mail.kernel.org (pdx-korg-mail-1.web.codeaurora.org [172.30.200.123]) by pdx-korg-patchwork-2.web.codeaurora.org (Postfix) with ESMTP id E635E912 for ; Tue, 30 Jun 2020 07:52:49 +0000 (UTC) Received: from vger.kernel.org (vger.kernel.org [23.128.96.18]) by mail.kernel.org (Postfix) with ESMTP id C7B5520768 for ; Tue, 30 Jun 2020 07:52:49 +0000 (UTC) Authentication-Results: mail.kernel.org; dkim=pass (1024-bit key) header.d=redhat.com header.i=@redhat.com header.b="XnMvjXo/" Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1731344AbgF3Hwt (ORCPT ); Tue, 30 Jun 2020 03:52:49 -0400 Received: from us-smtp-2.mimecast.com ([205.139.110.61]:35825 "EHLO us-smtp-delivery-1.mimecast.com" rhost-flags-OK-OK-OK-FAIL) by vger.kernel.org with ESMTP id S1731323AbgF3Hwr (ORCPT ); Tue, 30 Jun 2020 03:52:47 -0400 DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=redhat.com; s=mimecast20190719; t=1593503565; h=from:from:reply-to:subject:subject:date:date:message-id:message-id: to:to:cc:cc:in-reply-to:in-reply-to:references:references; bh=69CLOkx27owYWk54Ss3oJosZTkdWjdGWT3qu9pcVz/0=; b=XnMvjXo/ON/AQmhZ0TmnvGE7KTRIaueRJgLA/dEAqisUJdnmfYO7F+OzsQsUzahO6j2BDc ryBuQu/ESFHX9Mu+eJyLns1tGi0aHS8b5tj98fBgqxNyvA8g57JToFgIXXsYD1KwfdjLB9 9+o+WphZPruX+B1p+teWXzhyuXhwmBs= Received: from mimecast-mx01.redhat.com (mimecast-mx01.redhat.com [209.132.183.4]) (Using TLS) by relay.mimecast.com with ESMTP id us-mta-336-uk4oeNUXNaSLGH6CGdMGlA-1; Tue, 30 Jun 2020 03:52:41 -0400 X-MC-Unique: uk4oeNUXNaSLGH6CGdMGlA-1 Received: from smtp.corp.redhat.com (int-mx07.intmail.prod.int.phx2.redhat.com [10.5.11.22]) (using TLSv1.2 with cipher AECDH-AES256-SHA (256/256 bits)) (No client certificate requested) by mimecast-mx01.redhat.com (Postfix) with ESMTPS id EB1B8193F560; Tue, 30 Jun 2020 07:52:39 +0000 (UTC) Received: from lxbceph0.gsslab.pek2.redhat.com (vm37-55.gsslab.pek2.redhat.com [10.72.37.55]) by smtp.corp.redhat.com (Postfix) with ESMTP id CD37D10098A4; Tue, 30 Jun 2020 07:52:37 +0000 (UTC) From: xiubli@redhat.com To: jlayton@kernel.org Cc: idryomov@gmail.com, zyan@redhat.com, pdonnell@redhat.com, vshankar@redhat.com, ceph-devel@vger.kernel.org, Xiubo Li Subject: [PATCH v5 1/5] ceph: add check_session_state helper and make it global Date: Tue, 30 Jun 2020 03:52:15 -0400 Message-Id: <1593503539-1209-2-git-send-email-xiubli@redhat.com> In-Reply-To: <1593503539-1209-1-git-send-email-xiubli@redhat.com> References: <1593503539-1209-1-git-send-email-xiubli@redhat.com> X-Scanned-By: MIMEDefang 2.84 on 10.5.11.22 Sender: ceph-devel-owner@vger.kernel.org Precedence: bulk List-ID: X-Mailing-List: ceph-devel@vger.kernel.org From: Xiubo Li And remove the unsed mdsc parameter to simplify the code. URL: https://tracker.ceph.com/issues/43215 Signed-off-by: Xiubo Li --- fs/ceph/mds_client.c | 47 +++++++++++++++++++++++++++-------------------- fs/ceph/mds_client.h | 3 +++ 2 files changed, 30 insertions(+), 20 deletions(-) diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c index a504971..58c54d4 100644 --- a/fs/ceph/mds_client.c +++ b/fs/ceph/mds_client.c @@ -1785,8 +1785,7 @@ static void renewed_caps(struct ceph_mds_client *mdsc, /* * send a session close request */ -static int request_close_session(struct ceph_mds_client *mdsc, - struct ceph_mds_session *session) +static int request_close_session(struct ceph_mds_session *session) { struct ceph_msg *msg; @@ -1809,7 +1808,7 @@ static int __close_session(struct ceph_mds_client *mdsc, if (session->s_state >= CEPH_MDS_SESSION_CLOSING) return 0; session->s_state = CEPH_MDS_SESSION_CLOSING; - return request_close_session(mdsc, session); + return request_close_session(session); } static bool drop_negative_children(struct dentry *dentry) @@ -4263,6 +4262,29 @@ static void maybe_recover_session(struct ceph_mds_client *mdsc) ceph_force_reconnect(fsc->sb); } +bool check_session_state(struct ceph_mds_session *s) +{ + if (s->s_state == CEPH_MDS_SESSION_CLOSING) { + dout("resending session close request for mds%d\n", + s->s_mds); + request_close_session(s); + return false; + } + if (s->s_ttl && time_after(jiffies, s->s_ttl)) { + if (s->s_state == CEPH_MDS_SESSION_OPEN) { + s->s_state = CEPH_MDS_SESSION_HUNG; + pr_info("mds%d hung\n", s->s_mds); + } + } + if (s->s_state == CEPH_MDS_SESSION_NEW || + s->s_state == CEPH_MDS_SESSION_RESTARTING || + s->s_state == CEPH_MDS_SESSION_REJECTED) + /* this mds is failed or recovering, just wait */ + return false; + + return true; +} + /* * delayed work -- periodically trim expired leases, renew caps with mds */ @@ -4294,23 +4316,8 @@ static void delayed_work(struct work_struct *work) struct ceph_mds_session *s = __ceph_lookup_mds_session(mdsc, i); if (!s) continue; - if (s->s_state == CEPH_MDS_SESSION_CLOSING) { - dout("resending session close request for mds%d\n", - s->s_mds); - request_close_session(mdsc, s); - ceph_put_mds_session(s); - continue; - } - if (s->s_ttl && time_after(jiffies, s->s_ttl)) { - if (s->s_state == CEPH_MDS_SESSION_OPEN) { - s->s_state = CEPH_MDS_SESSION_HUNG; - pr_info("mds%d hung\n", s->s_mds); - } - } - if (s->s_state == CEPH_MDS_SESSION_NEW || - s->s_state == CEPH_MDS_SESSION_RESTARTING || - s->s_state == CEPH_MDS_SESSION_REJECTED) { - /* this mds is failed or recovering, just wait */ + + if (!check_session_state(s)) { ceph_put_mds_session(s); continue; } diff --git a/fs/ceph/mds_client.h b/fs/ceph/mds_client.h index 5e0c407..6147ff0 100644 --- a/fs/ceph/mds_client.h +++ b/fs/ceph/mds_client.h @@ -18,6 +18,7 @@ #include #include "metric.h" +#include "super.h" /* The first 8 bits are reserved for old ceph releases */ enum ceph_feature_type { @@ -476,6 +477,8 @@ struct ceph_mds_client { extern const char *ceph_mds_op_name(int op); +extern bool check_session_state(struct ceph_mds_session *s); + extern struct ceph_mds_session * __ceph_lookup_mds_session(struct ceph_mds_client *, int mds); From patchwork Tue Jun 30 07:52:16 2020 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Xiubo Li X-Patchwork-Id: 11633415 Return-Path: Received: from mail.kernel.org (pdx-korg-mail-1.web.codeaurora.org [172.30.200.123]) by pdx-korg-patchwork-2.web.codeaurora.org (Postfix) with ESMTP id 8DDE3161F for ; Tue, 30 Jun 2020 07:52:50 +0000 (UTC) Received: from vger.kernel.org (vger.kernel.org [23.128.96.18]) by mail.kernel.org (Postfix) with ESMTP id 7580B20768 for ; Tue, 30 Jun 2020 07:52:50 +0000 (UTC) Authentication-Results: mail.kernel.org; dkim=pass (1024-bit key) header.d=redhat.com header.i=@redhat.com header.b="PW1SK+pj" Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1731342AbgF3Hws (ORCPT ); Tue, 30 Jun 2020 03:52:48 -0400 Received: from us-smtp-delivery-1.mimecast.com ([207.211.31.120]:36823 "EHLO us-smtp-1.mimecast.com" rhost-flags-OK-OK-OK-FAIL) by vger.kernel.org with ESMTP id S1731334AbgF3Hwr (ORCPT ); Tue, 30 Jun 2020 03:52:47 -0400 DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=redhat.com; s=mimecast20190719; t=1593503566; h=from:from:reply-to:subject:subject:date:date:message-id:message-id: to:to:cc:cc:in-reply-to:in-reply-to:references:references; bh=lwdvplOD6S+epb2QnjHsJr6hI7dgFp/xOoG3CaiyzZA=; b=PW1SK+pjPW5AbtWex0NEEn6Xbdf9w/4HvgAuvsv8Djfn38WWMJt1b/GrCaYBZuvHMnA8HT UxAd3l1X2uFSoe+xTl5UnUOm0YZqTSCxUxFhFpzy1JlUAhSAqYylyYAVIsk9e97b93xPRF KmvALt5nVP1E9dwWtgJ2fF+8NdNfoVk= Received: from mimecast-mx01.redhat.com (mimecast-mx01.redhat.com [209.132.183.4]) (Using TLS) by relay.mimecast.com with ESMTP id us-mta-495-AHHySSNNPE-6-Hi7gUwmWQ-1; Tue, 30 Jun 2020 03:52:43 -0400 X-MC-Unique: AHHySSNNPE-6-Hi7gUwmWQ-1 Received: from smtp.corp.redhat.com (int-mx07.intmail.prod.int.phx2.redhat.com [10.5.11.22]) (using TLSv1.2 with cipher AECDH-AES256-SHA (256/256 bits)) (No client certificate requested) by mimecast-mx01.redhat.com (Postfix) with ESMTPS id CE132107ACF5; Tue, 30 Jun 2020 07:52:42 +0000 (UTC) Received: from lxbceph0.gsslab.pek2.redhat.com (vm37-55.gsslab.pek2.redhat.com [10.72.37.55]) by smtp.corp.redhat.com (Postfix) with ESMTP id 71A6C1000079; Tue, 30 Jun 2020 07:52:40 +0000 (UTC) From: xiubli@redhat.com To: jlayton@kernel.org Cc: idryomov@gmail.com, zyan@redhat.com, pdonnell@redhat.com, vshankar@redhat.com, ceph-devel@vger.kernel.org, Xiubo Li Subject: [PATCH v5 2/5] ceph: add global total_caps to count the mdsc's total caps number Date: Tue, 30 Jun 2020 03:52:16 -0400 Message-Id: <1593503539-1209-3-git-send-email-xiubli@redhat.com> In-Reply-To: <1593503539-1209-1-git-send-email-xiubli@redhat.com> References: <1593503539-1209-1-git-send-email-xiubli@redhat.com> X-Scanned-By: MIMEDefang 2.84 on 10.5.11.22 Sender: ceph-devel-owner@vger.kernel.org Precedence: bulk List-ID: X-Mailing-List: ceph-devel@vger.kernel.org From: Xiubo Li This will help to reduce using the global mdsc->metux lock in many places. URL: https://tracker.ceph.com/issues/43215 Signed-off-by: Xiubo Li --- fs/ceph/caps.c | 2 ++ fs/ceph/debugfs.c | 14 ++------------ fs/ceph/mds_client.c | 1 + fs/ceph/metric.c | 1 + fs/ceph/metric.h | 1 + 5 files changed, 7 insertions(+), 12 deletions(-) diff --git a/fs/ceph/caps.c b/fs/ceph/caps.c index 972c13a..5f48940 100644 --- a/fs/ceph/caps.c +++ b/fs/ceph/caps.c @@ -668,6 +668,7 @@ void ceph_add_cap(struct inode *inode, spin_lock(&session->s_cap_lock); list_add_tail(&cap->session_caps, &session->s_caps); session->s_nr_caps++; + atomic64_inc(&mdsc->metric.total_caps); spin_unlock(&session->s_cap_lock); } else { spin_lock(&session->s_cap_lock); @@ -1161,6 +1162,7 @@ void __ceph_remove_cap(struct ceph_cap *cap, bool queue_release) } else { list_del_init(&cap->session_caps); session->s_nr_caps--; + atomic64_dec(&mdsc->metric.total_caps); cap->session = NULL; removed = 1; } diff --git a/fs/ceph/debugfs.c b/fs/ceph/debugfs.c index 070ed84..3030f55 100644 --- a/fs/ceph/debugfs.c +++ b/fs/ceph/debugfs.c @@ -145,7 +145,7 @@ static int metric_show(struct seq_file *s, void *p) struct ceph_fs_client *fsc = s->private; struct ceph_mds_client *mdsc = fsc->mdsc; struct ceph_client_metric *m = &mdsc->metric; - int i, nr_caps = 0; + int nr_caps = 0; s64 total, sum, avg, min, max, sq; seq_printf(s, "item total avg_lat(us) min_lat(us) max_lat(us) stdev(us)\n"); @@ -190,17 +190,7 @@ static int metric_show(struct seq_file *s, void *p) percpu_counter_sum(&m->d_lease_mis), percpu_counter_sum(&m->d_lease_hit)); - mutex_lock(&mdsc->mutex); - for (i = 0; i < mdsc->max_sessions; i++) { - struct ceph_mds_session *s; - - s = __ceph_lookup_mds_session(mdsc, i); - if (!s) - continue; - nr_caps += s->s_nr_caps; - ceph_put_mds_session(s); - } - mutex_unlock(&mdsc->mutex); + nr_caps = atomic64_read(&m->total_caps); seq_printf(s, "%-14s%-16d%-16lld%lld\n", "caps", nr_caps, percpu_counter_sum(&m->i_caps_mis), percpu_counter_sum(&m->i_caps_hit)); diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c index 58c54d4..f3c7123 100644 --- a/fs/ceph/mds_client.c +++ b/fs/ceph/mds_client.c @@ -1485,6 +1485,7 @@ int ceph_iterate_session_caps(struct ceph_mds_session *session, cap->session = NULL; list_del_init(&cap->session_caps); session->s_nr_caps--; + atomic64_dec(&session->s_mdsc->metric.total_caps); if (cap->queue_release) __ceph_queue_cap_release(session, cap); else diff --git a/fs/ceph/metric.c b/fs/ceph/metric.c index 9217f35..269eacb 100644 --- a/fs/ceph/metric.c +++ b/fs/ceph/metric.c @@ -22,6 +22,7 @@ int ceph_metric_init(struct ceph_client_metric *m) if (ret) goto err_d_lease_mis; + atomic64_set(&m->total_caps, 0); ret = percpu_counter_init(&m->i_caps_hit, 0, GFP_KERNEL); if (ret) goto err_i_caps_hit; diff --git a/fs/ceph/metric.h b/fs/ceph/metric.h index ccd8128..23a3373 100644 --- a/fs/ceph/metric.h +++ b/fs/ceph/metric.h @@ -12,6 +12,7 @@ struct ceph_client_metric { struct percpu_counter d_lease_hit; struct percpu_counter d_lease_mis; + atomic64_t total_caps; struct percpu_counter i_caps_hit; struct percpu_counter i_caps_mis; From patchwork Tue Jun 30 07:52:17 2020 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Xiubo Li X-Patchwork-Id: 11633419 Return-Path: Received: from mail.kernel.org (pdx-korg-mail-1.web.codeaurora.org [172.30.200.123]) by pdx-korg-patchwork-2.web.codeaurora.org (Postfix) with ESMTP id BFDB8912 for ; Tue, 30 Jun 2020 07:52:53 +0000 (UTC) Received: from vger.kernel.org (vger.kernel.org [23.128.96.18]) by mail.kernel.org (Postfix) with ESMTP id A2A7120768 for ; Tue, 30 Jun 2020 07:52:53 +0000 (UTC) Authentication-Results: mail.kernel.org; dkim=pass (1024-bit key) header.d=redhat.com header.i=@redhat.com header.b="XZ/mnz5q" Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1731347AbgF3Hww (ORCPT ); Tue, 30 Jun 2020 03:52:52 -0400 Received: from us-smtp-2.mimecast.com ([205.139.110.61]:44213 "EHLO us-smtp-delivery-1.mimecast.com" rhost-flags-OK-OK-OK-FAIL) by vger.kernel.org with ESMTP id S1728749AbgF3Hwv (ORCPT ); Tue, 30 Jun 2020 03:52:51 -0400 DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=redhat.com; s=mimecast20190719; t=1593503569; h=from:from:reply-to:subject:subject:date:date:message-id:message-id: to:to:cc:cc:in-reply-to:in-reply-to:references:references; bh=OCz0khsSqwaO8ibxOLigvC8bZSAY1JcP4VYgcAe31As=; b=XZ/mnz5qreIOrzSmgMeXJZ7ARqXh6UVvGuM8MIPZSGDPR0wMdD5dTqIxX7i+VxMKkudg7B 2fLTfq3RLIBMWTyICM5G18OaaLkC/KPbRRgahhdvzv6iy5GDVG7TU+zLK6h7nXTYGxPR28 A+sm6g7FctC6heQCYzRL3iwW0v6zs6k= Received: from mimecast-mx01.redhat.com (mimecast-mx01.redhat.com [209.132.183.4]) (Using TLS) by relay.mimecast.com with ESMTP id us-mta-490-et4Bpch1Pg2PuqKZ8lrpdw-1; Tue, 30 Jun 2020 03:52:46 -0400 X-MC-Unique: et4Bpch1Pg2PuqKZ8lrpdw-1 Received: from smtp.corp.redhat.com (int-mx07.intmail.prod.int.phx2.redhat.com [10.5.11.22]) (using TLSv1.2 with cipher AECDH-AES256-SHA (256/256 bits)) (No client certificate requested) by mimecast-mx01.redhat.com (Postfix) with ESMTPS id B20F4A0BDC; Tue, 30 Jun 2020 07:52:45 +0000 (UTC) Received: from lxbceph0.gsslab.pek2.redhat.com (vm37-55.gsslab.pek2.redhat.com [10.72.37.55]) by smtp.corp.redhat.com (Postfix) with ESMTP id 55C4E1000079; Tue, 30 Jun 2020 07:52:43 +0000 (UTC) From: xiubli@redhat.com To: jlayton@kernel.org Cc: idryomov@gmail.com, zyan@redhat.com, pdonnell@redhat.com, vshankar@redhat.com, ceph-devel@vger.kernel.org, Xiubo Li Subject: [PATCH v5 3/5] ceph: periodically send perf metrics to ceph Date: Tue, 30 Jun 2020 03:52:17 -0400 Message-Id: <1593503539-1209-4-git-send-email-xiubli@redhat.com> In-Reply-To: <1593503539-1209-1-git-send-email-xiubli@redhat.com> References: <1593503539-1209-1-git-send-email-xiubli@redhat.com> X-Scanned-By: MIMEDefang 2.84 on 10.5.11.22 Sender: ceph-devel-owner@vger.kernel.org Precedence: bulk List-ID: X-Mailing-List: ceph-devel@vger.kernel.org From: Xiubo Li This will send the caps/read/write/metadata metrics to any available MDS only once per second as default, which will be the same as the userland client. It will skip the MDS sessions which don't support the metric collection, or the MDSs will close the socket connections directly when it get an unknown type message. We can disable the metric sending via the enable_send_metric module parameter. URL: https://tracker.ceph.com/issues/43215 Signed-off-by: Xiubo Li --- fs/ceph/mds_client.c | 12 ++++ fs/ceph/mds_client.h | 4 +- fs/ceph/metric.c | 157 +++++++++++++++++++++++++++++++++++++++++++ fs/ceph/metric.h | 82 ++++++++++++++++++++++ fs/ceph/super.c | 42 ++++++++++++ fs/ceph/super.h | 2 + include/linux/ceph/ceph_fs.h | 1 + 7 files changed, 299 insertions(+), 1 deletion(-) diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c index f3c7123..bcdda5a 100644 --- a/fs/ceph/mds_client.c +++ b/fs/ceph/mds_client.c @@ -1809,6 +1809,11 @@ static int __close_session(struct ceph_mds_client *mdsc, if (session->s_state >= CEPH_MDS_SESSION_CLOSING) return 0; session->s_state = CEPH_MDS_SESSION_CLOSING; + + if (test_bit(CEPHFS_FEATURE_METRIC_COLLECT, &session->s_features) + && atomic_dec_return(&mdsc->metric.mds_cnt) == 0) + cancel_delayed_work_sync(&mdsc->metric.delayed_work); + return request_close_session(session); } @@ -3310,6 +3315,9 @@ static void handle_session(struct ceph_mds_session *session, session->s_state = CEPH_MDS_SESSION_OPEN; session->s_features = features; renewed_caps(mdsc, session, 0); + if (test_bit(CEPHFS_FEATURE_METRIC_COLLECT, &session->s_features) + && atomic_inc_return(&mdsc->metric.mds_cnt) == 1) + metric_schedule_delayed(&mdsc->metric); wake = 1; if (mdsc->stopping) __close_session(mdsc, session); @@ -3809,6 +3817,10 @@ static void send_mds_reconnect(struct ceph_mds_client *mdsc, session->s_state = CEPH_MDS_SESSION_RECONNECTING; session->s_seq = 0; + if (test_bit(CEPHFS_FEATURE_METRIC_COLLECT, &session->s_features) + && atomic_dec_return(&mdsc->metric.mds_cnt) == 0) + cancel_delayed_work_sync(&mdsc->metric.delayed_work); + dout("session %p state %s\n", session, ceph_session_state_name(session->s_state)); diff --git a/fs/ceph/mds_client.h b/fs/ceph/mds_client.h index 6147ff0..bc9e959 100644 --- a/fs/ceph/mds_client.h +++ b/fs/ceph/mds_client.h @@ -28,8 +28,9 @@ enum ceph_feature_type { CEPHFS_FEATURE_LAZY_CAP_WANTED, CEPHFS_FEATURE_MULTI_RECONNECT, CEPHFS_FEATURE_DELEG_INO, + CEPHFS_FEATURE_METRIC_COLLECT, - CEPHFS_FEATURE_MAX = CEPHFS_FEATURE_DELEG_INO, + CEPHFS_FEATURE_MAX = CEPHFS_FEATURE_METRIC_COLLECT, }; /* @@ -43,6 +44,7 @@ enum ceph_feature_type { CEPHFS_FEATURE_LAZY_CAP_WANTED, \ CEPHFS_FEATURE_MULTI_RECONNECT, \ CEPHFS_FEATURE_DELEG_INO, \ + CEPHFS_FEATURE_METRIC_COLLECT, \ \ CEPHFS_FEATURE_MAX, \ } diff --git a/fs/ceph/metric.c b/fs/ceph/metric.c index 269eacb..8d93cf6 100644 --- a/fs/ceph/metric.c +++ b/fs/ceph/metric.c @@ -1,10 +1,162 @@ /* SPDX-License-Identifier: GPL-2.0 */ +#include #include #include #include #include "metric.h" +#include "mds_client.h" + +static bool ceph_mdsc_send_metrics(struct ceph_mds_client *mdsc, + struct ceph_mds_session *s, + u64 nr_caps) +{ + struct ceph_metric_head *head; + struct ceph_metric_cap *cap; + struct ceph_metric_read_latency *read; + struct ceph_metric_write_latency *write; + struct ceph_metric_metadata_latency *meta; + struct ceph_client_metric *m = &mdsc->metric; + struct ceph_msg *msg; + struct timespec64 ts; + s64 sum, total; + s32 items = 0; + s32 len; + + len = sizeof(*head) + sizeof(*cap) + sizeof(*read) + sizeof(*write) + + sizeof(*meta); + + msg = ceph_msg_new(CEPH_MSG_CLIENT_METRICS, len, GFP_NOFS, true); + if (!msg) { + pr_err("send metrics to mds%d, failed to allocate message\n", + s->s_mds); + return false; + } + + head = msg->front.iov_base; + + /* encode the cap metric */ + cap = (struct ceph_metric_cap *)(head + 1); + cap->type = cpu_to_le32(CLIENT_METRIC_TYPE_CAP_INFO); + cap->ver = 1; + cap->compat = 1; + cap->data_len = cpu_to_le32(sizeof(*cap) - 10); + cap->hit = cpu_to_le64(percpu_counter_sum(&mdsc->metric.i_caps_hit)); + cap->mis = cpu_to_le64(percpu_counter_sum(&mdsc->metric.i_caps_mis)); + cap->total = cpu_to_le64(nr_caps); + items++; + + /* encode the read latency metric */ + read = (struct ceph_metric_read_latency *)(cap + 1); + read->type = cpu_to_le32(CLIENT_METRIC_TYPE_READ_LATENCY); + read->ver = 1; + read->compat = 1; + read->data_len = cpu_to_le32(sizeof(*read) - 10); + total = m->total_reads; + sum = m->read_latency_sum; + jiffies_to_timespec64(sum, &ts); + read->sec = cpu_to_le32(ts.tv_sec); + read->nsec = cpu_to_le32(ts.tv_nsec); + items++; + + /* encode the write latency metric */ + write = (struct ceph_metric_write_latency *)(read + 1); + write->type = cpu_to_le32(CLIENT_METRIC_TYPE_WRITE_LATENCY); + write->ver = 1; + write->compat = 1; + write->data_len = cpu_to_le32(sizeof(*write) - 10); + total = m->total_writes; + sum = m->write_latency_sum; + jiffies_to_timespec64(sum, &ts); + write->sec = cpu_to_le32(ts.tv_sec); + write->nsec = cpu_to_le32(ts.tv_nsec); + items++; + + /* encode the metadata latency metric */ + meta = (struct ceph_metric_metadata_latency *)(write + 1); + meta->type = cpu_to_le32(CLIENT_METRIC_TYPE_METADATA_LATENCY); + meta->ver = 1; + meta->compat = 1; + meta->data_len = cpu_to_le32(sizeof(*meta) - 10); + total = m->total_metadatas; + sum = m->metadata_latency_sum; + jiffies_to_timespec64(sum, &ts); + meta->sec = cpu_to_le32(ts.tv_sec); + meta->nsec = cpu_to_le32(ts.tv_nsec); + items++; + + put_unaligned_le32(items, &head->num); + msg->front.iov_len = cpu_to_le32(len); + msg->hdr.version = cpu_to_le16(1); + msg->hdr.compat_version = cpu_to_le16(1); + msg->hdr.front_len = cpu_to_le32(msg->front.iov_len); + dout("client%llu send metrics to mds%d\n", + ceph_client_gid(mdsc->fsc->client), s->s_mds); + ceph_con_send(&s->s_con, msg); + + return true; +} + +static struct ceph_mds_session *metric_get_session(struct ceph_mds_client *mdsc) +{ + struct ceph_mds_session *s; + int i; + + mutex_lock(&mdsc->mutex); + for (i = 0; i < mdsc->max_sessions; i++) { + s = __ceph_lookup_mds_session(mdsc, i); + if (!s) + continue; + mutex_unlock(&mdsc->mutex); + + /* + * Skip it if MDS doesn't support the metric collection, + * or the MDS will close the session's socket connection + * directly when it get this message. + */ + if (check_session_state(s) && + test_bit(CEPHFS_FEATURE_METRIC_COLLECT, &s->s_features)) { + mdsc->metric.mds = i; + return s; + } + ceph_put_mds_session(s); + + mutex_lock(&mdsc->mutex); + } + mutex_unlock(&mdsc->mutex); + + return NULL; +} + +static void metric_delayed_work(struct work_struct *work) +{ + struct ceph_client_metric *m = + container_of(work, struct ceph_client_metric, delayed_work.work); + struct ceph_mds_client *mdsc = + container_of(m, struct ceph_mds_client, metric); + struct ceph_mds_session *s = NULL; + u64 nr_caps = atomic64_read(&m->total_caps); + + /* No mds supports the metric collection, will stop the work */ + if (!atomic_read(&m->mds_cnt)) + return; + + mutex_lock(&mdsc->mutex); + s = __ceph_lookup_mds_session(mdsc, m->mds); + mutex_unlock(&mdsc->mutex); + if (unlikely(!s || !check_session_state(s) || + !test_bit(CEPHFS_FEATURE_METRIC_COLLECT, &s->s_features))) + s = metric_get_session(mdsc); + + if (s) { + /* Only send the metric once in any available session */ + ceph_mdsc_send_metrics(mdsc, s, nr_caps); + ceph_put_mds_session(s); + } + + metric_schedule_delayed(m); +} int ceph_metric_init(struct ceph_client_metric *m) { @@ -52,6 +204,11 @@ int ceph_metric_init(struct ceph_client_metric *m) m->total_metadatas = 0; m->metadata_latency_sum = 0; + /* We assume the rank 0 support it as default */ + m->mds = 0; + atomic_set(&m->mds_cnt, 0); + INIT_DELAYED_WORK(&m->delayed_work, metric_delayed_work); + return 0; err_i_caps_mis: diff --git a/fs/ceph/metric.h b/fs/ceph/metric.h index 23a3373..68e2d17 100644 --- a/fs/ceph/metric.h +++ b/fs/ceph/metric.h @@ -6,6 +6,71 @@ #include #include +extern bool disable_send_metrics; + +enum ceph_metric_type { + CLIENT_METRIC_TYPE_CAP_INFO, + CLIENT_METRIC_TYPE_READ_LATENCY, + CLIENT_METRIC_TYPE_WRITE_LATENCY, + CLIENT_METRIC_TYPE_METADATA_LATENCY, + CLIENT_METRIC_TYPE_DENTRY_LEASE, + + CLIENT_METRIC_TYPE_MAX = CLIENT_METRIC_TYPE_DENTRY_LEASE, +}; + +/* metric caps header */ +struct ceph_metric_cap { + __le32 type; /* ceph metric type */ + + __u8 ver; + __u8 compat; + + __le32 data_len; /* length of sizeof(hit + mis + total) */ + __le64 hit; + __le64 mis; + __le64 total; +} __packed; + +/* metric read latency header */ +struct ceph_metric_read_latency { + __le32 type; /* ceph metric type */ + + __u8 ver; + __u8 compat; + + __le32 data_len; /* length of sizeof(sec + nsec) */ + __le32 sec; + __le32 nsec; +} __packed; + +/* metric write latency header */ +struct ceph_metric_write_latency { + __le32 type; /* ceph metric type */ + + __u8 ver; + __u8 compat; + + __le32 data_len; /* length of sizeof(sec + nsec) */ + __le32 sec; + __le32 nsec; +} __packed; + +/* metric metadata latency header */ +struct ceph_metric_metadata_latency { + __le32 type; /* ceph metric type */ + + __u8 ver; + __u8 compat; + + __le32 data_len; /* length of sizeof(sec + nsec) */ + __le32 sec; + __le32 nsec; +} __packed; + +struct ceph_metric_head { + __le32 num; /* the number of metrics that will be sent */ +} __packed; + /* This is the global metrics */ struct ceph_client_metric { atomic64_t total_dentries; @@ -36,8 +101,25 @@ struct ceph_client_metric { ktime_t metadata_latency_sq_sum; ktime_t metadata_latency_min; ktime_t metadata_latency_max; + + int mds; /* the MDS being used to send the metrics to */ + atomic_t mds_cnt; /* how many MDSs support metrics collection */ + struct delayed_work delayed_work; /* delayed work */ }; +static inline void metric_schedule_delayed(struct ceph_client_metric *m) +{ + /* + * If send metrics is disabled or no mds support metric + * collection, will stop the work + */ + if (disable_send_metrics || !atomic_read(&m->mds_cnt)) + return; + + /* per second */ + schedule_delayed_work(&m->delayed_work, round_jiffies_relative(HZ)); +} + extern int ceph_metric_init(struct ceph_client_metric *m); extern void ceph_metric_destroy(struct ceph_client_metric *m); diff --git a/fs/ceph/super.c b/fs/ceph/super.c index c9784eb1..cd33836 100644 --- a/fs/ceph/super.c +++ b/fs/ceph/super.c @@ -27,6 +27,9 @@ #include #include +static DEFINE_MUTEX(ceph_fsc_lock); +static LIST_HEAD(ceph_fsc_list); + /* * Ceph superblock operations * @@ -691,6 +694,10 @@ static struct ceph_fs_client *create_fs_client(struct ceph_mount_options *fsopt, if (!fsc->wb_pagevec_pool) goto fail_cap_wq; + mutex_lock(&ceph_fsc_lock); + list_add_tail(&fsc->metric_wakeup, &ceph_fsc_list); + mutex_unlock(&ceph_fsc_lock); + return fsc; fail_cap_wq: @@ -717,6 +724,10 @@ static void destroy_fs_client(struct ceph_fs_client *fsc) { dout("destroy_fs_client %p\n", fsc); + mutex_lock(&ceph_fsc_lock); + list_del(&fsc->metric_wakeup); + mutex_unlock(&ceph_fsc_lock); + ceph_mdsc_destroy(fsc); destroy_workqueue(fsc->inode_wq); destroy_workqueue(fsc->cap_wq); @@ -1282,6 +1293,37 @@ static void __exit exit_ceph(void) destroy_caches(); } +static int param_set_metrics(const char *val, const struct kernel_param *kp) +{ + struct ceph_fs_client *fsc; + int ret; + + ret = param_set_bool(val, kp); + if (ret) { + pr_err("Failed to parse sending metrics switch value '%s'\n", + val); + return ret; + } else if (!disable_send_metrics) { + // wake up all the mds clients + mutex_lock(&ceph_fsc_lock); + list_for_each_entry(fsc, &ceph_fsc_list, metric_wakeup) { + metric_schedule_delayed(&fsc->mdsc->metric); + } + mutex_unlock(&ceph_fsc_lock); + } + + return 0; +} + +static const struct kernel_param_ops param_ops_metrics = { + .set = param_set_metrics, + .get = param_get_bool, +}; + +bool disable_send_metrics = false; +module_param_cb(disable_send_metrics, ¶m_ops_metrics, &disable_send_metrics, 0644); +MODULE_PARM_DESC(disable_send_metrics, "Enable sending perf metrics to ceph cluster (default: on)"); + module_init(init_ceph); module_exit(exit_ceph); diff --git a/fs/ceph/super.h b/fs/ceph/super.h index 5a6cdd3..2dcb6a9 100644 --- a/fs/ceph/super.h +++ b/fs/ceph/super.h @@ -101,6 +101,8 @@ struct ceph_mount_options { struct ceph_fs_client { struct super_block *sb; + struct list_head metric_wakeup; + struct ceph_mount_options *mount_options; struct ceph_client *client; diff --git a/include/linux/ceph/ceph_fs.h b/include/linux/ceph/ceph_fs.h index ebf5ba6..455e9b9 100644 --- a/include/linux/ceph/ceph_fs.h +++ b/include/linux/ceph/ceph_fs.h @@ -130,6 +130,7 @@ struct ceph_dir_layout { #define CEPH_MSG_CLIENT_REQUEST 24 #define CEPH_MSG_CLIENT_REQUEST_FORWARD 25 #define CEPH_MSG_CLIENT_REPLY 26 +#define CEPH_MSG_CLIENT_METRICS 29 #define CEPH_MSG_CLIENT_CAPS 0x310 #define CEPH_MSG_CLIENT_LEASE 0x311 #define CEPH_MSG_CLIENT_SNAP 0x312 From patchwork Tue Jun 30 07:52:18 2020 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Xiubo Li X-Patchwork-Id: 11633421 Return-Path: Received: from mail.kernel.org (pdx-korg-mail-1.web.codeaurora.org [172.30.200.123]) by pdx-korg-patchwork-2.web.codeaurora.org (Postfix) with ESMTP id 836F0739 for ; Tue, 30 Jun 2020 07:52:55 +0000 (UTC) Received: from vger.kernel.org (vger.kernel.org [23.128.96.18]) by mail.kernel.org (Postfix) with ESMTP id 6B60E20768 for ; Tue, 30 Jun 2020 07:52:55 +0000 (UTC) Authentication-Results: mail.kernel.org; dkim=pass (1024-bit key) header.d=redhat.com header.i=@redhat.com header.b="XIrMBdiw" Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1731350AbgF3Hwy (ORCPT ); Tue, 30 Jun 2020 03:52:54 -0400 Received: from us-smtp-delivery-1.mimecast.com ([205.139.110.120]:22522 "EHLO us-smtp-1.mimecast.com" rhost-flags-OK-OK-OK-FAIL) by vger.kernel.org with ESMTP id S1729895AbgF3Hwx (ORCPT ); Tue, 30 Jun 2020 03:52:53 -0400 DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=redhat.com; s=mimecast20190719; t=1593503572; h=from:from:reply-to:subject:subject:date:date:message-id:message-id: to:to:cc:cc:in-reply-to:in-reply-to:references:references; bh=GvCNxSuo+qs/ZLiquF9oaqd1uyy8bYGZ0IICR6YkZHQ=; b=XIrMBdiwNiZMClCYOX90vZxyOwwS/AzEDihQ2MuhtU5lNdjNbwcnyg9y4mMqRY+14F+pMw 8Bbj5Ot5OVUk+EJpqOwlJ7UX9rs7e1Ysd4t5rPvDVqS/6nZ1VUGg/cAKdoA5AkXUfocUMn Nks7l39htTAXFlxlFmcjBgsPP7RGwBc= Received: from mimecast-mx01.redhat.com (mimecast-mx01.redhat.com [209.132.183.4]) (Using TLS) by relay.mimecast.com with ESMTP id us-mta-166-7tuvq5U1MEO9BnFDenEFcw-1; Tue, 30 Jun 2020 03:52:49 -0400 X-MC-Unique: 7tuvq5U1MEO9BnFDenEFcw-1 Received: from smtp.corp.redhat.com (int-mx07.intmail.prod.int.phx2.redhat.com [10.5.11.22]) (using TLSv1.2 with cipher AECDH-AES256-SHA (256/256 bits)) (No client certificate requested) by mimecast-mx01.redhat.com (Postfix) with ESMTPS id 959DC804001; Tue, 30 Jun 2020 07:52:48 +0000 (UTC) Received: from lxbceph0.gsslab.pek2.redhat.com (vm37-55.gsslab.pek2.redhat.com [10.72.37.55]) by smtp.corp.redhat.com (Postfix) with ESMTP id 393B6100EBA7; Tue, 30 Jun 2020 07:52:45 +0000 (UTC) From: xiubli@redhat.com To: jlayton@kernel.org Cc: idryomov@gmail.com, zyan@redhat.com, pdonnell@redhat.com, vshankar@redhat.com, ceph-devel@vger.kernel.org, Xiubo Li Subject: [PATCH v5 4/5] ceph: switch to WARN_ON_ONCE and bubble up errnos to the callers Date: Tue, 30 Jun 2020 03:52:18 -0400 Message-Id: <1593503539-1209-5-git-send-email-xiubli@redhat.com> In-Reply-To: <1593503539-1209-1-git-send-email-xiubli@redhat.com> References: <1593503539-1209-1-git-send-email-xiubli@redhat.com> X-Scanned-By: MIMEDefang 2.84 on 10.5.11.22 Sender: ceph-devel-owner@vger.kernel.org Precedence: bulk List-ID: X-Mailing-List: ceph-devel@vger.kernel.org From: Xiubo Li Signed-off-by: Xiubo Li --- fs/ceph/mds_client.c | 46 +++++++++++++++++++++++++++++++++++----------- 1 file changed, 35 insertions(+), 11 deletions(-) diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c index bcdda5a..93b539e 100644 --- a/fs/ceph/mds_client.c +++ b/fs/ceph/mds_client.c @@ -1168,7 +1168,7 @@ static struct ceph_msg *create_session_msg(u32 op, u64 seq) static const unsigned char feature_bits[] = CEPHFS_FEATURES_CLIENT_SUPPORTED; #define FEATURE_BYTES(c) (DIV_ROUND_UP((size_t)feature_bits[c - 1] + 1, 64) * 8) -static void encode_supported_features(void **p, void *end) +static int encode_supported_features(void **p, void *end) { static const size_t count = ARRAY_SIZE(feature_bits); @@ -1176,16 +1176,22 @@ static void encode_supported_features(void **p, void *end) size_t i; size_t size = FEATURE_BYTES(count); - BUG_ON(*p + 4 + size > end); + if (WARN_ON_ONCE(*p + 4 + size > end)) + return -ERANGE; + ceph_encode_32(p, size); memset(*p, 0, size); for (i = 0; i < count; i++) ((unsigned char*)(*p))[i / 8] |= BIT(feature_bits[i] % 8); *p += size; } else { - BUG_ON(*p + 4 > end); + if (WARN_ON_ONCE(*p + 4 > end)) + return -ERANGE; + ceph_encode_32(p, 0); } + + return 0; } /* @@ -1203,6 +1209,7 @@ static struct ceph_msg *create_session_open_msg(struct ceph_mds_client *mdsc, u6 struct ceph_mount_options *fsopt = mdsc->fsc->mount_options; size_t size, count; void *p, *end; + int ret; const char* metadata[][2] = { {"hostname", mdsc->nodename}, @@ -1232,7 +1239,7 @@ static struct ceph_msg *create_session_open_msg(struct ceph_mds_client *mdsc, u6 GFP_NOFS, false); if (!msg) { pr_err("create_session_msg ENOMEM creating msg\n"); - return NULL; + return ERR_PTR(-ENOMEM); } p = msg->front.iov_base; end = p + msg->front.iov_len; @@ -1269,7 +1276,13 @@ static struct ceph_msg *create_session_open_msg(struct ceph_mds_client *mdsc, u6 p += val_len; } - encode_supported_features(&p, end); + ret = encode_supported_features(&p, end); + if (ret) { + pr_err("encode_supported_features failed!\n"); + ceph_msg_put(msg); + return ERR_PTR(ret); + } + msg->front.iov_len = p - msg->front.iov_base; msg->hdr.front_len = cpu_to_le32(msg->front.iov_len); @@ -1297,8 +1310,8 @@ static int __open_session(struct ceph_mds_client *mdsc, /* send connect message */ msg = create_session_open_msg(mdsc, session->s_seq); - if (!msg) - return -ENOMEM; + if (IS_ERR(msg)) + return PTR_ERR(msg); ceph_con_send(&session->s_con, msg); return 0; } @@ -1312,6 +1325,7 @@ static int __open_session(struct ceph_mds_client *mdsc, __open_export_target_session(struct ceph_mds_client *mdsc, int target) { struct ceph_mds_session *session; + int ret; session = __ceph_lookup_mds_session(mdsc, target); if (!session) { @@ -1320,8 +1334,11 @@ static int __open_session(struct ceph_mds_client *mdsc, return session; } if (session->s_state == CEPH_MDS_SESSION_NEW || - session->s_state == CEPH_MDS_SESSION_CLOSING) - __open_session(mdsc, session); + session->s_state == CEPH_MDS_SESSION_CLOSING) { + ret = __open_session(mdsc, session); + if (ret) + return ERR_PTR(ret); + } return session; } @@ -2525,7 +2542,12 @@ static struct ceph_msg *create_request_message(struct ceph_mds_client *mdsc, ceph_encode_copy(&p, &ts, sizeof(ts)); } - BUG_ON(p > end); + if (WARN_ON_ONCE(p > end)) { + ceph_msg_put(msg); + msg = ERR_PTR(-ERANGE); + goto out_free2; + } + msg->front.iov_len = p - msg->front.iov_base; msg->hdr.front_len = cpu_to_le32(msg->front.iov_len); @@ -2761,7 +2783,9 @@ static void __do_request(struct ceph_mds_client *mdsc, } if (session->s_state == CEPH_MDS_SESSION_NEW || session->s_state == CEPH_MDS_SESSION_CLOSING) { - __open_session(mdsc, session); + err = __open_session(mdsc, session); + if (err) + goto out_session; /* retry the same mds later */ if (random) req->r_resend_mds = mds; From patchwork Tue Jun 30 07:52:19 2020 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Xiubo Li X-Patchwork-Id: 11633423 Return-Path: Received: from mail.kernel.org (pdx-korg-mail-1.web.codeaurora.org [172.30.200.123]) by pdx-korg-patchwork-2.web.codeaurora.org (Postfix) with ESMTP id 98A41739 for ; Tue, 30 Jun 2020 07:53:00 +0000 (UTC) Received: from vger.kernel.org (vger.kernel.org [23.128.96.18]) by mail.kernel.org (Postfix) with ESMTP id 80D7120768 for ; Tue, 30 Jun 2020 07:53:00 +0000 (UTC) Authentication-Results: mail.kernel.org; dkim=pass (1024-bit key) header.d=redhat.com header.i=@redhat.com header.b="ezkxG3ur" Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1731353AbgF3Hw7 (ORCPT ); Tue, 30 Jun 2020 03:52:59 -0400 Received: from us-smtp-delivery-1.mimecast.com ([205.139.110.120]:43976 "EHLO us-smtp-1.mimecast.com" rhost-flags-OK-OK-OK-FAIL) by vger.kernel.org with ESMTP id S1731351AbgF3Hw7 (ORCPT ); Tue, 30 Jun 2020 03:52:59 -0400 DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=redhat.com; s=mimecast20190719; t=1593503577; h=from:from:reply-to:subject:subject:date:date:message-id:message-id: to:to:cc:cc:in-reply-to:in-reply-to:references:references; bh=5+HwnJVn6rSGzJgQOV6Uc4bLWkbnJXk+UO3sh0KUp1Q=; b=ezkxG3urgR1+kRzFJMIOhRi48KIUAvV6YDAeuAlsHOCDNId2Ioz/xQn62k0M1JIblV5qY2 BxunMxywyzpelQ6jSg4JreApg1Y8f6Tebuj9ZXC/sK8cFk7ikvYjRJ893ZfzMHF1hmwbgY nPJRUaKIweM6ZHqRL2DXZkoPGkiGQ3I= Received: from mimecast-mx01.redhat.com (mimecast-mx01.redhat.com [209.132.183.4]) (Using TLS) by relay.mimecast.com with ESMTP id us-mta-376-WKfRZS0BPqysFqRY9JBBxQ-1; Tue, 30 Jun 2020 03:52:53 -0400 X-MC-Unique: WKfRZS0BPqysFqRY9JBBxQ-1 Received: from smtp.corp.redhat.com (int-mx07.intmail.prod.int.phx2.redhat.com [10.5.11.22]) (using TLSv1.2 with cipher AECDH-AES256-SHA (256/256 bits)) (No client certificate requested) by mimecast-mx01.redhat.com (Postfix) with ESMTPS id 7AD7A464; Tue, 30 Jun 2020 07:52:51 +0000 (UTC) Received: from lxbceph0.gsslab.pek2.redhat.com (vm37-55.gsslab.pek2.redhat.com [10.72.37.55]) by smtp.corp.redhat.com (Postfix) with ESMTP id 1CCBB1000079; Tue, 30 Jun 2020 07:52:48 +0000 (UTC) From: xiubli@redhat.com To: jlayton@kernel.org Cc: idryomov@gmail.com, zyan@redhat.com, pdonnell@redhat.com, vshankar@redhat.com, ceph-devel@vger.kernel.org, Xiubo Li Subject: [PATCH v5 5/5] ceph: send client provided metric flags in client metadata Date: Tue, 30 Jun 2020 03:52:19 -0400 Message-Id: <1593503539-1209-6-git-send-email-xiubli@redhat.com> In-Reply-To: <1593503539-1209-1-git-send-email-xiubli@redhat.com> References: <1593503539-1209-1-git-send-email-xiubli@redhat.com> X-Scanned-By: MIMEDefang 2.84 on 10.5.11.22 Sender: ceph-devel-owner@vger.kernel.org Precedence: bulk List-ID: X-Mailing-List: ceph-devel@vger.kernel.org From: Xiubo Li Will send the metric flags to MDS, currently it supports the cap, read latency, write latency and metadata latency. URL: https://tracker.ceph.com/issues/43435 Signed-off-by: Xiubo Li --- fs/ceph/mds_client.c | 60 ++++++++++++++++++++++++++++++++++++++++++++++++++-- fs/ceph/metric.h | 13 ++++++++++++ 2 files changed, 71 insertions(+), 2 deletions(-) diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c index 93b539e..7bcf4d64 100644 --- a/fs/ceph/mds_client.c +++ b/fs/ceph/mds_client.c @@ -1194,6 +1194,48 @@ static int encode_supported_features(void **p, void *end) return 0; } +static const unsigned char metric_bits[] = CEPHFS_METRIC_SPEC_CLIENT_SUPPORTED; +#define METRIC_BYTES(cnt) (DIV_ROUND_UP((size_t)metric_bits[cnt - 1] + 1, 64) * 8) +static int encode_metric_spec(void **p, void *end) +{ + static const size_t count = ARRAY_SIZE(metric_bits); + + /* header */ + if (WARN_ON_ONCE(*p + 2 > end)) + return -ERANGE; + + ceph_encode_8(p, 1); /* version */ + ceph_encode_8(p, 1); /* compat */ + + if (count > 0) { + size_t i; + size_t size = METRIC_BYTES(count); + + if (WARN_ON_ONCE(*p + 4 + 4 + size > end)) + return -ERANGE; + + /* metric spec info length */ + ceph_encode_32(p, 4 + size); + + /* metric spec */ + ceph_encode_32(p, size); + memset(*p, 0, size); + for (i = 0; i < count; i++) + ((unsigned char *)(*p))[i / 8] |= BIT(metric_bits[i] % 8); + *p += size; + } else { + if (WARN_ON_ONCE(*p + 4 + 4 > end)) + return -ERANGE; + + /* metric spec info length */ + ceph_encode_32(p, 4); + /* metric spec */ + ceph_encode_32(p, 0); + } + + return 0; +} + /* * session message, specialization for CEPH_SESSION_REQUEST_OPEN * to include additional client metadata fields. @@ -1234,6 +1276,13 @@ static struct ceph_msg *create_session_open_msg(struct ceph_mds_client *mdsc, u6 size = FEATURE_BYTES(count); extra_bytes += 4 + size; + /* metric spec */ + size = 0; + count = ARRAY_SIZE(metric_bits); + if (count > 0) + size = METRIC_BYTES(count); + extra_bytes += 2 + 4 + 4 + size; + /* Allocate the message */ msg = ceph_msg_new(CEPH_MSG_CLIENT_SESSION, sizeof(*h) + extra_bytes, GFP_NOFS, false); @@ -1252,9 +1301,9 @@ static struct ceph_msg *create_session_open_msg(struct ceph_mds_client *mdsc, u6 * Serialize client metadata into waiting buffer space, using * the format that userspace expects for map * - * ClientSession messages with metadata are v3 + * ClientSession messages with metadata are v4 */ - msg->hdr.version = cpu_to_le16(3); + msg->hdr.version = cpu_to_le16(4); msg->hdr.compat_version = cpu_to_le16(1); /* The write pointer, following the session_head structure */ @@ -1283,6 +1332,13 @@ static struct ceph_msg *create_session_open_msg(struct ceph_mds_client *mdsc, u6 return ERR_PTR(ret); } + ret = encode_metric_spec(&p, end); + if (ret) { + pr_err("encode_metric_spec failed!\n"); + ceph_msg_put(msg); + return ERR_PTR(ret); + } + msg->front.iov_len = p - msg->front.iov_base; msg->hdr.front_len = cpu_to_le32(msg->front.iov_len); diff --git a/fs/ceph/metric.h b/fs/ceph/metric.h index 68e2d17..3ebb0ef 100644 --- a/fs/ceph/metric.h +++ b/fs/ceph/metric.h @@ -18,6 +18,19 @@ enum ceph_metric_type { CLIENT_METRIC_TYPE_MAX = CLIENT_METRIC_TYPE_DENTRY_LEASE, }; +/* + * This will always have the highest metric bit value + * as the last element of the array. + */ +#define CEPHFS_METRIC_SPEC_CLIENT_SUPPORTED { \ + CLIENT_METRIC_TYPE_CAP_INFO, \ + CLIENT_METRIC_TYPE_READ_LATENCY, \ + CLIENT_METRIC_TYPE_WRITE_LATENCY, \ + CLIENT_METRIC_TYPE_METADATA_LATENCY, \ + \ + CLIENT_METRIC_TYPE_MAX, \ +} + /* metric caps header */ struct ceph_metric_cap { __le32 type; /* ceph metric type */