From: Chuck Lever Date: Wed, 29 Jun 2016 17:54:00 +0000 (-0400) Subject: xprtrdma: Allocate MRs on demand X-Git-Url: https://git.stricted.de/?a=commitdiff_plain;h=e2ac236c0b65129f12fef358390f76cc3cacb865;p=GitHub%2Fmoto-9609%2Fandroid_kernel_motorola_exynos9610.git xprtrdma: Allocate MRs on demand Frequent MR list exhaustion can impact I/O throughput, so enough MRs are always created during transport set-up to prevent running out. This means more MRs are created than most workloads need. Commit 94f58c58c0b4 ("xprtrdma: Allow Read list and Reply chunk simultaneously") introduced support for sending two chunk lists per RPC, which consumes more MRs per RPC. Instead of trying to provision more MRs, introduce a mechanism for allocating MRs on demand. A few MRs are allocated during transport set-up to kick things off. This significantly reduces the average number of MRs per transport while allowing the MR count to grow for workloads or devices that need more MRs. FRWR with mlx4 allocated almost 400 MRs per transport before this patch. Now it starts with 32. Signed-off-by: Chuck Lever Tested-by: Steve Wise Signed-off-by: Anna Schumaker --- diff --git a/net/sunrpc/xprtrdma/fmr_ops.c b/net/sunrpc/xprtrdma/fmr_ops.c index bc5f4a1e3122..758cd1a02249 100644 --- a/net/sunrpc/xprtrdma/fmr_ops.c +++ b/net/sunrpc/xprtrdma/fmr_ops.c @@ -46,7 +46,7 @@ fmr_is_supported(struct rpcrdma_ia *ia) } static int -__fmr_init(struct rpcrdma_mw *mw, struct ib_pd *pd) +fmr_op_init_mr(struct rpcrdma_ia *ia, struct rpcrdma_mw *mw) { static struct ib_fmr_attr fmr_attr = { .max_pages = RPCRDMA_MAX_FMR_SGES, @@ -66,7 +66,7 @@ __fmr_init(struct rpcrdma_mw *mw, struct ib_pd *pd) sg_init_table(mw->mw_sg, RPCRDMA_MAX_FMR_SGES); - mw->fmr.fm_mr = ib_alloc_fmr(pd, RPCRDMA_FMR_ACCESS_FLAGS, + mw->fmr.fm_mr = ib_alloc_fmr(ia->ri_pd, RPCRDMA_FMR_ACCESS_FLAGS, &fmr_attr); if (IS_ERR(mw->fmr.fm_mr)) goto out_fmr_err; @@ -96,7 +96,7 @@ __fmr_unmap(struct rpcrdma_mw *mw) } static void -__fmr_release(struct rpcrdma_mw *r) +fmr_op_release_mr(struct rpcrdma_mw *r) { LIST_HEAD(unmap_list); int rc; @@ -116,13 +116,11 @@ __fmr_release(struct rpcrdma_mw *r) if (rc) pr_err("rpcrdma: final ib_dealloc_fmr for %p returned %i\n", r, rc); + + kfree(r); } /* Reset of a single FMR. - * - * There's no recovery if this fails. The FMR is abandoned, but - * remains in rb_all. It will be cleaned up when the transport is - * destroyed. */ static void fmr_op_recover_mr(struct rpcrdma_mw *mw) @@ -166,41 +164,6 @@ fmr_op_maxpages(struct rpcrdma_xprt *r_xprt) RPCRDMA_MAX_HDR_SEGS * RPCRDMA_MAX_FMR_SGES); } -static int -fmr_op_init(struct rpcrdma_xprt *r_xprt) -{ - struct rpcrdma_buffer *buf = &r_xprt->rx_buf; - struct ib_pd *pd = r_xprt->rx_ia.ri_pd; - struct rpcrdma_mw *r; - int i, rc; - - spin_lock_init(&buf->rb_mwlock); - INIT_LIST_HEAD(&buf->rb_mws); - INIT_LIST_HEAD(&buf->rb_all); - - i = max_t(int, RPCRDMA_MAX_DATA_SEGS / RPCRDMA_MAX_FMR_SGES, 1); - i += 2; /* head + tail */ - i *= buf->rb_max_requests; /* one set for each RPC slot */ - dprintk("RPC: %s: initalizing %d FMRs\n", __func__, i); - - while (i--) { - r = kzalloc(sizeof(*r), GFP_KERNEL); - if (!r) - return -ENOMEM; - - rc = __fmr_init(r, pd); - if (rc) { - kfree(r); - return rc; - } - - r->mw_xprt = r_xprt; - list_add(&r->mw_list, &buf->rb_mws); - list_add(&r->mw_all, &buf->rb_all); - } - return 0; -} - /* Use the ib_map_phys_fmr() verb to register a memory region * for remote access via RDMA READ or RDMA WRITE. */ @@ -374,19 +337,6 @@ fmr_op_unmap_safe(struct rpcrdma_xprt *r_xprt, struct rpcrdma_req *req, } } -static void -fmr_op_destroy(struct rpcrdma_buffer *buf) -{ - struct rpcrdma_mw *r; - - while (!list_empty(&buf->rb_all)) { - r = list_entry(buf->rb_all.next, struct rpcrdma_mw, mw_all); - list_del(&r->mw_all); - __fmr_release(r); - kfree(r); - } -} - const struct rpcrdma_memreg_ops rpcrdma_fmr_memreg_ops = { .ro_map = fmr_op_map, .ro_unmap_sync = fmr_op_unmap_sync, @@ -394,7 +344,7 @@ const struct rpcrdma_memreg_ops rpcrdma_fmr_memreg_ops = { .ro_recover_mr = fmr_op_recover_mr, .ro_open = fmr_op_open, .ro_maxpages = fmr_op_maxpages, - .ro_init = fmr_op_init, - .ro_destroy = fmr_op_destroy, + .ro_init_mr = fmr_op_init_mr, + .ro_release_mr = fmr_op_release_mr, .ro_displayname = "fmr", }; diff --git a/net/sunrpc/xprtrdma/frwr_ops.c b/net/sunrpc/xprtrdma/frwr_ops.c index f3a06faf0a18..e77776bc5d59 100644 --- a/net/sunrpc/xprtrdma/frwr_ops.c +++ b/net/sunrpc/xprtrdma/frwr_ops.c @@ -91,12 +91,13 @@ out_not_supported: } static int -__frwr_init(struct rpcrdma_mw *r, struct ib_pd *pd, unsigned int depth) +frwr_op_init_mr(struct rpcrdma_ia *ia, struct rpcrdma_mw *r) { + unsigned int depth = ia->ri_max_frmr_depth; struct rpcrdma_frmr *f = &r->frmr; int rc; - f->fr_mr = ib_alloc_mr(pd, IB_MR_TYPE_MEM_REG, depth); + f->fr_mr = ib_alloc_mr(ia->ri_pd, IB_MR_TYPE_MEM_REG, depth); if (IS_ERR(f->fr_mr)) goto out_mr_err; @@ -123,7 +124,7 @@ out_list_err: } static void -__frwr_release(struct rpcrdma_mw *r) +frwr_op_release_mr(struct rpcrdma_mw *r) { int rc; @@ -132,6 +133,7 @@ __frwr_release(struct rpcrdma_mw *r) pr_err("rpcrdma: final ib_dereg_mr for %p returned %i\n", r, rc); kfree(r->mw_sg); + kfree(r); } static int @@ -319,45 +321,6 @@ frwr_wc_localinv_wake(struct ib_cq *cq, struct ib_wc *wc) complete_all(&frmr->fr_linv_done); } -static int -frwr_op_init(struct rpcrdma_xprt *r_xprt) -{ - struct rpcrdma_buffer *buf = &r_xprt->rx_buf; - unsigned int depth = r_xprt->rx_ia.ri_max_frmr_depth; - struct ib_pd *pd = r_xprt->rx_ia.ri_pd; - int i; - - spin_lock_init(&buf->rb_mwlock); - INIT_LIST_HEAD(&buf->rb_mws); - INIT_LIST_HEAD(&buf->rb_all); - - i = max_t(int, RPCRDMA_MAX_DATA_SEGS / depth, 1); - i += 2; /* head + tail */ - i *= buf->rb_max_requests; /* one set for each RPC slot */ - dprintk("RPC: %s: initalizing %d FRMRs\n", __func__, i); - - while (i--) { - struct rpcrdma_mw *r; - int rc; - - r = kzalloc(sizeof(*r), GFP_KERNEL); - if (!r) - return -ENOMEM; - - rc = __frwr_init(r, pd, depth); - if (rc) { - kfree(r); - return rc; - } - - r->mw_xprt = r_xprt; - list_add(&r->mw_list, &buf->rb_mws); - list_add(&r->mw_all, &buf->rb_all); - } - - return 0; -} - /* Post a REG_MR Work Request to register a memory region * for remote access via RDMA READ or RDMA WRITE. */ @@ -618,19 +581,6 @@ frwr_op_unmap_safe(struct rpcrdma_xprt *r_xprt, struct rpcrdma_req *req, } } -static void -frwr_op_destroy(struct rpcrdma_buffer *buf) -{ - struct rpcrdma_mw *r; - - while (!list_empty(&buf->rb_all)) { - r = list_entry(buf->rb_all.next, struct rpcrdma_mw, mw_all); - list_del(&r->mw_all); - __frwr_release(r); - kfree(r); - } -} - const struct rpcrdma_memreg_ops rpcrdma_frwr_memreg_ops = { .ro_map = frwr_op_map, .ro_unmap_sync = frwr_op_unmap_sync, @@ -638,7 +588,7 @@ const struct rpcrdma_memreg_ops rpcrdma_frwr_memreg_ops = { .ro_recover_mr = frwr_op_recover_mr, .ro_open = frwr_op_open, .ro_maxpages = frwr_op_maxpages, - .ro_init = frwr_op_init, - .ro_destroy = frwr_op_destroy, + .ro_init_mr = frwr_op_init_mr, + .ro_release_mr = frwr_op_release_mr, .ro_displayname = "frwr", }; diff --git a/net/sunrpc/xprtrdma/transport.c b/net/sunrpc/xprtrdma/transport.c index be4dd2c7c680..b1dd42a93484 100644 --- a/net/sunrpc/xprtrdma/transport.c +++ b/net/sunrpc/xprtrdma/transport.c @@ -682,9 +682,10 @@ void xprt_rdma_print_stats(struct rpc_xprt *xprt, struct seq_file *seq) r_xprt->rx_stats.failed_marshal_count, r_xprt->rx_stats.bad_reply_count, r_xprt->rx_stats.nomsg_call_count); - seq_printf(seq, "%lu %lu\n", + seq_printf(seq, "%lu %lu %lu\n", r_xprt->rx_stats.mrs_recovered, - r_xprt->rx_stats.mrs_orphaned); + r_xprt->rx_stats.mrs_orphaned, + r_xprt->rx_stats.mrs_allocated); } static int diff --git a/net/sunrpc/xprtrdma/verbs.c b/net/sunrpc/xprtrdma/verbs.c index db935ed3ac75..e8677eafb329 100644 --- a/net/sunrpc/xprtrdma/verbs.c +++ b/net/sunrpc/xprtrdma/verbs.c @@ -782,6 +782,55 @@ rpcrdma_defer_mr_recovery(struct rpcrdma_mw *mw) schedule_delayed_work(&buf->rb_recovery_worker, 0); } +static void +rpcrdma_create_mrs(struct rpcrdma_xprt *r_xprt) +{ + struct rpcrdma_buffer *buf = &r_xprt->rx_buf; + struct rpcrdma_ia *ia = &r_xprt->rx_ia; + unsigned int count; + LIST_HEAD(free); + LIST_HEAD(all); + + for (count = 0; count < 32; count++) { + struct rpcrdma_mw *mw; + int rc; + + mw = kzalloc(sizeof(*mw), GFP_KERNEL); + if (!mw) + break; + + rc = ia->ri_ops->ro_init_mr(ia, mw); + if (rc) { + kfree(mw); + break; + } + + mw->mw_xprt = r_xprt; + + list_add(&mw->mw_list, &free); + list_add(&mw->mw_all, &all); + } + + spin_lock(&buf->rb_mwlock); + list_splice(&free, &buf->rb_mws); + list_splice(&all, &buf->rb_all); + r_xprt->rx_stats.mrs_allocated += count; + spin_unlock(&buf->rb_mwlock); + + dprintk("RPC: %s: created %u MRs\n", __func__, count); +} + +static void +rpcrdma_mr_refresh_worker(struct work_struct *work) +{ + struct rpcrdma_buffer *buf = container_of(work, struct rpcrdma_buffer, + rb_refresh_worker.work); + struct rpcrdma_xprt *r_xprt = container_of(buf, struct rpcrdma_xprt, + rx_buf); + + rpcrdma_create_mrs(r_xprt); +} + struct rpcrdma_req * rpcrdma_create_req(struct rpcrdma_xprt *r_xprt) { @@ -837,21 +886,23 @@ int rpcrdma_buffer_create(struct rpcrdma_xprt *r_xprt) { struct rpcrdma_buffer *buf = &r_xprt->rx_buf; - struct rpcrdma_ia *ia = &r_xprt->rx_ia; int i, rc; buf->rb_max_requests = r_xprt->rx_data.max_requests; buf->rb_bc_srv_max_requests = 0; atomic_set(&buf->rb_credits, 1); + spin_lock_init(&buf->rb_mwlock); spin_lock_init(&buf->rb_lock); spin_lock_init(&buf->rb_recovery_lock); + INIT_LIST_HEAD(&buf->rb_mws); + INIT_LIST_HEAD(&buf->rb_all); INIT_LIST_HEAD(&buf->rb_stale_mrs); + INIT_DELAYED_WORK(&buf->rb_refresh_worker, + rpcrdma_mr_refresh_worker); INIT_DELAYED_WORK(&buf->rb_recovery_worker, rpcrdma_mr_recovery_worker); - rc = ia->ri_ops->ro_init(r_xprt); - if (rc) - goto out; + rpcrdma_create_mrs(r_xprt); INIT_LIST_HEAD(&buf->rb_send_bufs); INIT_LIST_HEAD(&buf->rb_allreqs); @@ -927,6 +978,32 @@ rpcrdma_destroy_req(struct rpcrdma_ia *ia, struct rpcrdma_req *req) kfree(req); } +static void +rpcrdma_destroy_mrs(struct rpcrdma_buffer *buf) +{ + struct rpcrdma_xprt *r_xprt = container_of(buf, struct rpcrdma_xprt, + rx_buf); + struct rpcrdma_ia *ia = rdmab_to_ia(buf); + struct rpcrdma_mw *mw; + unsigned int count; + + count = 0; + spin_lock(&buf->rb_mwlock); + while (!list_empty(&buf->rb_all)) { + mw = list_entry(buf->rb_all.next, struct rpcrdma_mw, mw_all); + list_del(&mw->mw_all); + + spin_unlock(&buf->rb_mwlock); + ia->ri_ops->ro_release_mr(mw); + count++; + spin_lock(&buf->rb_mwlock); + } + spin_unlock(&buf->rb_mwlock); + r_xprt->rx_stats.mrs_allocated = 0; + + dprintk("RPC: %s: released %u MRs\n", __func__, count); +} + void rpcrdma_buffer_destroy(struct rpcrdma_buffer *buf) { @@ -955,7 +1032,7 @@ rpcrdma_buffer_destroy(struct rpcrdma_buffer *buf) } spin_unlock(&buf->rb_reqslock); - ia->ri_ops->ro_destroy(buf); + rpcrdma_destroy_mrs(buf); } struct rpcrdma_mw * @@ -973,8 +1050,17 @@ rpcrdma_get_mw(struct rpcrdma_xprt *r_xprt) spin_unlock(&buf->rb_mwlock); if (!mw) - pr_err("RPC: %s: no MWs available\n", __func__); + goto out_nomws; return mw; + +out_nomws: + dprintk("RPC: %s: no MWs available\n", __func__); + schedule_delayed_work(&buf->rb_refresh_worker, 0); + + /* Allow the reply handler and refresh worker to run */ + cond_resched(); + + return NULL; } void diff --git a/net/sunrpc/xprtrdma/xprt_rdma.h b/net/sunrpc/xprtrdma/xprt_rdma.h index 08d441d65a83..649d01dda327 100644 --- a/net/sunrpc/xprtrdma/xprt_rdma.h +++ b/net/sunrpc/xprtrdma/xprt_rdma.h @@ -339,6 +339,7 @@ struct rpcrdma_buffer { spinlock_t rb_recovery_lock; /* protect rb_stale_mrs */ struct list_head rb_stale_mrs; struct delayed_work rb_recovery_worker; + struct delayed_work rb_refresh_worker; }; #define rdmab_to_ia(b) (&container_of((b), struct rpcrdma_xprt, rx_buf)->rx_ia) @@ -387,6 +388,7 @@ struct rpcrdma_stats { unsigned long bcall_count; unsigned long mrs_recovered; unsigned long mrs_orphaned; + unsigned long mrs_allocated; }; /* @@ -405,8 +407,9 @@ struct rpcrdma_memreg_ops { struct rpcrdma_ep *, struct rpcrdma_create_data_internal *); size_t (*ro_maxpages)(struct rpcrdma_xprt *); - int (*ro_init)(struct rpcrdma_xprt *); - void (*ro_destroy)(struct rpcrdma_buffer *); + int (*ro_init_mr)(struct rpcrdma_ia *, + struct rpcrdma_mw *); + void (*ro_release_mr)(struct rpcrdma_mw *); const char *ro_displayname; };