From ccb9f69fdb9eff9d5f3f4ad9ce6343cb76b0194e Mon Sep 17 00:00:00 2001 From: shaodenghui Date: Mon, 4 Mar 2024 09:34:25 +0800 Subject: [PATCH 1/4] iscsi: add member for NUMA aware order workqueue euleros inclusion category: feature bugzilla: https://gitee.com/openeuler/kernel/issues/I94XYA CVE: NA ------------------------------------------------- Add member to struct iscsi_conn. Signed-off-by: Yang Yingliang Reviewed-By: Xie XiuQi Signed-off-by: Yang Yingliang Signed-off-by: BiaoXiang Ye Reviewed-by: fang yi Signed-off-by: Zheng Zengkai Signed-off-by: shaodenghui --- include/linux/workqueue.h | 1 + include/scsi/libiscsi.h | 1 + 2 files changed, 2 insertions(+) diff --git a/include/linux/workqueue.h b/include/linux/workqueue.h index 9619098755fb..485c0f5b2518 100644 --- a/include/linux/workqueue.h +++ b/include/linux/workqueue.h @@ -415,6 +415,7 @@ enum { __WQ_ORDERED = 1 << 17, /* internal: workqueue is ordered */ __WQ_LEGACY = 1 << 18, /* internal: create*_workqueue() */ __WQ_ORDERED_EXPLICIT = 1 << 19, /* internal: alloc_ordered_workqueue() */ + __WQ_DYNAMIC = 1 << 25, /* internal: only support single work order WQ */ WQ_MAX_ACTIVE = 512, /* I like 512, better ideas? */ WQ_UNBOUND_MAX_ACTIVE = WQ_MAX_ACTIVE, diff --git a/include/scsi/libiscsi.h b/include/scsi/libiscsi.h index d253b82e973e..ead17d2224a1 100644 --- a/include/scsi/libiscsi.h +++ b/include/scsi/libiscsi.h @@ -266,6 +266,7 @@ struct iscsi_conn { /* custom statistics */ uint32_t eh_abort_cnt; uint32_t fmr_unalign_cnt; + int intimate_cpu; KABI_RESERVE(1) KABI_RESERVE(2) -- Gitee From fbd0253e9d794909c6248a79bea85e125397dd3e Mon Sep 17 00:00:00 2001 From: shaodenghui Date: Mon, 4 Mar 2024 09:34:26 +0800 Subject: [PATCH 2/4] workqueue: implement NUMA affinity for single thread workqueue euleros inclusion category: feature bugzilla: https://gitee.com/openeuler/kernel/issues/I94XYA CVE: NA ------------------------------------------------- Currently, single thread workqueue only have single pwq, all of works are queued the same workerpool. This is not optimal on NUMA machines, will cause workers jump around across node. This patch add a new wq flags __WQ_DYNAMIC, this new kind of single thread workqueue creates a separate pwq covering the intersecting CPUS for each NUMA node which has online CPUS in @attrs->cpumask instead of mapping all entries of numa_pwq_tbl[] to the same pwq. After this, we can specify the @cpu of queue_work_on, so the work can be executed on the same NUMA node of the specified @cpu. This kind of wq only support single work, multi works can't guarantee the work's order. Signed-off-by: Biaoxiang Ye Acked-by: Hanjun Guo Signed-off-by: Yang Yingliang Reviewed-by: fang yi Signed-off-by: Zheng Zengkai Signed-off-by: shaodenghui --- kernel/workqueue.c | 15 ++++++++++----- 1 file changed, 10 insertions(+), 5 deletions(-) diff --git a/kernel/workqueue.c b/kernel/workqueue.c index 1888741f5edd..cdfd4261b442 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -4355,6 +4355,9 @@ apply_wqattrs_prepare(struct workqueue_struct *wq, * it even if we don't use it immediately. */ copy_workqueue_attrs(new_attrs, attrs); + if (wq->flags & __WQ_DYNAMIC) + new_attrs->ordered = false; + wqattrs_actualize_cpumask(new_attrs, unbound_cpumask); cpumask_copy(new_attrs->__pod_cpumask, new_attrs->cpumask); ctx->dfl_pwq = alloc_unbound_pwq(wq, new_attrs); @@ -4591,10 +4594,12 @@ static int alloc_and_link_pwqs(struct workqueue_struct *wq) cpus_read_lock(); if (wq->flags & __WQ_ORDERED) { ret = apply_workqueue_attrs(wq, ordered_wq_attrs[highpri]); - /* there should only be single pwq for ordering guarantee */ - WARN(!ret && (wq->pwqs.next != &wq->dfl_pwq->pwqs_node || - wq->pwqs.prev != &wq->dfl_pwq->pwqs_node), - "ordering guarantee broken for workqueue %s\n", wq->name); + if (!(wq->flags & __WQ_DYNAMIC)) { + /* there should only be single pwq for ordering guarantee */ + WARN(!ret && (wq->pwqs.next != &wq->dfl_pwq->pwqs_node || + wq->pwqs.prev != &wq->dfl_pwq->pwqs_node), + "ordering guarantee broken for workqueue %s\n", wq->name); + } } else { ret = apply_workqueue_attrs(wq, unbound_std_wq_attrs[highpri]); } @@ -5798,7 +5803,7 @@ static int workqueue_apply_unbound_cpumask(const cpumask_var_t unbound_cpumask) continue; /* creating multiple pwqs breaks ordering guarantee */ - if (!list_empty(&wq->pwqs)) { + if (!list_empty(&wq->pwqs) && !(wq->flags & __WQ_DYNAMIC)) { if (wq->flags & __WQ_ORDERED_EXPLICIT) continue; wq->flags &= ~__WQ_ORDERED; -- Gitee From f0ee1e052419f7340e6dc8452fa9606b245df16f Mon Sep 17 00:00:00 2001 From: shaodenghui Date: Mon, 4 Mar 2024 09:34:27 +0800 Subject: [PATCH 3/4] iscsi: use dynamic single thread workqueue to improve performance euleros inclusion category: feature bugzilla: https://gitee.com/openeuler/kernel/issues/I94XYA CVE: NA ------------------------------------------------- On aarch64 NUMA machines, the kworker of iscsi created always jump around across node boundaries. If it work on the different node even different cpu package with the softirq of network interface, memcpy with in iscsi_tcp_segment_recv will be slow down, and iscsi got an terrible performance. In this patch, we trace the cpu of softirq, and tell queue_work_on to execute iscsi_xmitworker on the same NUMA node. The performance data as below: fio cmd: fio -filename=/dev/disk/by-id/wwn-0x6883fd3100a2ad260036281700000000 -direct=1 -iodepth=32 -rw=read -bs=64k -size=30G -ioengine=libaio -numjobs=1 -group_reporting -name=mytest -time_based -ramp_time=60 -runtime=60 before patch: Jobs: 1 (f=1): [R] [52.5% done] [852.3MB/0KB/0KB /s] [13.7K/0/0 iops] [eta 00m:57s] Jobs: 1 (f=1): [R] [53.3% done] [861.4MB/0KB/0KB /s] [13.8K/0/0 iops] [eta 00m:56s] Jobs: 1 (f=1): [R] [54.2% done] [868.2MB/0KB/0KB /s] [13.9K/0/0 iops] [eta 00m:55s] after pactch: Jobs: 1 (f=1): [R] [53.3% done] [1070MB/0KB/0KB /s] [17.2K/0/0 iops] [eta 00m:56s] Jobs: 1 (f=1): [R] [55.0% done] [1064MB/0KB/0KB /s] [17.3K/0/0 iops] [eta 00m:54s] Jobs: 1 (f=1): [R] [56.7% done] [1069MB/0KB/0KB /s] [17.1K/0/0 iops] [eta 00m:52s] cpu info: Architecture: aarch64 Byte Order: Little Endian CPU(s): 128 On-line CPU(s) list: 0-127 Thread(s) per core: 1 Core(s) per socket: 64 Socket(s): 2 NUMA node(s): 4 Model: 0 CPU max MHz: 2600.0000 CPU min MHz: 200.0000 BogoMIPS: 200.00 L1d cache: 64K L1i cache: 64K L2 cache: 512K L3 cache: 32768K NUMA node0 CPU(s): 0-31 NUMA node1 CPU(s): 32-63 NUMA node2 CPU(s): 64-95 NUMA node3 CPU(s): 96-127 Signed-off-by: Biaoxiang Ye Acked-by: Hanjun Guo Signed-off-by: Yang Yingliang Reviewed-by: fang yi Signed-off-by: Zheng Zengkai Signed-off-by: shaodenghui --- drivers/scsi/iscsi_tcp.c | 9 +++++++++ drivers/scsi/libiscsi.c | 17 ++++++++++++----- 2 files changed, 21 insertions(+), 5 deletions(-) diff --git a/drivers/scsi/iscsi_tcp.c b/drivers/scsi/iscsi_tcp.c index 8e14cea15f98..d68bf693162c 100644 --- a/drivers/scsi/iscsi_tcp.c +++ b/drivers/scsi/iscsi_tcp.c @@ -170,6 +170,7 @@ static void iscsi_sw_tcp_data_ready(struct sock *sk) struct iscsi_sw_tcp_conn *tcp_sw_conn; struct iscsi_tcp_conn *tcp_conn; struct iscsi_conn *conn; + int current_cpu; trace_sk_data_ready(sk); @@ -180,6 +181,14 @@ static void iscsi_sw_tcp_data_ready(struct sock *sk) return; } tcp_conn = conn->dd_data; + + /* save intimate cpu when in softirq */ + if (!sock_owned_by_user_nocheck(sk)) { + current_cpu = smp_processor_id(); + if (conn->intimate_cpu != current_cpu) + conn->intimate_cpu = current_cpu; + } + tcp_sw_conn = tcp_conn->dd_data; if (tcp_sw_conn->queue_recv) diff --git a/drivers/scsi/libiscsi.c b/drivers/scsi/libiscsi.c index 0fda8905eabd..0a8aee8fd742 100644 --- a/drivers/scsi/libiscsi.c +++ b/drivers/scsi/libiscsi.c @@ -89,9 +89,15 @@ inline void iscsi_conn_queue_xmit(struct iscsi_conn *conn) { struct Scsi_Host *shost = conn->session->host; struct iscsi_host *ihost = shost_priv(shost); + int intimate_cpu = conn->intimate_cpu; - if (ihost->workq) - queue_work(ihost->workq, &conn->xmitwork); + if (ihost->workq) { + /* we expect it to be excuted on the same numa of the intimate cpu */ + if ((intimate_cpu >= 0) && cpu_possible(intimate_cpu)) + queue_work_on(intimate_cpu, ihost->workq, &conn->xmitwork); + else + queue_work(ihost->workq, &conn->xmitwork); + } } EXPORT_SYMBOL_GPL(iscsi_conn_queue_xmit); @@ -2907,9 +2913,9 @@ struct Scsi_Host *iscsi_host_alloc(const struct scsi_host_template *sht, ihost = shost_priv(shost); if (xmit_can_sleep) { - ihost->workq = alloc_workqueue("iscsi_q_%d", - WQ_SYSFS | __WQ_LEGACY | WQ_MEM_RECLAIM | WQ_UNBOUND, - 1, shost->host_no); + /* this kind of workqueue only support single work */ + ihost->workq = alloc_ordered_workqueue("iscsi_q_%d", __WQ_LEGACY | WQ_MEM_RECLAIM | + __WQ_DYNAMIC, shost->host_no); if (!ihost->workq) goto free_host; } @@ -3190,6 +3196,7 @@ iscsi_conn_setup(struct iscsi_cls_session *cls_session, int dd_size, conn->c_stage = ISCSI_CONN_INITIAL_STAGE; conn->id = conn_idx; conn->exp_statsn = 0; + conn->intimate_cpu = -1; timer_setup(&conn->transport_timer, iscsi_check_transport_timeouts, 0); -- Gitee From 2358f2d6c525a59d7083415e860af480f57c5e8a Mon Sep 17 00:00:00 2001 From: Shao Denghui Date: Mon, 4 Mar 2024 09:34:28 +0800 Subject: [PATCH 4/4] kworker: add CONFIG_SCSI_KWORKER virt inclusion category: feature bugzilla: https://gitee.com/openeuler/kernel/issues/I94XYA ---------------------------------------------------------------------- Add CONFIG_SCSI_KWORKER to control scsi kworker code compile or not. Signed-off-by: shaodenghui --- arch/arm64/configs/openeuler_defconfig | 1 + arch/x86/configs/openeuler_defconfig | 1 + drivers/scsi/Kconfig | 18 ++++++++++++++++++ drivers/scsi/iscsi_tcp.c | 4 ++++ drivers/scsi/libiscsi.c | 13 +++++++++++++ kernel/workqueue.c | 15 ++++++++++++++- 6 files changed, 51 insertions(+), 1 deletion(-) diff --git a/arch/arm64/configs/openeuler_defconfig b/arch/arm64/configs/openeuler_defconfig index afde4d70ee13..3845f223efab 100644 --- a/arch/arm64/configs/openeuler_defconfig +++ b/arch/arm64/configs/openeuler_defconfig @@ -2486,6 +2486,7 @@ CONFIG_CHR_DEV_SCH=m CONFIG_SCSI_ENCLOSURE=m CONFIG_SCSI_CONSTANTS=y CONFIG_SCSI_LOGGING=y +CONFIG_SCSI_KWORKER=y CONFIG_SCSI_SCAN_ASYNC=y # diff --git a/arch/x86/configs/openeuler_defconfig b/arch/x86/configs/openeuler_defconfig index 627a08ecbf4a..9c12b2633cdf 100644 --- a/arch/x86/configs/openeuler_defconfig +++ b/arch/x86/configs/openeuler_defconfig @@ -2477,6 +2477,7 @@ CONFIG_CHR_DEV_SCH=m CONFIG_SCSI_ENCLOSURE=m CONFIG_SCSI_CONSTANTS=y CONFIG_SCSI_LOGGING=y +CONFIG_SCSI_KWORKER=y CONFIG_SCSI_SCAN_ASYNC=y # diff --git a/drivers/scsi/Kconfig b/drivers/scsi/Kconfig index 695a57d894cd..5dd1f2b956f9 100644 --- a/drivers/scsi/Kconfig +++ b/drivers/scsi/Kconfig @@ -218,6 +218,24 @@ config SCSI_LOGGING there should be no noticeable performance impact as long as you have logging turned off. +config SCSI_KWORKER + tristate "kworker NUMA affinity " + default n + help + kworker: Fix the problem of ipsan performance degradation on ARM + architecture. + + When the current downstream FS tests IPSAN, it is found that the + performance on ARM is much worse than that on X86, and the test data + of IPSAN fluctuates greatly. After analysis, the reason is that when + iscsi issues IO, the task is sent to kworker for processing by + iscsi_xmitworker. + + The workqueue created by iscsi can automatically identify the CPU of + the soft interrupt currently processed by iscsi, and automatically + schedule the workqueue to the corresponding NUMA node. + + config SCSI_SCAN_ASYNC bool "Asynchronous SCSI scanning" depends on SCSI diff --git a/drivers/scsi/iscsi_tcp.c b/drivers/scsi/iscsi_tcp.c index d68bf693162c..f47a0c37319f 100644 --- a/drivers/scsi/iscsi_tcp.c +++ b/drivers/scsi/iscsi_tcp.c @@ -170,7 +170,9 @@ static void iscsi_sw_tcp_data_ready(struct sock *sk) struct iscsi_sw_tcp_conn *tcp_sw_conn; struct iscsi_tcp_conn *tcp_conn; struct iscsi_conn *conn; +#ifdef CONFIG_SCSI_KWORKER int current_cpu; +#endif trace_sk_data_ready(sk); @@ -182,12 +184,14 @@ static void iscsi_sw_tcp_data_ready(struct sock *sk) } tcp_conn = conn->dd_data; +#ifdef CONFIG_SCSI_KWORKER /* save intimate cpu when in softirq */ if (!sock_owned_by_user_nocheck(sk)) { current_cpu = smp_processor_id(); if (conn->intimate_cpu != current_cpu) conn->intimate_cpu = current_cpu; } +#endif tcp_sw_conn = tcp_conn->dd_data; diff --git a/drivers/scsi/libiscsi.c b/drivers/scsi/libiscsi.c index 0a8aee8fd742..c5fe9003a994 100644 --- a/drivers/scsi/libiscsi.c +++ b/drivers/scsi/libiscsi.c @@ -89,6 +89,7 @@ inline void iscsi_conn_queue_xmit(struct iscsi_conn *conn) { struct Scsi_Host *shost = conn->session->host; struct iscsi_host *ihost = shost_priv(shost); +#ifdef CONFIG_SCSI_KWORKER int intimate_cpu = conn->intimate_cpu; if (ihost->workq) { @@ -98,6 +99,10 @@ inline void iscsi_conn_queue_xmit(struct iscsi_conn *conn) else queue_work(ihost->workq, &conn->xmitwork); } +#else + if (ihost->workq) + queue_work(ihost->workq, &conn->xmitwork); +#endif } EXPORT_SYMBOL_GPL(iscsi_conn_queue_xmit); @@ -2913,9 +2918,15 @@ struct Scsi_Host *iscsi_host_alloc(const struct scsi_host_template *sht, ihost = shost_priv(shost); if (xmit_can_sleep) { +#ifdef CONFIG_SCSI_KWORKER /* this kind of workqueue only support single work */ ihost->workq = alloc_ordered_workqueue("iscsi_q_%d", __WQ_LEGACY | WQ_MEM_RECLAIM | __WQ_DYNAMIC, shost->host_no); +#else + ihost->workq = alloc_workqueue("iscsi_q_%d", + WQ_SYSFS | __WQ_LEGACY | WQ_MEM_RECLAIM | WQ_UNBOUND, + 1, shost->host_no); +#endif if (!ihost->workq) goto free_host; } @@ -3196,7 +3207,9 @@ iscsi_conn_setup(struct iscsi_cls_session *cls_session, int dd_size, conn->c_stage = ISCSI_CONN_INITIAL_STAGE; conn->id = conn_idx; conn->exp_statsn = 0; +#ifdef CONFIG_SCSI_KWORKER conn->intimate_cpu = -1; +#endif timer_setup(&conn->transport_timer, iscsi_check_transport_timeouts, 0); diff --git a/kernel/workqueue.c b/kernel/workqueue.c index cdfd4261b442..4ba630a19ac6 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -4355,8 +4355,10 @@ apply_wqattrs_prepare(struct workqueue_struct *wq, * it even if we don't use it immediately. */ copy_workqueue_attrs(new_attrs, attrs); +#ifdef CONFIG_SCSI_KWORKER if (wq->flags & __WQ_DYNAMIC) new_attrs->ordered = false; +#endif wqattrs_actualize_cpumask(new_attrs, unbound_cpumask); cpumask_copy(new_attrs->__pod_cpumask, new_attrs->cpumask); @@ -4594,12 +4596,19 @@ static int alloc_and_link_pwqs(struct workqueue_struct *wq) cpus_read_lock(); if (wq->flags & __WQ_ORDERED) { ret = apply_workqueue_attrs(wq, ordered_wq_attrs[highpri]); +#ifdef CONFIG_SCSI_KWORKER if (!(wq->flags & __WQ_DYNAMIC)) { /* there should only be single pwq for ordering guarantee */ WARN(!ret && (wq->pwqs.next != &wq->dfl_pwq->pwqs_node || wq->pwqs.prev != &wq->dfl_pwq->pwqs_node), - "ordering guarantee broken for workqueue %s\n", wq->name); + "ordering guarantee broken for workqueue %s\n", wq->name); } +#else + /* there should only be single pwq for ordering guarantee */ + WARN(!ret && (wq->pwqs.next != &wq->dfl_pwq->pwqs_node || + wq->pwqs.prev != &wq->dfl_pwq->pwqs_node), + "ordering guarantee broken for workqueue %s\n", wq->name); +#endif } else { ret = apply_workqueue_attrs(wq, unbound_std_wq_attrs[highpri]); } @@ -5803,7 +5812,11 @@ static int workqueue_apply_unbound_cpumask(const cpumask_var_t unbound_cpumask) continue; /* creating multiple pwqs breaks ordering guarantee */ +#ifdef CONFIG_SCSI_KWORKER if (!list_empty(&wq->pwqs) && !(wq->flags & __WQ_DYNAMIC)) { +#else + if (!list_empty(&wq->pwqs)) { +#endif if (wq->flags & __WQ_ORDERED_EXPLICIT) continue; wq->flags &= ~__WQ_ORDERED; -- Gitee