| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Message-Id: <20240715203434.20212-1-stuart.w.hayes@gmail.com>
Date: Mon, 15 Jul 2024 15:34:34 -0500
From: Stuart Hayes <stuart.w.hayes@...il.com>
To: linux-kernel@...r.kernel.org,
Keith Busch <kbusch@...nel.org>,
Jens Axboe <axboe@...nel.dk>,
Christoph Hellwig <hch@....de>,
Sagi Grimberg <sagi@...mberg.me>,
linux-nvme@...ts.infradead.org
Cc: Hannes Reinecke <hare@...e.de>,
Martin Wilck <martin.wilck@...e.com>,
Ayush Siddarath <ayush.siddarath@...l.com>,
Stuart Hayes <stuart.w.hayes@...il.com>
Subject: [PATCH v3] nvme_core: scan namespaces asynchronously
Use async function calls to make namespace scanning happen in parallel.
Without the patch, NVME namespaces are scanned serially, so it can take
a long time for all of a controller's namespaces to become available,
especially with a slower (TCP) interface with large number of
namespaces.
It is not uncommon to have large numbers (hundreds or thousands) of
namespaces on nvme-of with storage servers.
The time it took for all namespaces to show up after connecting (via
TCP) to a controller with 1002 namespaces was measured on one system:
network latency without patch with patch
0 6s 1s
50ms 210s 10s
100ms 417s 18s
Measurements taken on another system show the effect of the patch on the
time nvme_scan_work() took to complete, when connecting to a linux
nvme-of target with varying numbers of namespaces, on a network of
400us.
namespaces without patch with patch
1 16ms 14ms
2 24ms 16ms
4 49ms 22ms
8 101ms 33ms
16 207ms 56ms
100 1.4s 0.6s
1000 12.9s 2.0s
On the same system, connecting to a local PCIe NVMe drive (a Samsung
PM1733) instead of a network target:
namespaces without patch with patch
1 13ms 12ms
2 41ms 13ms
Signed-off-by: Stuart Hayes <stuart.w.hayes@...il.com>
---
changes from V2:
* make a separate function nvme_scan_ns_async() that calls
nvme_scan_ns(), instead of modifying nvme_scan_ns()
* only scan asynchronously from nvme_scan_ns_list(), not from
nvme_scan_ns_sequential()
* provide more timing data in the commit message
changes from V1:
* remove module param to enable/disable async scanning
* add scan time measurements to commit message
drivers/nvme/host/core.c | 48 +++++++++++++++++++++++++++++++++-------
1 file changed, 40 insertions(+), 8 deletions(-)
diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c
index 782090ce0bc1..dbf05cfea063 100644
--- a/drivers/nvme/host/core.c
+++ b/drivers/nvme/host/core.c
@@ -4,6 +4,7 @@
* Copyright (c) 2011-2014, Intel Corporation.
*/
+#include <linux/async.h>
#include <linux/blkdev.h>
#include <linux/blk-mq.h>
#include <linux/blk-integrity.h>
@@ -3952,6 +3953,30 @@ static void nvme_scan_ns(struct nvme_ctrl *ctrl, unsigned nsid)
}
}
+/*
+ * struct async_scan_info - keeps track of controller & NSIDs to scan
+ * @ctrl: Controller on which namespaces are being scanned
+ * @next_idx: Index of next NSID to scan in ns_list
+ * @ns_list: Pointer to list of NSIDs to scan
+ */
+struct async_scan_info {
+ struct nvme_ctrl *ctrl;
+ atomic_t next_idx;
+ __le32 *ns_list;
+};
+
+static void nvme_scan_ns_async(void *data, async_cookie_t cookie)
+{
+ struct async_scan_info *scan_info = data;
+ int idx;
+ u32 nsid;
+
+ idx = (u32)atomic_fetch_add(1, &scan_info->next_idx);
+ nsid = le32_to_cpu(scan_info->ns_list[idx]);
+
+ nvme_scan_ns(scan_info->ctrl, nsid);
+}
+
static void nvme_remove_invalid_namespaces(struct nvme_ctrl *ctrl,
unsigned nsid)
{
@@ -3975,12 +4000,14 @@ static void nvme_remove_invalid_namespaces(struct nvme_ctrl *ctrl,
static int nvme_scan_ns_list(struct nvme_ctrl *ctrl)
{
const int nr_entries = NVME_IDENTIFY_DATA_SIZE / sizeof(__le32);
- __le32 *ns_list;
+ struct async_scan_info scan_info;
u32 prev = 0;
int ret = 0, i;
+ ASYNC_DOMAIN(domain);
- ns_list = kzalloc(NVME_IDENTIFY_DATA_SIZE, GFP_KERNEL);
- if (!ns_list)
+ scan_info.ctrl = ctrl;
+ scan_info.ns_list = kzalloc(NVME_IDENTIFY_DATA_SIZE, GFP_KERNEL);
+ if (!scan_info.ns_list)
return -ENOMEM;
for (;;) {
@@ -3990,28 +4017,33 @@ static int nvme_scan_ns_list(struct nvme_ctrl *ctrl)
.identify.nsid = cpu_to_le32(prev),
};
- ret = nvme_submit_sync_cmd(ctrl->admin_q, &cmd, ns_list,
- NVME_IDENTIFY_DATA_SIZE);
+ ret = nvme_submit_sync_cmd(ctrl->admin_q, &cmd,
+ scan_info.ns_list,
+ NVME_IDENTIFY_DATA_SIZE);
if (ret) {
dev_warn(ctrl->device,
"Identify NS List failed (status=0x%x)\n", ret);
goto free;
}
+ atomic_set(&scan_info.next_idx, 0);
for (i = 0; i < nr_entries; i++) {
- u32 nsid = le32_to_cpu(ns_list[i]);
+ u32 nsid = le32_to_cpu(scan_info.ns_list[i]);
if (!nsid) /* end of the list? */
goto out;
- nvme_scan_ns(ctrl, nsid);
+ async_schedule_domain(nvme_scan_ns_async, &scan_info,
+ &domain);
while (++prev < nsid)
nvme_ns_remove_by_nsid(ctrl, prev);
}
+ async_synchronize_full_domain(&domain);
}
out:
nvme_remove_invalid_namespaces(ctrl, prev);
free:
- kfree(ns_list);
+ async_synchronize_full_domain(&domain);
+ kfree(scan_info.ns_list);
return ret;
}
--
2.39.3
Powered by blists - more mailing lists