Archive-only list for patches
 help / color / mirror / Atom feed
From: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
To: stable@vger.kernel.org
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>,
	patches@lists.linux.dev, Yin Fengwei <fengwei.yin@intel.com>,
	kernel test robot <yujie.liu@intel.com>,
	"Paulo Alcantara (SUSE)" <pc@manguebit.com>,
	Shyam Prasad N <sprasad@microsoft.com>,
	Steve French <stfrench@microsoft.com>,
	Sasha Levin <sashal@kernel.org>
Subject: [PATCH 5.15 77/93] smb3: lower default deferred close timeout to address perf regression
Date: Wed, 12 Apr 2023 10:34:18 +0200	[thread overview]
Message-ID: <20230412082826.379618513@linuxfoundation.org> (raw)
In-Reply-To: <20230412082823.045155996@linuxfoundation.org>

From: Steve French <stfrench@microsoft.com>

[ Upstream commit 7e0e76d99079be13c9961dde7c93b2d1ee665af4 ]

Performance tests with large number of threads noted that the change
of the default closetimeo (deferred close timeout between when
close is done by application and when client has to send the close
to the server), to 5 seconds from 1 second, significantly degraded
perf in some cases like this (in the filebench example reported,
the stats show close requests on the wire taking twice as long,
and 50% regression in filebench perf). This is stil configurable
via mount parm closetimeo, but to be safe, decrease default back
to its previous value of 1 second.

Reported-by: Yin Fengwei <fengwei.yin@intel.com>
Reported-by: kernel test robot <yujie.liu@intel.com>
Link: https://lore.kernel.org/lkml/997614df-10d4-af53-9571-edec36b0e2f3@intel.com/
Fixes: 5efdd9122eff ("smb3: allow deferred close timeout to be configurable")
Cc: stable@vger.kernel.org # 6.0+
Tested-by: Yin Fengwei <fengwei.yin@intel.com>
Reviewed-by: Paulo Alcantara (SUSE) <pc@manguebit.com>
Reviewed-by: Shyam Prasad N <sprasad@microsoft.com>
Signed-off-by: Steve French <stfrench@microsoft.com>
Stable-dep-of: d19342c6609b ("cifs: sanitize paths in cifs_update_super_prepath.")
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 fs/cifs/fs_context.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/fs/cifs/fs_context.h b/fs/cifs/fs_context.h
index b5ae210bafe04..ad45256cf68e2 100644
--- a/fs/cifs/fs_context.h
+++ b/fs/cifs/fs_context.h
@@ -282,5 +282,5 @@ extern void smb3_update_mnt_flags(struct cifs_sb_info *cifs_sb);
  * max deferred close timeout (jiffies) - 2^30
  */
 #define SMB3_MAX_DCLOSETIMEO (1 << 30)
-#define SMB3_DEF_DCLOSETIMEO (5 * HZ) /* Can increase later, other clients use larger */
+#define SMB3_DEF_DCLOSETIMEO (1 * HZ) /* even 1 sec enough to help eg open/write/close/open/read */
 #endif
-- 
2.39.2




  parent reply	other threads:[~2023-04-12  8:38 UTC|newest]

Thread overview: 106+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2023-04-12  8:33 [PATCH 5.15 00/93] 5.15.107-rc1 review Greg Kroah-Hartman
2023-04-12  8:33 ` [PATCH 5.15 01/93] soc: sifive: ccache: Rename SiFive L2 cache to Composable cache Greg Kroah-Hartman
2023-04-12  9:36   ` Conor Dooley
2023-04-12 10:14     ` Greg Kroah-Hartman
2023-04-12  8:33 ` [PATCH 5.15 02/93] soc: sifive: ccache: determine the cache level from dts Greg Kroah-Hartman
2023-04-12  8:33 ` [PATCH 5.15 03/93] soc: sifive: ccache: reduce printing on init Greg Kroah-Hartman
2023-04-12  8:33 ` [PATCH 5.15 04/93] soc: sifive: ccache: use pr_fmt() to remove CCACHE: prefixes Greg Kroah-Hartman
2023-04-12  8:33 ` [PATCH 5.15 05/93] soc: sifive: ccache: fix missing iounmap() in error path in sifive_ccache_init() Greg Kroah-Hartman
2023-04-12  8:33 ` [PATCH 5.15 06/93] soc: sifive: ccache: fix missing free_irq() " Greg Kroah-Hartman
2023-04-12  8:33 ` [PATCH 5.15 07/93] soc: sifive: ccache: fix missing of_node_put() " Greg Kroah-Hartman
2023-04-12  8:33 ` [PATCH 5.15 08/93] ocfs2: ocfs2_mount_volume does cleanup job before return error Greg Kroah-Hartman
2023-04-12  8:33 ` [PATCH 5.15 09/93] ocfs2: rewrite error handling of ocfs2_fill_super Greg Kroah-Hartman
2023-04-12  8:33 ` [PATCH 5.15 10/93] ocfs2: fix memory leak in ocfs2_mount_volume() Greg Kroah-Hartman
2023-04-12  8:33 ` [PATCH 5.15 11/93] NFSD: Fix sparse warning Greg Kroah-Hartman
2023-04-12  8:33 ` [PATCH 5.15 12/93] NFSD: pass range end to vfs_fsync_range() instead of count Greg Kroah-Hartman
2023-04-12  8:33 ` [PATCH 5.15 13/93] RDMA/irdma: Do not request 2-level PBLEs for CQ alloc Greg Kroah-Hartman
2023-04-12  8:33 ` [PATCH 5.15 14/93] platform/x86: int3472: Split into 2 drivers Greg Kroah-Hartman
2023-04-12  8:33 ` [PATCH 5.15 15/93] platform/x86: int3472/discrete: Ensure the clk/power enable pins are in output mode Greg Kroah-Hartman
2023-04-12  8:33 ` [PATCH 5.15 16/93] iavf: return errno code instead of status code Greg Kroah-Hartman
2023-04-12  8:33 ` [PATCH 5.15 17/93] iavf/iavf_main: actually log ->src mask when talking about it Greg Kroah-Hartman
2023-04-12  8:33 ` [PATCH 5.15 18/93] serial: 8250_exar: derive nr_ports from PCI ID for Acces I/O cards Greg Kroah-Hartman
2023-04-12  8:33 ` [PATCH 5.15 19/93] serial: exar: Add support for Sealevel 7xxxC serial cards Greg Kroah-Hartman
2023-04-12  8:33 ` [PATCH 5.15 20/93] drm/amdgpu: Prevent race between late signaled fences and GPU reset Greg Kroah-Hartman
2023-04-12  8:33 ` [PATCH 5.15 21/93] drm/amdgpu: fix amdgpu_job_free_resources v2 Greg Kroah-Hartman
2023-04-12  8:33 ` [PATCH 5.15 22/93] bpf: hash map, avoid deadlock with suitable hash mask Greg Kroah-Hartman
2023-04-12  8:33 ` [PATCH 5.15 23/93] gpio: GPIO_REGMAP: select REGMAP instead of depending on it Greg Kroah-Hartman
2023-04-12  8:33 ` [PATCH 5.15 24/93] Drivers: vmbus: Check for channel allocation before looking up relids Greg Kroah-Hartman
2023-04-12  8:33 ` [PATCH 5.15 25/93] pwm: cros-ec: Explicitly set .polarity in .get_state() Greg Kroah-Hartman
2023-04-12  8:33 ` [PATCH 5.15 26/93] pwm: sprd: " Greg Kroah-Hartman
2023-04-12  8:33 ` [PATCH 5.15 27/93] KVM: s390: pv: fix external interruption loop not always detected Greg Kroah-Hartman
2023-04-12  8:33 ` [PATCH 5.15 28/93] wifi: mac80211: fix invalid drv_sta_pre_rcu_remove calls for non-uploaded sta Greg Kroah-Hartman
2023-04-12  8:33 ` [PATCH 5.15 29/93] net: qrtr: combine nameservice into main module Greg Kroah-Hartman
2023-04-12  8:33 ` [PATCH 5.15 30/93] net: qrtr: Fix a refcount bug in qrtr_recvmsg() Greg Kroah-Hartman
2023-04-12  8:33 ` [PATCH 5.15 31/93] NFSD: Avoid calling OPDESC() with ops->opnum == OP_ILLEGAL Greg Kroah-Hartman
2023-04-12  8:33 ` [PATCH 5.15 32/93] icmp: guard against too small mtu Greg Kroah-Hartman
2023-04-12  8:33 ` [PATCH 5.15 33/93] net: dont let netpoll invoke NAPI if in xmit context Greg Kroah-Hartman
2023-04-12  8:33 ` [PATCH 5.15 34/93] net: dsa: mv88e6xxx: Reset mv88e6393x force WD event bit Greg Kroah-Hartman
2023-04-12  8:33 ` [PATCH 5.15 35/93] sctp: check send stream number after wait_for_sndbuf Greg Kroah-Hartman
2023-04-12  8:33 ` [PATCH 5.15 36/93] net: qrtr: Do not do DEL_SERVER broadcast after DEL_CLIENT Greg Kroah-Hartman
2023-04-12  8:33 ` [PATCH 5.15 37/93] ipv6: Fix an uninit variable access bug in __ip6_make_skb() Greg Kroah-Hartman
2023-04-12  8:33 ` [PATCH 5.15 38/93] platform/x86: think-lmi: Fix memory leak when showing current settings Greg Kroah-Hartman
2023-04-12  8:33 ` [PATCH 5.15 39/93] platform/x86: think-lmi: Fix memory leaks when parsing ThinkStation WMI strings Greg Kroah-Hartman
2023-04-12  8:33 ` [PATCH 5.15 40/93] platform/x86: think-lmi: Clean up display of current_value on Thinkstation Greg Kroah-Hartman
2023-04-12  8:33 ` [PATCH 5.15 41/93] gpio: davinci: Add irq chip flag to skip set wake Greg Kroah-Hartman
2023-04-12  8:33 ` [PATCH 5.15 42/93] net: ethernet: ti: am65-cpsw: Fix mdio cleanup in probe Greg Kroah-Hartman
2023-04-12  8:33 ` [PATCH 5.15 43/93] net: stmmac: fix up RX flow hash indirection table when setting channels Greg Kroah-Hartman
2023-04-12  8:33 ` [PATCH 5.15 44/93] sunrpc: only free unix grouplist after RCU settles Greg Kroah-Hartman
2023-04-12  8:33 ` [PATCH 5.15 45/93] NFSD: callback request does not use correct credential for AUTH_SYS Greg Kroah-Hartman
2023-04-12  8:33 ` [PATCH 5.15 46/93] ice: fix wrong fallback logic for FDIR Greg Kroah-Hartman
2023-04-12  8:33 ` [PATCH 5.15 47/93] ice: Reset FDIR counter in FDIR init stage Greg Kroah-Hartman
2023-04-12  8:33 ` [PATCH 5.15 48/93] ethtool: reset #lanes when lanes is omitted Greg Kroah-Hartman
2023-04-12  8:33 ` [PATCH 5.15 49/93] gve: Secure enough bytes in the first TX desc for all TCP pkts Greg Kroah-Hartman
2023-04-12  8:33 ` [PATCH 5.15 50/93] kbuild: refactor single builds of *.ko Greg Kroah-Hartman
2023-04-12  8:33 ` [PATCH 5.15 51/93] usb: xhci: tegra: fix sleep in atomic call Greg Kroah-Hartman
2023-04-12  8:33 ` [PATCH 5.15 52/93] xhci: also avoid the XHCI_ZERO_64B_REGS quirk with a passthrough iommu Greg Kroah-Hartman
2023-04-12  8:33 ` [PATCH 5.15 53/93] usb: cdnsp: Fixes error: uninitialized symbol len Greg Kroah-Hartman
2023-04-12  8:33 ` [PATCH 5.15 54/93] usb: dwc3: pci: add support for the Intel Meteor Lake-S Greg Kroah-Hartman
2023-04-12  8:33 ` [PATCH 5.15 55/93] USB: serial: cp210x: add Silicon Labs IFS-USB-DATACABLE IDs Greg Kroah-Hartman
2023-04-12  8:33 ` [PATCH 5.15 56/93] usb: typec: altmodes/displayport: Fix configure initial pin assignment Greg Kroah-Hartman
2023-04-12  8:33 ` [PATCH 5.15 57/93] USB: serial: option: add Telit FE990 compositions Greg Kroah-Hartman
2023-04-12  8:33 ` [PATCH 5.15 58/93] USB: serial: option: add Quectel RM500U-CN modem Greg Kroah-Hartman
2023-04-12  8:34 ` [PATCH 5.15 59/93] iio: adis16480: select CONFIG_CRC32 Greg Kroah-Hartman
2023-04-12  8:34 ` [PATCH 5.15 60/93] iio: adc: ti-ads7950: Set `can_sleep` flag for GPIO chip Greg Kroah-Hartman
2023-04-12  8:34 ` [PATCH 5.15 61/93] iio: dac: cio-dac: Fix max DAC write value check for 12-bit Greg Kroah-Hartman
2023-04-12  8:34 ` [PATCH 5.15 62/93] iio: light: cm32181: Unregister second I2C client if present Greg Kroah-Hartman
2023-04-12  8:34 ` [PATCH 5.15 63/93] tty: serial: sh-sci: Fix transmit end interrupt handler Greg Kroah-Hartman
2023-04-12  8:34 ` [PATCH 5.15 64/93] tty: serial: sh-sci: Fix Rx on RZ/G2L SCI Greg Kroah-Hartman
2023-04-12  8:34 ` [PATCH 5.15 65/93] tty: serial: fsl_lpuart: avoid checking for transfer complete when UARTCTRL_SBK is asserted in lpuart32_tx_empty Greg Kroah-Hartman
2023-04-12  8:34 ` [PATCH 5.15 66/93] nilfs2: fix potential UAF of struct nilfs_sc_info in nilfs_segctor_thread() Greg Kroah-Hartman
2023-04-12  8:34 ` [PATCH 5.15 67/93] nilfs2: fix sysfs interface lifetime Greg Kroah-Hartman
2023-04-12  8:34 ` [PATCH 5.15 68/93] dt-bindings: serial: renesas,scif: Fix 4th IRQ for 4-IRQ SCIFs Greg Kroah-Hartman
2023-04-12  8:34 ` [PATCH 5.15 69/93] ksmbd: do not call kvmalloc() with __GFP_NORETRY | __GFP_NO_WARN Greg Kroah-Hartman
2023-04-12  8:34 ` [PATCH 5.15 70/93] ALSA: hda/realtek: Add quirk for Clevo X370SNW Greg Kroah-Hartman
2023-04-12  8:34 ` [PATCH 5.15 71/93] coresight: etm4x: Do not access TRCIDR1 for identification Greg Kroah-Hartman
2023-04-12  8:34 ` [PATCH 5.15 72/93] coresight-etm4: Fix for() loop drvdata->nr_addr_cmp range bug Greg Kroah-Hartman
2023-04-12  8:34 ` [PATCH 5.15 73/93] iio: adc: ad7791: fix IRQ flags Greg Kroah-Hartman
2023-04-12  8:34 ` [PATCH 5.15 74/93] scsi: qla2xxx: Fix memory leak in qla2x00_probe_one() Greg Kroah-Hartman
2023-04-12  8:34 ` [PATCH 5.15 75/93] scsi: iscsi_tcp: Check that sock is valid before iscsi_set_param() Greg Kroah-Hartman
2023-04-12  8:34 ` [PATCH 5.15 76/93] smb3: allow deferred close timeout to be configurable Greg Kroah-Hartman
2023-04-12  8:34 ` Greg Kroah-Hartman [this message]
2023-04-12  8:34 ` [PATCH 5.15 78/93] cifs: sanitize paths in cifs_update_super_prepath Greg Kroah-Hartman
2023-04-12  8:34 ` [PATCH 5.15 79/93] perf/core: Fix the same task check in perf_event_set_output Greg Kroah-Hartman
2023-04-12  8:34 ` [PATCH 5.15 80/93] ftrace: Mark get_lock_parent_ip() __always_inline Greg Kroah-Hartman
2023-04-12  8:34 ` [PATCH 5.15 81/93] ftrace: Fix issue that direct->addr not restored in modify_ftrace_direct() Greg Kroah-Hartman
2023-04-12  8:34 ` [PATCH 5.15 82/93] fs: drop peer group ids under namespace lock Greg Kroah-Hartman
2023-04-12  8:34 ` [PATCH 5.15 83/93] can: j1939: j1939_tp_tx_dat_new(): fix out-of-bounds memory access Greg Kroah-Hartman
2023-04-12  8:34 ` [PATCH 5.15 84/93] can: isotp: isotp_ops: fix poll() to not report false EPOLLOUT events Greg Kroah-Hartman
2023-04-12  8:34 ` [PATCH 5.15 85/93] tracing: Free error logs of tracing instances Greg Kroah-Hartman
2023-04-12  8:34 ` [PATCH 5.15 86/93] ASoC: hdac_hdmi: use set_stream() instead of set_tdm_slots() Greg Kroah-Hartman
2023-04-12  8:34 ` [PATCH 5.15 87/93] mm: vmalloc: avoid warn_alloc noise caused by fatal signal Greg Kroah-Hartman
2023-04-12  8:34 ` [PATCH 5.15 88/93] drm/panfrost: Fix the panfrost_mmu_map_fault_addr() error path Greg Kroah-Hartman
2023-04-12  8:34 ` [PATCH 5.15 89/93] drm/nouveau/disp: Support more modes by checking with lower bpc Greg Kroah-Hartman
2023-04-12  8:34 ` [PATCH 5.15 90/93] ring-buffer: Fix race while reader and writer are on the same page Greg Kroah-Hartman
2023-04-12  8:34 ` [PATCH 5.15 91/93] mm/swap: fix swap_info_struct race between swapoff and get_swap_pages() Greg Kroah-Hartman
2023-04-12  8:34 ` [PATCH 5.15 92/93] drm/bridge: lt9611: Fix PLL being unable to lock Greg Kroah-Hartman
2023-04-12  8:34 ` [PATCH 5.15 93/93] mm: take a page reference when removing device exclusive entries Greg Kroah-Hartman
2023-04-12 16:53 ` [PATCH 5.15 00/93] 5.15.107-rc1 review Florian Fainelli
2023-04-12 19:41 ` Shuah Khan
2023-04-12 20:41 ` Guenter Roeck
2023-04-12 21:47 ` [PATCH 5.15 00/93] 5.15.107-rc1 review (possible amdgpu regression) Eddie Chapman
2023-04-13 14:46   ` Greg Kroah-Hartman
2023-06-07 22:24     ` Eddie Chapman
2023-04-13  2:04 ` [PATCH 5.15 00/93] 5.15.107-rc1 review Bagas Sanjaya
2023-04-13 13:28 ` Ron Economos
2023-04-13 14:18 ` Naresh Kamboju
2023-04-13 14:51 ` Harshit Mogalapalli

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20230412082826.379618513@linuxfoundation.org \
    --to=gregkh@linuxfoundation.org \
    --cc=fengwei.yin@intel.com \
    --cc=patches@lists.linux.dev \
    --cc=pc@manguebit.com \
    --cc=sashal@kernel.org \
    --cc=sprasad@microsoft.com \
    --cc=stable@vger.kernel.org \
    --cc=stfrench@microsoft.com \
    --cc=yujie.liu@intel.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox