search for: gstack

...rt of debug locks PID=9372 ===== 8084 /usr/sbin/smbd brlock.tdb.2 7044 7044 20931 /usr/libexec/ctdb/ctdb_lock_helper brlock.tdb.2 7044 7044 W 21665 /usr/sbin/smbd brlock.tdb.2 174200 174200 ----- Stack trace for PID=21665 ----- 2017/04/19 12:11:39.571097 [ 5417]: /etc/ctdb/debug_locks.sh: line 73: gstack: command not found ----- Stack trace for PID=8084 ----- 2017/04/19 12:11:39.571346 [ 5417]: /etc/ctdb/debug_locks.sh: line 73: gstack: command not found ===== End of debug locks PID=9372 ===== 2017/04/19 12:37:19.547636 [vacuum-locking.tdb: 3790]: tdb(/var/lib/ctdb/locking.tdb.2): tdb_oob len 541...

On Wed, 19 Apr 2017 18:06:35 +0200, David Disseldorp via samba wrote: > > 2017/04/19 10:40:31.294250 [ 7423]: /etc/ctdb/debug_locks.sh: line 73: > > gstack: command not found > > This script attempts to dump the stack trace of the blocked process, > but can't as gstack isn't installed - it should be available in the > gdb package. > > @Martin: would the attached (untested) patch make sense? Gah, this time with the actual...

...========================================================= --- a/drivers/lguest/interrupts_and_traps.c +++ b/drivers/lguest/interrupts_and_traps.c @@ -16,24 +16,25 @@ static int idt_present(u32 lo, u32 hi) return (hi & 0x8000); } -static void push_guest_stack(struct lguest *lg, u32 __user **gstack, u32 val) -{ - lgwrite_u32(lg, (u32)--(*gstack), val); +static void push_guest_stack(struct lguest *lg, unsigned long *gstack, u32 val) +{ + *gstack -= 4; + lgwrite_u32(lg, *gstack, val); } static void set_guest_interrupt(struct lguest *lg, u32 lo, u32 hi, int has_err) { - u32 __user *gstack;...

...========================================================= --- a/drivers/lguest/interrupts_and_traps.c +++ b/drivers/lguest/interrupts_and_traps.c @@ -16,24 +16,25 @@ static int idt_present(u32 lo, u32 hi) return (hi & 0x8000); } -static void push_guest_stack(struct lguest *lg, u32 __user **gstack, u32 val) -{ - lgwrite_u32(lg, (u32)--(*gstack), val); +static void push_guest_stack(struct lguest *lg, unsigned long *gstack, u32 val) +{ + *gstack -= 4; + lgwrite_u32(lg, *gstack, val); } static void set_guest_interrupt(struct lguest *lg, u32 lo, u32 hi, int has_err) { - u32 __user *gstack;...

...problem, or a ctdb/smbd problem. Thoughts/suggestions are welcome... You need a stack trace of the stuck smbd process. If it is wedged in a system call on the cluster filesystem then you can blame the cluster filesystem. debug_locks.sh is meant to be able to get you the relevant stack trace via gstack. In fact, even before you get the stack trace you could check a process listing to see if the process is stuck in D state. gstack basically does: gdb -batch -ex "thread apply all bt" -p <pid> For a single-threaded process it leaves out "thread apply all". However, in...

...roblem. Thoughts/suggestions are welcome... > > You need a stack trace of the stuck smbd process. If it is wedged in a > system call on the cluster filesystem then you can blame the cluster > filesystem. debug_locks.sh is meant to be able to get you the relevant > stack trace via gstack. In fact, even before you get the stack trace > you could check a process listing to see if the process is stuck in D > state. So, yes, I do have a process stuck in the D state. is in an smbd process. matching up the times in the logs, I see that the the "Vacuuming child process ti...

...ns are welcome... > > > > You need a stack trace of the stuck smbd process. If it is wedged in a > > system call on the cluster filesystem then you can blame the cluster > > filesystem. debug_locks.sh is meant to be able to get you the relevant > > stack trace via gstack. In fact, even before you get the stack trace > > you could check a process listing to see if the process is stuck in D > > state. > > So, yes, I do have a process stuck in the D state. is in an smbd > process. matching up the times in the logs, I see that the the >...

Hi all, Gratefully-received recent feedback from CC'd was applied to excellent effect (and the advice from Matt Mackall about my personal appearance is best unrequited). The patch is split in 5 parts to correspond with the 9 parts Andrew sent out before, but here's the summary: 1) Sparse (thanks Christoph Hellwig): - lguest_const can be static now - lguest.c should include

Hi all, Gratefully-received recent feedback from CC'd was applied to excellent effect (and the advice from Matt Mackall about my personal appearance is best unrequited). The patch is split in 5 parts to correspond with the 9 parts Andrew sent out before, but here's the summary: 1) Sparse (thanks Christoph Hellwig): - lguest_const can be static now - lguest.c should include

...zzi via samba wrote: >> Hi all, >> >> I have a midsize AD domain with some 50k users but only 100 workstations >> joined. >> >> Sometimes I find server CPU throttling at 100%. In order to let it drop > > Can you find out where *exactly* that 100% is spent? gstack on the > spinning process with debug symbols would be very helpful here. not sure how to do it. can be like that https://gist.github.com/francescm/8e396f5470da8df8451be13777e18810 ? > >> and have smooth performance I delete cache: >> >> systemctl stop samba >> net...

Hello, I am using ntlm_auth called from FreeRADIUS to authenticate users on a network with their Active Directory credentials. The problem I seem to be having is that ntlm_auth is taking longer than it should and I can't seem to get it to go faster reliably. Some background information: Users are connecting to a wireless network using 802.1x. That network sends requests to FreeRADIUS which

...atabase files placed on a FUSE filesystem mount? If so I'd suggest testing POSIX locking on your filesystem using a tool like https://wiki.samba.org/index.php/Ping_pong . > ----- Stack trace for PID=8990 ----- > 2017/04/19 10:40:31.294250 [ 7423]: /etc/ctdb/debug_locks.sh: line 73: > gstack: command not found This script attempts to dump the stack trace of the blocked process, but can't as gstack isn't installed - it should be available in the gdb package. @Martin: would the attached (untested) patch make sense? Cheers, David

...ble, &lg->lguest_data->irq_enabled)) - irq_enable = 0; - eflags |= (irq_enable & X86_EFLAGS_IF); + if (get_user(irq_enable, &lg->lguest_data->irq_enabled) == 0 + && !(irq_enable & X86_EFLAGS_IF)) + eflags &= ~X86_EFLAGS_IF; push_guest_stack(lg, &gstack, eflags); push_guest_stack(lg, &gstack, lg->regs->cs);

...ble, &lg->lguest_data->irq_enabled)) - irq_enable = 0; - eflags |= (irq_enable & X86_EFLAGS_IF); + if (get_user(irq_enable, &lg->lguest_data->irq_enabled) == 0 + && !(irq_enable & X86_EFLAGS_IF)) + eflags &= ~X86_EFLAGS_IF; push_guest_stack(lg, &gstack, eflags); push_guest_stack(lg, &gstack, lg->regs->cs);

...ork-pv/arch/x86_64/lguest/interrupts_and_traps.c @@ -0,0 +1,292 @@ +#include <linux/uaccess.h> +#include <asm/lguest.h> +#include <asm/desc.h> +#include <asm/hw_irq.h> +#include "lguest.h" + +static void push_guest_stack(struct lguest_vcpu *vcpu, + u64 __user **gstack, u64 val) +{ + lhwrite_u64(vcpu, (u64)--(*gstack), val); +} + +static u64 pop_guest_stack(struct lguest_vcpu *vcpu, + u64 __user **gstack) +{ + return lhread_u64(vcpu, (u64)(*gstack)++); +} + +void guest_iret(struct lguest_vcpu *vcpu) +{ + struct lguest_regs *regs = &vcpu->regs; + u64 _...

...ork-pv/arch/x86_64/lguest/interrupts_and_traps.c @@ -0,0 +1,292 @@ +#include <linux/uaccess.h> +#include <asm/lguest.h> +#include <asm/desc.h> +#include <asm/hw_irq.h> +#include "lguest.h" + +static void push_guest_stack(struct lguest_vcpu *vcpu, + u64 __user **gstack, u64 val) +{ + lhwrite_u64(vcpu, (u64)--(*gstack), val); +} + +static u64 pop_guest_stack(struct lguest_vcpu *vcpu, + u64 __user **gstack) +{ + return lhread_u64(vcpu, (u64)(*gstack)++); +} + +void guest_iret(struct lguest_vcpu *vcpu) +{ + struct lguest_regs *regs = &vcpu->regs; + u64 _...

...it doesn't the only harm is a bloated file. > But it never does succeed after the first time I see this message, and > the locking.tdb file does not change size, bigger or smaller. > > I am not really clear on what the script cannot create, but I did find > no evidence of the gstack program being available on debian, so I > changed the script to run pstack instead, and then ran it manually with > set -x while the logs were recording the problem, and I think this is > the trace output it is trying to come up with, but sadly this isn't > meaningful to me (yet...

...this change > > > > >Can you see what the smbd hosting such a blocked client does? > > >If it is in D state (according to ps u), it sits in the > > >kernel. If not, you could try stracing the process (strace > > >-ttT -p <pid>) and see what it does. gstack <pid> also helps > > >often. > > > > We got the following strace over the samba process 'locked' > > The strace looks innocent. Have you been able to see what > state the process was in while the client was blocked? > > I will ask for it to my wo...

...thor: Wayne Davison <wayned@samba.org> Date: Sat Aug 2 09:14:36 2008 -0700 Added logic to the receiving side to ensure that the --delete-during code will not delete in a directory prior to receiving an I/O error for that directory (or not receiving it, as the case may be). $ gstack 22366 #0 0x0000000000a24ad3 in __select_nocancel () from /lib64/libc.so.6 #1 0x00007fa36509b660 in read_timeout () from /proc/22366/exe #2 0x00007fa36509bb86 in read_loop () from /proc/22366/exe #3 0x00007fa36509a241 in readfd_unbuffered () from /proc/22366/exe #4 0x00007fa36509bd33 in readfd...

...(u32 lo, u32 hi) +{ + return (lo & 0x0000FFFF) | (hi & 0xFFFF0000); +} + +static int idt_type(u32 lo, u32 hi) +{ + return (hi >> 8) & 0xF; +} + +static int idt_present(u32 lo, u32 hi) +{ + return (hi & 0x8000); +} + +static void push_guest_stack(struct lguest *lg, u32 __user **gstack, u32 val) +{ + lgwrite_u32(lg, (u32)--(*gstack), val); +} + +static void set_guest_interrupt(struct lguest *lg, u32 lo, u32 hi, int has_err) +{ + u32 __user *gstack; + u32 eflags, ss, irq_enable; + + /* If they want a ring change, we use new stack and push old ss/esp */ + if ((lg->regs->ss&am...