# Workers CPU leak **URL:** \ **Category:** NGINX\ **Created:** [February 24, 2016, 3:17pm UTC](https://www.ruby-forum.com/t/workers-cpu-leak/244126 "2016-02-24T15:17:19Z")\ **Posts on this page:** 19\ **Page:** 1
**Author:** ![Rafa\_F](https://www.ruby-forum.com/letter_avatar_proxy/v4/letter/r/958977/32.png) [@Rafa\_F](https://www.ruby-forum.com/u/Rafa_F)\ **Post date:** [February 24, 2016, 3:17pm UTC](https://www.ruby-forum.com/t/workers-cpu-leak/244126/1 "2016-02-24T15:17:19Z")
Hello, I have strange issuses with nginx workers. For some time after start Nginx I notice that some process of workers cause high load to CPU ( principally sys CPU). At first I’ve got syscall traces from one of such process: futex(0x157d914, FUTEX\_WAKE\_OP\_PRIVATE, 1, 1, 0x157d910, {FUTEX\_OP\_SET, 0, FUTEX\_OP\_CMP\_GT, 1}) = 1 epoll\_wait(38, {{EPOLLIN, {u32=7156096, u64=7156096}}}, 512, -1) = 1 epoll\_ctl(38, EPOLL\_CTL\_ADD, 178, {EPOLLOUT|EPOLLET, {u32=3888102096, u64=140028411886288}}) = 0 epoll\_wait(38, {{EPOLLOUT, {u32=3888102096, u64=140028411886288}}}, 512, -1) = 1 epoll\_ctl(38, EPOLL\_CTL\_DEL, 178, 7ffda2bc7f30) = 0 futex(0x157d914, FUTEX\_WAKE\_OP\_PRIVATE, 1, 1, 0x157d910, {FUTEX\_OP\_SET, 0, FUTEX\_OP\_CMP\_GT, 1}) = 1 epoll\_wait(38, {{EPOLLIN, {u32=7156096, u64=7156096}}}, 512, -1) = 1 epoll\_ctl(38, EPOLL\_CTL\_ADD, 178, {EPOLLOUT|EPOLLET, {u32=3888102096, u64=140028411886288}}) = 0 epoll\_wait(38, {{EPOLLOUT, {u32=3888102096, u64=140028411886288}}}, 512, -1) = 1 epoll\_ctl(38, EPOLL\_CTL\_DEL, 178, 7ffda2bc7f30) = 0 futex(0x157d914, FUTEX\_WAKE\_OP\_PRIVATE, 1, 1, 0x157d910, {FUTEX\_OP\_SET, 0, FUTEX\_OP\_CMP\_GT, 1}) = 1 futex(0x157d8d0, FUTEX\_WAKE\_PRIVATE, 1) = 1 epoll\_wait, epoll\_ctl, futex are repeated circularly. Then I’ve got lsof of process and see who owns of 38 file descriptor: nginx 18862 www 38u a\_inode 0,9 0 6 [eventpoll] also I see several CLOSE\_WAIT sockets nginx 18862 www 101u IPv4 85643376 0t0 TCP 154.59.82.194:http-\>105.107.179.210:24519 (CLOSE\_WAIT) nginx 18862 www 133r REG 8,3 0 4743 /mnt/ssd1/wwwroot/71/7/27394667.mp4 (deleted) nginx 18862 www 178u IPv4 86054929 0t0 TCP 154.59.82.194:http-\>[5adc98ed.bb.sky.com:45665](http://5adc98ed.bb.sky.com:45665) (CLOSE\_WAIT) nginx 18862 www 179r REG 8,3 0 5098 /mnt/ssd1/wwwroot/21/9/29603499.mp4 (deleted) Nginx has such version and modules: nginx version: nginx/1.9.11 built with OpenSSL 1.0.2f 28 Jan 2016 TLS SNI support enabled configure arguments: --prefix=/usr --conf-path=/etc/nginx/nginx.conf –error-log-path=/var/log/nginx/error\_log --pid-path=/run/nginx.pid –lock-path=/run/lock/nginx.lock --with-cc-opt=-I/usr/include –with-ld-opt=-L/usr/lib64 --http-log-path=/var/log/nginx/access\_log –http-client-body-temp-path=/var/lib/nginx/tmp/client –http-proxy-temp-path=/var/lib/nginx/tmp/proxy –http-fastcgi-temp-path=/var/lib/nginx/tmp/fastcgi –http-scgi-temp-path=/var/lib/nginx/tmp/scgi –http-uwsgi-temp-path=/var/lib/nginx/tmp/uwsgi --with-file-aio –with-ipv6 –with-pcre --with-threads --without-http\_autoindex\_module –without-http\_fastcgi\_module --without-http\_geo\_module –without-http\_limit\_req\_module --without-http\_limit\_conn\_module –without-http\_memcached\_module --without-http\_uwsgi\_module –with-http\_flv\_module --with-http\_gzip\_static\_module –with-http\_mp4\_module –with-http\_perl\_module –add-module=external\_module/headers-more-nginx-module-0.261 –add-module=external\_module/ngx\_estreaming\_module-0.01 –add-module=external\_module/ngx\_slice\_module-0.01 –with-http\_ssl\_module –without-mail\_imap\_module --without-mail\_pop3\_module –without-mail\_smtp\_module --user=‘www --group=www’ and using for video streaming. Has anyone encountered such behavior ? Help please. Posted at Nginx Forum: > **[Workers CPU leak \[epoll\_wait,epoll\_ctl\]](https://forum.nginx.org/read.php?2,264764,264764#msg-264764)** > > Hello, I have strange issuses with nginx workers. For some time after start Nginx I notice that some process of workers cause high load to CPU ( principally sys CPU). At first I've got syscall traces from one of such process: futex(0x157d914,... ---
**Author:** ![vizl](https://www.ruby-forum.com/letter_avatar_proxy/v4/letter/v/e0b2c6/32.png) [@vizl](https://www.ruby-forum.com/u/vizl)\ **Post date:** [February 24, 2016, 3:39pm UTC](https://www.ruby-forum.com/t/workers-cpu-leak/244126/2 "2016-02-24T15:39:31Z")
P.S: we are using Gentoo with 4.4.1 kernel and CPU X3330 @ 2.66GHz GenuineIntel GNU/Linux Posted at Nginx Forum: > **[Re: Workers CPU leak \[epoll\_wait,epoll\_ctl\]](https://forum.nginx.org/read.php?2,264764,264766#msg-264766)** > > Hello, I have strange issuses with nginx workers. For some time after start Nginx I notice that some process of workers cause high load to CPU ( principally sys CPU). At first I've got syscall traces from one of such process: futex(0x157d914,... ---
**Author:** ![vizl](https://www.ruby-forum.com/letter_avatar_proxy/v4/letter/v/e0b2c6/32.png) [@vizl](https://www.ruby-forum.com/u/vizl)\ **Post date:** [March 4, 2016, 1:12pm UTC](https://www.ruby-forum.com/t/workers-cpu-leak/244126/3 "2016-03-04T13:12:45Z")
Sorry for long answer, but we have doing some tests, and notice that probles is appear when thread\_pool enabled. thread\_pool default threads=128 max\_queue=1024 We need to use thread\_pool, and can’t permenent disable it unfortunately Posted at Nginx Forum: > **[Re: Workers CPU leak \[epoll\_wait,epoll\_ctl\]](https://forum.nginx.org/read.php?2,264764,265085#msg-265085)** > > Hello, I have strange issuses with nginx workers. For some time after start Nginx I notice that some process of workers cause high load to CPU ( principally sys CPU). At first I've got syscall traces from one of such process: futex(0x157d914,... ---
**Author:** ![vizl](https://www.ruby-forum.com/letter_avatar_proxy/v4/letter/v/e0b2c6/32.png) [@vizl](https://www.ruby-forum.com/u/vizl)\ **Post date:** [March 4, 2016, 1:21pm UTC](https://www.ruby-forum.com/t/workers-cpu-leak/244126/4 "2016-03-04T13:21:32Z")
On Friday 04 March 2016 07:12:09 vizl wrote: > Sorry for long answer, but we have doing some tests, and notice that probles > is appear when thread\_pool enabled. > > thread\_pool default threads=128 max\_queue=1024 > > We need to use thread\_pool, and can’t permenent disable it unfortunately [..] Do you modify files that are served by nginx? Do you have open\_file\_cache enabled? wbr, Valentin V. Bartenev ---
**Author:** ![vizl](https://www.ruby-forum.com/letter_avatar_proxy/v4/letter/v/e0b2c6/32.png) [@vizl](https://www.ruby-forum.com/u/vizl)\ **Post date:** [February 24, 2016, 4:26pm UTC](https://www.ruby-forum.com/t/workers-cpu-leak/244126/5 "2016-02-24T16:26:15Z")
On Wednesday 24 February 2016 09:17:01 vizl wrote: > u64=140028411886288}}) = 0 > epoll\_ctl(38, EPOLL\_CTL\_DEL, 178, 7ffda2bc7f30) = 0 > > –http-client-body-temp-path=/var/lib/nginx/tmp/client > –add-module=external\_module/headers-more-nginx-module-0.261 > –add-module=external\_module/ngx\_estreaming\_module-0.01 > –add-module=external\_module/ngx\_slice\_module-0.01 --with-http\_ssl\_module > –without-mail\_imap\_module --without-mail\_pop3\_module > –without-mail\_smtp\_module --user=‘www --group=www’ > > and using for video streaming. > > Has anyone encountered such behavior ? Help please. [..] Could you provide a minimal configuration that is causing problems with debug log? See: [A debugging log](http://nginx.org/en/docs/debugging_log.html) wbr, Valentin V. Bartenev ---
**Author:** ![vizl](https://www.ruby-forum.com/letter_avatar_proxy/v4/letter/v/e0b2c6/32.png) [@vizl](https://www.ruby-forum.com/u/vizl)\ **Post date:** [March 4, 2016, 1:25pm UTC](https://www.ruby-forum.com/t/workers-cpu-leak/244126/6 "2016-03-04T13:25:02Z")
On 3/4/16 3:20 PM, Valentin V. Bartenev wrote: > Do you modify files that are served by nginx? > Do you have open\_file\_cache enabled? Can we ask you again about the nginx configuration? – Maxim K. ---
**Author:** ![vizl](https://www.ruby-forum.com/letter_avatar_proxy/v4/letter/v/e0b2c6/32.png) [@vizl](https://www.ruby-forum.com/u/vizl)\ **Post date:** [March 4, 2016, 2:26pm UTC](https://www.ruby-forum.com/t/workers-cpu-leak/244126/7 "2016-03-04T14:26:22Z")
user www; worker\_processes 16; thread\_pool default threads=128 max\_queue=1024; worker\_rlimit\_nofile 65536; ###timer\_resolution 100ms; #error\_log /home/logs/error\_log.nginx error; error\_log /home/logs/error\_log.nginx.debug debug; events { worker\_connections 30000; use epoll; } http { include mime.types; default\_type application/octet-stream; index index.html index.htm; output\_buffers 2 256k; read\_ahead 256k; # was 1m; aio threads=default; aio on; sendfile on; sendfile\_max\_chunk 256k; server { listen \*:80 default rcvbuf=32768 backlog=2048 reuseport deferred; listen \*:443 ssl default rcvbuf=32768 backlog=2048 reuseport deferred; server\_name localhost; access\_log /home/logs/access.log; error\_log /home/logs/error.log warn; root /mnt; expires 20m; ``` location ~ ^/crossdomain.xml { } location ~ \.[Ff][Ll][Vv]$ { flv; } location ~ \.[Mm][Pp]4$ { mp4; } ``` } } Posted at Nginx Forum: > **[Re: Workers CPU leak \[epoll\_wait,epoll\_ctl\]](https://forum.nginx.org/read.php?2,264764,265089#msg-265089)** > > Hello, I have strange issuses with nginx workers. For some time after start Nginx I notice that some process of workers cause high load to CPU ( principally sys CPU). At first I've got syscall traces from one of such process: futex(0x157d914,... ---
**Author:** ![vizl](https://www.ruby-forum.com/letter_avatar_proxy/v4/letter/v/e0b2c6/32.png) [@vizl](https://www.ruby-forum.com/u/vizl)\ **Post date:** [March 4, 2016, 3:43pm UTC](https://www.ruby-forum.com/t/workers-cpu-leak/244126/8 "2016-03-04T15:43:29Z")
Sorry, my misprint. Config whithout aio on; only aio threads=default; > do you or some tool periodically change the files ? > no, files are unchanged, just periodically some new are added and some > expired are deleted Posted at Nginx Forum: [https://forum.nginx.org/read.php?2,264764,265095#msg-265095](https://forum.nginx.org/read.php?2,264764,265095#msg-265095) ---
**Author:** ![vizl](https://www.ruby-forum.com/letter_avatar_proxy/v4/letter/v/e0b2c6/32.png) [@vizl](https://www.ruby-forum.com/u/vizl)\ **Post date:** [March 4, 2016, 2:45pm UTC](https://www.ruby-forum.com/t/workers-cpu-leak/244126/9 "2016-03-04T14:45:04Z")
On Friday 04 March 2016 08:25:43 vizl wrote: > worker\_connections 30000; > aio threads=default; > aio on; This is invalid configuration due to duplicated “aio” directive. I assume it’s not the configuration with which your nginx is currently running. > ``` > expires 20m; > > ``` The question remains the same: do you or some tool periodically change the files? wbr, Valentin V. Bartenev ---
**Author:** ![vizl](https://www.ruby-forum.com/letter_avatar_proxy/v4/letter/v/e0b2c6/32.png) [@vizl](https://www.ruby-forum.com/u/vizl)\ **Post date:** [March 4, 2016, 3:46pm UTC](https://www.ruby-forum.com/t/workers-cpu-leak/244126/10 "2016-03-04T15:46:24Z")
On Friday 04 March 2016 09:42:45 vizl wrote: > Sorry, my misprint. > > Config whithout aio on; > > only aio threads=default; > > > do you or some tool periodically change the files ? > > no, files are unchanged, just periodically some new are added and some > > expired are deleted Could you provide the debug log? wbr, Valentin V. Bartenev ---
**Author:** ![vizl](https://www.ruby-forum.com/letter_avatar_proxy/v4/letter/v/e0b2c6/32.png) [@vizl](https://www.ruby-forum.com/u/vizl)\ **Post date:** [March 9, 2016, 3:28pm UTC](https://www.ruby-forum.com/t/workers-cpu-leak/244126/11 "2016-03-09T15:28:46Z")
Debug log regarding to hanged PID 7479 [http://dev.vizl.org/debug.log.txt](http://dev.vizl.org/debug.log.txt) Posted at Nginx Forum: > **[Re: Workers CPU leak \[epoll\_wait,epoll\_ctl\]](https://forum.nginx.org/read.php?2,264764,265188#msg-265188)** > > Hello, I have strange issuses with nginx workers. For some time after start Nginx I notice that some process of workers cause high load to CPU ( principally sys CPU). At first I've got syscall traces from one of such process: futex(0x157d914,... ---
**Author:** ![vizl](https://www.ruby-forum.com/letter_avatar_proxy/v4/letter/v/e0b2c6/32.png) [@vizl](https://www.ruby-forum.com/u/vizl)\ **Post date:** [March 9, 2016, 4:13pm UTC](https://www.ruby-forum.com/t/workers-cpu-leak/244126/12 "2016-03-09T16:13:10Z")
Hello! On Wed, Mar 09, 2016 at 09:28:20AM -0500, vizl wrote: > Debug log regarding to hanged PID 7479 [http://dev.vizl.org/debug.log.txt](http://dev.vizl.org/debug.log.txt) This looks like a threads + sendfile() loop due to non-atomic updates of underlying file, similar to one recently reported on the Russian mailing list. Correct solution would be to fix your system to update files atomically instead of overwriting them in place. The patch below will resolve CPU hog and will log an alert instead: # HG changeset patch # User Maxim D. [removed\_email\_address@domain.invalid](mailto:removed_email_address@domain.invalid) # Date 1457536139 -10800 # Wed Mar 09 18:08:59 2016 +0300 # Node ID e96e5dfe4ff8ffe301264c3eb2771596fae24d38 # Parent 93049710cb7f6ea91fa9bd707e88fbe79d82d0ef Truncation detection in sendfile() on Linux. This addresses connection hangs as observed in ticket #504, and CPU hogs with “aio threads; sendfile on” as reported in the mailing list, see [Re: nginx отъедает все процессорное время](http://mailman.nginx.org/pipermail/nginx-ru/2016-March/057638.html). The alert is identical to one used on FreeBSD. diff --git a/src/os/unix/ngx\_linux\_sendfile\_chain.c b/src/os/unix/ngx\_linux\_sendfile\_chain.c — a/src/os/unix/ngx\_linux\_sendfile\_chain.c +++ b/src/os/unix/ngx\_linux\_sendfile\_chain.c @@ -292,6 +292,19 @@ eintr: } } - if (n == 0) { - ``` /* ``` - ``` * if sendfile returns zero, then someone has truncated the ``` file, - ``` * so the offset became beyond the end of the file ``` - ``` */ ``` - - ``` ngx_log_error(NGX_LOG_ALERT, c->log, 0, ``` - ``` "sendfile() reported that \"%s\" was truncated at ``` %O", - ``` file->file->name.data, file->file_pos); ``` - - ``` return NGX_ERROR; ``` - } - ngx\_log\_debug3(NGX\_LOG\_DEBUG\_EVENT, c-\>log, 0, “sendfile: %z of %uz @%O”, n, size, file-\>file\_pos); @@ -349,6 +362,19 @@ ngx\_linux\_sendfile\_thread(ngx\_connection return NGX\_ERROR; } - ``` if (ctx->err != NGX_AGAIN && ctx->sent == 0) { ``` - ``` /* ``` - ``` * if sendfile returns zero, then someone has truncated the ``` file, - ``` * so the offset became beyond the end of the file ``` - ``` */ ``` - - ``` ngx_log_error(NGX_LOG_ALERT, c->log, 0, ``` - ``` "sendfile() reported that \"%s\" was ``` truncated at %O", - ``` file->file->name.data, file->file_pos); ``` - - ``` return NGX_ERROR; ``` - ``` } ``` - ``` *sent = ctx->sent; return (ctx->sent == ctx->size) ? NGX_DONE : NGX_AGAIN; ``` – Maxim D. > **[nginx](http://nginx.org/)** ---
**Author:** ![vizl](https://www.ruby-forum.com/letter_avatar_proxy/v4/letter/v/e0b2c6/32.png) [@vizl](https://www.ruby-forum.com/u/vizl)\ **Post date:** [March 9, 2016, 4:56pm UTC](https://www.ruby-forum.com/t/workers-cpu-leak/244126/13 "2016-03-09T16:56:59Z")
Thank you. We don’t make any changes with files or overwrite them while sendfile processing it. Only create temp file and then mv it. Maybe Is it the same bug concerned with treads aio like in this messeges, [https://forum.nginx.org/read.php?21,264701,265016#msg-265016](https://forum.nginx.org/read.php?21,264701,265016#msg-265016) and it would be fixed in future ? Posted at Nginx Forum: > **[Re: Workers CPU leak \[epoll\_wait,epoll\_ctl\]](https://forum.nginx.org/read.php?2,264764,265193#msg-265193)** > > Hello, I have strange issuses with nginx workers. For some time after start Nginx I notice that some process of workers cause high load to CPU ( principally sys CPU). At first I've got syscall traces from one of such process: futex(0x157d914,... ---
**Author:** ![vizl](https://www.ruby-forum.com/letter_avatar_proxy/v4/letter/v/e0b2c6/32.png) [@vizl](https://www.ruby-forum.com/u/vizl)\ **Post date:** [March 9, 2016, 5:19pm UTC](https://www.ruby-forum.com/t/workers-cpu-leak/244126/14 "2016-03-09T17:19:46Z")
Hello! On Wed, Mar 09, 2016 at 10:56:40AM -0500, vizl wrote: > Thank you. > We don’t make any changes with files or overwrite them while sendfile > processing it. > Only create temp file and then mv it. The debug log suggests this is not true. > Maybe Is it the same bug concerned with treads aio like in this messeges, > [https://forum.nginx.org/read.php?21,264701,265016#msg-265016](https://forum.nginx.org/read.php?21,264701,265016#msg-265016) > and it would be fixed in future ? Yes, and the patch provided links to the very same thread and resolves the problem in nginx, i.e., CPU hog. With the patch an alert will be correctly logged. Note well that the root cause of CPU hog observed are non-atomic file updates. You will still see other problems till this is resolved (including data corruption), even with the patch. – Maxim D. > **[nginx](http://nginx.org/)** ---
**Author:** ![vizl](https://www.ruby-forum.com/letter_avatar_proxy/v4/letter/v/e0b2c6/32.png) [@vizl](https://www.ruby-forum.com/u/vizl)\ **Post date:** [March 20, 2016, 9:34pm UTC](https://www.ruby-forum.com/t/workers-cpu-leak/244126/15 "2016-03-20T21:34:48Z")
We found, that we are running ‘truncate -s 0’ to file before removing them. Can it potentially cause the mentioned above problems ? Posted at Nginx Forum: > **[Re: Workers CPU leak \[epoll\_wait,epoll\_ctl\]](https://forum.nginx.org/read.php?2,264764,265516#msg-265516)** > > Hello, I have strange issuses with nginx workers. For some time after start Nginx I notice that some process of workers cause high load to CPU ( principally sys CPU). At first I've got syscall traces from one of such process: futex(0x157d914,... ---
**Author:** ![vizl](https://www.ruby-forum.com/letter_avatar_proxy/v4/letter/v/e0b2c6/32.png) [@vizl](https://www.ruby-forum.com/u/vizl)\ **Post date:** [March 21, 2016, 9:09am UTC](https://www.ruby-forum.com/t/workers-cpu-leak/244126/16 "2016-03-21T09:09:57Z")
On 3/20/16 11:34 PM, vizl wrote: > We found, that we are running ‘truncate -s 0’ to file before removing them. > Can it potentially cause the mentioned above problems ? Yes, quite possible. The fix was committed to the mainline branch and will be available in 1.9.13: > **[\[nginx\] Truncation detection in sendfile() on Linux.](http://mailman.nginx.org/pipermail/nginx-devel/2016-March/008012.html)** – Maxim K. ---
**Author:** ![vizl](https://www.ruby-forum.com/letter_avatar_proxy/v4/letter/v/e0b2c6/32.png) [@vizl](https://www.ruby-forum.com/u/vizl)\ **Post date:** [March 10, 2016, 3:09pm UTC](https://www.ruby-forum.com/t/workers-cpu-leak/244126/17 "2016-03-10T15:09:28Z")
One thing: when we disable threads in config, and leave only “senfile on;” the problem was gone. So if problem caused by sendfile and non-atomic file updates, why it does not apeared when threads off ? Posted at Nginx Forum: > **[Re: Workers CPU leak \[epoll\_wait,epoll\_ctl\]](https://forum.nginx.org/read.php?2,264764,265214#msg-265214)** > > Hello, I have strange issuses with nginx workers. For some time after start Nginx I notice that some process of workers cause high load to CPU ( principally sys CPU). At first I've got syscall traces from one of such process: futex(0x157d914,... ---
**Author:** ![vizl](https://www.ruby-forum.com/letter_avatar_proxy/v4/letter/v/e0b2c6/32.png) [@vizl](https://www.ruby-forum.com/u/vizl)\ **Post date:** [March 21, 2016, 2:30pm UTC](https://www.ruby-forum.com/t/workers-cpu-leak/244126/18 "2016-03-21T14:30:03Z")
Hello! On Sun, Mar 20, 2016 at 04:34:14PM -0400, vizl wrote: > We found, that we are running ‘truncate -s 0’ to file before removing them. > Can it potentially cause the mentioned above problems ? Yes, for sure. This is a modification of a file being served, and it’s expected to cause the CPU hog in question when using sendfile in threads on Linux. In nginx 1.9.13 nginx will log an alert instead, see this commit: > **[hg.nginx.org is decommissioned](http://hg.nginx.org/nginx/rev/4df3d9fcdee8)** – Maxim D. > **[nginx](http://nginx.org/)** ---
**Author:** ![vizl](https://www.ruby-forum.com/letter_avatar_proxy/v4/letter/v/e0b2c6/32.png) [@vizl](https://www.ruby-forum.com/u/vizl)\ **Post date:** [March 21, 2016, 1:01pm UTC](https://www.ruby-forum.com/t/workers-cpu-leak/244126/19 "2016-03-21T13:01:16Z")
Thank you. Waiting for 1.9.13 branch. Posted at Nginx Forum: > **[Re: Workers CPU leak \[epoll\_wait,epoll\_ctl\]](https://forum.nginx.org/read.php?2,264764,265536#msg-265536)** > > Hello, I have strange issuses with nginx workers. For some time after start Nginx I notice that some process of workers cause high load to CPU ( principally sys CPU). At first I've got syscall traces from one of such process: futex(0x157d914,...