| 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: <c95c25c6fb3931498b8d83b8ae1130208cda5af8.1456178093.git.shli@fb.com> Date: Mon, 22 Feb 2016 14:01:25 -0800 From: Shaohua Li <shli@...com> To: <linux-kernel@...r.kernel.org>, <linux-block@...r.kernel.org> CC: <axboe@...nel.dk>, <tj@...nel.org>, Vivek Goyal <vgoyal@...hat.com>, "jmoyer @ redhat . com" <jmoyer@...hat.com>, <Kernel-team@...com> Subject: [PATCH V2 10/13] blk-throttle: over estimate bandwidth If we don't dispatch enough requests, disk can't reach the max bandwidth. As we don't know the max bandwidth, we over estimate the bandwidth and dispatch more requests. This way the disk can reach the max bandwidth slowly. The downside is this can introduce fairness issue, but since we only over estimate 1/8 extra bandwidth, the fairness issue isn't big. But again, this could cause fairness issue for specific workloads. Signed-off-by: Shaohua Li <shli@...com> --- block/blk-throttle.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/block/blk-throttle.c b/block/blk-throttle.c index 68e2598..f78d470 100644 --- a/block/blk-throttle.c +++ b/block/blk-throttle.c @@ -281,6 +281,8 @@ static inline uint64_t queue_bandwidth(struct throtl_data *td) /* can't estimate bandwidth, can't do proporation control */ if (bw == 0) bw = -1; + else + bw += bw >> 3; return bw; } @@ -292,6 +294,8 @@ static inline uint64_t queue_iops(struct throtl_data *td) /* can't estimate iops, can't do proporation control */ if (iops == 0) iops = -1; + else + iops += iops >> 3; return iops; } -- 2.6.5
Powered by blists - more mailing lists