From c8f56cf3f10aacbaf68f35491c32b17fcb956294 Mon Sep 17 00:00:00 2001
From: illustris <rharikrishnan95@gmail.com>
Date: Sun, 11 Jan 2026 10:53:20 +0530
Subject: [PATCH] remove valgrind, update docs

---
 README.md                         | 11 ++++++-----
 nix/packages.nix                  |  3 +--
 scenario3-syscall-storm/README.md | 18 ++++++++++++++++++
 3 files changed, 25 insertions(+), 7 deletions(-)

diff --git a/README.md b/README.md
index de877b4..df0db62 100644
--- a/README.md
+++ b/README.md
@@ -65,7 +65,6 @@ sudo apt install -y \
 # Optional but recommended
 sudo apt install -y \
     hyperfine \
-    valgrind \
     systemtap-sdt-dev
 
 # Python tools
@@ -125,7 +124,7 @@ Get all workshop tools in your current shell without installing anything system-
 cd perf-workshop
 nix develop
 
-# Now you have: perf, strace, py-spy, bpftrace, hyperfine, valgrind, flamegraph, pyroscope
+# Now you have: perf, strace, py-spy, bpftrace, hyperfine, flamegraph, pyroscope
 perf --version
 py-spy --help
 ```
@@ -272,8 +271,11 @@ perf-workshop/
 ├── scenario4-cache-misses/
 │   ├── README.md
 │   ├── Makefile
-│   ├── cache_demo.c            # Row vs column major
-│   └── list_vs_array.c         # Array vs linked list
+│   ├── matrix_col_major.c      # BAD: Column-major traversal
+│   ├── matrix_row_major.c      # GOOD: Row-major traversal
+│   ├── list_scattered.c        # BAD: Scattered linked list
+│   ├── list_sequential.c       # MEDIUM: Sequential linked list
+│   └── array_sum.c             # GOOD: Contiguous array
 ├── scenario5-debug-symbols/
 │   ├── README.md
 │   ├── Makefile
@@ -372,7 +374,6 @@ cat README.md
 ### Tools to Explore Later
 - `bpftrace` - High-level tracing language
 - `eBPF` - In-kernel programmability
-- `Valgrind` - Memory profiling
 - `gprof` - Traditional profiler
 
 ---
diff --git a/nix/packages.nix b/nix/packages.nix
index 21ef4ae..1dc2b59 100644
--- a/nix/packages.nix
+++ b/nix/packages.nix
@@ -22,9 +22,8 @@ with pkgs; [
 	]))
 	py-spy
 
-	# Benchmarking and debugging
+	# Benchmarking and visualization
 	hyperfine
-	valgrind
 	flamegraph
 
 	# USDT/SDT support (provides sys/sdt.h)
diff --git a/scenario3-syscall-storm/README.md b/scenario3-syscall-storm/README.md
index c71f855..07b1d39 100644
--- a/scenario3-syscall-storm/README.md
+++ b/scenario3-syscall-storm/README.md
@@ -134,6 +134,24 @@ Look at:
 - `cpu-migrations`
 - `instructions per cycle`
 
+## Exercise 6: Benchmarking with hyperfine
+
+Use `hyperfine` for proper statistical benchmarking with warmup runs:
+
+```bash
+hyperfine --warmup 1 './read_slow testfile' './read_fast testfile'
+```
+
+This gives you:
+- Mean execution time with standard deviation
+- Min/max times
+- Direct comparison between implementations
+
+For all three implementations:
+```bash
+hyperfine --warmup 1 './read_slow testfile' './read_stdio testfile' './read_fast testfile'
+```
+
 ## Further Exploration
 
 1. What happens with `read(fd, buf, 4096)` vs `read(fd, buf, 65536)`?